diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
--- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -817,13 +817,12 @@
 
   if (ST->hasMVEIntegerOps() && (Opcode == Instruction::InsertElement ||
                                  Opcode == Instruction::ExtractElement)) {
-    // We say MVE moves costs at least the MVEVectorCostFactor, even though
-    // they are scalar instructions. This helps prevent mixing scalar and
-    // vector, to prevent vectorising where we end up just scalarising the
-    // result anyway.
-    return std::max(BaseT::getVectorInstrCost(Opcode, ValTy, Index),
-                    ST->getMVEVectorCostFactor(TTI::TCK_RecipThroughput)) *
-           cast<FixedVectorType>(ValTy)->getNumElements() / 2;
+    // Integer cross-lane moves are more expensive than float, which can
+    // sometimes just be vmovs. Integer involve being passes to GPR registers,
+    // causing more of a delay.
+    std::pair<unsigned, MVT> LT =
+        getTLI()->getTypeLegalizationCost(DL, ValTy->getScalarType());
+    return LT.first * (ValTy->getScalarType()->isIntegerTy() ? 4 : 1);
   }
 
   return BaseT::getVectorInstrCost(Opcode, ValTy, Index);
diff --git a/llvm/test/Analysis/CostModel/ARM/arith-overflow.ll b/llvm/test/Analysis/CostModel/ARM/arith-overflow.ll
--- a/llvm/test/Analysis/CostModel/ARM/arith-overflow.ll
+++ b/llvm/test/Analysis/CostModel/ARM/arith-overflow.ll
@@ -67,21 +67,21 @@
 ;
 ; MVE-RECIP-LABEL: 'sadd'
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 242 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 866 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 186 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 370 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 738 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 90 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 498 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1890 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 274 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 546 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 298 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1874 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 7332 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 170 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 530 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1060 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1098 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 7316 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 28968 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1044 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2088 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; V8M-SIZE-LABEL: 'sadd'
@@ -124,21 +124,21 @@
 ;
 ; MVE-SIZE-LABEL: 'sadd'
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 78 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 150 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 203 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 787 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 107 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 211 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 779 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 3092 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 203 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 404 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 3084 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 12310 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 396 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 790 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %I64 = call {i64, i1} @llvm.sadd.with.overflow.i64(i64 undef, i64 undef)
@@ -225,21 +225,21 @@
 ;
 ; MVE-RECIP-LABEL: 'uadd'
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call { i64, i1 } @llvm.uadd.with.overflow.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.uadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 undef, i32 undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.uadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 264 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1040 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1032 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4112 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; V8M-SIZE-LABEL: 'uadd'
@@ -282,21 +282,21 @@
 ;
 ; MVE-SIZE-LABEL: 'uadd'
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call { i64, i1 } @llvm.uadd.with.overflow.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 41 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 73 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 145 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.uadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 undef, i32 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.uadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 264 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 260 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1032 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1028 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4104 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 132 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 264 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %I64 = call {i64, i1} @llvm.uadd.with.overflow.i64(i64 undef, i64 undef)
@@ -383,21 +383,21 @@
 ;
 ; MVE-RECIP-LABEL: 'ssub'
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %I64 = call { i64, i1 } @llvm.ssub.with.overflow.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 242 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 866 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.ssub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 186 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 370 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 738 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.ssub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I32 = call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 undef, i32 undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 90 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.ssub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 498 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1890 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 274 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 546 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I16 = call { i16, i1 } @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 298 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1874 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 7332 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 170 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 530 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1060 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I8 = call { i8, i1 } @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1098 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 7316 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 28968 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1044 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2088 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; V8M-SIZE-LABEL: 'ssub'
@@ -440,21 +440,21 @@
 ;
 ; MVE-SIZE-LABEL: 'ssub'
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %I64 = call { i64, i1 } @llvm.ssub.with.overflow.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 78 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 150 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.ssub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %I32 = call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 undef, i32 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.ssub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 203 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 787 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 107 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 211 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %I16 = call { i16, i1 } @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 779 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 3092 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 203 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 404 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %I8 = call { i8, i1 } @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 3084 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 12310 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 396 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 790 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %I64 = call {i64, i1} @llvm.ssub.with.overflow.i64(i64 undef, i64 undef)
@@ -541,21 +541,21 @@
 ;
 ; MVE-RECIP-LABEL: 'usub'
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call { i64, i1 } @llvm.usub.with.overflow.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.usub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.usub.with.overflow.i32(i32 undef, i32 undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.usub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 264 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1040 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1032 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4112 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; V8M-SIZE-LABEL: 'usub'
@@ -598,21 +598,21 @@
 ;
 ; MVE-SIZE-LABEL: 'usub'
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call { i64, i1 } @llvm.usub.with.overflow.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 41 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 73 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 145 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.usub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.usub.with.overflow.i32(i32 undef, i32 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.usub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 264 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 260 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1032 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1028 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4104 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 132 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 264 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %I64 = call {i64, i1} @llvm.usub.with.overflow.i64(i64 undef, i64 undef)
@@ -699,21 +699,21 @@
 ;
 ; MVE-RECIP-LABEL: 'smul'
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 120 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 768 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1056 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2112 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 380 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1464 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 118 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 348 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1016 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 420 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1512 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 228 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 616 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1252 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4712 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 356 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 872 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; V8M-SIZE-LABEL: 'smul'
@@ -756,21 +756,21 @@
 ;
 ; MVE-SIZE-LABEL: 'smul'
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 101 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 85 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 165 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 325 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 218 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 816 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 79 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 186 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 368 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 332 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1174 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 278 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 71 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1164 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4374 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 268 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 534 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %I64 = call {i64, i1} @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
@@ -857,21 +857,21 @@
 ;
 ; MVE-RECIP-LABEL: 'umul'
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 248 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 624 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 492 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 984 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1968 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 376 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1456 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 116 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 344 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1008 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 416 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1504 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 608 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 92 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1248 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4704 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 352 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 864 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; V8M-SIZE-LABEL: 'umul'
@@ -914,21 +914,21 @@
 ;
 ; MVE-SIZE-LABEL: 'umul'
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 61 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 93 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 181 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 216 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 812 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 78 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 184 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 364 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1170 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 138 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 274 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 70 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1162 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4370 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 266 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 530 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %I64 = call {i64, i1} @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
diff --git a/llvm/test/Analysis/CostModel/ARM/arith-ssat.ll b/llvm/test/Analysis/CostModel/ARM/arith-ssat.ll
--- a/llvm/test/Analysis/CostModel/ARM/arith-ssat.ll
+++ b/llvm/test/Analysis/CostModel/ARM/arith-ssat.ll
@@ -85,22 +85,22 @@
 ;
 ; MVE-RECIP-LABEL: 'add'
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 118 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 378 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1330 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 302 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 602 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1202 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 180 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 180 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 180 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -160,22 +160,22 @@
 ;
 ; MVE-SIZE-LABEL: 'add'
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 81 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 153 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -291,22 +291,22 @@
 ;
 ; MVE-RECIP-LABEL: 'sub'
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 118 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 378 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1330 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 302 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 602 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1202 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 180 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 180 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 180 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -366,22 +366,22 @@
 ;
 ; MVE-SIZE-LABEL: 'sub'
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 81 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 153 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/ARM/arith-usat.ll b/llvm/test/Analysis/CostModel/ARM/arith-usat.ll
--- a/llvm/test/Analysis/CostModel/ARM/arith-usat.ll
+++ b/llvm/test/Analysis/CostModel/ARM/arith-usat.ll
@@ -85,22 +85,22 @@
 ;
 ; MVE-RECIP-LABEL: 'add'
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 448 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -160,22 +160,22 @@
 ;
 ; MVE-SIZE-LABEL: 'add'
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 146 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -291,22 +291,22 @@
 ;
 ; MVE-RECIP-LABEL: 'sub'
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 448 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -366,22 +366,22 @@
 ;
 ; MVE-SIZE-LABEL: 'sub'
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 146 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/ARM/arith.ll b/llvm/test/Analysis/CostModel/ARM/arith.ll
--- a/llvm/test/Analysis/CostModel/ARM/arith.ll
+++ b/llvm/test/Analysis/CostModel/ARM/arith.ll
@@ -375,12 +375,12 @@
 
 define void @vi8() {
 ; CHECK-MVE1-LABEL: 'vi8'
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %c2 = add <2 x i8> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %d2 = sub <2 x i8> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %e2 = mul <2 x i8> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %f2 = ashr <2 x i8> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %g2 = lshr <2 x i8> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %h2 = shl <2 x i8> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %c2 = add <2 x i8> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %d2 = sub <2 x i8> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %e2 = mul <2 x i8> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f2 = ashr <2 x i8> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %g2 = lshr <2 x i8> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %h2 = shl <2 x i8> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i2 = and <2 x i8> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j2 = or <2 x i8> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k2 = xor <2 x i8> undef, undef
@@ -414,12 +414,12 @@
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE2-LABEL: 'vi8'
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %c2 = add <2 x i8> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %d2 = sub <2 x i8> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %e2 = mul <2 x i8> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %f2 = ashr <2 x i8> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %g2 = lshr <2 x i8> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %h2 = shl <2 x i8> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %c2 = add <2 x i8> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %d2 = sub <2 x i8> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %e2 = mul <2 x i8> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f2 = ashr <2 x i8> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %g2 = lshr <2 x i8> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %h2 = shl <2 x i8> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %i2 = and <2 x i8> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %j2 = or <2 x i8> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %k2 = xor <2 x i8> undef, undef
@@ -609,12 +609,12 @@
 ; CHECK-V8R-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-SIZE-LABEL: 'vi8'
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %c2 = add <2 x i8> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %d2 = sub <2 x i8> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %e2 = mul <2 x i8> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %f2 = ashr <2 x i8> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %g2 = lshr <2 x i8> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %h2 = shl <2 x i8> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %c2 = add <2 x i8> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %d2 = sub <2 x i8> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %e2 = mul <2 x i8> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f2 = ashr <2 x i8> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %g2 = lshr <2 x i8> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %h2 = shl <2 x i8> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i2 = and <2 x i8> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j2 = or <2 x i8> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k2 = xor <2 x i8> undef, undef
@@ -688,12 +688,12 @@
 
 define void @vi16() {
 ; CHECK-MVE1-LABEL: 'vi16'
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %c2 = add <2 x i16> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %d2 = sub <2 x i16> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %e2 = mul <2 x i16> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %f2 = ashr <2 x i16> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %g2 = lshr <2 x i16> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %h2 = shl <2 x i16> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %c2 = add <2 x i16> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %d2 = sub <2 x i16> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %e2 = mul <2 x i16> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f2 = ashr <2 x i16> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %g2 = lshr <2 x i16> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %h2 = shl <2 x i16> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i2 = and <2 x i16> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j2 = or <2 x i16> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k2 = xor <2 x i16> undef, undef
@@ -727,12 +727,12 @@
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE2-LABEL: 'vi16'
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %c2 = add <2 x i16> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %d2 = sub <2 x i16> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %e2 = mul <2 x i16> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %f2 = ashr <2 x i16> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %g2 = lshr <2 x i16> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %h2 = shl <2 x i16> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %c2 = add <2 x i16> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %d2 = sub <2 x i16> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %e2 = mul <2 x i16> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f2 = ashr <2 x i16> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %g2 = lshr <2 x i16> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %h2 = shl <2 x i16> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %i2 = and <2 x i16> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %j2 = or <2 x i16> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %k2 = xor <2 x i16> undef, undef
@@ -922,12 +922,12 @@
 ; CHECK-V8R-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-SIZE-LABEL: 'vi16'
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %c2 = add <2 x i16> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %d2 = sub <2 x i16> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %e2 = mul <2 x i16> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %f2 = ashr <2 x i16> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %g2 = lshr <2 x i16> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %h2 = shl <2 x i16> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %c2 = add <2 x i16> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %d2 = sub <2 x i16> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %e2 = mul <2 x i16> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f2 = ashr <2 x i16> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %g2 = lshr <2 x i16> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %h2 = shl <2 x i16> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i2 = and <2 x i16> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j2 = or <2 x i16> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k2 = xor <2 x i16> undef, undef
@@ -1001,12 +1001,12 @@
 
 define void @vi32() {
 ; CHECK-MVE1-LABEL: 'vi32'
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %c2 = add <2 x i32> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %d2 = sub <2 x i32> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %e2 = mul <2 x i32> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %f2 = ashr <2 x i32> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %g2 = lshr <2 x i32> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %h2 = shl <2 x i32> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %c2 = add <2 x i32> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %d2 = sub <2 x i32> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %e2 = mul <2 x i32> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f2 = ashr <2 x i32> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %g2 = lshr <2 x i32> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %h2 = shl <2 x i32> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i2 = and <2 x i32> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j2 = or <2 x i32> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k2 = xor <2 x i32> undef, undef
@@ -1040,12 +1040,12 @@
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE2-LABEL: 'vi32'
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %c2 = add <2 x i32> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %d2 = sub <2 x i32> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %e2 = mul <2 x i32> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %f2 = ashr <2 x i32> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %g2 = lshr <2 x i32> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %h2 = shl <2 x i32> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %c2 = add <2 x i32> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %d2 = sub <2 x i32> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %e2 = mul <2 x i32> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f2 = ashr <2 x i32> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %g2 = lshr <2 x i32> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %h2 = shl <2 x i32> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %i2 = and <2 x i32> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %j2 = or <2 x i32> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %k2 = xor <2 x i32> undef, undef
@@ -1235,12 +1235,12 @@
 ; CHECK-V8R-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-SIZE-LABEL: 'vi32'
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %c2 = add <2 x i32> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %d2 = sub <2 x i32> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %e2 = mul <2 x i32> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %f2 = ashr <2 x i32> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %g2 = lshr <2 x i32> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %h2 = shl <2 x i32> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %c2 = add <2 x i32> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %d2 = sub <2 x i32> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %e2 = mul <2 x i32> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f2 = ashr <2 x i32> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %g2 = lshr <2 x i32> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %h2 = shl <2 x i32> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i2 = and <2 x i32> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j2 = or <2 x i32> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k2 = xor <2 x i32> undef, undef
@@ -1314,21 +1314,21 @@
 
 define void @vi64() {
 ; CHECK-MVE1-LABEL: 'vi64'
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %c2 = add <2 x i64> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %d2 = sub <2 x i64> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %e2 = mul <2 x i64> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %f2 = ashr <2 x i64> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %g2 = lshr <2 x i64> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %h2 = shl <2 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %c2 = add <2 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %d2 = sub <2 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %e2 = mul <2 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f2 = ashr <2 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %g2 = lshr <2 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %h2 = shl <2 x i64> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i2 = and <2 x i64> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j2 = or <2 x i64> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k2 = xor <2 x i64> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %c4 = add <4 x i64> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %d4 = sub <4 x i64> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %e4 = mul <4 x i64> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %f4 = ashr <4 x i64> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %g4 = lshr <4 x i64> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %h4 = shl <4 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %c4 = add <4 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %d4 = sub <4 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e4 = mul <4 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %f4 = ashr <4 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %g4 = lshr <4 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %h4 = shl <4 x i64> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %i4 = and <4 x i64> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %j4 = or <4 x i64> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %k4 = xor <4 x i64> undef, undef
@@ -1341,33 +1341,33 @@
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %i8 = and <8 x i64> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %j8 = or <8 x i64> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %k8 = xor <8 x i64> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %c16 = add <16 x i64> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %d16 = sub <16 x i64> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %e16 = mul <16 x i64> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %f16 = ashr <16 x i64> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %g16 = lshr <16 x i64> undef, undef
-; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %h16 = shl <16 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %c16 = add <16 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %d16 = sub <16 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %e16 = mul <16 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %f16 = ashr <16 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %g16 = lshr <16 x i64> undef, undef
+; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %h16 = shl <16 x i64> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %i16 = and <16 x i64> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %j16 = or <16 x i64> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %k16 = xor <16 x i64> undef, undef
 ; CHECK-MVE1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE2-LABEL: 'vi64'
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %c2 = add <2 x i64> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %d2 = sub <2 x i64> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %e2 = mul <2 x i64> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %f2 = ashr <2 x i64> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %g2 = lshr <2 x i64> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %h2 = shl <2 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %c2 = add <2 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %d2 = sub <2 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %e2 = mul <2 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f2 = ashr <2 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %g2 = lshr <2 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %h2 = shl <2 x i64> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %i2 = and <2 x i64> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %j2 = or <2 x i64> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %k2 = xor <2 x i64> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %c4 = add <4 x i64> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %d4 = sub <4 x i64> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %e4 = mul <4 x i64> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %f4 = ashr <4 x i64> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %g4 = lshr <4 x i64> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %h4 = shl <4 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %c4 = add <4 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %d4 = sub <4 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e4 = mul <4 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %f4 = ashr <4 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %g4 = lshr <4 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %h4 = shl <4 x i64> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %i4 = and <4 x i64> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %j4 = or <4 x i64> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %k4 = xor <4 x i64> undef, undef
@@ -1380,24 +1380,24 @@
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %i8 = and <8 x i64> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %j8 = or <8 x i64> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %k8 = xor <8 x i64> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %c16 = add <16 x i64> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %d16 = sub <16 x i64> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %e16 = mul <16 x i64> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %f16 = ashr <16 x i64> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %g16 = lshr <16 x i64> undef, undef
-; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %h16 = shl <16 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %c16 = add <16 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %d16 = sub <16 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %e16 = mul <16 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %f16 = ashr <16 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %g16 = lshr <16 x i64> undef, undef
+; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %h16 = shl <16 x i64> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %i16 = and <16 x i64> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %j16 = or <16 x i64> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %k16 = xor <16 x i64> undef, undef
 ; CHECK-MVE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE4-LABEL: 'vi64'
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %c2 = add <2 x i64> undef, undef
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %d2 = sub <2 x i64> undef, undef
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %e2 = mul <2 x i64> undef, undef
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %f2 = ashr <2 x i64> undef, undef
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %g2 = lshr <2 x i64> undef, undef
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %h2 = shl <2 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %c2 = add <2 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %d2 = sub <2 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %e2 = mul <2 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f2 = ashr <2 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %g2 = lshr <2 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %h2 = shl <2 x i64> undef, undef
 ; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %i2 = and <2 x i64> undef, undef
 ; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %j2 = or <2 x i64> undef, undef
 ; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %k2 = xor <2 x i64> undef, undef
@@ -1410,21 +1410,21 @@
 ; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %i4 = and <4 x i64> undef, undef
 ; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %j4 = or <4 x i64> undef, undef
 ; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %k4 = xor <4 x i64> undef, undef
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %c8 = add <8 x i64> undef, undef
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %d8 = sub <8 x i64> undef, undef
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %e8 = mul <8 x i64> undef, undef
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %f8 = ashr <8 x i64> undef, undef
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %g8 = lshr <8 x i64> undef, undef
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %h8 = shl <8 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %c8 = add <8 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %d8 = sub <8 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %e8 = mul <8 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %f8 = ashr <8 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %g8 = lshr <8 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %h8 = shl <8 x i64> undef, undef
 ; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %i8 = and <8 x i64> undef, undef
 ; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %j8 = or <8 x i64> undef, undef
 ; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %k8 = xor <8 x i64> undef, undef
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 544 for instruction: %c16 = add <16 x i64> undef, undef
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 544 for instruction: %d16 = sub <16 x i64> undef, undef
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 544 for instruction: %e16 = mul <16 x i64> undef, undef
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 544 for instruction: %f16 = ashr <16 x i64> undef, undef
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 544 for instruction: %g16 = lshr <16 x i64> undef, undef
-; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 544 for instruction: %h16 = shl <16 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %c16 = add <16 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %d16 = sub <16 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %e16 = mul <16 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %f16 = ashr <16 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %g16 = lshr <16 x i64> undef, undef
+; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %h16 = shl <16 x i64> undef, undef
 ; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %i16 = and <16 x i64> undef, undef
 ; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %j16 = or <16 x i64> undef, undef
 ; CHECK-MVE4-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %k16 = xor <16 x i64> undef, undef
@@ -1548,21 +1548,21 @@
 ; CHECK-V8R-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-SIZE-LABEL: 'vi64'
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %c2 = add <2 x i64> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %d2 = sub <2 x i64> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %e2 = mul <2 x i64> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %f2 = ashr <2 x i64> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %g2 = lshr <2 x i64> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %h2 = shl <2 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %c2 = add <2 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %d2 = sub <2 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %e2 = mul <2 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f2 = ashr <2 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %g2 = lshr <2 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %h2 = shl <2 x i64> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i2 = and <2 x i64> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j2 = or <2 x i64> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k2 = xor <2 x i64> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %c4 = add <4 x i64> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %d4 = sub <4 x i64> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %e4 = mul <4 x i64> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %f4 = ashr <4 x i64> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %g4 = lshr <4 x i64> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %h4 = shl <4 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %c4 = add <4 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %d4 = sub <4 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e4 = mul <4 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %f4 = ashr <4 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %g4 = lshr <4 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %h4 = shl <4 x i64> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %i4 = and <4 x i64> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %j4 = or <4 x i64> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %k4 = xor <4 x i64> undef, undef
@@ -1575,12 +1575,12 @@
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %i8 = and <8 x i64> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %j8 = or <8 x i64> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %k8 = xor <8 x i64> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %c16 = add <16 x i64> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %d16 = sub <16 x i64> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %e16 = mul <16 x i64> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %f16 = ashr <16 x i64> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %g16 = lshr <16 x i64> undef, undef
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %h16 = shl <16 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %c16 = add <16 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %d16 = sub <16 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %e16 = mul <16 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %f16 = ashr <16 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %g16 = lshr <16 x i64> undef, undef
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %h16 = shl <16 x i64> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %i16 = and <16 x i64> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %j16 = or <16 x i64> undef, undef
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %k16 = xor <16 x i64> undef, undef
diff --git a/llvm/test/Analysis/CostModel/ARM/cast.ll b/llvm/test/Analysis/CostModel/ARM/cast.ll
--- a/llvm/test/Analysis/CostModel/ARM/cast.ll
+++ b/llvm/test/Analysis/CostModel/ARM/cast.ll
@@ -557,36 +557,36 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r87hf = fpext <4 x half> undef to <4 x float>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r88hf = fpext <8 x half> undef to <8 x float>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %r89hf = fpext <16 x half> undef to <16 x float>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r90 = fptoui <2 x float> undef to <2 x i1>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r91 = fptosi <2 x float> undef to <2 x i1>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r92 = fptoui <2 x float> undef to <2 x i8>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r93 = fptosi <2 x float> undef to <2 x i8>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r94 = fptoui <2 x float> undef to <2 x i16>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r95 = fptosi <2 x float> undef to <2 x i16>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r96 = fptoui <2 x float> undef to <2 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r97 = fptosi <2 x float> undef to <2 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r98 = fptoui <2 x float> undef to <2 x i64>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r99 = fptosi <2 x float> undef to <2 x i64>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r90h = fptoui <2 x half> undef to <2 x i1>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r91h = fptosi <2 x half> undef to <2 x i1>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r92h = fptoui <2 x half> undef to <2 x i8>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r93h = fptosi <2 x half> undef to <2 x i8>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r94h = fptoui <2 x half> undef to <2 x i16>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r95h = fptosi <2 x half> undef to <2 x i16>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r96h = fptoui <2 x half> undef to <2 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r97h = fptosi <2 x half> undef to <2 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r98h = fptoui <2 x half> undef to <2 x i64>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r99h = fptosi <2 x half> undef to <2 x i64>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r100 = fptoui <2 x double> undef to <2 x i1>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r101 = fptosi <2 x double> undef to <2 x i1>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r102 = fptoui <2 x double> undef to <2 x i8>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r103 = fptosi <2 x double> undef to <2 x i8>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r104 = fptoui <2 x double> undef to <2 x i16>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r105 = fptosi <2 x double> undef to <2 x i16>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r106 = fptoui <2 x double> undef to <2 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r107 = fptosi <2 x double> undef to <2 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r108 = fptoui <2 x double> undef to <2 x i64>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r109 = fptosi <2 x double> undef to <2 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r90 = fptoui <2 x float> undef to <2 x i1>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r91 = fptosi <2 x float> undef to <2 x i1>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r92 = fptoui <2 x float> undef to <2 x i8>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r93 = fptosi <2 x float> undef to <2 x i8>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r94 = fptoui <2 x float> undef to <2 x i16>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r95 = fptosi <2 x float> undef to <2 x i16>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r96 = fptoui <2 x float> undef to <2 x i32>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r97 = fptosi <2 x float> undef to <2 x i32>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %r98 = fptoui <2 x float> undef to <2 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %r99 = fptosi <2 x float> undef to <2 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r90h = fptoui <2 x half> undef to <2 x i1>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r91h = fptosi <2 x half> undef to <2 x i1>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r92h = fptoui <2 x half> undef to <2 x i8>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r93h = fptosi <2 x half> undef to <2 x i8>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r94h = fptoui <2 x half> undef to <2 x i16>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r95h = fptosi <2 x half> undef to <2 x i16>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r96h = fptoui <2 x half> undef to <2 x i32>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r97h = fptosi <2 x half> undef to <2 x i32>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %r98h = fptoui <2 x half> undef to <2 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %r99h = fptosi <2 x half> undef to <2 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r100 = fptoui <2 x double> undef to <2 x i1>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r101 = fptosi <2 x double> undef to <2 x i1>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r102 = fptoui <2 x double> undef to <2 x i8>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r103 = fptosi <2 x double> undef to <2 x i8>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r104 = fptoui <2 x double> undef to <2 x i16>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r105 = fptosi <2 x double> undef to <2 x i16>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r106 = fptoui <2 x double> undef to <2 x i32>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %r107 = fptosi <2 x double> undef to <2 x i32>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %r108 = fptoui <2 x double> undef to <2 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %r109 = fptosi <2 x double> undef to <2 x i64>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r110 = fptoui <4 x float> undef to <4 x i1>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r111 = fptosi <4 x float> undef to <4 x i1>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r112 = fptoui <4 x float> undef to <4 x i8>
@@ -595,8 +595,8 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r115 = fptosi <4 x float> undef to <4 x i16>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r116 = fptoui <4 x float> undef to <4 x i32>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r117 = fptosi <4 x float> undef to <4 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %r118 = fptoui <4 x float> undef to <4 x i64>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %r119 = fptosi <4 x float> undef to <4 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 274 for instruction: %r118 = fptoui <4 x float> undef to <4 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 274 for instruction: %r119 = fptosi <4 x float> undef to <4 x i64>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r110h = fptoui <4 x half> undef to <4 x i1>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r111h = fptosi <4 x half> undef to <4 x i1>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r112h = fptoui <4 x half> undef to <4 x i8>
@@ -605,18 +605,18 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r115h = fptosi <4 x half> undef to <4 x i16>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r116h = fptoui <4 x half> undef to <4 x i32>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r117h = fptosi <4 x half> undef to <4 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %r118h = fptoui <4 x half> undef to <4 x i64>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %r119h = fptosi <4 x half> undef to <4 x i64>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %r120 = fptoui <4 x double> undef to <4 x i1>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %r121 = fptosi <4 x double> undef to <4 x i1>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %r122 = fptoui <4 x double> undef to <4 x i8>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %r123 = fptosi <4 x double> undef to <4 x i8>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %r124 = fptoui <4 x double> undef to <4 x i16>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %r125 = fptosi <4 x double> undef to <4 x i16>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %r126 = fptoui <4 x double> undef to <4 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %r127 = fptosi <4 x double> undef to <4 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %r128 = fptoui <4 x double> undef to <4 x i64>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %r129 = fptosi <4 x double> undef to <4 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 274 for instruction: %r118h = fptoui <4 x half> undef to <4 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 274 for instruction: %r119h = fptosi <4 x half> undef to <4 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 146 for instruction: %r120 = fptoui <4 x double> undef to <4 x i1>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 146 for instruction: %r121 = fptosi <4 x double> undef to <4 x i1>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 146 for instruction: %r122 = fptoui <4 x double> undef to <4 x i8>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 146 for instruction: %r123 = fptosi <4 x double> undef to <4 x i8>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 146 for instruction: %r124 = fptoui <4 x double> undef to <4 x i16>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 146 for instruction: %r125 = fptosi <4 x double> undef to <4 x i16>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 146 for instruction: %r126 = fptoui <4 x double> undef to <4 x i32>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 146 for instruction: %r127 = fptosi <4 x double> undef to <4 x i32>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %r128 = fptoui <4 x double> undef to <4 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %r129 = fptosi <4 x double> undef to <4 x i64>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r130 = fptoui <8 x float> undef to <8 x i1>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r131 = fptosi <8 x float> undef to <8 x i1>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r132 = fptoui <8 x float> undef to <8 x i8>
@@ -625,8 +625,8 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r135 = fptosi <8 x float> undef to <8 x i16>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r136 = fptoui <8 x float> undef to <8 x i32>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r137 = fptosi <8 x float> undef to <8 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 328 for instruction: %r138 = fptoui <8 x float> undef to <8 x i64>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 328 for instruction: %r139 = fptosi <8 x float> undef to <8 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1096 for instruction: %r138 = fptoui <8 x float> undef to <8 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1096 for instruction: %r139 = fptosi <8 x float> undef to <8 x i64>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r130h = fptoui <8 x half> undef to <8 x i1>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r131h = fptosi <8 x half> undef to <8 x i1>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r132h = fptoui <8 x half> undef to <8 x i8>
@@ -635,18 +635,18 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r135h = fptosi <8 x half> undef to <8 x i16>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r136h = fptoui <8 x half> undef to <8 x i32>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r137h = fptosi <8 x half> undef to <8 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r138h = fptoui <8 x half> undef to <8 x i64>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r139h = fptosi <8 x half> undef to <8 x i64>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r140 = fptoui <8 x double> undef to <8 x i1>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r141 = fptosi <8 x double> undef to <8 x i1>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r142 = fptoui <8 x double> undef to <8 x i8>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r143 = fptosi <8 x double> undef to <8 x i8>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r144 = fptoui <8 x double> undef to <8 x i16>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r145 = fptosi <8 x double> undef to <8 x i16>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 328 for instruction: %r146 = fptoui <8 x double> undef to <8 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 328 for instruction: %r147 = fptosi <8 x double> undef to <8 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 320 for instruction: %r148 = fptoui <8 x double> undef to <8 x i64>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 320 for instruction: %r149 = fptosi <8 x double> undef to <8 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1098 for instruction: %r138h = fptoui <8 x half> undef to <8 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1098 for instruction: %r139h = fptosi <8 x half> undef to <8 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 586 for instruction: %r140 = fptoui <8 x double> undef to <8 x i1>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 586 for instruction: %r141 = fptosi <8 x double> undef to <8 x i1>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 586 for instruction: %r142 = fptoui <8 x double> undef to <8 x i8>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 586 for instruction: %r143 = fptosi <8 x double> undef to <8 x i8>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 586 for instruction: %r144 = fptoui <8 x double> undef to <8 x i16>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 586 for instruction: %r145 = fptosi <8 x double> undef to <8 x i16>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 584 for instruction: %r146 = fptoui <8 x double> undef to <8 x i32>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 584 for instruction: %r147 = fptosi <8 x double> undef to <8 x i32>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1088 for instruction: %r148 = fptoui <8 x double> undef to <8 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1088 for instruction: %r149 = fptosi <8 x double> undef to <8 x i64>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r150 = fptoui <16 x float> undef to <16 x i1>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r151 = fptosi <16 x float> undef to <16 x i1>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r152 = fptoui <16 x float> undef to <16 x i8>
@@ -655,8 +655,8 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %r155 = fptosi <16 x float> undef to <16 x i16>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r156 = fptoui <16 x float> undef to <16 x i32>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r157 = fptosi <16 x float> undef to <16 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1312 for instruction: %r158 = fptoui <16 x float> undef to <16 x i64>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1312 for instruction: %r159 = fptosi <16 x float> undef to <16 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4384 for instruction: %r158 = fptoui <16 x float> undef to <16 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4384 for instruction: %r159 = fptosi <16 x float> undef to <16 x i64>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r150h = fptoui <16 x half> undef to <16 x i1>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r151h = fptosi <16 x half> undef to <16 x i1>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r152h = fptoui <16 x half> undef to <16 x i8>
@@ -665,18 +665,18 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r155h = fptosi <16 x half> undef to <16 x i16>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %r156h = fptoui <16 x half> undef to <16 x i32>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %r157h = fptosi <16 x half> undef to <16 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1320 for instruction: %r158h = fptoui <16 x half> undef to <16 x i64>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1320 for instruction: %r159h = fptosi <16 x half> undef to <16 x i64>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1322 for instruction: %r160 = fptoui <16 x double> undef to <16 x i1>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1322 for instruction: %r161 = fptosi <16 x double> undef to <16 x i1>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1322 for instruction: %r162 = fptoui <16 x double> undef to <16 x i8>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1322 for instruction: %r163 = fptosi <16 x double> undef to <16 x i8>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1320 for instruction: %r164 = fptoui <16 x double> undef to <16 x i16>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1320 for instruction: %r165 = fptosi <16 x double> undef to <16 x i16>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1312 for instruction: %r166 = fptoui <16 x double> undef to <16 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1312 for instruction: %r167 = fptosi <16 x double> undef to <16 x i32>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1280 for instruction: %r168 = fptoui <16 x double> undef to <16 x i64>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1280 for instruction: %r169 = fptosi <16 x double> undef to <16 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4392 for instruction: %r158h = fptoui <16 x half> undef to <16 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4392 for instruction: %r159h = fptosi <16 x half> undef to <16 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2346 for instruction: %r160 = fptoui <16 x double> undef to <16 x i1>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2346 for instruction: %r161 = fptosi <16 x double> undef to <16 x i1>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2346 for instruction: %r162 = fptoui <16 x double> undef to <16 x i8>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2346 for instruction: %r163 = fptosi <16 x double> undef to <16 x i8>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2344 for instruction: %r164 = fptoui <16 x double> undef to <16 x i16>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2344 for instruction: %r165 = fptosi <16 x double> undef to <16 x i16>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2336 for instruction: %r166 = fptoui <16 x double> undef to <16 x i32>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2336 for instruction: %r167 = fptosi <16 x double> undef to <16 x i32>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4352 for instruction: %r168 = fptoui <16 x double> undef to <16 x i64>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4352 for instruction: %r169 = fptosi <16 x double> undef to <16 x i64>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r170 = uitofp <2 x i1> undef to <2 x float>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r171 = sitofp <2 x i1> undef to <2 x float>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r172 = uitofp <2 x i8> undef to <2 x float>
@@ -697,16 +697,16 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r177h = sitofp <2 x i32> undef to <2 x half>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r178h = uitofp <2 x i64> undef to <2 x half>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r179h = sitofp <2 x i64> undef to <2 x half>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %r180 = uitofp <2 x i1> undef to <2 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %r181 = sitofp <2 x i1> undef to <2 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %r182 = uitofp <2 x i8> undef to <2 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %r183 = sitofp <2 x i8> undef to <2 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %r184 = uitofp <2 x i16> undef to <2 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %r185 = sitofp <2 x i16> undef to <2 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %r186 = uitofp <2 x i32> undef to <2 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %r187 = sitofp <2 x i32> undef to <2 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %r188 = uitofp <2 x i64> undef to <2 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %r189 = sitofp <2 x i64> undef to <2 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %r180 = uitofp <2 x i1> undef to <2 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %r181 = sitofp <2 x i1> undef to <2 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %r182 = uitofp <2 x i8> undef to <2 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %r183 = sitofp <2 x i8> undef to <2 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %r184 = uitofp <2 x i16> undef to <2 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %r185 = sitofp <2 x i16> undef to <2 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %r186 = uitofp <2 x i32> undef to <2 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %r187 = sitofp <2 x i32> undef to <2 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %r188 = uitofp <2 x i64> undef to <2 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %r189 = sitofp <2 x i64> undef to <2 x double>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r190 = uitofp <4 x i1> undef to <4 x float>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r191 = sitofp <4 x i1> undef to <4 x float>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r192 = uitofp <4 x i8> undef to <4 x float>
@@ -727,16 +727,16 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r197h = sitofp <4 x i32> undef to <4 x half>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r198h = uitofp <4 x i64> undef to <4 x half>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r199h = sitofp <4 x i64> undef to <4 x half>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 130 for instruction: %r200 = uitofp <4 x i1> undef to <4 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 130 for instruction: %r201 = sitofp <4 x i1> undef to <4 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 130 for instruction: %r202 = uitofp <4 x i8> undef to <4 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 130 for instruction: %r203 = sitofp <4 x i8> undef to <4 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 130 for instruction: %r204 = uitofp <4 x i16> undef to <4 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 130 for instruction: %r205 = sitofp <4 x i16> undef to <4 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 130 for instruction: %r206 = uitofp <4 x i32> undef to <4 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 130 for instruction: %r207 = sitofp <4 x i32> undef to <4 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %r208 = uitofp <4 x i64> undef to <4 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %r209 = sitofp <4 x i64> undef to <4 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 98 for instruction: %r200 = uitofp <4 x i1> undef to <4 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 98 for instruction: %r201 = sitofp <4 x i1> undef to <4 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 98 for instruction: %r202 = uitofp <4 x i8> undef to <4 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 98 for instruction: %r203 = sitofp <4 x i8> undef to <4 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 98 for instruction: %r204 = uitofp <4 x i16> undef to <4 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 98 for instruction: %r205 = sitofp <4 x i16> undef to <4 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 98 for instruction: %r206 = uitofp <4 x i32> undef to <4 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 98 for instruction: %r207 = sitofp <4 x i32> undef to <4 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %r208 = uitofp <4 x i64> undef to <4 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %r209 = sitofp <4 x i64> undef to <4 x double>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r210 = uitofp <8 x i1> undef to <8 x float>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r211 = sitofp <8 x i1> undef to <8 x float>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r212 = uitofp <8 x i8> undef to <8 x float>
@@ -757,16 +757,16 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r217h = sitofp <8 x i32> undef to <8 x half>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r218h = uitofp <8 x i64> undef to <8 x half>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r219h = sitofp <8 x i64> undef to <8 x half>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r220 = uitofp <8 x i1> undef to <8 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r221 = sitofp <8 x i1> undef to <8 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r222 = uitofp <8 x i8> undef to <8 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r223 = sitofp <8 x i8> undef to <8 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r224 = uitofp <8 x i16> undef to <8 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r225 = sitofp <8 x i16> undef to <8 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r226 = uitofp <8 x i16> undef to <8 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r227 = sitofp <8 x i16> undef to <8 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 512 for instruction: %r228 = uitofp <8 x i64> undef to <8 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 512 for instruction: %r229 = sitofp <8 x i64> undef to <8 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 394 for instruction: %r220 = uitofp <8 x i1> undef to <8 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 394 for instruction: %r221 = sitofp <8 x i1> undef to <8 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 394 for instruction: %r222 = uitofp <8 x i8> undef to <8 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 394 for instruction: %r223 = sitofp <8 x i8> undef to <8 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 394 for instruction: %r224 = uitofp <8 x i16> undef to <8 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 394 for instruction: %r225 = sitofp <8 x i16> undef to <8 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 394 for instruction: %r226 = uitofp <8 x i16> undef to <8 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 394 for instruction: %r227 = sitofp <8 x i16> undef to <8 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 384 for instruction: %r228 = uitofp <8 x i64> undef to <8 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 384 for instruction: %r229 = sitofp <8 x i64> undef to <8 x double>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r230 = uitofp <16 x i1> undef to <16 x float>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r231 = sitofp <16 x i1> undef to <16 x float>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r232 = uitofp <16 x i8> undef to <16 x float>
@@ -787,16 +787,16 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %r237h = sitofp <16 x i32> undef to <16 x half>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 168 for instruction: %r238h = uitofp <16 x i64> undef to <16 x half>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 168 for instruction: %r239h = sitofp <16 x i64> undef to <16 x half>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2090 for instruction: %r240 = uitofp <16 x i1> undef to <16 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2090 for instruction: %r241 = sitofp <16 x i1> undef to <16 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2090 for instruction: %r242 = uitofp <16 x i8> undef to <16 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2090 for instruction: %r243 = sitofp <16 x i8> undef to <16 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2088 for instruction: %r244 = uitofp <16 x i16> undef to <16 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2088 for instruction: %r245 = sitofp <16 x i16> undef to <16 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2088 for instruction: %r246 = uitofp <16 x i16> undef to <16 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2088 for instruction: %r247 = sitofp <16 x i16> undef to <16 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2048 for instruction: %r248 = uitofp <16 x i64> undef to <16 x double>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2048 for instruction: %r249 = sitofp <16 x i64> undef to <16 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1578 for instruction: %r240 = uitofp <16 x i1> undef to <16 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1578 for instruction: %r241 = sitofp <16 x i1> undef to <16 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1578 for instruction: %r242 = uitofp <16 x i8> undef to <16 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1578 for instruction: %r243 = sitofp <16 x i8> undef to <16 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1576 for instruction: %r244 = uitofp <16 x i16> undef to <16 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1576 for instruction: %r245 = sitofp <16 x i16> undef to <16 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1576 for instruction: %r246 = uitofp <16 x i16> undef to <16 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1576 for instruction: %r247 = sitofp <16 x i16> undef to <16 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1536 for instruction: %r248 = uitofp <16 x i64> undef to <16 x double>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1536 for instruction: %r249 = sitofp <16 x i64> undef to <16 x double>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; CHECK-V8M-MAIN-RECIP-LABEL: 'casts'
diff --git a/llvm/test/Analysis/CostModel/ARM/cast_ldst.ll b/llvm/test/Analysis/CostModel/ARM/cast_ldst.ll
--- a/llvm/test/Analysis/CostModel/ARM/cast_ldst.ll
+++ b/llvm/test/Analysis/CostModel/ARM/cast_ldst.ll
@@ -81,14 +81,14 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadi8 = load i8, i8* undef, align 1
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadi16 = load i16, i16* undef, align 2
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadi32 = load i32, i32* undef, align 4
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %loadv2i8 = load <2 x i8>, <2 x i8>* undef, align 2
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %loadv2i8 = load <2 x i8>, <2 x i8>* undef, align 2
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %loadv4i8 = load <4 x i8>, <4 x i8>* undef, align 4
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %loadv8i8 = load <8 x i8>, <8 x i8>* undef, align 8
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %loadv16i8 = load <16 x i8>, <16 x i8>* undef, align 16
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %loadv2i16 = load <2 x i16>, <2 x i16>* undef, align 4
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %loadv2i16 = load <2 x i16>, <2 x i16>* undef, align 4
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %loadv4i16 = load <4 x i16>, <4 x i16>* undef, align 8
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %loadv8i16 = load <8 x i16>, <8 x i16>* undef, align 16
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %loadv2i32 = load <2 x i32>, <2 x i32>* undef, align 8
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %loadv2i32 = load <2 x i32>, <2 x i32>* undef, align 8
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %loadv4i32 = load <4 x i32>, <4 x i32>* undef, align 16
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r0 = sext i8 %loadi8 to i16
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r1 = zext i8 %loadi8 to i16
@@ -774,9 +774,9 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %i1632, i16* undef, align 2
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %i1664, i16* undef, align 2
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 %i3264, i32* undef, align 4
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <2 x i8> %v2816, <2 x i8>* undef, align 2
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <2 x i8> %v2832, <2 x i8>* undef, align 2
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <2 x i8> %v2864, <2 x i8>* undef, align 2
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: store <2 x i8> %v2816, <2 x i8>* undef, align 2
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: store <2 x i8> %v2832, <2 x i8>* undef, align 2
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: store <2 x i8> %v2864, <2 x i8>* undef, align 2
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i8> %v4816, <4 x i8>* undef, align 4
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i8> %v4832, <4 x i8>* undef, align 4
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i8> %v4864, <4 x i8>* undef, align 4
@@ -786,13 +786,13 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <16 x i8> %v16816, <16 x i8>* undef, align 16
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <16 x i8> %v16832, <16 x i8>* undef, align 16
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <16 x i8> %v16864, <16 x i8>* undef, align 16
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <2 x i16> %v21632, <2 x i16>* undef, align 4
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <2 x i16> %v21664, <2 x i16>* undef, align 4
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: store <2 x i16> %v21632, <2 x i16>* undef, align 4
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: store <2 x i16> %v21664, <2 x i16>* undef, align 4
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i16> %v41632, <4 x i16>* undef, align 8
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i16> %v41664, <4 x i16>* undef, align 8
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <8 x i16> %v81632, <8 x i16>* undef, align 16
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <8 x i16> %v81664, <8 x i16>* undef, align 16
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <2 x i32> %v23264, <2 x i32>* undef, align 8
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: store <2 x i32> %v23264, <2 x i32>* undef, align 8
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i32> %v43264, <4 x i32>* undef, align 16
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
@@ -1273,11 +1273,11 @@
 ; CHECK-MVE-RECIP-LABEL: 'load_fpextends'
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadf16 = load half, half* undef, align 2
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadf32 = load float, float* undef, align 4
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %loadv2f16 = load <2 x half>, <2 x half>* undef, align 4
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %loadv4f16 = load <4 x half>, <4 x half>* undef, align 8
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %loadv2f16 = load <2 x half>, <2 x half>* undef, align 4
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %loadv4f16 = load <4 x half>, <4 x half>* undef, align 8
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %loadv8f16 = load <8 x half>, <8 x half>* undef, align 16
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %loadv16f16 = load <16 x half>, <16 x half>* undef, align 32
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %loadv2f32 = load <2 x float>, <2 x float>* undef, align 8
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %loadv2f32 = load <2 x float>, <2 x float>* undef, align 8
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %loadv4f32 = load <4 x float>, <4 x float>* undef, align 16
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %loadv8f32 = load <8 x float>, <8 x float>* undef, align 32
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r1 = fpext half %loadf16 to float
@@ -1567,13 +1567,13 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store half %i1632, half* undef, align 2
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store half %i1664, half* undef, align 2
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store float %i3264, float* undef, align 4
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <2 x half> %v21632, <2 x half>* undef, align 4
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <2 x half> %v21664, <2 x half>* undef, align 4
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <2 x half> %v21632, <2 x half>* undef, align 4
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <2 x half> %v21664, <2 x half>* undef, align 4
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x half> %v41632, <4 x half>* undef, align 8
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: store <4 x half> %v41664, <4 x half>* undef, align 8
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <4 x half> %v41664, <4 x half>* undef, align 8
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <8 x half> %v81632, <8 x half>* undef, align 16
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <8 x half> %v81664, <8 x half>* undef, align 16
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <2 x float> %v23264, <2 x float>* undef, align 8
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <2 x float> %v23264, <2 x float>* undef, align 8
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x float> %v43264, <4 x float>* undef, align 16
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
diff --git a/llvm/test/Analysis/CostModel/ARM/cmps.ll b/llvm/test/Analysis/CostModel/ARM/cmps.ll
--- a/llvm/test/Analysis/CostModel/ARM/cmps.ll
+++ b/llvm/test/Analysis/CostModel/ARM/cmps.ll
@@ -22,9 +22,9 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a9 = fcmp ogt double undef, undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a10 = fcmp olt <8 x half> undef, undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a11 = fcmp oge <4 x float> undef, undef
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %a12 = fcmp oge <2 x double> undef, undef
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a12 = fcmp oge <2 x double> undef, undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %p = icmp eq i32* undef, undef
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %q = icmp eq <4 x i32*> undef, undef
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %q = icmp eq <4 x i32*> undef, undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; CHECK-V8M-MAIN-RECIP-LABEL: 'cmps'
@@ -183,8 +183,8 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %s4 = select <4 x i1> %c4, <4 x i32> undef, <4 x i32> undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %c5 = icmp slt i32* undef, undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %s5 = select i1 %c5, i32* undef, i32* undef
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %c6 = icmp slt <4 x i32*> undef, undef
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %s6 = select <4 x i1> %c6, <4 x i32*> undef, <4 x i32*> undef
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %c6 = icmp slt <4 x i32*> undef, undef
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %s6 = select <4 x i1> %c6, <4 x i32*> undef, <4 x i32*> undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-V8M-MAIN-RECIP-LABEL: 'minmax'
diff --git a/llvm/test/Analysis/CostModel/ARM/divrem.ll b/llvm/test/Analysis/CostModel/ARM/divrem.ll
--- a/llvm/test/Analysis/CostModel/ARM/divrem.ll
+++ b/llvm/test/Analysis/CostModel/ARM/divrem.ll
@@ -423,22 +423,22 @@
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-LABEL: 'vi8'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t1 = sdiv <2 x i8> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t2 = udiv <2 x i8> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t3 = srem <2 x i8> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t4 = urem <2 x i8> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t1 = sdiv <2 x i8> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t2 = udiv <2 x i8> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t3 = srem <2 x i8> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t4 = urem <2 x i8> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f1 = sdiv <4 x i8> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f2 = udiv <4 x i8> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f3 = srem <4 x i8> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f4 = urem <4 x i8> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e1 = sdiv <8 x i8> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e2 = udiv <8 x i8> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e3 = srem <8 x i8> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e4 = urem <8 x i8> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s1 = sdiv <16 x i8> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s2 = udiv <16 x i8> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s3 = srem <16 x i8> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s4 = urem <16 x i8> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e1 = sdiv <8 x i8> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e2 = udiv <8 x i8> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e3 = srem <8 x i8> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e4 = urem <8 x i8> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s1 = sdiv <16 x i8> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s2 = udiv <16 x i8> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s3 = srem <16 x i8> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s4 = urem <16 x i8> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-V8M-MAIN-LABEL: 'vi8'
@@ -538,22 +538,22 @@
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-LABEL: 'vi16'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t1 = sdiv <2 x i16> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t2 = udiv <2 x i16> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t3 = srem <2 x i16> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t4 = urem <2 x i16> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t1 = sdiv <2 x i16> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t2 = udiv <2 x i16> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t3 = srem <2 x i16> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t4 = urem <2 x i16> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f1 = sdiv <4 x i16> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f2 = udiv <4 x i16> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f3 = srem <4 x i16> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f4 = urem <4 x i16> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e1 = sdiv <8 x i16> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e2 = udiv <8 x i16> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e3 = srem <8 x i16> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e4 = urem <8 x i16> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s1 = sdiv <16 x i16> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s2 = udiv <16 x i16> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s3 = srem <16 x i16> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s4 = urem <16 x i16> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e1 = sdiv <8 x i16> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e2 = udiv <8 x i16> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e3 = srem <8 x i16> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e4 = urem <8 x i16> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s1 = sdiv <16 x i16> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s2 = udiv <16 x i16> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s3 = srem <16 x i16> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s4 = urem <16 x i16> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-V8M-MAIN-LABEL: 'vi16'
@@ -653,22 +653,22 @@
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-LABEL: 'vi32'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t1 = sdiv <2 x i32> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t2 = udiv <2 x i32> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t3 = srem <2 x i32> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t4 = urem <2 x i32> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t1 = sdiv <2 x i32> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t2 = udiv <2 x i32> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t3 = srem <2 x i32> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t4 = urem <2 x i32> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f1 = sdiv <4 x i32> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f2 = udiv <4 x i32> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f3 = srem <4 x i32> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f4 = urem <4 x i32> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e1 = sdiv <8 x i32> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e2 = udiv <8 x i32> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e3 = srem <8 x i32> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e4 = urem <8 x i32> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s1 = sdiv <16 x i32> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s2 = udiv <16 x i32> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s3 = srem <16 x i32> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s4 = urem <16 x i32> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e1 = sdiv <8 x i32> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e2 = udiv <8 x i32> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e3 = srem <8 x i32> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e4 = urem <8 x i32> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s1 = sdiv <16 x i32> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s2 = udiv <16 x i32> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s3 = srem <16 x i32> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s4 = urem <16 x i32> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-V8M-MAIN-LABEL: 'vi32'
@@ -768,22 +768,22 @@
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-LABEL: 'vi64'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t1 = sdiv <2 x i64> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t2 = udiv <2 x i64> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t3 = srem <2 x i64> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t4 = urem <2 x i64> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %f1 = sdiv <4 x i64> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %f2 = udiv <4 x i64> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f3 = srem <4 x i64> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f4 = urem <4 x i64> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %t1 = sdiv <2 x i64> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %t2 = udiv <2 x i64> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %t3 = srem <2 x i64> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %t4 = urem <2 x i64> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %f1 = sdiv <4 x i64> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %f2 = udiv <4 x i64> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %f3 = srem <4 x i64> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %f4 = urem <4 x i64> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %e1 = sdiv <8 x i64> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %e2 = udiv <8 x i64> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e3 = srem <8 x i64> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e4 = urem <8 x i64> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %s1 = sdiv <16 x i64> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %s2 = udiv <16 x i64> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s3 = srem <16 x i64> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s4 = urem <16 x i64> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %s1 = sdiv <16 x i64> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %s2 = udiv <16 x i64> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %s3 = srem <16 x i64> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %s4 = urem <16 x i64> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-V8M-MAIN-LABEL: 'vi64'
@@ -873,12 +873,12 @@
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-LABEL: 'vf16'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %1 = fdiv <2 x half> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %2 = frem <2 x half> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %3 = fdiv <4 x half> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %4 = frem <4 x half> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %5 = fdiv <8 x half> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %6 = frem <8 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %1 = fdiv <2 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %2 = frem <2 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %3 = fdiv <4 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %4 = frem <4 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %5 = fdiv <8 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %6 = frem <8 x half> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-V8M-MAIN-LABEL: 'vf16'
@@ -928,12 +928,12 @@
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-LABEL: 'vf32'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %1 = fdiv <2 x float> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %2 = frem <2 x float> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %3 = fdiv <4 x float> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %4 = frem <4 x float> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %5 = fdiv <8 x float> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %6 = frem <8 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %1 = fdiv <2 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %2 = frem <2 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %3 = fdiv <4 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %4 = frem <4 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %5 = fdiv <8 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %6 = frem <8 x float> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-V8M-MAIN-LABEL: 'vf32'
@@ -983,12 +983,12 @@
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-LABEL: 'vf64'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %1 = fdiv <2 x double> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %2 = frem <2 x double> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %3 = fdiv <4 x double> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %4 = frem <4 x double> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %5 = fdiv <8 x double> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %6 = frem <8 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %1 = fdiv <2 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %2 = frem <2 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %3 = fdiv <4 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %4 = frem <4 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %5 = fdiv <8 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %6 = frem <8 x double> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-V8M-MAIN-LABEL: 'vf64'
@@ -1048,22 +1048,22 @@
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-LABEL: 'vi8_2'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t1 = sdiv <2 x i8> undef, <i8 2, i8 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t2 = udiv <2 x i8> undef, <i8 2, i8 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t3 = srem <2 x i8> undef, <i8 2, i8 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t4 = urem <2 x i8> undef, <i8 2, i8 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t1 = sdiv <2 x i8> undef, <i8 2, i8 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t2 = udiv <2 x i8> undef, <i8 2, i8 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t3 = srem <2 x i8> undef, <i8 2, i8 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t4 = urem <2 x i8> undef, <i8 2, i8 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f1 = sdiv <4 x i8> undef, <i8 2, i8 2, i8 2, i8 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f2 = udiv <4 x i8> undef, <i8 2, i8 2, i8 2, i8 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f3 = srem <4 x i8> undef, <i8 2, i8 2, i8 2, i8 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f4 = urem <4 x i8> undef, <i8 2, i8 2, i8 2, i8 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e1 = sdiv <8 x i8> undef, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e2 = udiv <8 x i8> undef, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e3 = srem <8 x i8> undef, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e4 = urem <8 x i8> undef, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s1 = sdiv <16 x i8> undef, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s2 = udiv <16 x i8> undef, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s3 = srem <16 x i8> undef, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s4 = urem <16 x i8> undef, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e1 = sdiv <8 x i8> undef, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e2 = udiv <8 x i8> undef, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e3 = srem <8 x i8> undef, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e4 = urem <8 x i8> undef, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s1 = sdiv <16 x i8> undef, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s2 = udiv <16 x i8> undef, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s3 = srem <16 x i8> undef, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s4 = urem <16 x i8> undef, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-V8M-MAIN-LABEL: 'vi8_2'
@@ -1163,22 +1163,22 @@
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-LABEL: 'vi16_2'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t1 = sdiv <2 x i16> undef, <i16 2, i16 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t2 = udiv <2 x i16> undef, <i16 2, i16 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t3 = srem <2 x i16> undef, <i16 2, i16 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t4 = urem <2 x i16> undef, <i16 2, i16 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t1 = sdiv <2 x i16> undef, <i16 2, i16 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t2 = udiv <2 x i16> undef, <i16 2, i16 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t3 = srem <2 x i16> undef, <i16 2, i16 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t4 = urem <2 x i16> undef, <i16 2, i16 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f1 = sdiv <4 x i16> undef, <i16 2, i16 2, i16 2, i16 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f2 = udiv <4 x i16> undef, <i16 2, i16 2, i16 2, i16 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f3 = srem <4 x i16> undef, <i16 2, i16 2, i16 2, i16 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f4 = urem <4 x i16> undef, <i16 2, i16 2, i16 2, i16 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e1 = sdiv <8 x i16> undef, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e2 = udiv <8 x i16> undef, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e3 = srem <8 x i16> undef, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e4 = urem <8 x i16> undef, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s1 = sdiv <16 x i16> undef, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s2 = udiv <16 x i16> undef, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s3 = srem <16 x i16> undef, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s4 = urem <16 x i16> undef, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e1 = sdiv <8 x i16> undef, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e2 = udiv <8 x i16> undef, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e3 = srem <8 x i16> undef, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e4 = urem <8 x i16> undef, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s1 = sdiv <16 x i16> undef, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s2 = udiv <16 x i16> undef, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s3 = srem <16 x i16> undef, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s4 = urem <16 x i16> undef, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-V8M-MAIN-LABEL: 'vi16_2'
@@ -1278,22 +1278,22 @@
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-LABEL: 'vi32_2'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t1 = sdiv <2 x i32> undef, <i32 2, i32 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t2 = udiv <2 x i32> undef, <i32 2, i32 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t3 = srem <2 x i32> undef, <i32 2, i32 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t4 = urem <2 x i32> undef, <i32 2, i32 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t1 = sdiv <2 x i32> undef, <i32 2, i32 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t2 = udiv <2 x i32> undef, <i32 2, i32 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t3 = srem <2 x i32> undef, <i32 2, i32 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %t4 = urem <2 x i32> undef, <i32 2, i32 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f1 = sdiv <4 x i32> undef, <i32 2, i32 2, i32 2, i32 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f2 = udiv <4 x i32> undef, <i32 2, i32 2, i32 2, i32 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f3 = srem <4 x i32> undef, <i32 2, i32 2, i32 2, i32 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f4 = urem <4 x i32> undef, <i32 2, i32 2, i32 2, i32 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e1 = sdiv <8 x i32> undef, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e2 = udiv <8 x i32> undef, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e3 = srem <8 x i32> undef, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e4 = urem <8 x i32> undef, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s1 = sdiv <16 x i32> undef, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s2 = udiv <16 x i32> undef, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s3 = srem <16 x i32> undef, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s4 = urem <16 x i32> undef, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e1 = sdiv <8 x i32> undef, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e2 = udiv <8 x i32> undef, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e3 = srem <8 x i32> undef, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %e4 = urem <8 x i32> undef, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s1 = sdiv <16 x i32> undef, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s2 = udiv <16 x i32> undef, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s3 = srem <16 x i32> undef, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %s4 = urem <16 x i32> undef, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-V8M-MAIN-LABEL: 'vi32_2'
@@ -1393,22 +1393,22 @@
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-LABEL: 'vi64_2'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t1 = sdiv <2 x i64> undef, <i64 2, i64 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t2 = udiv <2 x i64> undef, <i64 2, i64 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t3 = srem <2 x i64> undef, <i64 2, i64 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %t4 = urem <2 x i64> undef, <i64 2, i64 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %f1 = sdiv <4 x i64> undef, <i64 2, i64 2, i64 2, i64 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %f2 = udiv <4 x i64> undef, <i64 2, i64 2, i64 2, i64 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f3 = srem <4 x i64> undef, <i64 2, i64 2, i64 2, i64 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %f4 = urem <4 x i64> undef, <i64 2, i64 2, i64 2, i64 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %t1 = sdiv <2 x i64> undef, <i64 2, i64 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %t2 = udiv <2 x i64> undef, <i64 2, i64 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %t3 = srem <2 x i64> undef, <i64 2, i64 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %t4 = urem <2 x i64> undef, <i64 2, i64 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %f1 = sdiv <4 x i64> undef, <i64 2, i64 2, i64 2, i64 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %f2 = udiv <4 x i64> undef, <i64 2, i64 2, i64 2, i64 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %f3 = srem <4 x i64> undef, <i64 2, i64 2, i64 2, i64 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %f4 = urem <4 x i64> undef, <i64 2, i64 2, i64 2, i64 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %e1 = sdiv <8 x i64> undef, <i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %e2 = udiv <8 x i64> undef, <i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e3 = srem <8 x i64> undef, <i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e4 = urem <8 x i64> undef, <i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %s1 = sdiv <16 x i64> undef, <i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %s2 = udiv <16 x i64> undef, <i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s3 = srem <16 x i64> undef, <i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %s4 = urem <16 x i64> undef, <i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %s1 = sdiv <16 x i64> undef, <i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %s2 = udiv <16 x i64> undef, <i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %s3 = srem <16 x i64> undef, <i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %s4 = urem <16 x i64> undef, <i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-V8M-MAIN-LABEL: 'vi64_2'
@@ -1498,12 +1498,12 @@
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-LABEL: 'vf16_2'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %1 = fdiv <2 x half> undef, <half 0xH4000, half 0xH4000>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %2 = frem <2 x half> undef, <half 0xH4000, half 0xH4000>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %3 = fdiv <4 x half> undef, <half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %4 = frem <4 x half> undef, <half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %5 = fdiv <8 x half> undef, <half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %6 = frem <8 x half> undef, <half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %1 = fdiv <2 x half> undef, <half 0xH4000, half 0xH4000>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %2 = frem <2 x half> undef, <half 0xH4000, half 0xH4000>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %3 = fdiv <4 x half> undef, <half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %4 = frem <4 x half> undef, <half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %5 = fdiv <8 x half> undef, <half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %6 = frem <8 x half> undef, <half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-V8M-MAIN-LABEL: 'vf16_2'
@@ -1553,12 +1553,12 @@
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-LABEL: 'vf32_2'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %1 = fdiv <2 x float> undef, <float 2.000000e+00, float 2.000000e+00>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %2 = frem <2 x float> undef, <float 2.000000e+00, float 2.000000e+00>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %3 = fdiv <4 x float> undef, <float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %4 = frem <4 x float> undef, <float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %5 = fdiv <8 x float> undef, <float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %6 = frem <8 x float> undef, <float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %1 = fdiv <2 x float> undef, <float 2.000000e+00, float 2.000000e+00>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %2 = frem <2 x float> undef, <float 2.000000e+00, float 2.000000e+00>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %3 = fdiv <4 x float> undef, <float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %4 = frem <4 x float> undef, <float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %5 = fdiv <8 x float> undef, <float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %6 = frem <8 x float> undef, <float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-V8M-MAIN-LABEL: 'vf32_2'
@@ -1608,12 +1608,12 @@
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVE-LABEL: 'vf64_2'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %1 = fdiv <2 x double> undef, <double 2.000000e+00, double 2.000000e+00>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %2 = frem <2 x double> undef, <double 2.000000e+00, double 2.000000e+00>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %3 = fdiv <4 x double> undef, <double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %4 = frem <4 x double> undef, <double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %5 = fdiv <8 x double> undef, <double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %6 = frem <8 x double> undef, <double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %1 = fdiv <2 x double> undef, <double 2.000000e+00, double 2.000000e+00>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %2 = frem <2 x double> undef, <double 2.000000e+00, double 2.000000e+00>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %3 = fdiv <4 x double> undef, <double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %4 = frem <4 x double> undef, <double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %5 = fdiv <8 x double> undef, <double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %6 = frem <8 x double> undef, <double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-V8M-MAIN-LABEL: 'vf64_2'
diff --git a/llvm/test/Analysis/CostModel/ARM/fparith.ll b/llvm/test/Analysis/CostModel/ARM/fparith.ll
--- a/llvm/test/Analysis/CostModel/ARM/fparith.ll
+++ b/llvm/test/Analysis/CostModel/ARM/fparith.ll
@@ -61,15 +61,15 @@
 
 define void @vf32() {
 ; CHECK-MVE-LABEL: 'vf32'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %c2 = fadd <2 x float> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %d2 = fsub <2 x float> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %e2 = fmul <2 x float> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %c4 = fadd <4 x float> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %d4 = fsub <4 x float> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %e4 = fmul <4 x float> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %c8 = fadd <8 x float> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %d8 = fsub <8 x float> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e8 = fmul <8 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %c2 = fadd <2 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %d2 = fsub <2 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %e2 = fmul <2 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %c4 = fadd <4 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %d4 = fsub <4 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %e4 = fmul <4 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %c8 = fadd <8 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %d8 = fsub <8 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %e8 = fmul <8 x float> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVEFP-LABEL: 'vf32'
@@ -98,15 +98,15 @@
 
 define void @vf16() {
 ; CHECK-MVE-LABEL: 'vf16'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %c2 = fadd <2 x half> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %d2 = fsub <2 x half> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %e2 = fmul <2 x half> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %c4 = fadd <4 x half> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %d4 = fsub <4 x half> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %e4 = fmul <4 x half> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %c8 = fadd <8 x half> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %d8 = fsub <8 x half> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e8 = fmul <8 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %c2 = fadd <2 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %d2 = fsub <2 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %e2 = fmul <2 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %c4 = fadd <4 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %d4 = fsub <4 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %e4 = fmul <4 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %c8 = fadd <8 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %d8 = fsub <8 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %e8 = fmul <8 x half> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVEFP-LABEL: 'vf16'
@@ -135,27 +135,27 @@
 
 define void @vf64() {
 ; CHECK-MVE-LABEL: 'vf64'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %c2 = fadd <2 x double> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %d2 = fsub <2 x double> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %e2 = fmul <2 x double> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %c4 = fadd <4 x double> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %d4 = fsub <4 x double> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %e4 = fmul <4 x double> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %c8 = fadd <8 x double> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %d8 = fsub <8 x double> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e8 = fmul <8 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %c2 = fadd <2 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %d2 = fsub <2 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %e2 = fmul <2 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %c4 = fadd <4 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %d4 = fsub <4 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %e4 = fmul <4 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %c8 = fadd <8 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %d8 = fsub <8 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %e8 = fmul <8 x double> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVEFP-LABEL: 'vf64'
-; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %c2 = fadd <2 x double> undef, undef
-; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %d2 = fsub <2 x double> undef, undef
-; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %e2 = fmul <2 x double> undef, undef
-; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %c4 = fadd <4 x double> undef, undef
-; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %d4 = fsub <4 x double> undef, undef
-; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %e4 = fmul <4 x double> undef, undef
-; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %c8 = fadd <8 x double> undef, undef
-; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %d8 = fsub <8 x double> undef, undef
-; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %e8 = fmul <8 x double> undef, undef
+; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %c2 = fadd <2 x double> undef, undef
+; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %d2 = fsub <2 x double> undef, undef
+; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %e2 = fmul <2 x double> undef, undef
+; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %c4 = fadd <4 x double> undef, undef
+; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %d4 = fsub <4 x double> undef, undef
+; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %e4 = fmul <4 x double> undef, undef
+; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %c8 = fadd <8 x double> undef, undef
+; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %d8 = fsub <8 x double> undef, undef
+; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %e8 = fmul <8 x double> undef, undef
 ; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %c2 = fadd <2 x double> undef, undef
diff --git a/llvm/test/Analysis/CostModel/ARM/intrinsic-cost-kinds.ll b/llvm/test/Analysis/CostModel/ARM/intrinsic-cost-kinds.ll
--- a/llvm/test/Analysis/CostModel/ARM/intrinsic-cost-kinds.ll
+++ b/llvm/test/Analysis/CostModel/ARM/intrinsic-cost-kinds.ll
@@ -95,7 +95,7 @@
 define void @log2(float %a, <16 x float> %va) {
 ; THRU-LABEL: 'log2'
 ; THRU-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %s = call float @llvm.log2.f32(float %a)
-; THRU-NEXT:  Cost Model: Found an estimated cost of 672 for instruction: %v = call <16 x float> @llvm.log2.v16f32(<16 x float> %va)
+; THRU-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %v = call <16 x float> @llvm.log2.v16f32(<16 x float> %va)
 ; THRU-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; LATE-LABEL: 'log2'
@@ -105,12 +105,12 @@
 ;
 ; SIZE-LABEL: 'log2'
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s = call float @llvm.log2.f32(float %a)
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %v = call <16 x float> @llvm.log2.v16f32(<16 x float> %va)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %v = call <16 x float> @llvm.log2.v16f32(<16 x float> %va)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE_LATE-LABEL: 'log2'
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %s = call float @llvm.log2.f32(float %a)
-; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 672 for instruction: %v = call <16 x float> @llvm.log2.v16f32(<16 x float> %va)
+; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %v = call <16 x float> @llvm.log2.v16f32(<16 x float> %va)
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   %s = call float @llvm.log2.f32(float %a)
@@ -121,7 +121,7 @@
 define void @constrained_fadd(float %a, <16 x float> %va) {
 ; THRU-LABEL: 'constrained_fadd'
 ; THRU-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s = call float @llvm.experimental.constrained.fadd.f32(float %a, float %a, metadata !"round.dynamic", metadata !"fpexcept.ignore")
-; THRU-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %t = call <16 x float> @llvm.experimental.constrained.fadd.v16f32(<16 x float> %va, <16 x float> %va, metadata !"round.dynamic", metadata !"fpexcept.ignore")
+; THRU-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %t = call <16 x float> @llvm.experimental.constrained.fadd.v16f32(<16 x float> %va, <16 x float> %va, metadata !"round.dynamic", metadata !"fpexcept.ignore")
 ; THRU-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; LATE-LABEL: 'constrained_fadd'
@@ -131,12 +131,12 @@
 ;
 ; SIZE-LABEL: 'constrained_fadd'
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s = call float @llvm.experimental.constrained.fadd.f32(float %a, float %a, metadata !"round.dynamic", metadata !"fpexcept.ignore")
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %t = call <16 x float> @llvm.experimental.constrained.fadd.v16f32(<16 x float> %va, <16 x float> %va, metadata !"round.dynamic", metadata !"fpexcept.ignore")
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %t = call <16 x float> @llvm.experimental.constrained.fadd.v16f32(<16 x float> %va, <16 x float> %va, metadata !"round.dynamic", metadata !"fpexcept.ignore")
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE_LATE-LABEL: 'constrained_fadd'
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s = call float @llvm.experimental.constrained.fadd.f32(float %a, float %a, metadata !"round.dynamic", metadata !"fpexcept.ignore")
-; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %t = call <16 x float> @llvm.experimental.constrained.fadd.v16f32(<16 x float> %va, <16 x float> %va, metadata !"round.dynamic", metadata !"fpexcept.ignore")
+; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %t = call <16 x float> @llvm.experimental.constrained.fadd.v16f32(<16 x float> %va, <16 x float> %va, metadata !"round.dynamic", metadata !"fpexcept.ignore")
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   %s = call float @llvm.experimental.constrained.fadd.f32(float %a, float %a, metadata !"round.dynamic", metadata !"fpexcept.ignore")
@@ -147,7 +147,7 @@
 define void @fmaximum(float %a, float %b, <16 x float> %va, <16 x float> %vb) {
 ; THRU-LABEL: 'fmaximum'
 ; THRU-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %s = call float @llvm.maximum.f32(float %a, float %b)
-; THRU-NEXT:  Cost Model: Found an estimated cost of 928 for instruction: %v = call <16 x float> @llvm.maximum.v16f32(<16 x float> %va, <16 x float> %vb)
+; THRU-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %v = call <16 x float> @llvm.maximum.v16f32(<16 x float> %va, <16 x float> %vb)
 ; THRU-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; LATE-LABEL: 'fmaximum'
@@ -157,12 +157,12 @@
 ;
 ; SIZE-LABEL: 'fmaximum'
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s = call float @llvm.maximum.f32(float %a, float %b)
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 784 for instruction: %v = call <16 x float> @llvm.maximum.v16f32(<16 x float> %va, <16 x float> %vb)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v = call <16 x float> @llvm.maximum.v16f32(<16 x float> %va, <16 x float> %vb)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE_LATE-LABEL: 'fmaximum'
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %s = call float @llvm.maximum.f32(float %a, float %b)
-; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 928 for instruction: %v = call <16 x float> @llvm.maximum.v16f32(<16 x float> %va, <16 x float> %vb)
+; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %v = call <16 x float> @llvm.maximum.v16f32(<16 x float> %va, <16 x float> %vb)
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   %s = call float @llvm.maximum.f32(float %a, float %b)
@@ -225,7 +225,7 @@
 define void @fshl(i32 %a, i32 %b, i32 %c, <16 x i32> %va, <16 x i32> %vb, <16 x i32> %vc) {
 ; THRU-LABEL: 'fshl'
 ; THRU-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %s = call i32 @llvm.fshl.i32(i32 %a, i32 %b, i32 %c)
-; THRU-NEXT:  Cost Model: Found an estimated cost of 832 for instruction: %v = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i32> %vc)
+; THRU-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i32> %vc)
 ; THRU-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; LATE-LABEL: 'fshl'
@@ -235,12 +235,12 @@
 ;
 ; SIZE-LABEL: 'fshl'
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %s = call i32 @llvm.fshl.i32(i32 %a, i32 %b, i32 %c)
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 805 for instruction: %v = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i32> %vc)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 229 for instruction: %v = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i32> %vc)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE_LATE-LABEL: 'fshl'
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %s = call i32 @llvm.fshl.i32(i32 %a, i32 %b, i32 %c)
-; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 826 for instruction: %v = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i32> %vc)
+; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 250 for instruction: %v = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i32> %vc)
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   %s = call i32 @llvm.fshl.i32(i32 %a, i32 %b, i32 %c)
@@ -250,7 +250,7 @@
 
 define void @maskedgather(<16 x float*> %va, <16 x i1> %vb, <16 x float> %vc) {
 ; THRU-LABEL: 'maskedgather'
-; THRU-NEXT:  Cost Model: Found an estimated cost of 576 for instruction: %v = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %va, i32 1, <16 x i1> %vb, <16 x float> %vc)
+; THRU-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %v = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %va, i32 1, <16 x i1> %vb, <16 x float> %vc)
 ; THRU-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; LATE-LABEL: 'maskedgather'
@@ -258,11 +258,11 @@
 ; LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE-LABEL: 'maskedgather'
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 576 for instruction: %v = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %va, i32 1, <16 x i1> %vb, <16 x float> %vc)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %v = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %va, i32 1, <16 x i1> %vb, <16 x float> %vc)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE_LATE-LABEL: 'maskedgather'
-; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 576 for instruction: %v = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %va, i32 1, <16 x i1> %vb, <16 x float> %vc)
+; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %v = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %va, i32 1, <16 x i1> %vb, <16 x float> %vc)
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   %v = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %va, i32 1, <16 x i1> %vb, <16 x float> %vc)
@@ -271,7 +271,7 @@
 
 define void @maskedscatter(<16 x float> %va, <16 x float*> %vb, <16 x i1> %vc) {
 ; THRU-LABEL: 'maskedscatter'
-; THRU-NEXT:  Cost Model: Found an estimated cost of 576 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> %va, <16 x float*> %vb, i32 1, <16 x i1> %vc)
+; THRU-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> %va, <16 x float*> %vb, i32 1, <16 x i1> %vc)
 ; THRU-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; LATE-LABEL: 'maskedscatter'
@@ -279,11 +279,11 @@
 ; LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE-LABEL: 'maskedscatter'
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 576 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> %va, <16 x float*> %vb, i32 1, <16 x i1> %vc)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> %va, <16 x float*> %vb, i32 1, <16 x i1> %vc)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE_LATE-LABEL: 'maskedscatter'
-; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 576 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> %va, <16 x float*> %vb, i32 1, <16 x i1> %vc)
+; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> %va, <16 x float*> %vb, i32 1, <16 x i1> %vc)
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> %va, <16 x float*> %vb, i32 1, <16 x i1> %vc)
@@ -292,7 +292,7 @@
 
 define void @reduce_fmax(<16 x float> %va) {
 ; THRU-LABEL: 'reduce_fmax'
-; THRU-NEXT:  Cost Model: Found an estimated cost of 696 for instruction: %v = call float @llvm.vector.reduce.fmax.v16f32(<16 x float> %va)
+; THRU-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %v = call float @llvm.vector.reduce.fmax.v16f32(<16 x float> %va)
 ; THRU-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; LATE-LABEL: 'reduce_fmax'
@@ -300,11 +300,11 @@
 ; LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE-LABEL: 'reduce_fmax'
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 685 for instruction: %v = call float @llvm.vector.reduce.fmax.v16f32(<16 x float> %va)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 122 for instruction: %v = call float @llvm.vector.reduce.fmax.v16f32(<16 x float> %va)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE_LATE-LABEL: 'reduce_fmax'
-; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 694 for instruction: %v = call float @llvm.vector.reduce.fmax.v16f32(<16 x float> %va)
+; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 131 for instruction: %v = call float @llvm.vector.reduce.fmax.v16f32(<16 x float> %va)
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   %v = call float @llvm.vector.reduce.fmax.v16f32(<16 x float> %va)
diff --git a/llvm/test/Analysis/CostModel/ARM/load_store.ll b/llvm/test/Analysis/CostModel/ARM/load_store.ll
--- a/llvm/test/Analysis/CostModel/ARM/load_store.ll
+++ b/llvm/test/Analysis/CostModel/ARM/load_store.ll
@@ -69,16 +69,16 @@
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store i128 undef, i128* undef, align 4
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store float undef, float* undef, align 4
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store double undef, double* undef, align 4
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <2 x i8> undef, <2 x i8>* undef, align 1
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <2 x i16> undef, <2 x i16>* undef, align 2
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <2 x i32> undef, <2 x i32>* undef, align 4
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: store <2 x i8> undef, <2 x i8>* undef, align 1
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: store <2 x i16> undef, <2 x i16>* undef, align 2
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: store <2 x i32> undef, <2 x i32>* undef, align 4
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <2 x i64> undef, <2 x i64>* undef, align 4
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i32> undef, <4 x i32>* undef, align 4
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <8 x i16> undef, <8 x i16>* undef, align 2
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <16 x i8> undef, <16 x i8>* undef, align 1
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x float> undef, <4 x float>* undef, align 4
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x double> undef, <4 x double>* undef, align 4
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <2 x float> undef, <2 x float>* undef, align 4
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <2 x float> undef, <2 x float>* undef, align 4
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <2 x double> undef, <2 x double>* undef, align 4
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <2 x i64> undef, <2 x i64>* undef, align 1
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i32> undef, <4 x i32>* undef, align 1
@@ -256,16 +256,16 @@
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %5 = load i128, i128* undef, align 4
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = load float, float* undef, align 4
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = load double, double* undef, align 4
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %8 = load <2 x i8>, <2 x i8>* undef, align 1
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %9 = load <2 x i16>, <2 x i16>* undef, align 2
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = load <2 x i32>, <2 x i32>* undef, align 4
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %8 = load <2 x i8>, <2 x i8>* undef, align 1
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %9 = load <2 x i16>, <2 x i16>* undef, align 2
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %10 = load <2 x i32>, <2 x i32>* undef, align 4
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %11 = load <2 x i64>, <2 x i64>* undef, align 4
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = load <4 x i32>, <4 x i32>* undef, align 4
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = load <8 x i16>, <8 x i16>* undef, align 2
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = load <16 x i8>, <16 x i8>* undef, align 1
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %15 = load <4 x float>, <4 x float>* undef, align 4
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %16 = load <4 x double>, <4 x double>* undef, align 4
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %17 = load <2 x float>, <2 x float>* undef, align 4
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %17 = load <2 x float>, <2 x float>* undef, align 4
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %18 = load <2 x double>, <2 x double>* undef, align 4
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = load <2 x i64>, <2 x i64>* undef, align 1
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %20 = load <4 x i32>, <4 x i32>* undef, align 1
diff --git a/llvm/test/Analysis/CostModel/ARM/mve-abs.ll b/llvm/test/Analysis/CostModel/ARM/mve-abs.ll
--- a/llvm/test/Analysis/CostModel/ARM/mve-abs.ll
+++ b/llvm/test/Analysis/CostModel/ARM/mve-abs.ll
@@ -31,22 +31,22 @@
 define i32 @abs(i32 %arg) {
 ; MVE-RECIP-LABEL: 'abs'
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 false)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 448 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 false)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 false)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 false)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 false)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 false)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 false)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 false)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 false)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 false)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 false)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 false)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 false)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 false)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 false)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false)
@@ -56,22 +56,22 @@
 ;
 ; MVE-SIZE-LABEL: 'abs'
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 false)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 146 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 false)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 false)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 false)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 false)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 false)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 false)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 false)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 false)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 false)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 false)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 false)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 false)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 false)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 false)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false)
diff --git a/llvm/test/Analysis/CostModel/ARM/mve-cmp.ll b/llvm/test/Analysis/CostModel/ARM/mve-cmp.ll
--- a/llvm/test/Analysis/CostModel/ARM/mve-cmp.ll
+++ b/llvm/test/Analysis/CostModel/ARM/mve-cmp.ll
@@ -4,21 +4,21 @@
 
 define void @icmp() {
 ; CHECK-LABEL: 'icmp'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v2i8 = icmp slt <2 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %v2i8 = icmp slt <2 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4i8 = icmp slt <4 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i8 = icmp slt <8 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i8 = icmp slt <16 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1028 for instruction: %v32i8 = icmp slt <32 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v2i16 = icmp slt <2 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 132 for instruction: %v32i8 = icmp slt <32 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %v2i16 = icmp slt <2 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4i16 = icmp slt <4 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i16 = icmp slt <8 x i16> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 260 for instruction: %v16i16 = icmp slt <16 x i16> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v2i32 = icmp slt <2 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %v16i16 = icmp slt <16 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %v2i32 = icmp slt <2 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4i32 = icmp slt <4 x i32> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %v8i32 = icmp slt <8 x i32> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 264 for instruction: %v16i32 = icmp slt <16 x i32> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v2i64 = icmp slt <2 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %v4i64 = icmp slt <4 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %v8i32 = icmp slt <8 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %v16i32 = icmp slt <16 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %v2i64 = icmp slt <2 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %v4i64 = icmp slt <4 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %v8i64 = icmp slt <8 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
@@ -47,31 +47,31 @@
 
 define void @fcmp() {
 ; CHECK-MVE-LABEL: 'fcmp'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %v2f16 = fcmp olt <2 x half> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %v4f16 = fcmp olt <4 x half> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %v8f16 = fcmp olt <8 x half> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %v16f16 = fcmp olt <16 x half> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %v2f32 = fcmp olt <2 x float> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %v4f32 = fcmp olt <4 x float> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %v8f32 = fcmp olt <8 x float> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %v16f32 = fcmp olt <16 x float> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %v2f64 = fcmp olt <2 x double> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %v4f64 = fcmp olt <4 x double> undef, undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %v8f64 = fcmp olt <8 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v2f16 = fcmp olt <2 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %v4f16 = fcmp olt <4 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %v8f16 = fcmp olt <8 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %v16f16 = fcmp olt <16 x half> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v2f32 = fcmp olt <2 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %v4f32 = fcmp olt <4 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %v8f32 = fcmp olt <8 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %v16f32 = fcmp olt <16 x float> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v2f64 = fcmp olt <2 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %v4f64 = fcmp olt <4 x double> undef, undef
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %v8f64 = fcmp olt <8 x double> undef, undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-MVEFP-LABEL: 'fcmp'
 ; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f16 = fcmp olt <2 x half> undef, undef
 ; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f16 = fcmp olt <4 x half> undef, undef
 ; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f16 = fcmp olt <8 x half> undef, undef
-; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 260 for instruction: %v16f16 = fcmp olt <16 x half> undef, undef
+; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %v16f16 = fcmp olt <16 x half> undef, undef
 ; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32 = fcmp olt <2 x float> undef, undef
 ; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f32 = fcmp olt <4 x float> undef, undef
-; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %v8f32 = fcmp olt <8 x float> undef, undef
-; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 264 for instruction: %v16f32 = fcmp olt <16 x float> undef, undef
-; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v2f64 = fcmp olt <2 x double> undef, undef
-; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %v4f64 = fcmp olt <4 x double> undef, undef
-; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %v8f64 = fcmp olt <8 x double> undef, undef
+; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %v8f32 = fcmp olt <8 x float> undef, undef
+; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %v16f32 = fcmp olt <16 x float> undef, undef
+; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v2f64 = fcmp olt <2 x double> undef, undef
+; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v4f64 = fcmp olt <4 x double> undef, undef
+; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v8f64 = fcmp olt <8 x double> undef, undef
 ; CHECK-MVEFP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %v2f16 = fcmp olt <2 x half> undef, undef
diff --git a/llvm/test/Analysis/CostModel/ARM/mve-gather-scatter-cost.ll b/llvm/test/Analysis/CostModel/ARM/mve-gather-scatter-cost.ll
--- a/llvm/test/Analysis/CostModel/ARM/mve-gather-scatter-cost.ll
+++ b/llvm/test/Analysis/CostModel/ARM/mve-gather-scatter-cost.ll
@@ -3,32 +3,32 @@
 
 define i32 @masked_gather() {
 ; CHECK-LABEL: 'masked_gather'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 4, <4 x i1> undef, <4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 4, <2 x i1> undef, <2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 576 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 4, <16 x i1> undef, <16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 4, <8 x i1> undef, <8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 4, <4 x i1> undef, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 4, <2 x i1> undef, <2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 4, <16 x i1> undef, <16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 4, <8 x i1> undef, <8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 4, <4 x i1> undef, <4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 4, <2 x i1> undef, <2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 544 for instruction: %V16F16 = call <16 x half> @llvm.masked.gather.v16f16.v16p0f16(<16 x half*> undef, i32 2, <16 x i1> undef, <16 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V8F16 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> undef, i32 2, <8 x i1> undef, <8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V4F16 = call <4 x half> @llvm.masked.gather.v4f16.v4p0f16(<4 x half*> undef, i32 2, <4 x i1> undef, <4 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2F16 = call <2 x half> @llvm.masked.gather.v2f16.v2p0f16(<2 x half*> undef, i32 2, <2 x i1> undef, <2 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 4, <4 x i1> undef, <4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 4, <2 x i1> undef, <2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 576 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 4, <16 x i1> undef, <16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 4, <8 x i1> undef, <8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 4, <2 x i1> undef, <2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V16F16 = call <16 x half> @llvm.masked.gather.v16f16.v16p0f16(<16 x half*> undef, i32 2, <16 x i1> undef, <16 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8F16 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> undef, i32 2, <8 x i1> undef, <8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4F16 = call <4 x half> @llvm.masked.gather.v4f16.v4p0f16(<4 x half*> undef, i32 2, <4 x i1> undef, <4 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F16 = call <2 x half> @llvm.masked.gather.v2f16.v2p0f16(<2 x half*> undef, i32 2, <2 x i1> undef, <2 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 4, <4 x i1> undef, <4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 4, <2 x i1> undef, <2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 4, <16 x i1> undef, <16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 4, <8 x i1> undef, <8 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 4, <4 x i1> undef, <4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 4, <2 x i1> undef, <2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 544 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 2, <16 x i1> undef, <16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 2, <8 x i1> undef, <8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 4, <2 x i1> undef, <2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 2, <16 x i1> undef, <16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 2, <8 x i1> undef, <8 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 2, <4 x i1> undef, <4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.masked.gather.v2i16.v2p0i16(<2 x i16*> undef, i32 2, <2 x i1> undef, <2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2112 for instruction: %V32I8 = call <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*> undef, i32 1, <32 x i1> undef, <32 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %V16I8 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> undef, i32 1, <16 x i1> undef, <16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V8I8 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> undef, i32 1, <8 x i1> undef, <8 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V2I16 = call <2 x i16> @llvm.masked.gather.v2i16.v2p0i16(<2 x i16*> undef, i32 2, <2 x i1> undef, <2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 320 for instruction: %V32I8 = call <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*> undef, i32 1, <32 x i1> undef, <32 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V16I8 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> undef, i32 1, <16 x i1> undef, <16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8I8 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> undef, i32 1, <8 x i1> undef, <8 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V4I8 = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*> undef, i32 1, <4 x i1> undef, <4 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.masked.gather.v2i8.v2p0i8(<2 x i8*> undef, i32 1, <2 x i1> undef, <2 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V4I32p = call <4 x i32*> @llvm.masked.gather.v4p0i32.v4p0p0i32(<4 x i32**> undef, i32 4, <4 x i1> undef, <4 x i32*> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V2I8 = call <2 x i8> @llvm.masked.gather.v2i8.v2p0i8(<2 x i8*> undef, i32 1, <2 x i1> undef, <2 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V4I32p = call <4 x i32*> @llvm.masked.gather.v4p0i32.v4p0p0i32(<4 x i32**> undef, i32 4, <4 x i1> undef, <4 x i32*> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
   %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 4, <4 x i1> undef, <4 x double> undef)
@@ -70,31 +70,31 @@
 
 define i32 @masked_scatter() {
 ; CHECK-LABEL: 'masked_scatter'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 4, <4 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 4, <2 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 576 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 4, <16 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 4, <8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 4, <4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 4, <2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 4, <16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 4, <8 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 4, <4 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 4, <2 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 544 for instruction: call void @llvm.masked.scatter.v16f16.v16p0f16(<16 x half> undef, <16 x half*> undef, i32 2, <16 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> undef, <8 x half*> undef, i32 2, <8 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4f16.v4p0f16(<4 x half> undef, <4 x half*> undef, i32 2, <4 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v2f16.v2p0f16(<2 x half> undef, <2 x half*> undef, i32 2, <2 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 4, <4 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 4, <2 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 576 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 4, <16 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 4, <8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 4, <2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v16f16.v16p0f16(<16 x half> undef, <16 x half*> undef, i32 2, <16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> undef, <8 x half*> undef, i32 2, <8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.scatter.v4f16.v4p0f16(<4 x half> undef, <4 x half*> undef, i32 2, <4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2f16.v2p0f16(<2 x half> undef, <2 x half*> undef, i32 2, <2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 4, <4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 4, <2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 4, <16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 4, <8 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 4, <4 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 4, <2 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 544 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 2, <16 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 2, <8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 4, <2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 2, <16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 2, <8 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 2, <4 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v2i16.v2p0i16(<2 x i16> undef, <2 x i16*> undef, i32 2, <2 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2112 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.scatter.v2i16.v2p0i16(<2 x i16> undef, <2 x i16*> undef, i32 2, <2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 320 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8> undef, <4 x i8*> undef, i32 1, <4 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v2i8.v2p0i8(<2 x i8> undef, <2 x i8*> undef, i32 1, <2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.scatter.v2i8.v2p0i8(<2 x i8> undef, <2 x i8*> undef, i32 1, <2 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
   call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 4, <4 x i1> undef)
@@ -205,8 +205,8 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res3 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep3, i32 4, <4 x i1> %mask, <4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %res3, <4 x float*> %gep3, i32 4, <4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gepu = getelementptr float, float* %base, <4 x i32> %ind32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %resu = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gepu, i32 1, <4 x i1> %mask, <4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %resu, <4 x float*> %gepu, i32 1, <4 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %resu = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gepu, i32 1, <4 x i1> %mask, <4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %resu, <4 x float*> %gepu, i32 1, <4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepos = getelementptr i8, i8* %base8, <4 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %geposb = bitcast <4 x i8*> %gepos to <4 x float*>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %resos = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %geposb, i32 4, <4 x i1> %mask, <4 x float> undef)
@@ -336,26 +336,26 @@
 define void @gep_v8i16(i16* %base, i8* %base8, i32* %base32, <8 x i32> %ind32, <8 x i16> %ind16, <8 x i8> %ind8, <8 x i1> %mask)  {
 ; CHECK-LABEL: 'gep_v8i16'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep1 = getelementptr i16, i16* %base, <8 x i32> %ind32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %res1 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep1, i32 2, <8 x i1> %mask, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res1, <8 x i16*> %gep1, i32 2, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %res1 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep1, i32 2, <8 x i1> %mask, <8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res1, <8 x i16*> %gep1, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %indzext = zext <8 x i16> %ind16 to <8 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep2 = getelementptr i16, i16* %base, <8 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res2 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep2, i32 2, <8 x i1> %mask, <8 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res2, <8 x i16*> %gep2, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %indsext = sext <8 x i16> %ind16 to <8 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep3 = getelementptr i16, i16* %base, <8 x i32> %indsext
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %res3 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep3, i32 2, <8 x i1> %mask, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res3, <8 x i16*> %gep3, i32 2, <8 x i1> %mask)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %resu = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep2, i32 1, <8 x i1> %mask, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resu, <8 x i16*> %gep2, i32 1, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %res3 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep3, i32 2, <8 x i1> %mask, <8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res3, <8 x i16*> %gep3, i32 2, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %resu = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep2, i32 1, <8 x i1> %mask, <8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resu, <8 x i16*> %gep2, i32 1, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepos = getelementptr i8, i8* %base8, <8 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %geposb = bitcast <8 x i8*> %gepos to <8 x i16*>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %resos = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %geposb, i32 2, <8 x i1> %mask, <8 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resos, <8 x i16*> %geposb, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i32, i32* %base32, <8 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbsb = bitcast <8 x i32*> %gepbs to <8 x i16*>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %resbs = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gepbsb, i32 2, <8 x i1> %mask, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resbs, <8 x i16*> %gepbsb, i32 2, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %resbs = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gepbsb, i32 2, <8 x i1> %mask, <8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resbs, <8 x i16*> %gepbsb, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %indzext4 = zext <8 x i16> %ind16 to <8 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep4 = getelementptr i16, i16* %base, <8 x i32> %indzext4
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %indtrunc = trunc <8 x i32> %ind32 to <8 x i16>
@@ -417,26 +417,26 @@
 define void @gep_v8f16(half* %base, i8* %base8, i32* %base32, <8 x i32> %ind32, <8 x i16> %ind16, <8 x i1> %mask)  {
 ; CHECK-LABEL: 'gep_v8f16'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gep1 = getelementptr half, half* %base, <8 x i32> %ind32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %res1 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep1, i32 2, <8 x i1> %mask, <8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %res1, <8 x half*> %gep1, i32 2, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %res1 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep1, i32 2, <8 x i1> %mask, <8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %res1, <8 x half*> %gep1, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %indzext = zext <8 x i16> %ind16 to <8 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gep2 = getelementptr half, half* %base, <8 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res2 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep2, i32 2, <8 x i1> %mask, <8 x half> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %res2, <8 x half*> %gep2, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %indsext = sext <8 x i16> %ind16 to <8 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gep3 = getelementptr half, half* %base, <8 x i32> %indsext
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %res3 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep3, i32 2, <8 x i1> %mask, <8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %res3, <8 x half*> %gep3, i32 2, <8 x i1> %mask)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %resu = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep2, i32 1, <8 x i1> %mask, <8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %resu, <8 x half*> %gep2, i32 1, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %res3 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep3, i32 2, <8 x i1> %mask, <8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %res3, <8 x half*> %gep3, i32 2, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %resu = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep2, i32 1, <8 x i1> %mask, <8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %resu, <8 x half*> %gep2, i32 1, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepos = getelementptr i8, i8* %base8, <8 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %geposb = bitcast <8 x i8*> %gepos to <8 x half*>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %resos = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %geposb, i32 2, <8 x i1> %mask, <8 x half> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %resos, <8 x half*> %geposb, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i32, i32* %base32, <8 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbsb = bitcast <8 x i32*> %gepbs to <8 x half*>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %resbs = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gepbsb, i32 2, <8 x i1> %mask, <8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %resbs, <8 x half*> %gepbsb, i32 2, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %resbs = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gepbsb, i32 2, <8 x i1> %mask, <8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %resbs, <8 x half*> %gepbsb, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   ; no offset ext
@@ -509,20 +509,20 @@
 define void @gep_v16i8(i8* %base, i16* %base16, <16 x i8> %ind8, <16 x i32> %ind32, <16 x i1> %mask)  {
 ; CHECK-LABEL: 'gep_v16i8'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep1 = getelementptr i8, i8* %base, <16 x i32> %ind32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %res1 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep1, i32 1, <16 x i1> %mask, <16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res1, <16 x i8*> %gep1, i32 2, <16 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %res1 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep1, i32 1, <16 x i1> %mask, <16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res1, <16 x i8*> %gep1, i32 2, <16 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %indzext = zext <16 x i8> %ind8 to <16 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep2 = getelementptr i8, i8* %base, <16 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %res2 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep2, i32 2, <16 x i1> %mask, <16 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res2, <16 x i8*> %gep2, i32 2, <16 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %indsext = sext <16 x i8> %ind8 to <16 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep3 = getelementptr i8, i8* %base, <16 x i32> %indsext
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %res3 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep3, i32 2, <16 x i1> %mask, <16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res3, <16 x i8*> %gep3, i32 2, <16 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %res3 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep3, i32 2, <16 x i1> %mask, <16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res3, <16 x i8*> %gep3, i32 2, <16 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i16, i16* %base16, <16 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbsb = bitcast <16 x i16*> %gepbs to <16 x i8*>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %resbs = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gepbsb, i32 2, <16 x i1> %mask, <16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %resbs, <16 x i8*> %gepbsb, i32 2, <16 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %resbs = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gepbsb, i32 2, <16 x i1> %mask, <16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %resbs, <16 x i8*> %gepbsb, i32 2, <16 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %indzext4 = zext <16 x i8> %ind8 to <16 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep4 = getelementptr i8, i8* %base, <16 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %indtrunc = trunc <16 x i32> %ind32 to <16 x i8>
@@ -564,8 +564,8 @@
 define void @gep_v16i8p(<16 x i8*> %base, i32 %off, <16 x i1> %mask)  {
 ; CHECK-LABEL: 'gep_v16i8p'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i8, <16 x i8*> %base, i32 %off
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %resbs = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gepbs, i32 2, <16 x i1> %mask, <16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %resbs, <16 x i8*> %gepbs, i32 2, <16 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %resbs = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gepbs, i32 2, <16 x i1> %mask, <16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %resbs, <16 x i8*> %gepbs, i32 2, <16 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %gepbs = getelementptr i8, <16 x i8*> %base, i32 %off
diff --git a/llvm/test/Analysis/CostModel/ARM/mve-minmax.ll b/llvm/test/Analysis/CostModel/ARM/mve-minmax.ll
--- a/llvm/test/Analysis/CostModel/ARM/mve-minmax.ll
+++ b/llvm/test/Analysis/CostModel/ARM/mve-minmax.ll
@@ -33,22 +33,22 @@
 define i32 @smin(i32 %arg) {
 ; MVE-RECIP-LABEL: 'smin'
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 152 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 304 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2I32 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V2I32 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2I16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V2I16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2I8 = call <2 x i8> @llvm.smin.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V2I8 = call <2 x i8> @llvm.smin.v2i8(<2 x i8> undef, <2 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -140,22 +140,22 @@
 define i32 @smax(i32 %arg) {
 ; MVE-RECIP-LABEL: 'smax'
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 152 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 304 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2I32 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V2I32 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2I16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V2I16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2I8 = call <2 x i8> @llvm.smax.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V2I8 = call <2 x i8> @llvm.smax.v2i8(<2 x i8> undef, <2 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -248,22 +248,22 @@
 define i32 @umin(i32 %arg) {
 ; MVE-RECIP-LABEL: 'umin'
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 152 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 304 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2I32 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V2I32 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2I16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V2I16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2I8 = call <2 x i8> @llvm.umin.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V2I8 = call <2 x i8> @llvm.umin.v2i8(<2 x i8> undef, <2 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -355,22 +355,22 @@
 define i32 @sub(i32 %arg) {
 ; MVE-RECIP-LABEL: 'sub'
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 152 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 304 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2I32 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V2I32 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2I16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V2I16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2I8 = call <2 x i8> @llvm.umax.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V2I8 = call <2 x i8> @llvm.umax.v2i8(<2 x i8> undef, <2 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -455,45 +455,45 @@
 define float @minnum(float %arg) {
 ; MVEI-RECIP-LABEL: 'minnum'
 ; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.minnum.f64(double undef, double undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2F64 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V4F64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V8F64 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2F64 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V4F64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8F64 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
 ; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.minnum.f32(float undef, float undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2F32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V4F32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V8F32 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 416 for instruction: %V16F32 = call <16 x float> @llvm.minnum.v16f32(<16 x float> undef, <16 x float> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2F32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V4F32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8F32 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 176 for instruction: %V16F32 = call <16 x float> @llvm.minnum.v16f32(<16 x float> undef, <16 x float> undef)
 ; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F16 = call half @llvm.minnum.f16(half undef, half undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2F16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V4F16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V8F16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 416 for instruction: %V16F16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 1344 for instruction: %V32F16 = call <32 x half> @llvm.minnum.v32f16(<32 x half> undef, <32 x half> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2F16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V4F16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8F16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 176 for instruction: %V16F16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 352 for instruction: %V32F16 = call <32 x half> @llvm.minnum.v32f16(<32 x half> undef, <32 x half> undef)
 ; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret float undef
 ;
 ; MVEI-SIZE-LABEL: 'minnum'
 ; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.minnum.f64(double undef, double undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4F64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8F64 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
 ; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.minnum.f32(float undef, float undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4F32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8F32 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %V16F32 = call <16 x float> @llvm.minnum.v16f32(<16 x float> undef, <16 x float> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x float> @llvm.minnum.v16f32(<16 x float> undef, <16 x float> undef)
 ; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.minnum.f16(half undef, half undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4F16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8F16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %V16F16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 1056 for instruction: %V32F16 = call <32 x half> @llvm.minnum.v32f16(<32 x half> undef, <32 x half> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V32F16 = call <32 x half> @llvm.minnum.v32f16(<32 x half> undef, <32 x half> undef)
 ; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret float undef
 ;
 ; MVEF-RECIP-LABEL: 'minnum'
 ; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.minnum.f64(double undef, double undef)
-; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2F64 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
-; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V4F64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
-; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V8F64 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
+; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2F64 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
+; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V4F64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
+; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8F64 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
 ; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.minnum.f32(float undef, float undef)
 ; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef)
 ; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
@@ -509,9 +509,9 @@
 ;
 ; MVEF-SIZE-LABEL: 'minnum'
 ; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.minnum.f64(double undef, double undef)
-; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
-; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4F64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
-; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8F64 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
+; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
+; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
+; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
 ; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.minnum.f32(float undef, float undef)
 ; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef)
 ; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
@@ -567,45 +567,45 @@
 define float @maxnum(float %arg) {
 ; MVEI-RECIP-LABEL: 'maxnum'
 ; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.maxnum.f64(double undef, double undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2F64 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V4F64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V8F64 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2F64 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V4F64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8F64 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
 ; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.maxnum.f32(float undef, float undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2F32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V4F32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V8F32 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 416 for instruction: %V16F32 = call <16 x float> @llvm.maxnum.v16f32(<16 x float> undef, <16 x float> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2F32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V4F32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8F32 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 176 for instruction: %V16F32 = call <16 x float> @llvm.maxnum.v16f32(<16 x float> undef, <16 x float> undef)
 ; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F16 = call half @llvm.maxnum.f16(half undef, half undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2F16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V4F16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V8F16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 416 for instruction: %V16F16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef)
-; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 1344 for instruction: %V32F16 = call <32 x half> @llvm.maxnum.v32f16(<32 x half> undef, <32 x half> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2F16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V4F16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8F16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 176 for instruction: %V16F16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef)
+; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 352 for instruction: %V32F16 = call <32 x half> @llvm.maxnum.v32f16(<32 x half> undef, <32 x half> undef)
 ; MVEI-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret float undef
 ;
 ; MVEI-SIZE-LABEL: 'maxnum'
 ; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.maxnum.f64(double undef, double undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4F64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8F64 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
 ; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.maxnum.f32(float undef, float undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4F32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8F32 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %V16F32 = call <16 x float> @llvm.maxnum.v16f32(<16 x float> undef, <16 x float> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x float> @llvm.maxnum.v16f32(<16 x float> undef, <16 x float> undef)
 ; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.maxnum.f16(half undef, half undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4F16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8F16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 272 for instruction: %V16F16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef)
-; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 1056 for instruction: %V32F16 = call <32 x half> @llvm.maxnum.v32f16(<32 x half> undef, <32 x half> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef)
+; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V32F16 = call <32 x half> @llvm.maxnum.v32f16(<32 x half> undef, <32 x half> undef)
 ; MVEI-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret float undef
 ;
 ; MVEF-RECIP-LABEL: 'maxnum'
 ; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.maxnum.f64(double undef, double undef)
-; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2F64 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
-; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V4F64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
-; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V8F64 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
+; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2F64 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
+; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V4F64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
+; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8F64 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
 ; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.maxnum.f32(float undef, float undef)
 ; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef)
 ; MVEF-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
@@ -621,9 +621,9 @@
 ;
 ; MVEF-SIZE-LABEL: 'maxnum'
 ; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.maxnum.f64(double undef, double undef)
-; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
-; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4F64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
-; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8F64 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
+; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
+; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
+; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
 ; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.maxnum.f32(float undef, float undef)
 ; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef)
 ; MVEF-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
diff --git a/llvm/test/Analysis/CostModel/ARM/mve-vecreduce-add.ll b/llvm/test/Analysis/CostModel/ARM/mve-vecreduce-add.ll
--- a/llvm/test/Analysis/CostModel/ARM/mve-vecreduce-add.ll
+++ b/llvm/test/Analysis/CostModel/ARM/mve-vecreduce-add.ll
@@ -3,8 +3,8 @@
 
 define void @add_i8() {
 ; CHECK-LABEL: 'add_i8'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a0 = call i8 @llvm.vector.reduce.add.v1i8(<1 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a1 = call i8 @llvm.vector.reduce.add.v2i8(<2 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a0 = call i8 @llvm.vector.reduce.add.v1i8(<1 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a1 = call i8 @llvm.vector.reduce.add.v2i8(<2 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2 = call i8 @llvm.vector.reduce.add.v4i8(<4 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a3 = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a4 = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> undef)
@@ -26,13 +26,13 @@
 define void @add_i16() {
 ; CHECK-LABEL: 'add_i16'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a0za = zext <1 x i8> undef to <1 x i16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a0z = call i16 @llvm.vector.reduce.add.v1i16(<1 x i16> %a0za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a0z = call i16 @llvm.vector.reduce.add.v1i16(<1 x i16> %a0za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a0sa = sext <1 x i8> undef to <1 x i16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a0s = call i16 @llvm.vector.reduce.add.v1i16(<1 x i16> %a0sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a0s = call i16 @llvm.vector.reduce.add.v1i16(<1 x i16> %a0sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a1za = zext <2 x i8> undef to <2 x i16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a1z = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> %a1za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a1z = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> %a1za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a1sa = sext <2 x i8> undef to <2 x i16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a1s = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> %a1sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a1s = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> %a1sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2za = zext <4 x i8> undef to <4 x i16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2z = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> %a2za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2sa = sext <4 x i8> undef to <4 x i16>
@@ -45,8 +45,8 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a4z = call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> %a4za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %a4sa = sext <16 x i8> undef to <16 x i16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a4s = call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> %a4sa)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a5 = call i16 @llvm.vector.reduce.add.v1i16(<1 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a6 = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a5 = call i16 @llvm.vector.reduce.add.v1i16(<1 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a6 = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a7 = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a8 = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a9 = call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> undef)
@@ -98,13 +98,13 @@
 define void @add_i32() {
 ; CHECK-LABEL: 'add_i32'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a0za = zext <1 x i8> undef to <1 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a0z = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a0za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a0z = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a0za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a0sa = sext <1 x i8> undef to <1 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a0s = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a0sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a0s = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a0sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a1za = zext <2 x i8> undef to <2 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a1z = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a1za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a1z = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a1za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a1sa = sext <2 x i8> undef to <2 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a1s = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a1sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a1s = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a1sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a2za = zext <4 x i8> undef to <4 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2z = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %a2za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a2sa = sext <4 x i8> undef to <4 x i32>
@@ -118,13 +118,13 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %a4sa = sext <16 x i8> undef to <16 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a4s = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> %a4sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a5za = zext <1 x i16> undef to <1 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a5z = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a5za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a5z = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a5za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a5sa = sext <1 x i16> undef to <1 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a5s = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a5sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a5s = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a5sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a6za = zext <2 x i16> undef to <2 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a6z = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a6za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a6z = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a6za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a6sa = sext <2 x i16> undef to <2 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a6s = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a6sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a6s = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a6sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a7za = zext <4 x i16> undef to <4 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a7z = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %a7za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a7sa = sext <4 x i16> undef to <4 x i32>
@@ -137,8 +137,8 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a9z = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> %a9za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %a9sa = sext <16 x i16> undef to <16 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a9s = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> %a9sa)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a10 = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a11 = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a10 = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a11 = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a12 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a13 = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a14 = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> undef)
@@ -219,71 +219,71 @@
 
 define void @add_i64() {
 ; CHECK-LABEL: 'add_i64'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a0za = zext <1 x i8> undef to <1 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a0z = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a0za)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a0sa = sext <1 x i8> undef to <1 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a0s = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a0sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %a0za = zext <1 x i8> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a0z = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a0za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %a0sa = sext <1 x i8> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a0s = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a0sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a1za = zext <2 x i8> undef to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %a1z = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a1za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %a1z = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a1za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %a1sa = sext <2 x i8> undef to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %a1s = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a1sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %a1s = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a1sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %a2za = zext <4 x i8> undef to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %a2z = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a2za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a2z = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a2za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %a2sa = sext <4 x i8> undef to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %a2s = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a2sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a2s = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a2sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %a3za = zext <8 x i8> undef to <8 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 202 for instruction: %a3z = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a3za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 408 for instruction: %a3z = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a3za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %a3sa = sext <8 x i8> undef to <8 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 202 for instruction: %a3s = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a3sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 408 for instruction: %a3s = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a3sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 298 for instruction: %a4za = zext <16 x i8> undef to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 730 for instruction: %a4z = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a4za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 808 for instruction: %a4z = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a4za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1322 for instruction: %a4sa = sext <16 x i8> undef to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 730 for instruction: %a4s = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a4sa)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a5za = zext <1 x i16> undef to <1 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a5z = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a5za)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a5sa = sext <1 x i16> undef to <1 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a5s = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a5sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 808 for instruction: %a4s = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a4sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %a5za = zext <1 x i16> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a5z = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a5za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %a5sa = sext <1 x i16> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a5s = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a5sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a6za = zext <2 x i16> undef to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %a6z = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a6za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %a6z = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a6za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %a6sa = sext <2 x i16> undef to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %a6s = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a6sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %a6s = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a6sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %a7za = zext <4 x i16> undef to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %a7z = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a7za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a7z = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a7za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %a7sa = sext <4 x i16> undef to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %a7s = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a7sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a7s = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a7sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %a8za = zext <8 x i16> undef to <8 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 202 for instruction: %a8z = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a8za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 408 for instruction: %a8z = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a8za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %a8sa = sext <8 x i16> undef to <8 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 202 for instruction: %a8s = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a8sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 408 for instruction: %a8s = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a8sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 296 for instruction: %a9za = zext <16 x i16> undef to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 730 for instruction: %a9z = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a9za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 808 for instruction: %a9z = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a9za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1320 for instruction: %a9sa = sext <16 x i16> undef to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 730 for instruction: %a9s = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a9sa)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a10za = zext <1 x i32> undef to <1 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a10z = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a10za)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a10sa = sext <1 x i32> undef to <1 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a10s = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a10sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 808 for instruction: %a9s = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a9sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %a10za = zext <1 x i32> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a10z = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a10za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %a10sa = sext <1 x i32> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a10s = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a10sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a11za = zext <2 x i32> undef to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %a11z = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a11za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %a11z = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a11za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %a11sa = sext <2 x i32> undef to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %a11s = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a11sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %a11s = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a11sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %a12za = zext <4 x i32> undef to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %a12z = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a12za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a12z = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a12za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %a12sa = sext <4 x i32> undef to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %a12s = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a12sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a12s = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a12sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %a13za = zext <8 x i32> undef to <8 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 202 for instruction: %a13z = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a13za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 408 for instruction: %a13z = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a13za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 264 for instruction: %a13sa = sext <8 x i32> undef to <8 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 202 for instruction: %a13s = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a13sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 408 for instruction: %a13s = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a13sa)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %a14za = zext <16 x i32> undef to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 730 for instruction: %a14z = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a14za)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 808 for instruction: %a14z = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a14za)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1056 for instruction: %a14sa = sext <16 x i32> undef to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 730 for instruction: %a14s = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a14sa)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a15 = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %a16 = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %a17 = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 202 for instruction: %a18 = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 730 for instruction: %a19 = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 808 for instruction: %a14s = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a14sa)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a15 = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %a16 = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a17 = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 408 for instruction: %a18 = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 808 for instruction: %a19 = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %a0za = zext <1 x i8> undef to <1 x i64>
@@ -392,9 +392,9 @@
 define void @mla_i8() {
 ; CHECK-LABEL: 'mla_i8'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a0m = mul <1 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a0 = call i8 @llvm.vector.reduce.add.v1i8(<1 x i8> %a0m)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a1m = mul <2 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a1 = call i8 @llvm.vector.reduce.add.v2i8(<2 x i8> %a1m)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a0 = call i8 @llvm.vector.reduce.add.v1i8(<1 x i8> %a0m)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %a1m = mul <2 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a1 = call i8 @llvm.vector.reduce.add.v2i8(<2 x i8> %a1m)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2m = mul <4 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2 = call i8 @llvm.vector.reduce.add.v4i8(<4 x i8> %a2m)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a3m = mul <8 x i8> undef, undef
@@ -426,19 +426,19 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a0za = zext <1 x i8> undef to <1 x i16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a0zb = zext <1 x i8> undef to <1 x i16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a0zm = mul <1 x i16> %a0za, %a0zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a0z = call i16 @llvm.vector.reduce.add.v1i16(<1 x i16> %a0zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a0z = call i16 @llvm.vector.reduce.add.v1i16(<1 x i16> %a0zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a0sa = sext <1 x i8> undef to <1 x i16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a0sb = sext <1 x i8> undef to <1 x i16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a0sm = mul <1 x i16> %a0sa, %a0sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a0s = call i16 @llvm.vector.reduce.add.v1i16(<1 x i16> %a0sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a0s = call i16 @llvm.vector.reduce.add.v1i16(<1 x i16> %a0sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a1za = zext <2 x i8> undef to <2 x i16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a1zb = zext <2 x i8> undef to <2 x i16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %a1zm = mul <2 x i16> %a1za, %a1zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a1z = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> %a1zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %a1zm = mul <2 x i16> %a1za, %a1zb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a1z = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> %a1zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a1sa = sext <2 x i8> undef to <2 x i16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a1sb = sext <2 x i8> undef to <2 x i16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %a1sm = mul <2 x i16> %a1sa, %a1sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a1s = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> %a1sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %a1sm = mul <2 x i16> %a1sa, %a1sb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a1s = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> %a1sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2za = zext <4 x i8> undef to <4 x i16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2zb = zext <4 x i8> undef to <4 x i16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2zm = mul <4 x i16> %a2za, %a2zb
@@ -464,9 +464,9 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a4sm = mul <16 x i16> %a4sa, %a4sb
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a4s = call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> %a4sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a5m = mul <1 x i16> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a5 = call i16 @llvm.vector.reduce.add.v1i16(<1 x i16> %a5m)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a6m = mul <2 x i16> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a6 = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> %a6m)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a5 = call i16 @llvm.vector.reduce.add.v1i16(<1 x i16> %a5m)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %a6m = mul <2 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a6 = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> %a6m)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a7m = mul <4 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a7 = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> %a7m)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a8m = mul <8 x i16> undef, undef
@@ -548,19 +548,19 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a0za = zext <1 x i8> undef to <1 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a0zb = zext <1 x i8> undef to <1 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a0zm = mul <1 x i32> %a0za, %a0zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a0z = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a0zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a0z = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a0zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a0sa = sext <1 x i8> undef to <1 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a0sb = sext <1 x i8> undef to <1 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a0sm = mul <1 x i32> %a0sa, %a0sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a0s = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a0sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a0s = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a0sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a1za = zext <2 x i8> undef to <2 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a1zb = zext <2 x i8> undef to <2 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %a1zm = mul <2 x i32> %a1za, %a1zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a1z = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a1zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %a1zm = mul <2 x i32> %a1za, %a1zb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a1z = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a1zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a1sa = sext <2 x i8> undef to <2 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a1sb = sext <2 x i8> undef to <2 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %a1sm = mul <2 x i32> %a1sa, %a1sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a1s = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a1sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %a1sm = mul <2 x i32> %a1sa, %a1sb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a1s = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a1sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a2za = zext <4 x i8> undef to <4 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a2zb = zext <4 x i8> undef to <4 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2zm = mul <4 x i32> %a2za, %a2zb
@@ -588,19 +588,19 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a5za = zext <1 x i16> undef to <1 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a5zb = zext <1 x i16> undef to <1 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a5zm = mul <1 x i32> %a5za, %a5zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a5z = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a5zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a5z = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a5zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a5sa = sext <1 x i16> undef to <1 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a5sb = sext <1 x i16> undef to <1 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a5sm = mul <1 x i32> %a5sa, %a5sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a5s = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a5sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a5s = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a5sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a6za = zext <2 x i16> undef to <2 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a6zb = zext <2 x i16> undef to <2 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %a6zm = mul <2 x i32> %a6za, %a6zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a6z = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a6zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %a6zm = mul <2 x i32> %a6za, %a6zb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a6z = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a6zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a6sa = sext <2 x i16> undef to <2 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a6sb = sext <2 x i16> undef to <2 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %a6sm = mul <2 x i32> %a6sa, %a6sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a6s = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a6sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %a6sm = mul <2 x i32> %a6sa, %a6sb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a6s = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a6sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a7za = zext <4 x i16> undef to <4 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a7zb = zext <4 x i16> undef to <4 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a7zm = mul <4 x i32> %a7za, %a7zb
@@ -626,9 +626,9 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a9sm = mul <16 x i32> %a9sa, %a9sb
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a9s = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> %a9sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a10m = mul <1 x i32> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a10 = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a10m)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a11m = mul <2 x i32> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %a11 = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a11m)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a10 = call i32 @llvm.vector.reduce.add.v1i32(<1 x i32> %a10m)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %a11m = mul <2 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %a11 = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %a11m)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a12m = mul <4 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a12 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %a12m)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a13m = mul <8 x i32> undef, undef
@@ -757,136 +757,136 @@
 
 define void @mla_i64() {
 ; CHECK-LABEL: 'mla_i64'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a0za = zext <1 x i8> undef to <1 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a0zb = zext <1 x i8> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %a0za = zext <1 x i8> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %a0zb = zext <1 x i8> undef to <1 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a0zm = mul <1 x i64> %a0za, %a0zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a0z = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a0zm)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a0sa = sext <1 x i8> undef to <1 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a0sb = sext <1 x i8> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a0z = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a0zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %a0sa = sext <1 x i8> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %a0sb = sext <1 x i8> undef to <1 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a0sm = mul <1 x i64> %a0sa, %a0sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a0s = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a0sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a0s = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a0sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a1za = zext <2 x i8> undef to <2 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a1zb = zext <2 x i8> undef to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %a1zm = mul <2 x i64> %a1za, %a1zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %a1z = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a1zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %a1zm = mul <2 x i64> %a1za, %a1zb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %a1z = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a1zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %a1sa = sext <2 x i8> undef to <2 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %a1sb = sext <2 x i8> undef to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %a1sm = mul <2 x i64> %a1sa, %a1sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %a1s = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a1sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %a1sm = mul <2 x i64> %a1sa, %a1sb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %a1s = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a1sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %a2za = zext <4 x i8> undef to <4 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %a2zb = zext <4 x i8> undef to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %a2zm = mul <4 x i64> %a2za, %a2zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %a2z = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a2zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %a2zm = mul <4 x i64> %a2za, %a2zb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a2z = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a2zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %a2sa = sext <4 x i8> undef to <4 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %a2sb = sext <4 x i8> undef to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %a2sm = mul <4 x i64> %a2sa, %a2sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %a2s = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a2sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %a2sm = mul <4 x i64> %a2sa, %a2sb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a2s = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a2sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %a3za = zext <8 x i8> undef to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %a3zb = zext <8 x i8> undef to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a3zm = mul <8 x i64> %a3za, %a3zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 202 for instruction: %a3z = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a3zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 408 for instruction: %a3z = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a3zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %a3sa = sext <8 x i8> undef to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %a3sb = sext <8 x i8> undef to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a3sm = mul <8 x i64> %a3sa, %a3sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 202 for instruction: %a3s = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a3sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 408 for instruction: %a3s = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a3sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 298 for instruction: %a4za = zext <16 x i8> undef to <16 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 298 for instruction: %a4zb = zext <16 x i8> undef to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 800 for instruction: %a4zm = mul <16 x i64> %a4za, %a4zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 730 for instruction: %a4z = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a4zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 416 for instruction: %a4zm = mul <16 x i64> %a4za, %a4zb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 808 for instruction: %a4z = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a4zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1322 for instruction: %a4sa = sext <16 x i8> undef to <16 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1322 for instruction: %a4sb = sext <16 x i8> undef to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 800 for instruction: %a4sm = mul <16 x i64> %a4sa, %a4sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 730 for instruction: %a4s = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a4sm)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a5za = zext <1 x i16> undef to <1 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a5zb = zext <1 x i16> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 416 for instruction: %a4sm = mul <16 x i64> %a4sa, %a4sb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 808 for instruction: %a4s = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a4sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %a5za = zext <1 x i16> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %a5zb = zext <1 x i16> undef to <1 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a5zm = mul <1 x i64> %a5za, %a5zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a5z = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a5zm)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a5sa = sext <1 x i16> undef to <1 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a5sb = sext <1 x i16> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a5z = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a5zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %a5sa = sext <1 x i16> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %a5sb = sext <1 x i16> undef to <1 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a5sm = mul <1 x i64> %a5sa, %a5sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a5s = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a5sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a5s = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a5sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a6za = zext <2 x i16> undef to <2 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a6zb = zext <2 x i16> undef to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %a6zm = mul <2 x i64> %a6za, %a6zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %a6z = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a6zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %a6zm = mul <2 x i64> %a6za, %a6zb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %a6z = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a6zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %a6sa = sext <2 x i16> undef to <2 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %a6sb = sext <2 x i16> undef to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %a6sm = mul <2 x i64> %a6sa, %a6sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %a6s = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a6sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %a6sm = mul <2 x i64> %a6sa, %a6sb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %a6s = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a6sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %a7za = zext <4 x i16> undef to <4 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %a7zb = zext <4 x i16> undef to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %a7zm = mul <4 x i64> %a7za, %a7zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %a7z = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a7zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %a7zm = mul <4 x i64> %a7za, %a7zb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a7z = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a7zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %a7sa = sext <4 x i16> undef to <4 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %a7sb = sext <4 x i16> undef to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %a7sm = mul <4 x i64> %a7sa, %a7sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %a7s = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a7sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %a7sm = mul <4 x i64> %a7sa, %a7sb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a7s = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a7sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %a8za = zext <8 x i16> undef to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %a8zb = zext <8 x i16> undef to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a8zm = mul <8 x i64> %a8za, %a8zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 202 for instruction: %a8z = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a8zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 408 for instruction: %a8z = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a8zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %a8sa = sext <8 x i16> undef to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %a8sb = sext <8 x i16> undef to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a8sm = mul <8 x i64> %a8sa, %a8sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 202 for instruction: %a8s = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a8sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 408 for instruction: %a8s = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a8sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 296 for instruction: %a9za = zext <16 x i16> undef to <16 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 296 for instruction: %a9zb = zext <16 x i16> undef to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 800 for instruction: %a9zm = mul <16 x i64> %a9za, %a9zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 730 for instruction: %a9z = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a9zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 416 for instruction: %a9zm = mul <16 x i64> %a9za, %a9zb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 808 for instruction: %a9z = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a9zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1320 for instruction: %a9sa = sext <16 x i16> undef to <16 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1320 for instruction: %a9sb = sext <16 x i16> undef to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 800 for instruction: %a9sm = mul <16 x i64> %a9sa, %a9sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 730 for instruction: %a9s = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a9sm)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a10za = zext <1 x i32> undef to <1 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a10zb = zext <1 x i32> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 416 for instruction: %a9sm = mul <16 x i64> %a9sa, %a9sb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 808 for instruction: %a9s = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a9sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %a10za = zext <1 x i32> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %a10zb = zext <1 x i32> undef to <1 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a10zm = mul <1 x i64> %a10za, %a10zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a10z = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a10zm)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a10sa = sext <1 x i32> undef to <1 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %a10sb = sext <1 x i32> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a10z = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a10zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %a10sa = sext <1 x i32> undef to <1 x i64>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %a10sb = sext <1 x i32> undef to <1 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a10sm = mul <1 x i64> %a10sa, %a10sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a10s = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a10sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a10s = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a10sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a11za = zext <2 x i32> undef to <2 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a11zb = zext <2 x i32> undef to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %a11zm = mul <2 x i64> %a11za, %a11zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %a11z = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a11zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %a11zm = mul <2 x i64> %a11za, %a11zb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %a11z = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a11zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %a11sa = sext <2 x i32> undef to <2 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %a11sb = sext <2 x i32> undef to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %a11sm = mul <2 x i64> %a11sa, %a11sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %a11s = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a11sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %a11sm = mul <2 x i64> %a11sa, %a11sb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %a11s = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a11sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %a12za = zext <4 x i32> undef to <4 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %a12zb = zext <4 x i32> undef to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %a12zm = mul <4 x i64> %a12za, %a12zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %a12z = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a12zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %a12zm = mul <4 x i64> %a12za, %a12zb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a12z = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a12zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %a12sa = sext <4 x i32> undef to <4 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %a12sb = sext <4 x i32> undef to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %a12sm = mul <4 x i64> %a12sa, %a12sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %a12s = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a12sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %a12sm = mul <4 x i64> %a12sa, %a12sb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a12s = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a12sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %a13za = zext <8 x i32> undef to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %a13zb = zext <8 x i32> undef to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a13zm = mul <8 x i64> %a13za, %a13zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 202 for instruction: %a13z = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a13zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 408 for instruction: %a13z = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a13zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 264 for instruction: %a13sa = sext <8 x i32> undef to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 264 for instruction: %a13sb = sext <8 x i32> undef to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a13sm = mul <8 x i64> %a13sa, %a13sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 202 for instruction: %a13s = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a13sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 408 for instruction: %a13s = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a13sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %a14za = zext <16 x i32> undef to <16 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %a14zb = zext <16 x i32> undef to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 800 for instruction: %a14zm = mul <16 x i64> %a14za, %a14zb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 730 for instruction: %a14z = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a14zm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 416 for instruction: %a14zm = mul <16 x i64> %a14za, %a14zb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 808 for instruction: %a14z = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a14zm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1056 for instruction: %a14sa = sext <16 x i32> undef to <16 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1056 for instruction: %a14sb = sext <16 x i32> undef to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 800 for instruction: %a14sm = mul <16 x i64> %a14sa, %a14sb
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 730 for instruction: %a14s = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a14sm)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 416 for instruction: %a14sm = mul <16 x i64> %a14sa, %a14sb
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 808 for instruction: %a14s = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a14sm)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a15m = mul <1 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a15 = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a15m)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a16m = mul <2 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %a16 = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a16m)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %a17m = mul <4 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %a17 = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a17m)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %a15 = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> %a15m)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %a16m = mul <2 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %a16 = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a16m)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %a17m = mul <4 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %a17 = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %a17m)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %a18m = mul <8 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 202 for instruction: %a18 = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a18m)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %a19m = mul <16 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 730 for instruction: %a19 = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a19m)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 408 for instruction: %a18 = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %a18m)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %a19m = mul <16 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 808 for instruction: %a19 = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> %a19m)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %a0za = zext <1 x i8> undef to <1 x i64>
diff --git a/llvm/test/Analysis/CostModel/ARM/reduce-smax.ll b/llvm/test/Analysis/CostModel/ARM/reduce-smax.ll
--- a/llvm/test/Analysis/CostModel/ARM/reduce-smax.ll
+++ b/llvm/test/Analysis/CostModel/ARM/reduce-smax.ll
@@ -21,11 +21,11 @@
 ; NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; MVE-LABEL: 'reduce_i64'
-; MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.vector.reduce.smax.v1i64(<1 x i64> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V2 = call i64 @llvm.vector.reduce.smax.v2i64(<2 x i64> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 98 for instruction: %V4 = call i64 @llvm.vector.reduce.smax.v4i64(<4 x i64> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 282 for instruction: %V8 = call i64 @llvm.vector.reduce.smax.v8i64(<8 x i64> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 970 for instruction: %V16 = call i64 @llvm.vector.reduce.smax.v16i64(<16 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V1 = call i64 @llvm.vector.reduce.smax.v1i64(<1 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 148 for instruction: %V2 = call i64 @llvm.vector.reduce.smax.v2i64(<2 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %V4 = call i64 @llvm.vector.reduce.smax.v4i64(<4 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 568 for instruction: %V8 = call i64 @llvm.vector.reduce.smax.v8i64(<8 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1128 for instruction: %V16 = call i64 @llvm.vector.reduce.smax.v16i64(<16 x i64> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1  = call i64 @llvm.vector.reduce.smax.v1i64(<1 x i64> undef)
@@ -54,11 +54,11 @@
 ; NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; MVE-LABEL: 'reduce_i32'
-; MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V2 = call i32 @llvm.vector.reduce.smax.v2i32(<2 x i32> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V2 = call i32 @llvm.vector.reduce.smax.v2i32(<2 x i32> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V4 = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 240 for instruction: %V8 = call i32 @llvm.vector.reduce.smax.v8i32(<8 x i32> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 696 for instruction: %V16 = call i32 @llvm.vector.reduce.smax.v16i32(<16 x i32> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 2504 for instruction: %V32 = call i32 @llvm.vector.reduce.smax.v32i32(<32 x i32> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %V8 = call i32 @llvm.vector.reduce.smax.v8i32(<8 x i32> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 376 for instruction: %V16 = call i32 @llvm.vector.reduce.smax.v16i32(<16 x i32> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 712 for instruction: %V32 = call i32 @llvm.vector.reduce.smax.v32i32(<32 x i32> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i32 @llvm.vector.reduce.smax.v2i32(<2 x i32> undef)
@@ -89,12 +89,12 @@
 ; NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; MVE-LABEL: 'reduce_i16'
-; MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V2 = call i16 @llvm.vector.reduce.smax.v2i16(<2 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V2 = call i16 @llvm.vector.reduce.smax.v2i16(<2 x i16> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V4 = call i16 @llvm.vector.reduce.smax.v4i16(<4 x i16> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 788 for instruction: %V8 = call i16 @llvm.vector.reduce.smax.v8i16(<8 x i16> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 1176 for instruction: %V16 = call i16 @llvm.vector.reduce.smax.v16i16(<16 x i16> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 2976 for instruction: %V32 = call i16 @llvm.vector.reduce.smax.v32i16(<32 x i16> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 10160 for instruction: %V64 = call i16 @llvm.vector.reduce.smax.v64i16(<64 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 400 for instruction: %V8 = call i16 @llvm.vector.reduce.smax.v8i16(<8 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 532 for instruction: %V16 = call i16 @llvm.vector.reduce.smax.v16i16(<16 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 860 for instruction: %V32 = call i16 @llvm.vector.reduce.smax.v32i16(<32 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1516 for instruction: %V64 = call i16 @llvm.vector.reduce.smax.v64i16(<64 x i16> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i16 @llvm.vector.reduce.smax.v2i16(<2 x i16> undef)
@@ -128,13 +128,13 @@
 ; NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; MVE-LABEL: 'reduce_i8'
-; MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V2 = call i8 @llvm.vector.reduce.smax.v2i8(<2 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V2 = call i8 @llvm.vector.reduce.smax.v2i8(<2 x i8> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V4 = call i8 @llvm.vector.reduce.smax.v4i8(<4 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 788 for instruction: %V8 = call i8 @llvm.vector.reduce.smax.v8i8(<8 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 4128 for instruction: %V16 = call i8 @llvm.vector.reduce.smax.v16i8(<16 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 5668 for instruction: %V32 = call i8 @llvm.vector.reduce.smax.v32i8(<32 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 12844 for instruction: %V64 = call i8 @llvm.vector.reduce.smax.v64i8(<64 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 41532 for instruction: %V128 = call i8 @llvm.vector.reduce.smax.v128i8(<128 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 400 for instruction: %V8 = call i8 @llvm.vector.reduce.smax.v8i8(<8 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1044 for instruction: %V16 = call i8 @llvm.vector.reduce.smax.v16i8(<16 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1304 for instruction: %V32 = call i8 @llvm.vector.reduce.smax.v32i8(<32 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1952 for instruction: %V64 = call i8 @llvm.vector.reduce.smax.v64i8(<64 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 3248 for instruction: %V128 = call i8 @llvm.vector.reduce.smax.v128i8(<128 x i8> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2   = call i8 @llvm.vector.reduce.smax.v2i8(<2 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/ARM/reduce-smin.ll b/llvm/test/Analysis/CostModel/ARM/reduce-smin.ll
--- a/llvm/test/Analysis/CostModel/ARM/reduce-smin.ll
+++ b/llvm/test/Analysis/CostModel/ARM/reduce-smin.ll
@@ -21,11 +21,11 @@
 ; NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; MVE-LABEL: 'reduce_i64'
-; MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.vector.reduce.smin.v1i64(<1 x i64> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V2 = call i64 @llvm.vector.reduce.smin.v2i64(<2 x i64> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 98 for instruction: %V4 = call i64 @llvm.vector.reduce.smin.v4i64(<4 x i64> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 282 for instruction: %V8 = call i64 @llvm.vector.reduce.smin.v8i64(<8 x i64> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 970 for instruction: %V16 = call i64 @llvm.vector.reduce.smin.v16i64(<16 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V1 = call i64 @llvm.vector.reduce.smin.v1i64(<1 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 148 for instruction: %V2 = call i64 @llvm.vector.reduce.smin.v2i64(<2 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %V4 = call i64 @llvm.vector.reduce.smin.v4i64(<4 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 568 for instruction: %V8 = call i64 @llvm.vector.reduce.smin.v8i64(<8 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1128 for instruction: %V16 = call i64 @llvm.vector.reduce.smin.v16i64(<16 x i64> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1  = call i64 @llvm.vector.reduce.smin.v1i64(<1 x i64> undef)
@@ -54,11 +54,11 @@
 ; NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; MVE-LABEL: 'reduce_i32'
-; MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V2 = call i32 @llvm.vector.reduce.smin.v2i32(<2 x i32> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V2 = call i32 @llvm.vector.reduce.smin.v2i32(<2 x i32> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V4 = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 240 for instruction: %V8 = call i32 @llvm.vector.reduce.smin.v8i32(<8 x i32> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 696 for instruction: %V16 = call i32 @llvm.vector.reduce.smin.v16i32(<16 x i32> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 2504 for instruction: %V32 = call i32 @llvm.vector.reduce.smin.v32i32(<32 x i32> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %V8 = call i32 @llvm.vector.reduce.smin.v8i32(<8 x i32> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 376 for instruction: %V16 = call i32 @llvm.vector.reduce.smin.v16i32(<16 x i32> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 712 for instruction: %V32 = call i32 @llvm.vector.reduce.smin.v32i32(<32 x i32> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i32 @llvm.vector.reduce.smin.v2i32(<2 x i32> undef)
@@ -89,12 +89,12 @@
 ; NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; MVE-LABEL: 'reduce_i16'
-; MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V2 = call i16 @llvm.vector.reduce.smin.v2i16(<2 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V2 = call i16 @llvm.vector.reduce.smin.v2i16(<2 x i16> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V4 = call i16 @llvm.vector.reduce.smin.v4i16(<4 x i16> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 788 for instruction: %V8 = call i16 @llvm.vector.reduce.smin.v8i16(<8 x i16> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 1176 for instruction: %V16 = call i16 @llvm.vector.reduce.smin.v16i16(<16 x i16> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 2976 for instruction: %V32 = call i16 @llvm.vector.reduce.smin.v32i16(<32 x i16> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 10160 for instruction: %V64 = call i16 @llvm.vector.reduce.smin.v64i16(<64 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 400 for instruction: %V8 = call i16 @llvm.vector.reduce.smin.v8i16(<8 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 532 for instruction: %V16 = call i16 @llvm.vector.reduce.smin.v16i16(<16 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 860 for instruction: %V32 = call i16 @llvm.vector.reduce.smin.v32i16(<32 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1516 for instruction: %V64 = call i16 @llvm.vector.reduce.smin.v64i16(<64 x i16> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i16 @llvm.vector.reduce.smin.v2i16(<2 x i16> undef)
@@ -128,13 +128,13 @@
 ; NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; MVE-LABEL: 'reduce_i8'
-; MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V2 = call i8 @llvm.vector.reduce.smin.v2i8(<2 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V2 = call i8 @llvm.vector.reduce.smin.v2i8(<2 x i8> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V4 = call i8 @llvm.vector.reduce.smin.v4i8(<4 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 788 for instruction: %V8 = call i8 @llvm.vector.reduce.smin.v8i8(<8 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 4128 for instruction: %V16 = call i8 @llvm.vector.reduce.smin.v16i8(<16 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 5668 for instruction: %V32 = call i8 @llvm.vector.reduce.smin.v32i8(<32 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 12844 for instruction: %V64 = call i8 @llvm.vector.reduce.smin.v64i8(<64 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 41532 for instruction: %V128 = call i8 @llvm.vector.reduce.smin.v128i8(<128 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 400 for instruction: %V8 = call i8 @llvm.vector.reduce.smin.v8i8(<8 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1044 for instruction: %V16 = call i8 @llvm.vector.reduce.smin.v16i8(<16 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1304 for instruction: %V32 = call i8 @llvm.vector.reduce.smin.v32i8(<32 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1952 for instruction: %V64 = call i8 @llvm.vector.reduce.smin.v64i8(<64 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 3248 for instruction: %V128 = call i8 @llvm.vector.reduce.smin.v128i8(<128 x i8> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2   = call i8 @llvm.vector.reduce.smin.v2i8(<2 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/ARM/reduce-umax.ll b/llvm/test/Analysis/CostModel/ARM/reduce-umax.ll
--- a/llvm/test/Analysis/CostModel/ARM/reduce-umax.ll
+++ b/llvm/test/Analysis/CostModel/ARM/reduce-umax.ll
@@ -21,11 +21,11 @@
 ; NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; MVE-LABEL: 'reduce_i64'
-; MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.vector.reduce.umax.v1i64(<1 x i64> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V2 = call i64 @llvm.vector.reduce.umax.v2i64(<2 x i64> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 98 for instruction: %V4 = call i64 @llvm.vector.reduce.umax.v4i64(<4 x i64> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 282 for instruction: %V8 = call i64 @llvm.vector.reduce.umax.v8i64(<8 x i64> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 970 for instruction: %V16 = call i64 @llvm.vector.reduce.umax.v16i64(<16 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V1 = call i64 @llvm.vector.reduce.umax.v1i64(<1 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 148 for instruction: %V2 = call i64 @llvm.vector.reduce.umax.v2i64(<2 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %V4 = call i64 @llvm.vector.reduce.umax.v4i64(<4 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 568 for instruction: %V8 = call i64 @llvm.vector.reduce.umax.v8i64(<8 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1128 for instruction: %V16 = call i64 @llvm.vector.reduce.umax.v16i64(<16 x i64> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1  = call i64 @llvm.vector.reduce.umax.v1i64(<1 x i64> undef)
@@ -54,11 +54,11 @@
 ; NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; MVE-LABEL: 'reduce_i32'
-; MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V2 = call i32 @llvm.vector.reduce.umax.v2i32(<2 x i32> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V2 = call i32 @llvm.vector.reduce.umax.v2i32(<2 x i32> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V4 = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 240 for instruction: %V8 = call i32 @llvm.vector.reduce.umax.v8i32(<8 x i32> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 696 for instruction: %V16 = call i32 @llvm.vector.reduce.umax.v16i32(<16 x i32> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 2504 for instruction: %V32 = call i32 @llvm.vector.reduce.umax.v32i32(<32 x i32> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %V8 = call i32 @llvm.vector.reduce.umax.v8i32(<8 x i32> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 376 for instruction: %V16 = call i32 @llvm.vector.reduce.umax.v16i32(<16 x i32> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 712 for instruction: %V32 = call i32 @llvm.vector.reduce.umax.v32i32(<32 x i32> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i32 @llvm.vector.reduce.umax.v2i32(<2 x i32> undef)
@@ -89,12 +89,12 @@
 ; NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; MVE-LABEL: 'reduce_i16'
-; MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V2 = call i16 @llvm.vector.reduce.umax.v2i16(<2 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V2 = call i16 @llvm.vector.reduce.umax.v2i16(<2 x i16> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V4 = call i16 @llvm.vector.reduce.umax.v4i16(<4 x i16> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 788 for instruction: %V8 = call i16 @llvm.vector.reduce.umax.v8i16(<8 x i16> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 1176 for instruction: %V16 = call i16 @llvm.vector.reduce.umax.v16i16(<16 x i16> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 2976 for instruction: %V32 = call i16 @llvm.vector.reduce.umax.v32i16(<32 x i16> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 10160 for instruction: %V64 = call i16 @llvm.vector.reduce.umax.v64i16(<64 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 400 for instruction: %V8 = call i16 @llvm.vector.reduce.umax.v8i16(<8 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 532 for instruction: %V16 = call i16 @llvm.vector.reduce.umax.v16i16(<16 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 860 for instruction: %V32 = call i16 @llvm.vector.reduce.umax.v32i16(<32 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1516 for instruction: %V64 = call i16 @llvm.vector.reduce.umax.v64i16(<64 x i16> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i16 @llvm.vector.reduce.umax.v2i16(<2 x i16> undef)
@@ -128,13 +128,13 @@
 ; NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; MVE-LABEL: 'reduce_i8'
-; MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V2 = call i8 @llvm.vector.reduce.umax.v2i8(<2 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V2 = call i8 @llvm.vector.reduce.umax.v2i8(<2 x i8> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V4 = call i8 @llvm.vector.reduce.umax.v4i8(<4 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 788 for instruction: %V8 = call i8 @llvm.vector.reduce.umax.v8i8(<8 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 4128 for instruction: %V16 = call i8 @llvm.vector.reduce.umax.v16i8(<16 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 5668 for instruction: %V32 = call i8 @llvm.vector.reduce.umax.v32i8(<32 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 12844 for instruction: %V64 = call i8 @llvm.vector.reduce.umax.v64i8(<64 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 41532 for instruction: %V128 = call i8 @llvm.vector.reduce.umax.v128i8(<128 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 400 for instruction: %V8 = call i8 @llvm.vector.reduce.umax.v8i8(<8 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1044 for instruction: %V16 = call i8 @llvm.vector.reduce.umax.v16i8(<16 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1304 for instruction: %V32 = call i8 @llvm.vector.reduce.umax.v32i8(<32 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1952 for instruction: %V64 = call i8 @llvm.vector.reduce.umax.v64i8(<64 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 3248 for instruction: %V128 = call i8 @llvm.vector.reduce.umax.v128i8(<128 x i8> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2   = call i8 @llvm.vector.reduce.umax.v2i8(<2 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/ARM/reduce-umin.ll b/llvm/test/Analysis/CostModel/ARM/reduce-umin.ll
--- a/llvm/test/Analysis/CostModel/ARM/reduce-umin.ll
+++ b/llvm/test/Analysis/CostModel/ARM/reduce-umin.ll
@@ -21,11 +21,11 @@
 ; NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; MVE-LABEL: 'reduce_i64'
-; MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.vector.reduce.umin.v1i64(<1 x i64> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V2 = call i64 @llvm.vector.reduce.umin.v2i64(<2 x i64> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 98 for instruction: %V4 = call i64 @llvm.vector.reduce.umin.v4i64(<4 x i64> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 282 for instruction: %V8 = call i64 @llvm.vector.reduce.umin.v8i64(<8 x i64> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 970 for instruction: %V16 = call i64 @llvm.vector.reduce.umin.v16i64(<16 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V1 = call i64 @llvm.vector.reduce.umin.v1i64(<1 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 148 for instruction: %V2 = call i64 @llvm.vector.reduce.umin.v2i64(<2 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %V4 = call i64 @llvm.vector.reduce.umin.v4i64(<4 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 568 for instruction: %V8 = call i64 @llvm.vector.reduce.umin.v8i64(<8 x i64> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1128 for instruction: %V16 = call i64 @llvm.vector.reduce.umin.v16i64(<16 x i64> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1  = call i64 @llvm.vector.reduce.umin.v1i64(<1 x i64> undef)
@@ -54,11 +54,11 @@
 ; NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; MVE-LABEL: 'reduce_i32'
-; MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V2 = call i32 @llvm.vector.reduce.umin.v2i32(<2 x i32> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V2 = call i32 @llvm.vector.reduce.umin.v2i32(<2 x i32> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V4 = call i32 @llvm.vector.reduce.umin.v4i32(<4 x i32> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 240 for instruction: %V8 = call i32 @llvm.vector.reduce.umin.v8i32(<8 x i32> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 696 for instruction: %V16 = call i32 @llvm.vector.reduce.umin.v16i32(<16 x i32> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 2504 for instruction: %V32 = call i32 @llvm.vector.reduce.umin.v32i32(<32 x i32> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %V8 = call i32 @llvm.vector.reduce.umin.v8i32(<8 x i32> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 376 for instruction: %V16 = call i32 @llvm.vector.reduce.umin.v16i32(<16 x i32> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 712 for instruction: %V32 = call i32 @llvm.vector.reduce.umin.v32i32(<32 x i32> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i32 @llvm.vector.reduce.umin.v2i32(<2 x i32> undef)
@@ -89,12 +89,12 @@
 ; NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; MVE-LABEL: 'reduce_i16'
-; MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V2 = call i16 @llvm.vector.reduce.umin.v2i16(<2 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V2 = call i16 @llvm.vector.reduce.umin.v2i16(<2 x i16> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V4 = call i16 @llvm.vector.reduce.umin.v4i16(<4 x i16> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 788 for instruction: %V8 = call i16 @llvm.vector.reduce.umin.v8i16(<8 x i16> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 1176 for instruction: %V16 = call i16 @llvm.vector.reduce.umin.v16i16(<16 x i16> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 2976 for instruction: %V32 = call i16 @llvm.vector.reduce.umin.v32i16(<32 x i16> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 10160 for instruction: %V64 = call i16 @llvm.vector.reduce.umin.v64i16(<64 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 400 for instruction: %V8 = call i16 @llvm.vector.reduce.umin.v8i16(<8 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 532 for instruction: %V16 = call i16 @llvm.vector.reduce.umin.v16i16(<16 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 860 for instruction: %V32 = call i16 @llvm.vector.reduce.umin.v32i16(<32 x i16> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1516 for instruction: %V64 = call i16 @llvm.vector.reduce.umin.v64i16(<64 x i16> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i16 @llvm.vector.reduce.umin.v2i16(<2 x i16> undef)
@@ -128,13 +128,13 @@
 ; NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; MVE-LABEL: 'reduce_i8'
-; MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V2 = call i8 @llvm.vector.reduce.umin.v2i8(<2 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V2 = call i8 @llvm.vector.reduce.umin.v2i8(<2 x i8> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V4 = call i8 @llvm.vector.reduce.umin.v4i8(<4 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 788 for instruction: %V8 = call i8 @llvm.vector.reduce.umin.v8i8(<8 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 4128 for instruction: %V16 = call i8 @llvm.vector.reduce.umin.v16i8(<16 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 5668 for instruction: %V32 = call i8 @llvm.vector.reduce.umin.v32i8(<32 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 12844 for instruction: %V64 = call i8 @llvm.vector.reduce.umin.v64i8(<64 x i8> undef)
-; MVE-NEXT:  Cost Model: Found an estimated cost of 41532 for instruction: %V128 = call i8 @llvm.vector.reduce.umin.v128i8(<128 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 400 for instruction: %V8 = call i8 @llvm.vector.reduce.umin.v8i8(<8 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1044 for instruction: %V16 = call i8 @llvm.vector.reduce.umin.v16i8(<16 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1304 for instruction: %V32 = call i8 @llvm.vector.reduce.umin.v32i8(<32 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 1952 for instruction: %V64 = call i8 @llvm.vector.reduce.umin.v64i8(<64 x i8> undef)
+; MVE-NEXT:  Cost Model: Found an estimated cost of 3248 for instruction: %V128 = call i8 @llvm.vector.reduce.umin.v128i8(<128 x i8> undef)
 ; MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2   = call i8 @llvm.vector.reduce.umin.v2i8(<2 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/ARM/select.ll b/llvm/test/Analysis/CostModel/ARM/select.ll
--- a/llvm/test/Analysis/CostModel/ARM/select.ll
+++ b/llvm/test/Analysis/CostModel/ARM/select.ll
@@ -18,28 +18,28 @@
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4 = select i1 undef, i64 undef, i64 undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v5 = select i1 undef, float undef, float undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v6 = select i1 undef, double undef, double undef
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v7 = select <2 x i1> undef, <2 x i8> undef, <2 x i8> undef
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %v7 = select <2 x i1> undef, <2 x i8> undef, <2 x i8> undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8 = select <4 x i1> undef, <4 x i8> undef, <4 x i8> undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v9 = select <8 x i1> undef, <8 x i8> undef, <8 x i8> undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v10 = select <16 x i1> undef, <16 x i8> undef, <16 x i8> undef
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v11 = select <2 x i1> undef, <2 x i16> undef, <2 x i16> undef
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %v11 = select <2 x i1> undef, <2 x i16> undef, <2 x i16> undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v12 = select <4 x i1> undef, <4 x i16> undef, <4 x i16> undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v13 = select <8 x i1> undef, <8 x i16> undef, <8 x i16> undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v13b = select <16 x i1> undef, <16 x i16> undef, <16 x i16> undef
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v14 = select <2 x i1> undef, <2 x i32> undef, <2 x i32> undef
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %v14 = select <2 x i1> undef, <2 x i32> undef, <2 x i32> undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v15 = select <4 x i1> undef, <4 x i32> undef, <4 x i32> undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v15b = select <8 x i1> undef, <8 x i32> undef, <8 x i32> undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v15c = select <16 x i1> undef, <16 x i32> undef, <16 x i32> undef
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16 = select <2 x i1> undef, <2 x i64> undef, <2 x i64> undef
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %v16a = select <4 x i1> undef, <4 x i64> undef, <4 x i64> undef
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %v16 = select <2 x i1> undef, <2 x i64> undef, <2 x i64> undef
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %v16a = select <4 x i1> undef, <4 x i64> undef, <4 x i64> undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %v16b = select <8 x i1> undef, <8 x i64> undef, <8 x i64> undef
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 576 for instruction: %v16c = select <16 x i1> undef, <16 x i64> undef, <16 x i64> undef
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 320 for instruction: %v16c = select <16 x i1> undef, <16 x i64> undef, <16 x i64> undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v17 = select <2 x i1> undef, <2 x float> undef, <2 x float> undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v18 = select <4 x i1> undef, <4 x float> undef, <4 x float> undef
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v19 = select <2 x i1> undef, <2 x double> undef, <2 x double> undef
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v20 = select <1 x i1> undef, <1 x i32> undef, <1 x i32> undef
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v19 = select <2 x i1> undef, <2 x double> undef, <2 x double> undef
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %v20 = select <1 x i1> undef, <1 x i32> undef, <1 x i32> undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v21 = select <3 x i1> undef, <3 x float> undef, <3 x float> undef
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %v22 = select <5 x i1> undef, <5 x double> undef, <5 x double> undef
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %v22 = select <5 x i1> undef, <5 x double> undef, <5 x double> undef
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-NEON-RECIP-LABEL: 'selects'
diff --git a/llvm/test/Analysis/CostModel/ARM/shuffle.ll b/llvm/test/Analysis/CostModel/ARM/shuffle.ll
--- a/llvm/test/Analysis/CostModel/ARM/shuffle.ll
+++ b/llvm/test/Analysis/CostModel/ARM/shuffle.ll
@@ -4,19 +4,19 @@
 
 define void @broadcast() {
 ; CHECK-MVE-LABEL: 'broadcast'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v2i8 = shufflevector <2 x i8> undef, <2 x i8> undef, <2 x i32> zeroinitializer
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %v2i8 = shufflevector <2 x i8> undef, <2 x i8> undef, <2 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4i8 = shufflevector <4 x i8> undef, <4 x i8> undef, <4 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> zeroinitializer
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v2i16 = shufflevector <2 x i16> undef, <2 x i16> undef, <2 x i32> zeroinitializer
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %v2i16 = shufflevector <2 x i16> undef, <2 x i16> undef, <2 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4i16 = shufflevector <4 x i16> undef, <4 x i16> undef, <4 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> zeroinitializer
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v2i32 = shufflevector <2 x i32> undef, <2 x i32> undef, <2 x i32> zeroinitializer
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %v2i32 = shufflevector <2 x i32> undef, <2 x i32> undef, <2 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4i32 = shufflevector <4 x i32> undef, <4 x i32> undef, <4 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <8 x i32> zeroinitializer
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v2i64 = shufflevector <2 x i64> undef, <2 x i64> undef, <2 x i32> zeroinitializer
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %v4i64 = shufflevector <4 x i64> undef, <4 x i64> undef, <4 x i32> zeroinitializer
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %v2i64 = shufflevector <2 x i64> undef, <2 x i64> undef, <2 x i32> zeroinitializer
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %v4i64 = shufflevector <4 x i64> undef, <4 x i64> undef, <4 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f16 = shufflevector <2 x half> undef, <2 x half> undef, <2 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f16 = shufflevector <4 x half> undef, <4 x half> undef, <4 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f16 = shufflevector <8 x half> undef, <8 x half> undef, <8 x i32> zeroinitializer
@@ -24,8 +24,8 @@
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32 = shufflevector <2 x float> undef, <2 x float> undef, <2 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f32 = shufflevector <4 x float> undef, <4 x float> undef, <4 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8f32 = shufflevector <8 x float> undef, <8 x float> undef, <8 x i32> zeroinitializer
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v2f64 = shufflevector <2 x double> undef, <2 x double> undef, <2 x i32> zeroinitializer
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %v4f64 = shufflevector <4 x double> undef, <4 x double> undef, <4 x i32> zeroinitializer
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v2f64 = shufflevector <2 x double> undef, <2 x double> undef, <2 x i32> zeroinitializer
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %v4f64 = shufflevector <4 x double> undef, <4 x double> undef, <4 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-NEON-LABEL: 'broadcast'
@@ -88,28 +88,28 @@
 ;; Reverse shuffles should be lowered to vrev and possibly a vext (for quadwords, on neon)
 define void @reverse() {
 ; CHECK-MVE-LABEL: 'reverse'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v2i8 = shufflevector <2 x i8> undef, <2 x i8> undef, <2 x i32> <i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v2i8 = shufflevector <2 x i8> undef, <2 x i8> undef, <2 x i32> <i32 1, i32 0>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v4i8 = shufflevector <4 x i8> undef, <4 x i8> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v8i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1024 for instruction: %v16i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v2i16 = shufflevector <2 x i16> undef, <2 x i16> undef, <2 x i32> <i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %v8i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v16i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v2i16 = shufflevector <2 x i16> undef, <2 x i16> undef, <2 x i32> <i32 1, i32 0>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v4i16 = shufflevector <4 x i16> undef, <4 x i16> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v8i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1024 for instruction: %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v2i32 = shufflevector <2 x i32> undef, <2 x i32> undef, <2 x i32> <i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %v8i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v2i32 = shufflevector <2 x i32> undef, <2 x i32> undef, <2 x i32> <i32 1, i32 0>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v4i32 = shufflevector <4 x i32> undef, <4 x i32> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v8i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v2i64 = shufflevector <2 x i64> undef, <2 x i64> undef, <2 x i32> <i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v4i64 = shufflevector <4 x i64> undef, <4 x i64> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %v8i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v2i64 = shufflevector <2 x i64> undef, <2 x i64> undef, <2 x i32> <i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %v4i64 = shufflevector <4 x i64> undef, <4 x i64> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f16 = shufflevector <2 x half> undef, <2 x half> undef, <2 x i32> <i32 1, i32 0>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f16 = shufflevector <4 x half> undef, <4 x half> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v8f16 = shufflevector <8 x half> undef, <8 x half> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1024 for instruction: %v16f16 = shufflevector <16 x half> undef, <16 x half> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v8f16 = shufflevector <8 x half> undef, <8 x half> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v16f16 = shufflevector <16 x half> undef, <16 x half> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32 = shufflevector <2 x float> undef, <2 x float> undef, <2 x i32> <i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v4f32 = shufflevector <4 x float> undef, <4 x float> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v8f32 = shufflevector <8 x float> undef, <8 x float> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v2f64 = shufflevector <2 x double> undef, <2 x double> undef, <2 x i32> <i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v4f64 = shufflevector <4 x double> undef, <4 x double> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v4f32 = shufflevector <4 x float> undef, <4 x float> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v8f32 = shufflevector <8 x float> undef, <8 x float> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v2f64 = shufflevector <2 x double> undef, <2 x double> undef, <2 x i32> <i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v4f64 = shufflevector <4 x double> undef, <4 x double> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-NEON-LABEL: 'reverse'
@@ -233,28 +233,28 @@
 
 define void @select() {
 ; CHECK-MVE-LABEL: 'select'
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v2i8 = shufflevector <2 x i8> undef, <2 x i8> undef, <2 x i32> <i32 0, i32 3>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v2i8 = shufflevector <2 x i8> undef, <2 x i8> undef, <2 x i32> <i32 0, i32 3>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v4i8 = shufflevector <4 x i8> undef, <4 x i8> undef, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v8i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> <i32 8, i32 1, i32 10, i32 11, i32 4, i32 5, i32 6, i32 15>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1024 for instruction: %v16i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> <i32 0, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v2i16 = shufflevector <2 x i16> undef, <2 x i16> undef, <2 x i32> <i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %v8i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> <i32 8, i32 1, i32 10, i32 11, i32 4, i32 5, i32 6, i32 15>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v16i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> <i32 0, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v2i16 = shufflevector <2 x i16> undef, <2 x i16> undef, <2 x i32> <i32 1, i32 0>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v4i16 = shufflevector <4 x i16> undef, <4 x i16> undef, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v8i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> <i32 8, i32 1, i32 10, i32 11, i32 4, i32 5, i32 6, i32 15>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1024 for instruction: %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 0, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v2i32 = shufflevector <2 x i32> undef, <2 x i32> undef, <2 x i32> <i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %v8i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> <i32 8, i32 1, i32 10, i32 11, i32 4, i32 5, i32 6, i32 15>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 0, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v2i32 = shufflevector <2 x i32> undef, <2 x i32> undef, <2 x i32> <i32 1, i32 0>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v4i32 = shufflevector <4 x i32> undef, <4 x i32> undef, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v8i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <8 x i32> <i32 8, i32 1, i32 10, i32 11, i32 4, i32 5, i32 6, i32 15>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v2i64 = shufflevector <2 x i64> undef, <2 x i64> undef, <2 x i32> <i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v4i64 = shufflevector <4 x i64> undef, <4 x i64> undef, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %v8i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <8 x i32> <i32 8, i32 1, i32 10, i32 11, i32 4, i32 5, i32 6, i32 15>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v2i64 = shufflevector <2 x i64> undef, <2 x i64> undef, <2 x i32> <i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %v4i64 = shufflevector <4 x i64> undef, <4 x i64> undef, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f16 = shufflevector <2 x half> undef, <2 x half> undef, <2 x i32> <i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v4f16 = shufflevector <4 x half> undef, <4 x half> undef, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v8f16 = shufflevector <8 x half> undef, <8 x half> undef, <8 x i32> <i32 8, i32 1, i32 10, i32 11, i32 4, i32 5, i32 6, i32 15>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1024 for instruction: %v16f16 = shufflevector <16 x half> undef, <16 x half> undef, <16 x i32> <i32 0, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v4f16 = shufflevector <4 x half> undef, <4 x half> undef, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v8f16 = shufflevector <8 x half> undef, <8 x half> undef, <8 x i32> <i32 8, i32 1, i32 10, i32 11, i32 4, i32 5, i32 6, i32 15>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v16f16 = shufflevector <16 x half> undef, <16 x half> undef, <16 x i32> <i32 0, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32 = shufflevector <2 x float> undef, <2 x float> undef, <2 x i32> <i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v4f32 = shufflevector <4 x float> undef, <4 x float> undef, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v8f32 = shufflevector <8 x float> undef, <8 x float> undef, <8 x i32> <i32 8, i32 1, i32 10, i32 11, i32 4, i32 5, i32 6, i32 15>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v2f64 = shufflevector <2 x double> undef, <2 x double> undef, <2 x i32> <i32 1, i32 0>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v4f64 = shufflevector <4 x double> undef, <4 x double> undef, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v4f32 = shufflevector <4 x float> undef, <4 x float> undef, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v8f32 = shufflevector <8 x float> undef, <8 x float> undef, <8 x i32> <i32 8, i32 1, i32 10, i32 11, i32 4, i32 5, i32 6, i32 15>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v2f64 = shufflevector <2 x double> undef, <2 x double> undef, <2 x i32> <i32 1, i32 0>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v4f64 = shufflevector <4 x double> undef, <4 x double> undef, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-NEON-LABEL: 'select'
@@ -321,16 +321,16 @@
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4i16 = shufflevector <4 x i16> undef, <4 x i16> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1024 for instruction: %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4i32 = shufflevector <4 x i32> undef, <4 x i32> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v8i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v4i64 = shufflevector <4 x i64> undef, <4 x i64> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %v8i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %v4i64 = shufflevector <4 x i64> undef, <4 x i64> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f16 = shufflevector <4 x half> undef, <4 x half> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f16 = shufflevector <8 x half> undef, <8 x half> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1024 for instruction: %v16f16 = shufflevector <16 x half> undef, <16 x half> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v16f16 = shufflevector <16 x half> undef, <16 x half> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f32 = shufflevector <4 x float> undef, <4 x float> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v8f32 = shufflevector <8 x float> undef, <8 x float> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v4f64 = shufflevector <4 x double> undef, <4 x double> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v8f32 = shufflevector <8 x float> undef, <8 x float> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v4f64 = shufflevector <4 x double> undef, <4 x double> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-NEON-LABEL: 'vrev2'
@@ -381,11 +381,11 @@
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1024 for instruction: %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v8i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %v8i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f16 = shufflevector <8 x half> undef, <8 x half> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1024 for instruction: %v16f16 = shufflevector <16 x half> undef, <16 x half> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %v8f32 = shufflevector <8 x float> undef, <8 x float> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %v16f16 = shufflevector <16 x half> undef, <16 x half> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v8f32 = shufflevector <8 x float> undef, <8 x float> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-NEON-LABEL: 'vrev4'
diff --git a/llvm/test/Transforms/LoopVectorize/ARM/mve-icmpcost.ll b/llvm/test/Transforms/LoopVectorize/ARM/mve-icmpcost.ll
--- a/llvm/test/Transforms/LoopVectorize/ARM/mve-icmpcost.ll
+++ b/llvm/test/Transforms/LoopVectorize/ARM/mve-icmpcost.ll
@@ -20,18 +20,18 @@
 ; CHECK: LV: Scalar loop costs: 5.
 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction:   %i.016 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction:   %arrayidx = getelementptr inbounds i16, i16* %s, i32 %i.016
-; CHECK: LV: Found an estimated cost of 10 for VF 2 For instruction:   %1 = load i16, i16* %arrayidx, align 2
+; CHECK: LV: Found an estimated cost of 18 for VF 2 For instruction:   %1 = load i16, i16* %arrayidx, align 2
 ; CHECK: LV: Found an estimated cost of 4 for VF 2 For instruction:   %conv = sext i16 %1 to i32
-; CHECK: LV: Found an estimated cost of 12 for VF 2 For instruction:   %cmp2 = icmp sgt i32 %conv, %conv1
+; CHECK: LV: Found an estimated cost of 20 for VF 2 For instruction:   %cmp2 = icmp sgt i32 %conv, %conv1
 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction:   br i1 %cmp2, label %if.then, label %for.inc
-; CHECK: LV: Found an estimated cost of 14 for VF 2 For instruction:   %conv6 = add i16 %1, %0
+; CHECK: LV: Found an estimated cost of 26 for VF 2 For instruction:   %conv6 = add i16 %1, %0
 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction:   %arrayidx7 = getelementptr inbounds i16, i16* %d, i32 %i.016
 ; CHECK: LV: Found an estimated cost of 16 for VF 2 For instruction:   store i16 %conv6, i16* %arrayidx7, align 2
 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction:   br label %for.inc
 ; CHECK: LV: Found an estimated cost of 1 for VF 2 For instruction:   %inc = add nuw nsw i32 %i.016, 1
 ; CHECK: LV: Found an estimated cost of 1 for VF 2 For instruction:   %exitcond.not = icmp eq i32 %inc, %n
 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction:   br i1 %exitcond.not, label %for.cond.cleanup.loopexit, label %for.body
-; CHECK: LV: Vector loop of width 2 costs: 29.
+; CHECK: LV: Vector loop of width 2 costs: 43.
 ; CHECK: LV: Found an estimated cost of 0 for VF 4 For instruction:   %i.016 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
 ; CHECK: LV: Found an estimated cost of 0 for VF 4 For instruction:   %arrayidx = getelementptr inbounds i16, i16* %s, i32 %i.016
 ; CHECK: LV: Found an estimated cost of 2 for VF 4 For instruction:   %1 = load i16, i16* %arrayidx, align 2
@@ -50,7 +50,7 @@
 ; CHECK: LV: Found an estimated cost of 0 for VF 8 For instruction:   %arrayidx = getelementptr inbounds i16, i16* %s, i32 %i.016
 ; CHECK: LV: Found an estimated cost of 2 for VF 8 For instruction:   %1 = load i16, i16* %arrayidx, align 2
 ; CHECK: LV: Found an estimated cost of 2 for VF 8 For instruction:   %conv = sext i16 %1 to i32
-; CHECK: LV: Found an estimated cost of 68 for VF 8 For instruction:   %cmp2 = icmp sgt i32 %conv, %conv1
+; CHECK: LV: Found an estimated cost of 36 for VF 8 For instruction:   %cmp2 = icmp sgt i32 %conv, %conv1
 ; CHECK: LV: Found an estimated cost of 0 for VF 8 For instruction:   br i1 %cmp2, label %if.then, label %for.inc
 ; CHECK: LV: Found an estimated cost of 2 for VF 8 For instruction:   %conv6 = add i16 %1, %0
 ; CHECK: LV: Found an estimated cost of 0 for VF 8 For instruction:   %arrayidx7 = getelementptr inbounds i16, i16* %d, i32 %i.016
@@ -59,7 +59,7 @@
 ; CHECK: LV: Found an estimated cost of 1 for VF 8 For instruction:   %inc = add nuw nsw i32 %i.016, 1
 ; CHECK: LV: Found an estimated cost of 1 for VF 8 For instruction:   %exitcond.not = icmp eq i32 %inc, %n
 ; CHECK: LV: Found an estimated cost of 0 for VF 8 For instruction:   br i1 %exitcond.not, label %for.cond.cleanup.loopexit, label %for.body
-; CHECK: LV: Vector loop of width 8 costs: 9.
+; CHECK: LV: Vector loop of width 8 costs: 5.
 ; CHECK: LV: Selecting VF: 4.
 define void @expensive_icmp(i16* noalias nocapture %d, i16* nocapture readonly %s, i32 %n, i16 zeroext %m) #0 {
 entry:
@@ -120,22 +120,22 @@
 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction:   %pDst.addr.010 = phi i8* [ %incdec.ptr5, %while.body ], [ %pDst, %while.body.preheader ]
 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction:   %pSrcB.addr.09 = phi i8* [ %incdec.ptr2, %while.body ], [ %pSrcB, %while.body.preheader ]
 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction:   %incdec.ptr = getelementptr inbounds i8, i8* %pSrcA.addr.011, i32 1
-; CHECK: LV: Found an estimated cost of 10 for VF 2 For instruction:   %0 = load i8, i8* %pSrcA.addr.011, align 1
+; CHECK: LV: Found an estimated cost of 18 for VF 2 For instruction:   %0 = load i8, i8* %pSrcA.addr.011, align 1
 ; CHECK: LV: Found an estimated cost of 4 for VF 2 For instruction:   %conv1 = sext i8 %0 to i32
 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction:   %incdec.ptr2 = getelementptr inbounds i8, i8* %pSrcB.addr.09, i32 1
-; CHECK: LV: Found an estimated cost of 10 for VF 2 For instruction:   %1 = load i8, i8* %pSrcB.addr.09, align 1
+; CHECK: LV: Found an estimated cost of 18 for VF 2 For instruction:   %1 = load i8, i8* %pSrcB.addr.09, align 1
 ; CHECK: LV: Found an estimated cost of 4 for VF 2 For instruction:   %conv3 = sext i8 %1 to i32
-; CHECK: LV: Found an estimated cost of 14 for VF 2 For instruction:   %mul = mul nsw i32 %conv3, %conv1
-; CHECK: LV: Found an estimated cost of 10 for VF 2 For instruction:   %shr = ashr i32 %mul, 7
+; CHECK: LV: Found an estimated cost of 26 for VF 2 For instruction:   %mul = mul nsw i32 %conv3, %conv1
+; CHECK: LV: Found an estimated cost of 18 for VF 2 For instruction:   %shr = ashr i32 %mul, 7
 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction:   %2 = icmp slt i32 %shr, 127
-; CHECK: LV: Found an estimated cost of 24 for VF 2 For instruction:   %spec.select.i = select i1 %2, i32 %shr, i32 127
+; CHECK: LV: Found an estimated cost of 40 for VF 2 For instruction:   %spec.select.i = select i1 %2, i32 %shr, i32 127
 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction:   %conv4 = trunc i32 %spec.select.i to i8
 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction:   %incdec.ptr5 = getelementptr inbounds i8, i8* %pDst.addr.010, i32 1
-; CHECK: LV: Found an estimated cost of 10 for VF 2 For instruction:   store i8 %conv4, i8* %pDst.addr.010, align 1
+; CHECK: LV: Found an estimated cost of 18 for VF 2 For instruction:   store i8 %conv4, i8* %pDst.addr.010, align 1
 ; CHECK: LV: Found an estimated cost of 1 for VF 2 For instruction:   %dec = add i32 %blkCnt.012, -1
 ; CHECK: LV: Found an estimated cost of 1 for VF 2 For instruction:   %cmp.not = icmp eq i32 %dec, 0
 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction:   br i1 %cmp.not, label %while.end.loopexit, label %while.body
-; CHECK: LV: Vector loop of width 2 costs: 44.
+; CHECK: LV: Vector loop of width 2 costs: 74.
 ; CHECK: LV: Found an estimated cost of 0 for VF 4 For instruction:   %blkCnt.012 = phi i32 [ %dec, %while.body ], [ %blockSize, %while.body.preheader ]
 ; CHECK: LV: Found an estimated cost of 0 for VF 4 For instruction:   %pSrcA.addr.011 = phi i8* [ %incdec.ptr, %while.body ], [ %pSrcA, %while.body.preheader ]
 ; CHECK: LV: Found an estimated cost of 0 for VF 4 For instruction:   %pDst.addr.010 = phi i8* [ %incdec.ptr5, %while.body ], [ %pDst, %while.body.preheader ]
@@ -238,8 +238,8 @@
 }
 
 ; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction:   %cmp1 = fcmp
-; CHECK: LV: Found an estimated cost of 10 for VF 2 For instruction:   %cmp1 = fcmp
-; CHECK: LV: Found an estimated cost of 36 for VF 4 For instruction:   %cmp1 = fcmp
+; CHECK: LV: Found an estimated cost of 12 for VF 2 For instruction:   %cmp1 = fcmp
+; CHECK: LV: Found an estimated cost of 24 for VF 4 For instruction:   %cmp1 = fcmp
 define void @floatcmp(float* nocapture readonly %pSrc, i32* nocapture %pDst, i32 %blockSize) #0 {
 entry:
   %cmp.not7 = icmp eq i32 %blockSize, 0
diff --git a/llvm/test/Transforms/LoopVectorize/ARM/mve-interleaved-cost.ll b/llvm/test/Transforms/LoopVectorize/ARM/mve-interleaved-cost.ll
--- a/llvm/test/Transforms/LoopVectorize/ARM/mve-interleaved-cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/ARM/mve-interleaved-cost.ll
@@ -15,10 +15,10 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "i8_factor_2"
-; VF_2:          Found an estimated cost of 20 for VF 2 For instruction: %tmp2 = load i8, i8* %tmp0, align 1
+; VF_2:          Found an estimated cost of 24 for VF 2 For instruction: %tmp2 = load i8, i8* %tmp0, align 1
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load i8, i8* %tmp1, align 1
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i8 0, i8* %tmp0, align 1
-; VF_2-NEXT:     Found an estimated cost of 12 for VF 2 For instruction: store i8 0, i8* %tmp1, align 1
+; VF_2-NEXT:     Found an estimated cost of 8 for VF 2 For instruction: store i8 0, i8* %tmp1, align 1
 ; VF_4-LABEL:  Checking a loop in "i8_factor_2"
 ; VF_4:          Found an estimated cost of 4 for VF 4 For instruction: %tmp2 = load i8, i8* %tmp0, align 1
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i8, i8* %tmp1, align 1
@@ -56,10 +56,10 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "i16_factor_2"
-; VF_2:          Found an estimated cost of 20 for VF 2 For instruction: %tmp2 = load i16, i16* %tmp0, align 2
+; VF_2:          Found an estimated cost of 24 for VF 2 For instruction: %tmp2 = load i16, i16* %tmp0, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load i16, i16* %tmp1, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i16 0, i16* %tmp0, align 2
-; VF_2-NEXT:     Found an estimated cost of 12 for VF 2 For instruction: store i16 0, i16* %tmp1, align 2
+; VF_2-NEXT:     Found an estimated cost of 8 for VF 2 For instruction: store i16 0, i16* %tmp1, align 2
 ; VF_4-LABEL:  Checking a loop in "i16_factor_2"
 ; VF_4:          Found an estimated cost of 4 for VF 4 For instruction: %tmp2 = load i16, i16* %tmp0, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i16, i16* %tmp1, align 2
@@ -97,10 +97,10 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "i32_factor_2"
-; VF_2:          Found an estimated cost of 20 for VF 2 For instruction: %tmp2 = load i32, i32* %tmp0, align 4
+; VF_2:          Found an estimated cost of 24 for VF 2 For instruction: %tmp2 = load i32, i32* %tmp0, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load i32, i32* %tmp1, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp0, align 4
-; VF_2-NEXT:     Found an estimated cost of 12 for VF 2 For instruction: store i32 0, i32* %tmp1, align 4
+; VF_2-NEXT:     Found an estimated cost of 8 for VF 2 For instruction: store i32 0, i32* %tmp1, align 4
 ; VF_4-LABEL:  Checking a loop in "i32_factor_2"
 ; VF_4:          Found an estimated cost of 4 for VF 4 For instruction: %tmp2 = load i32, i32* %tmp0, align 4
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i32, i32* %tmp1, align 4
@@ -138,25 +138,25 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "i64_factor_2"
-; VF_2:          Found an estimated cost of 24 for VF 2 For instruction: %tmp2 = load i64, i64* %tmp0, align 8
+; VF_2:          Found an estimated cost of 44 for VF 2 For instruction: %tmp2 = load i64, i64* %tmp0, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load i64, i64* %tmp1, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i64 0, i64* %tmp0, align 8
-; VF_2-NEXT:     Found an estimated cost of 16 for VF 2 For instruction: store i64 0, i64* %tmp1, align 8
+; VF_2-NEXT:     Found an estimated cost of 12 for VF 2 For instruction: store i64 0, i64* %tmp1, align 8
 ; VF_4-LABEL:  Checking a loop in "i64_factor_2"
-; VF_4:          Found an estimated cost of 80 for VF 4 For instruction: %tmp2 = load i64, i64* %tmp0, align 8
+; VF_4:          Found an estimated cost of 88 for VF 4 For instruction: %tmp2 = load i64, i64* %tmp0, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i64, i64* %tmp1, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store i64 0, i64* %tmp0, align 8
-; VF_4-NEXT:     Found an estimated cost of 48 for VF 4 For instruction: store i64 0, i64* %tmp1, align 8
+; VF_4-NEXT:     Found an estimated cost of 24 for VF 4 For instruction: store i64 0, i64* %tmp1, align 8
 ; VF_8-LABEL:  Checking a loop in "i64_factor_2"
-; VF_8:          Found an estimated cost of 288 for VF 8 For instruction: %tmp2 = load i64, i64* %tmp0, align 8
+; VF_8:          Found an estimated cost of 176 for VF 8 For instruction: %tmp2 = load i64, i64* %tmp0, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i64, i64* %tmp1, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i64 0, i64* %tmp0, align 8
-; VF_8-NEXT:     Found an estimated cost of 160 for VF 8 For instruction: store i64 0, i64* %tmp1, align 8
+; VF_8-NEXT:     Found an estimated cost of 48 for VF 8 For instruction: store i64 0, i64* %tmp1, align 8
 ; VF_16-LABEL: Checking a loop in "i64_factor_2"
-; VF_16:         Found an estimated cost of 1088 for VF 16 For instruction: %tmp2 = load i64, i64* %tmp0, align 8
+; VF_16:         Found an estimated cost of 352 for VF 16 For instruction: %tmp2 = load i64, i64* %tmp0, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load i64, i64* %tmp1, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i64 0, i64* %tmp0, align 8
-; VF_16-NEXT:    Found an estimated cost of 576 for VF 16 For instruction: store i64 0, i64* %tmp1, align 8
+; VF_16-NEXT:    Found an estimated cost of 96 for VF 16 For instruction: store i64 0, i64* %tmp1, align 8
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %tmp0 = getelementptr inbounds %i64.2, %i64.2* %data, i64 %i, i32 0
@@ -179,15 +179,15 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "f16_factor_2"
-; VF_2:          Found an estimated cost of 20 for VF 2 For instruction: %tmp2 = load half, half* %tmp0, align 2
+; VF_2:          Found an estimated cost of 12 for VF 2 For instruction: %tmp2 = load half, half* %tmp0, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load half, half* %tmp1, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store half 0xH0000, half* %tmp0, align 2
-; VF_2-NEXT:     Found an estimated cost of 12 for VF 2 For instruction: store half 0xH0000, half* %tmp1, align 2
+; VF_2-NEXT:     Found an estimated cost of 8 for VF 2 For instruction: store half 0xH0000, half* %tmp1, align 2
 ; VF_4-LABEL:  Checking a loop in "f16_factor_2"
-; VF_4:          Found an estimated cost of 72 for VF 4 For instruction: %tmp2 = load half, half* %tmp0, align 2
+; VF_4:          Found an estimated cost of 18 for VF 4 For instruction: %tmp2 = load half, half* %tmp0, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load half, half* %tmp1, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store half 0xH0000, half* %tmp0, align 2
-; VF_4-NEXT:     Found an estimated cost of 40 for VF 4 For instruction: store half 0xH0000, half* %tmp1, align 2
+; VF_4-NEXT:     Found an estimated cost of 16 for VF 4 For instruction: store half 0xH0000, half* %tmp1, align 2
 ; VF_8-LABEL:  Checking a loop in "f16_factor_2"
 ; VF_8:          Found an estimated cost of 4 for VF 8 For instruction: %tmp2 = load half, half* %tmp0, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load half, half* %tmp1, align 2
@@ -220,10 +220,10 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "f32_factor_2"
-; VF_2:          Found an estimated cost of 20 for VF 2 For instruction: %tmp2 = load float, float* %tmp0, align 4
+; VF_2:          Found an estimated cost of 10 for VF 2 For instruction: %tmp2 = load float, float* %tmp0, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load float, float* %tmp1, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store float 0.000000e+00, float* %tmp0, align 4
-; VF_2-NEXT:     Found an estimated cost of 12 for VF 2 For instruction: store float 0.000000e+00, float* %tmp1, align 4
+; VF_2-NEXT:     Found an estimated cost of 8 for VF 2 For instruction: store float 0.000000e+00, float* %tmp1, align 4
 ; VF_4-LABEL:  Checking a loop in "f32_factor_2"
 ; VF_4:          Found an estimated cost of 4 for VF 4 For instruction: %tmp2 = load float, float* %tmp0, align 4
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load float, float* %tmp1, align 4
@@ -261,25 +261,25 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "f64_factor_2"
-; VF_2:          Found an estimated cost of 20 for VF 2 For instruction: %tmp2 = load double, double* %tmp0, align 8
+; VF_2:          Found an estimated cost of 12 for VF 2 For instruction: %tmp2 = load double, double* %tmp0, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load double, double* %tmp1, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store double 0.000000e+00, double* %tmp0, align 8
-; VF_2-NEXT:     Found an estimated cost of 12 for VF 2 For instruction: store double 0.000000e+00, double* %tmp1, align 8
+; VF_2-NEXT:     Found an estimated cost of 8 for VF 2 For instruction: store double 0.000000e+00, double* %tmp1, align 8
 ; VF_4-LABEL:  Checking a loop in "f64_factor_2"
-; VF_4:          Found an estimated cost of 72 for VF 4 For instruction: %tmp2 = load double, double* %tmp0, align 8
+; VF_4:          Found an estimated cost of 24 for VF 4 For instruction: %tmp2 = load double, double* %tmp0, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load double, double* %tmp1, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store double 0.000000e+00, double* %tmp0, align 8
-; VF_4-NEXT:     Found an estimated cost of 40 for VF 4 For instruction: store double 0.000000e+00, double* %tmp1, align 8
+; VF_4-NEXT:     Found an estimated cost of 16 for VF 4 For instruction: store double 0.000000e+00, double* %tmp1, align 8
 ; VF_8-LABEL:  Checking a loop in "f64_factor_2"
-; VF_8:          Found an estimated cost of 272 for VF 8 For instruction: %tmp2 = load double, double* %tmp0, align 8
+; VF_8:          Found an estimated cost of 48 for VF 8 For instruction: %tmp2 = load double, double* %tmp0, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load double, double* %tmp1, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store double 0.000000e+00, double* %tmp0, align 8
-; VF_8-NEXT:     Found an estimated cost of 144 for VF 8 For instruction: store double 0.000000e+00, double* %tmp1, align 8
+; VF_8-NEXT:     Found an estimated cost of 32 for VF 8 For instruction: store double 0.000000e+00, double* %tmp1, align 8
 ; VF_16-LABEL: Checking a loop in "f64_factor_2"
-; VF_16:         Found an estimated cost of 1056 for VF 16 For instruction: %tmp2 = load double, double* %tmp0, align 8
+; VF_16:         Found an estimated cost of 96 for VF 16 For instruction: %tmp2 = load double, double* %tmp0, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load double, double* %tmp1, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store double 0.000000e+00, double* %tmp0, align 8
-; VF_16-NEXT:    Found an estimated cost of 544 for VF 16 For instruction: store double 0.000000e+00, double* %tmp1, align 8
+; VF_16-NEXT:    Found an estimated cost of 64 for VF 16 For instruction: store double 0.000000e+00, double* %tmp1, align 8
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %tmp0 = getelementptr inbounds %f64.2, %f64.2* %data, i64 %i, i32 0
@@ -306,33 +306,33 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "i8_factor_3"
-; VF_2:          Found an estimated cost of 30 for VF 2 For instruction: %tmp3 = load i8, i8* %tmp0, align 1
+; VF_2:          Found an estimated cost of 36 for VF 2 For instruction: %tmp3 = load i8, i8* %tmp0, align 1
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp4 = load i8, i8* %tmp1, align 1
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i8, i8* %tmp2, align 1
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i8 0, i8* %tmp0, align 1
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i8 0, i8* %tmp1, align 1
-; VF_2-NEXT:     Found an estimated cost of 18 for VF 2 For instruction: store i8 0, i8* %tmp2, align 1
+; VF_2-NEXT:     Found an estimated cost of 12 for VF 2 For instruction: store i8 0, i8* %tmp2, align 1
 ; VF_4-LABEL:  Checking a loop in "i8_factor_3"
-; VF_4:          Found an estimated cost of 108 for VF 4 For instruction: %tmp3 = load i8, i8* %tmp0, align 1
+; VF_4:          Found an estimated cost of 72 for VF 4 For instruction: %tmp3 = load i8, i8* %tmp0, align 1
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp4 = load i8, i8* %tmp1, align 1
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i8, i8* %tmp2, align 1
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store i8 0, i8* %tmp0, align 1
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store i8 0, i8* %tmp1, align 1
-; VF_4-NEXT:     Found an estimated cost of 60 for VF 4 For instruction: store i8 0, i8* %tmp2, align 1
+; VF_4-NEXT:     Found an estimated cost of 24 for VF 4 For instruction: store i8 0, i8* %tmp2, align 1
 ; VF_8-LABEL:  Checking a loop in "i8_factor_3"
-; VF_8:          Found an estimated cost of 408 for VF 8 For instruction: %tmp3 = load i8, i8* %tmp0, align 1
+; VF_8:          Found an estimated cost of 144 for VF 8 For instruction: %tmp3 = load i8, i8* %tmp0, align 1
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp4 = load i8, i8* %tmp1, align 1
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i8, i8* %tmp2, align 1
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp0, align 1
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp1, align 1
-; VF_8-NEXT:     Found an estimated cost of 216 for VF 8 For instruction: store i8 0, i8* %tmp2, align 1
+; VF_8-NEXT:     Found an estimated cost of 48 for VF 8 For instruction: store i8 0, i8* %tmp2, align 1
 ; VF_16-LABEL: Checking a loop in "i8_factor_3"
-; VF_16:         Found an estimated cost of 1584 for VF 16 For instruction: %tmp3 = load i8, i8* %tmp0, align 1
+; VF_16:         Found an estimated cost of 288 for VF 16 For instruction: %tmp3 = load i8, i8* %tmp0, align 1
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp4 = load i8, i8* %tmp1, align 1
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i8, i8* %tmp2, align 1
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i8 0, i8* %tmp0, align 1
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i8 0, i8* %tmp1, align 1
-; VF_16-NEXT:    Found an estimated cost of 816 for VF 16 For instruction: store i8 0, i8* %tmp2, align 1
+; VF_16-NEXT:    Found an estimated cost of 96 for VF 16 For instruction: store i8 0, i8* %tmp2, align 1
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %tmp0 = getelementptr inbounds %i8.3, %i8.3* %data, i64 %i, i32 0
@@ -358,33 +358,33 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "i16_factor_3"
-; VF_2:          Found an estimated cost of 30 for VF 2 For instruction: %tmp3 = load i16, i16* %tmp0, align 2
+; VF_2:          Found an estimated cost of 36 for VF 2 For instruction: %tmp3 = load i16, i16* %tmp0, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp4 = load i16, i16* %tmp1, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i16, i16* %tmp2, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i16 0, i16* %tmp0, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i16 0, i16* %tmp1, align 2
-; VF_2-NEXT:     Found an estimated cost of 18 for VF 2 For instruction: store i16 0, i16* %tmp2, align 2
+; VF_2-NEXT:     Found an estimated cost of 12 for VF 2 For instruction: store i16 0, i16* %tmp2, align 2
 ; VF_4-LABEL:  Checking a loop in "i16_factor_3"
-; VF_4:          Found an estimated cost of 108 for VF 4 For instruction: %tmp3 = load i16, i16* %tmp0, align 2
+; VF_4:          Found an estimated cost of 72 for VF 4 For instruction: %tmp3 = load i16, i16* %tmp0, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp4 = load i16, i16* %tmp1, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i16, i16* %tmp2, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp0, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp1, align 2
-; VF_4-NEXT:     Found an estimated cost of 60 for VF 4 For instruction: store i16 0, i16* %tmp2, align 2
+; VF_4-NEXT:     Found an estimated cost of 24 for VF 4 For instruction: store i16 0, i16* %tmp2, align 2
 ; VF_8-LABEL:  Checking a loop in "i16_factor_3"
-; VF_8:          Found an estimated cost of 408 for VF 8 For instruction: %tmp3 = load i16, i16* %tmp0, align 2
+; VF_8:          Found an estimated cost of 144 for VF 8 For instruction: %tmp3 = load i16, i16* %tmp0, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp4 = load i16, i16* %tmp1, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i16, i16* %tmp2, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp0, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp1, align 2
-; VF_8-NEXT:     Found an estimated cost of 216 for VF 8 For instruction: store i16 0, i16* %tmp2, align 2
+; VF_8-NEXT:     Found an estimated cost of 48 for VF 8 For instruction: store i16 0, i16* %tmp2, align 2
 ; VF_16-LABEL: Checking a loop in "i16_factor_3"
-; VF_16:         Found an estimated cost of 1584 for VF 16 For instruction: %tmp3 = load i16, i16* %tmp0, align 2
+; VF_16:         Found an estimated cost of 288 for VF 16 For instruction: %tmp3 = load i16, i16* %tmp0, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp4 = load i16, i16* %tmp1, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i16, i16* %tmp2, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i16 0, i16* %tmp0, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i16 0, i16* %tmp1, align 2
-; VF_16-NEXT:    Found an estimated cost of 816 for VF 16 For instruction: store i16 0, i16* %tmp2, align 2
+; VF_16-NEXT:    Found an estimated cost of 96 for VF 16 For instruction: store i16 0, i16* %tmp2, align 2
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %tmp0 = getelementptr inbounds %i16.3, %i16.3* %data, i64 %i, i32 0
@@ -410,12 +410,12 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "i32_factor_3"
-; VF_2:          Found an estimated cost of 30 for VF 2 For instruction: %tmp3 = load i32, i32* %tmp0, align 4
+; VF_2:          Found an estimated cost of 36 for VF 2 For instruction: %tmp3 = load i32, i32* %tmp0, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp4 = load i32, i32* %tmp1, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i32, i32* %tmp2, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp0, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp1, align 4
-; VF_2-NEXT:     Found an estimated cost of 18 for VF 2 For instruction: store i32 0, i32* %tmp2, align 4
+; VF_2-NEXT:     Found an estimated cost of 12 for VF 2 For instruction: store i32 0, i32* %tmp2, align 4
 ; VF_4-LABEL:  Checking a loop in "i32_factor_3"
 ; VF_4:          Found an estimated cost of 24 for VF 4 For instruction: %tmp3 = load i32, i32* %tmp0, align 4
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp4 = load i32, i32* %tmp1, align 4
@@ -424,19 +424,19 @@
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store i32 0, i32* %tmp1, align 4
 ; VF_4-NEXT:     Found an estimated cost of 24 for VF 4 For instruction: store i32 0, i32* %tmp2, align 4
 ; VF_8-LABEL:  Checking a loop in "i32_factor_3"
-; VF_8:          Found an estimated cost of 408 for VF 8 For instruction: %tmp3 = load i32, i32* %tmp0, align 4
+; VF_8:          Found an estimated cost of 144 for VF 8 For instruction: %tmp3 = load i32, i32* %tmp0, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp4 = load i32, i32* %tmp1, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i32, i32* %tmp2, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp0, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp1, align 4
-; VF_8-NEXT:     Found an estimated cost of 216 for VF 8 For instruction: store i32 0, i32* %tmp2, align 4
+; VF_8-NEXT:     Found an estimated cost of 48 for VF 8 For instruction: store i32 0, i32* %tmp2, align 4
 ; VF_16-LABEL: Checking a loop in "i32_factor_3"
-; VF_16:         Found an estimated cost of 1584 for VF 16 For instruction: %tmp3 = load i32, i32* %tmp0, align 4
+; VF_16:         Found an estimated cost of 288 for VF 16 For instruction: %tmp3 = load i32, i32* %tmp0, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp4 = load i32, i32* %tmp1, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i32, i32* %tmp2, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i32 0, i32* %tmp0, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i32 0, i32* %tmp1, align 4
-; VF_16-NEXT:    Found an estimated cost of 816 for VF 16 For instruction: store i32 0, i32* %tmp2, align 4
+; VF_16-NEXT:    Found an estimated cost of 96 for VF 16 For instruction: store i32 0, i32* %tmp2, align 4
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %tmp0 = getelementptr inbounds %i32.3, %i32.3* %data, i64 %i, i32 0
@@ -462,33 +462,33 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "i64_factor_3"
-; VF_2:          Found an estimated cost of 36 for VF 2 For instruction: %tmp3 = load i64, i64* %tmp0, align 8
+; VF_2:          Found an estimated cost of 66 for VF 2 For instruction: %tmp3 = load i64, i64* %tmp0, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp4 = load i64, i64* %tmp1, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i64, i64* %tmp2, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i64 0, i64* %tmp0, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i64 0, i64* %tmp1, align 8
-; VF_2-NEXT:     Found an estimated cost of 24 for VF 2 For instruction: store i64 0, i64* %tmp2, align 8
+; VF_2-NEXT:     Found an estimated cost of 18 for VF 2 For instruction: store i64 0, i64* %tmp2, align 8
 ; VF_4-LABEL:  Checking a loop in "i64_factor_3"
-; VF_4:          Found an estimated cost of 120 for VF 4 For instruction: %tmp3 = load i64, i64* %tmp0, align 8
+; VF_4:          Found an estimated cost of 132 for VF 4 For instruction: %tmp3 = load i64, i64* %tmp0, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp4 = load i64, i64* %tmp1, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i64, i64* %tmp2, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store i64 0, i64* %tmp0, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store i64 0, i64* %tmp1, align 8
-; VF_4-NEXT:     Found an estimated cost of 72 for VF 4 For instruction: store i64 0, i64* %tmp2, align 8
+; VF_4-NEXT:     Found an estimated cost of 36 for VF 4 For instruction: store i64 0, i64* %tmp2, align 8
 ; VF_8-LABEL:  Checking a loop in "i64_factor_3"
-; VF_8:          Found an estimated cost of 432 for VF 8 For instruction: %tmp3 = load i64, i64* %tmp0, align 8
+; VF_8:          Found an estimated cost of 264 for VF 8 For instruction: %tmp3 = load i64, i64* %tmp0, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp4 = load i64, i64* %tmp1, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i64, i64* %tmp2, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i64 0, i64* %tmp0, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i64 0, i64* %tmp1, align 8
-; VF_8-NEXT:     Found an estimated cost of 240 for VF 8 For instruction: store i64 0, i64* %tmp2, align 8
+; VF_8-NEXT:     Found an estimated cost of 72 for VF 8 For instruction: store i64 0, i64* %tmp2, align 8
 ; VF_16-LABEL: Checking a loop in "i64_factor_3"
-; VF_16:         Found an estimated cost of 1632 for VF 16 For instruction: %tmp3 = load i64, i64* %tmp0, align 8
+; VF_16:         Found an estimated cost of 528 for VF 16 For instruction: %tmp3 = load i64, i64* %tmp0, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp4 = load i64, i64* %tmp1, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i64, i64* %tmp2, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i64 0, i64* %tmp0, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i64 0, i64* %tmp1, align 8
-; VF_16-NEXT:    Found an estimated cost of 864 for VF 16 For instruction: store i64 0, i64* %tmp2, align 8
+; VF_16-NEXT:    Found an estimated cost of 144 for VF 16 For instruction: store i64 0, i64* %tmp2, align 8
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %tmp0 = getelementptr inbounds %i64.3, %i64.3* %data, i64 %i, i32 0
@@ -514,33 +514,33 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "f16_factor_3"
-; VF_2:          Found an estimated cost of 30 for VF 2 For instruction: %tmp3 = load half, half* %tmp0, align 2
+; VF_2:          Found an estimated cost of 18 for VF 2 For instruction: %tmp3 = load half, half* %tmp0, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp4 = load half, half* %tmp1, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load half, half* %tmp2, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store half 0xH0000, half* %tmp0, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store half 0xH0000, half* %tmp1, align 2
-; VF_2-NEXT:     Found an estimated cost of 18 for VF 2 For instruction: store half 0xH0000, half* %tmp2, align 2
+; VF_2-NEXT:     Found an estimated cost of 12 for VF 2 For instruction: store half 0xH0000, half* %tmp2, align 2
 ; VF_4-LABEL:  Checking a loop in "f16_factor_3"
-; VF_4:          Found an estimated cost of 108 for VF 4 For instruction: %tmp3 = load half, half* %tmp0, align 2
+; VF_4:          Found an estimated cost of 28 for VF 4 For instruction: %tmp3 = load half, half* %tmp0, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp4 = load half, half* %tmp1, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load half, half* %tmp2, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store half 0xH0000, half* %tmp0, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store half 0xH0000, half* %tmp1, align 2
-; VF_4-NEXT:     Found an estimated cost of 60 for VF 4 For instruction: store half 0xH0000, half* %tmp2, align 2
+; VF_4-NEXT:     Found an estimated cost of 24 for VF 4 For instruction: store half 0xH0000, half* %tmp2, align 2
 ; VF_8-LABEL:  Checking a loop in "f16_factor_3"
-; VF_8:          Found an estimated cost of 408 for VF 8 For instruction: %tmp3 = load half, half* %tmp0, align 2
+; VF_8:          Found an estimated cost of 56 for VF 8 For instruction: %tmp3 = load half, half* %tmp0, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp4 = load half, half* %tmp1, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load half, half* %tmp2, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store half 0xH0000, half* %tmp0, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store half 0xH0000, half* %tmp1, align 2
-; VF_8-NEXT:     Found an estimated cost of 216 for VF 8 For instruction: store half 0xH0000, half* %tmp2, align 2
+; VF_8-NEXT:     Found an estimated cost of 48 for VF 8 For instruction: store half 0xH0000, half* %tmp2, align 2
 ; VF_16-LABEL: Checking a loop in "f16_factor_3"
-; VF_16:         Found an estimated cost of 1584 for VF 16 For instruction: %tmp3 = load half, half* %tmp0, align 2
+; VF_16:         Found an estimated cost of 112 for VF 16 For instruction: %tmp3 = load half, half* %tmp0, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp4 = load half, half* %tmp1, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load half, half* %tmp2, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store half 0xH0000, half* %tmp0, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store half 0xH0000, half* %tmp1, align 2
-; VF_16-NEXT:    Found an estimated cost of 816 for VF 16 For instruction: store half 0xH0000, half* %tmp2, align 2
+; VF_16-NEXT:    Found an estimated cost of 96 for VF 16 For instruction: store half 0xH0000, half* %tmp2, align 2
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %tmp0 = getelementptr inbounds %f16.3, %f16.3* %data, i64 %i, i32 0
@@ -566,12 +566,12 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "f32_factor_3"
-; VF_2:          Found an estimated cost of 30 for VF 2 For instruction: %tmp3 = load float, float* %tmp0, align 4
+; VF_2:          Found an estimated cost of 16 for VF 2 For instruction: %tmp3 = load float, float* %tmp0, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp4 = load float, float* %tmp1, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load float, float* %tmp2, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store float 0.000000e+00, float* %tmp0, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store float 0.000000e+00, float* %tmp1, align 4
-; VF_2-NEXT:     Found an estimated cost of 18 for VF 2 For instruction: store float 0.000000e+00, float* %tmp2, align 4
+; VF_2-NEXT:     Found an estimated cost of 12 for VF 2 For instruction: store float 0.000000e+00, float* %tmp2, align 4
 ; VF_4-LABEL:  Checking a loop in "f32_factor_3"
 ; VF_4:          Found an estimated cost of 24 for VF 4 For instruction: %tmp3 = load float, float* %tmp0, align 4
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp4 = load float, float* %tmp1, align 4
@@ -580,19 +580,19 @@
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store float 0.000000e+00, float* %tmp1, align 4
 ; VF_4-NEXT:     Found an estimated cost of 24 for VF 4 For instruction: store float 0.000000e+00, float* %tmp2, align 4
 ; VF_8-LABEL:  Checking a loop in "f32_factor_3"
-; VF_8:          Found an estimated cost of 408 for VF 8 For instruction: %tmp3 = load float, float* %tmp0, align 4
+; VF_8:          Found an estimated cost of 64 for VF 8 For instruction: %tmp3 = load float, float* %tmp0, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp4 = load float, float* %tmp1, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load float, float* %tmp2, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store float 0.000000e+00, float* %tmp0, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store float 0.000000e+00, float* %tmp1, align 4
-; VF_8-NEXT:     Found an estimated cost of 216 for VF 8 For instruction: store float 0.000000e+00, float* %tmp2, align 4
+; VF_8-NEXT:     Found an estimated cost of 48 for VF 8 For instruction: store float 0.000000e+00, float* %tmp2, align 4
 ; VF_16-LABEL: Checking a loop in "f32_factor_3"
-; VF_16:         Found an estimated cost of 1584 for VF 16 For instruction: %tmp3 = load float, float* %tmp0, align 4
+; VF_16:         Found an estimated cost of 128 for VF 16 For instruction: %tmp3 = load float, float* %tmp0, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp4 = load float, float* %tmp1, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load float, float* %tmp2, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store float 0.000000e+00, float* %tmp0, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store float 0.000000e+00, float* %tmp1, align 4
-; VF_16-NEXT:    Found an estimated cost of 816 for VF 16 For instruction: store float 0.000000e+00, float* %tmp2, align 4
+; VF_16-NEXT:    Found an estimated cost of 96 for VF 16 For instruction: store float 0.000000e+00, float* %tmp2, align 4
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %tmp0 = getelementptr inbounds %f32.3, %f32.3* %data, i64 %i, i32 0
@@ -618,33 +618,33 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "f64_factor_3"
-; VF_2:          Found an estimated cost of 30 for VF 2 For instruction: %tmp3 = load double, double* %tmp0, align 8
+; VF_2:          Found an estimated cost of 18 for VF 2 For instruction: %tmp3 = load double, double* %tmp0, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp4 = load double, double* %tmp1, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load double, double* %tmp2, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store double 0.000000e+00, double* %tmp0, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store double 0.000000e+00, double* %tmp1, align 8
-; VF_2-NEXT:     Found an estimated cost of 18 for VF 2 For instruction: store double 0.000000e+00, double* %tmp2, align 8
+; VF_2-NEXT:     Found an estimated cost of 12 for VF 2 For instruction: store double 0.000000e+00, double* %tmp2, align 8
 ; VF_4-LABEL:  Checking a loop in "f64_factor_3"
-; VF_4:          Found an estimated cost of 108 for VF 4 For instruction: %tmp3 = load double, double* %tmp0, align 8
+; VF_4:          Found an estimated cost of 36 for VF 4 For instruction: %tmp3 = load double, double* %tmp0, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp4 = load double, double* %tmp1, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load double, double* %tmp2, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store double 0.000000e+00, double* %tmp0, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store double 0.000000e+00, double* %tmp1, align 8
-; VF_4-NEXT:     Found an estimated cost of 60 for VF 4 For instruction: store double 0.000000e+00, double* %tmp2, align 8
+; VF_4-NEXT:     Found an estimated cost of 24 for VF 4 For instruction: store double 0.000000e+00, double* %tmp2, align 8
 ; VF_8-LABEL:  Checking a loop in "f64_factor_3"
-; VF_8:          Found an estimated cost of 408 for VF 8 For instruction: %tmp3 = load double, double* %tmp0, align 8
+; VF_8:          Found an estimated cost of 72 for VF 8 For instruction: %tmp3 = load double, double* %tmp0, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp4 = load double, double* %tmp1, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load double, double* %tmp2, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store double 0.000000e+00, double* %tmp0, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store double 0.000000e+00, double* %tmp1, align 8
-; VF_8-NEXT:     Found an estimated cost of 216 for VF 8 For instruction: store double 0.000000e+00, double* %tmp2, align 8
+; VF_8-NEXT:     Found an estimated cost of 48 for VF 8 For instruction: store double 0.000000e+00, double* %tmp2, align 8
 ; VF_16-LABEL: Checking a loop in "f64_factor_3"
-; VF_16:         Found an estimated cost of 1584 for VF 16 For instruction: %tmp3 = load double, double* %tmp0, align 8
+; VF_16:         Found an estimated cost of 144 for VF 16 For instruction: %tmp3 = load double, double* %tmp0, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp4 = load double, double* %tmp1, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load double, double* %tmp2, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store double 0.000000e+00, double* %tmp0, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store double 0.000000e+00, double* %tmp1, align 8
-; VF_16-NEXT:    Found an estimated cost of 816 for VF 16 For instruction: store double 0.000000e+00, double* %tmp2, align 8
+; VF_16-NEXT:    Found an estimated cost of 96 for VF 16 For instruction: store double 0.000000e+00, double* %tmp2, align 8
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %tmp0 = getelementptr inbounds %f64.3, %f64.3* %data, i64 %i, i32 0
@@ -673,41 +673,41 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "i8_factor_4"
-; VF_2:          Found an estimated cost of 40 for VF 2 For instruction: %tmp4 = load i8, i8* %tmp0, align 1
+; VF_2:          Found an estimated cost of 48 for VF 2 For instruction: %tmp4 = load i8, i8* %tmp0, align 1
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i8, i8* %tmp1, align 1
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp6 = load i8, i8* %tmp2, align 1
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp7 = load i8, i8* %tmp3, align 1
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i8 0, i8* %tmp0, align 1
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i8 0, i8* %tmp1, align 1
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i8 0, i8* %tmp2, align 1
-; VF_2-NEXT:     Found an estimated cost of 24 for VF 2 For instruction: store i8 0, i8* %tmp3, align 1
+; VF_2-NEXT:     Found an estimated cost of 16 for VF 2 For instruction: store i8 0, i8* %tmp3, align 1
 ; VF_4-LABEL: Checking a loop in "i8_factor_4"
-; VF_4:         Found an estimated cost of 144 for VF 4 For instruction: %tmp4 = load i8, i8* %tmp0, align 1
+; VF_4:         Found an estimated cost of 96 for VF 4 For instruction: %tmp4 = load i8, i8* %tmp0, align 1
 ; VF_4-NEXT:    Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i8, i8* %tmp1, align 1
 ; VF_4-NEXT:    Found an estimated cost of 0 for VF 4 For instruction: %tmp6 = load i8, i8* %tmp2, align 1
 ; VF_4-NEXT:    Found an estimated cost of 0 for VF 4 For instruction: %tmp7 = load i8, i8* %tmp3, align 1
 ; VF_4-NEXT:    Found an estimated cost of 0 for VF 4 For instruction: store i8 0, i8* %tmp0, align 1
 ; VF_4-NEXT:    Found an estimated cost of 0 for VF 4 For instruction: store i8 0, i8* %tmp1, align 1
 ; VF_4-NEXT:    Found an estimated cost of 0 for VF 4 For instruction: store i8 0, i8* %tmp2, align 1
-; VF_4-NEXT:    Found an estimated cost of 80 for VF 4 For instruction: store i8 0, i8* %tmp3, align 1
+; VF_4-NEXT:    Found an estimated cost of 32 for VF 4 For instruction: store i8 0, i8* %tmp3, align 1
 ; VF_8-LABEL:  Checking a loop in "i8_factor_4"
-; VF_8:          Found an estimated cost of 544 for VF 8 For instruction: %tmp4 = load i8, i8* %tmp0, align 1
+; VF_8:          Found an estimated cost of 192 for VF 8 For instruction: %tmp4 = load i8, i8* %tmp0, align 1
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i8, i8* %tmp1, align 1
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp6 = load i8, i8* %tmp2, align 1
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp7 = load i8, i8* %tmp3, align 1
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp0, align 1
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp1, align 1
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp2, align 1
-; VF_8-NEXT:     Found an estimated cost of 288 for VF 8 For instruction: store i8 0, i8* %tmp3, align 1
+; VF_8-NEXT:     Found an estimated cost of 64 for VF 8 For instruction: store i8 0, i8* %tmp3, align 1
 ; VF_16-LABEL: Checking a loop in "i8_factor_4"
-; VF_16:         Found an estimated cost of 2112 for VF 16 For instruction: %tmp4 = load i8, i8* %tmp0, align 1
+; VF_16:         Found an estimated cost of 384 for VF 16 For instruction: %tmp4 = load i8, i8* %tmp0, align 1
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i8, i8* %tmp1, align 1
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp6 = load i8, i8* %tmp2, align 1
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp7 = load i8, i8* %tmp3, align 1
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i8 0, i8* %tmp0, align 1
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i8 0, i8* %tmp1, align 1
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i8 0, i8* %tmp2, align 1
-; VF_16-NEXT:    Found an estimated cost of 1088 for VF 16 For instruction: store i8 0, i8* %tmp3, align 1
+; VF_16-NEXT:    Found an estimated cost of 128 for VF 16 For instruction: store i8 0, i8* %tmp3, align 1
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %tmp0 = getelementptr inbounds %i8.4, %i8.4* %data, i64 %i, i32 0
@@ -736,41 +736,41 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "i16_factor_4"
-; VF_2:          Found an estimated cost of 40 for VF 2 For instruction: %tmp4 = load i16, i16* %tmp0, align 2
+; VF_2:          Found an estimated cost of 48 for VF 2 For instruction: %tmp4 = load i16, i16* %tmp0, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i16, i16* %tmp1, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp6 = load i16, i16* %tmp2, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp7 = load i16, i16* %tmp3, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i16 0, i16* %tmp0, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i16 0, i16* %tmp1, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i16 0, i16* %tmp2, align 2
-; VF_2-NEXT:     Found an estimated cost of 24 for VF 2 For instruction: store i16 0, i16* %tmp3, align 2
+; VF_2-NEXT:     Found an estimated cost of 16 for VF 2 For instruction: store i16 0, i16* %tmp3, align 2
 ; VF_4-LABEL:  Checking a loop in "i16_factor_4"
-; VF_4:          Found an estimated cost of 144 for VF 4 For instruction: %tmp4 = load i16, i16* %tmp0, align 2
+; VF_4:          Found an estimated cost of 96 for VF 4 For instruction: %tmp4 = load i16, i16* %tmp0, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i16, i16* %tmp1, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp6 = load i16, i16* %tmp2, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp7 = load i16, i16* %tmp3, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp0, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp1, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp2, align 2
-; VF_4-NEXT:     Found an estimated cost of 80 for VF 4 For instruction: store i16 0, i16* %tmp3, align 2
+; VF_4-NEXT:     Found an estimated cost of 32 for VF 4 For instruction: store i16 0, i16* %tmp3, align 2
 ; VF_8-LABEL:  Checking a loop in "i16_factor_4"
-; VF_8:          Found an estimated cost of 544 for VF 8 For instruction: %tmp4 = load i16, i16* %tmp0, align 2
+; VF_8:          Found an estimated cost of 192 for VF 8 For instruction: %tmp4 = load i16, i16* %tmp0, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i16, i16* %tmp1, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp6 = load i16, i16* %tmp2, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp7 = load i16, i16* %tmp3, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp0, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp1, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp2, align 2
-; VF_8-NEXT:     Found an estimated cost of 288 for VF 8 For instruction: store i16 0, i16* %tmp3, align 2
+; VF_8-NEXT:     Found an estimated cost of 64 for VF 8 For instruction: store i16 0, i16* %tmp3, align 2
 ; VF_16-LABEL: Checking a loop in "i16_factor_4"
-; VF_16:         Found an estimated cost of 2112 for VF 16 For instruction: %tmp4 = load i16, i16* %tmp0, align 2
+; VF_16:         Found an estimated cost of 384 for VF 16 For instruction: %tmp4 = load i16, i16* %tmp0, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i16, i16* %tmp1, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp6 = load i16, i16* %tmp2, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp7 = load i16, i16* %tmp3, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i16 0, i16* %tmp0, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i16 0, i16* %tmp1, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i16 0, i16* %tmp2, align 2
-; VF_16-NEXT:    Found an estimated cost of 1088 for VF 16 For instruction: store i16 0, i16* %tmp3, align 2
+; VF_16-NEXT:    Found an estimated cost of 128 for VF 16 For instruction: store i16 0, i16* %tmp3, align 2
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %tmp0 = getelementptr inbounds %i16.4, %i16.4* %data, i64 %i, i32 0
@@ -799,14 +799,14 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "i32_factor_4"
-; VF_2:          Found an estimated cost of 40 for VF 2 For instruction: %tmp4 = load i32, i32* %tmp0, align 4
+; VF_2:          Found an estimated cost of 48 for VF 2 For instruction: %tmp4 = load i32, i32* %tmp0, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i32, i32* %tmp1, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp6 = load i32, i32* %tmp2, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp7 = load i32, i32* %tmp3, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp0, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp1, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp2, align 4
-; VF_2-NEXT:     Found an estimated cost of 24 for VF 2 For instruction: store i32 0, i32* %tmp3, align 4
+; VF_2-NEXT:     Found an estimated cost of 16 for VF 2 For instruction: store i32 0, i32* %tmp3, align 4
 ; VF_4-LABEL:  Checking a loop in "i32_factor_4"
 ; VF_4:          Found an estimated cost of 32 for VF 4 For instruction: %tmp4 = load i32, i32* %tmp0, align 4
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i32, i32* %tmp1, align 4
@@ -817,23 +817,23 @@
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store i32 0, i32* %tmp2, align 4
 ; VF_4-NEXT:     Found an estimated cost of 32 for VF 4 For instruction: store i32 0, i32* %tmp3, align 4
 ; VF_8-LABEL:  Checking a loop in "i32_factor_4"
-; VF_8:          Found an estimated cost of 544 for VF 8 For instruction: %tmp4 = load i32, i32* %tmp0, align 4
+; VF_8:          Found an estimated cost of 192 for VF 8 For instruction: %tmp4 = load i32, i32* %tmp0, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i32, i32* %tmp1, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp6 = load i32, i32* %tmp2, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp7 = load i32, i32* %tmp3, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp0, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp1, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp2, align 4
-; VF_8-NEXT:     Found an estimated cost of 288 for VF 8 For instruction: store i32 0, i32* %tmp3, align 4
+; VF_8-NEXT:     Found an estimated cost of 64 for VF 8 For instruction: store i32 0, i32* %tmp3, align 4
 ; VF_16-LABEL: Checking a loop in "i32_factor_4"
-; VF_16:         Found an estimated cost of 2112 for VF 16 For instruction: %tmp4 = load i32, i32* %tmp0, align 4
+; VF_16:         Found an estimated cost of 384 for VF 16 For instruction: %tmp4 = load i32, i32* %tmp0, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i32, i32* %tmp1, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp6 = load i32, i32* %tmp2, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp7 = load i32, i32* %tmp3, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i32 0, i32* %tmp0, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i32 0, i32* %tmp1, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i32 0, i32* %tmp2, align 4
-; VF_16-NEXT:    Found an estimated cost of 1088 for VF 16 For instruction: store i32 0, i32* %tmp3, align 4
+; VF_16-NEXT:    Found an estimated cost of 128 for VF 16 For instruction: store i32 0, i32* %tmp3, align 4
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %tmp0 = getelementptr inbounds %i32.4, %i32.4* %data, i64 %i, i32 0
@@ -862,41 +862,41 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "i64_factor_4"
-; VF_2:          Found an estimated cost of 48 for VF 2 For instruction: %tmp4 = load i64, i64* %tmp0, align 8
+; VF_2:          Found an estimated cost of 88 for VF 2 For instruction: %tmp4 = load i64, i64* %tmp0, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i64, i64* %tmp1, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp6 = load i64, i64* %tmp2, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp7 = load i64, i64* %tmp3, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i64 0, i64* %tmp0, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i64 0, i64* %tmp1, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store i64 0, i64* %tmp2, align 8
-; VF_2-NEXT:     Found an estimated cost of 32 for VF 2 For instruction: store i64 0, i64* %tmp3, align 8
+; VF_2-NEXT:     Found an estimated cost of 24 for VF 2 For instruction: store i64 0, i64* %tmp3, align 8
 ; VF_4-LABEL:  Checking a loop in "i64_factor_4"
-; VF_4:          Found an estimated cost of 160 for VF 4 For instruction: %tmp4 = load i64, i64* %tmp0, align 8
+; VF_4:          Found an estimated cost of 176 for VF 4 For instruction: %tmp4 = load i64, i64* %tmp0, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i64, i64* %tmp1, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp6 = load i64, i64* %tmp2, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp7 = load i64, i64* %tmp3, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store i64 0, i64* %tmp0, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store i64 0, i64* %tmp1, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store i64 0, i64* %tmp2, align 8
-; VF_4-NEXT:     Found an estimated cost of 96 for VF 4 For instruction: store i64 0, i64* %tmp3, align 8
+; VF_4-NEXT:     Found an estimated cost of 48 for VF 4 For instruction: store i64 0, i64* %tmp3, align 8
 ; VF_8-LABEL:  Checking a loop in "i64_factor_4"
-; VF_8:          Found an estimated cost of 576 for VF 8 For instruction: %tmp4 = load i64, i64* %tmp0, align 8
+; VF_8:          Found an estimated cost of 352 for VF 8 For instruction: %tmp4 = load i64, i64* %tmp0, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i64, i64* %tmp1, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp6 = load i64, i64* %tmp2, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp7 = load i64, i64* %tmp3, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i64 0, i64* %tmp0, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i64 0, i64* %tmp1, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store i64 0, i64* %tmp2, align 8
-; VF_8-NEXT:     Found an estimated cost of 320 for VF 8 For instruction: store i64 0, i64* %tmp3, align 8
+; VF_8-NEXT:     Found an estimated cost of 96 for VF 8 For instruction: store i64 0, i64* %tmp3, align 8
 ; VF_16-LABEL: Checking a loop in "i64_factor_4"
-; VF_16:         Found an estimated cost of 2176 for VF 16 For instruction: %tmp4 = load i64, i64* %tmp0, align 8
+; VF_16:         Found an estimated cost of 704 for VF 16 For instruction: %tmp4 = load i64, i64* %tmp0, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i64, i64* %tmp1, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp6 = load i64, i64* %tmp2, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp7 = load i64, i64* %tmp3, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i64 0, i64* %tmp0, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i64 0, i64* %tmp1, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store i64 0, i64* %tmp2, align 8
-; VF_16-NEXT:    Found an estimated cost of 1152 for VF 16 For instruction: store i64 0, i64* %tmp3, align 8
+; VF_16-NEXT:    Found an estimated cost of 192 for VF 16 For instruction: store i64 0, i64* %tmp3, align 8
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %tmp0 = getelementptr inbounds %i64.4, %i64.4* %data, i64 %i, i32 0
@@ -925,41 +925,41 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "f16_factor_4"
-; VF_2:          Found an estimated cost of 40 for VF 2 For instruction: %tmp4 = load half, half* %tmp0, align 2
+; VF_2:          Found an estimated cost of 18 for VF 2 For instruction: %tmp4 = load half, half* %tmp0, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load half, half* %tmp1, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp6 = load half, half* %tmp2, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp7 = load half, half* %tmp3, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store half 0xH0000, half* %tmp0, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store half 0xH0000, half* %tmp1, align 2
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store half 0xH0000, half* %tmp2, align 2
-; VF_2-NEXT:     Found an estimated cost of 24 for VF 2 For instruction: store half 0xH0000, half* %tmp3, align 2
+; VF_2-NEXT:     Found an estimated cost of 16 for VF 2 For instruction: store half 0xH0000, half* %tmp3, align 2
 ; VF_4-LABEL:  Checking a loop in "f16_factor_4"
-; VF_4:          Found an estimated cost of 144 for VF 4 For instruction: %tmp4 = load half, half* %tmp0, align 2
+; VF_4:          Found an estimated cost of 36 for VF 4 For instruction: %tmp4 = load half, half* %tmp0, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load half, half* %tmp1, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp6 = load half, half* %tmp2, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp7 = load half, half* %tmp3, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store half 0xH0000, half* %tmp0, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store half 0xH0000, half* %tmp1, align 2
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store half 0xH0000, half* %tmp2, align 2
-; VF_4-NEXT:     Found an estimated cost of 80 for VF 4 For instruction: store half 0xH0000, half* %tmp3, align 2
+; VF_4-NEXT:     Found an estimated cost of 32 for VF 4 For instruction: store half 0xH0000, half* %tmp3, align 2
 ; VF_8-LABEL:  Checking a loop in "f16_factor_4"
-; VF_8:          Found an estimated cost of 544 for VF 8 For instruction: %tmp4 = load half, half* %tmp0, align 2
+; VF_8:          Found an estimated cost of 72 for VF 8 For instruction: %tmp4 = load half, half* %tmp0, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load half, half* %tmp1, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp6 = load half, half* %tmp2, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp7 = load half, half* %tmp3, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store half 0xH0000, half* %tmp0, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store half 0xH0000, half* %tmp1, align 2
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store half 0xH0000, half* %tmp2, align 2
-; VF_8-NEXT:     Found an estimated cost of 288 for VF 8 For instruction: store half 0xH0000, half* %tmp3, align 2
+; VF_8-NEXT:     Found an estimated cost of 64 for VF 8 For instruction: store half 0xH0000, half* %tmp3, align 2
 ; VF_16-LABEL: Checking a loop in "f16_factor_4"
-; VF_16:         Found an estimated cost of 2112 for VF 16 For instruction: %tmp4 = load half, half* %tmp0, align 2
+; VF_16:         Found an estimated cost of 144 for VF 16 For instruction: %tmp4 = load half, half* %tmp0, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load half, half* %tmp1, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp6 = load half, half* %tmp2, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp7 = load half, half* %tmp3, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store half 0xH0000, half* %tmp0, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store half 0xH0000, half* %tmp1, align 2
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store half 0xH0000, half* %tmp2, align 2
-; VF_16-NEXT:    Found an estimated cost of 1088 for VF 16 For instruction: store half 0xH0000, half* %tmp3, align 2
+; VF_16-NEXT:    Found an estimated cost of 128 for VF 16 For instruction: store half 0xH0000, half* %tmp3, align 2
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %tmp0 = getelementptr inbounds %f16.4, %f16.4* %data, i64 %i, i32 0
@@ -988,14 +988,14 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "f32_factor_4"
-; VF_2:          Found an estimated cost of 40 for VF 2 For instruction: %tmp4 = load float, float* %tmp0, align 4
+; VF_2:          Found an estimated cost of 20 for VF 2 For instruction: %tmp4 = load float, float* %tmp0, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load float, float* %tmp1, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp6 = load float, float* %tmp2, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp7 = load float, float* %tmp3, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store float 0.000000e+00, float* %tmp0, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store float 0.000000e+00, float* %tmp1, align 4
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store float 0.000000e+00, float* %tmp2, align 4
-; VF_2-NEXT:     Found an estimated cost of 24 for VF 2 For instruction: store float 0.000000e+00, float* %tmp3, align 4
+; VF_2-NEXT:     Found an estimated cost of 16 for VF 2 For instruction: store float 0.000000e+00, float* %tmp3, align 4
 ; VF_4-LABEL:  Checking a loop in "f32_factor_4"
 ; VF_4:          Found an estimated cost of 32 for VF 4 For instruction: %tmp4 = load float, float* %tmp0, align 4
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load float, float* %tmp1, align 4
@@ -1006,23 +1006,23 @@
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store float 0.000000e+00, float* %tmp2, align 4
 ; VF_4-NEXT:     Found an estimated cost of 32 for VF 4 For instruction: store float 0.000000e+00, float* %tmp3, align 4
 ; VF_8-LABEL:  Checking a loop in "f32_factor_4"
-; VF_8:          Found an estimated cost of 544 for VF 8 For instruction: %tmp4 = load float, float* %tmp0, align 4
+; VF_8:          Found an estimated cost of 80 for VF 8 For instruction: %tmp4 = load float, float* %tmp0, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load float, float* %tmp1, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp6 = load float, float* %tmp2, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp7 = load float, float* %tmp3, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store float 0.000000e+00, float* %tmp0, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store float 0.000000e+00, float* %tmp1, align 4
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store float 0.000000e+00, float* %tmp2, align 4
-; VF_8-NEXT:     Found an estimated cost of 288 for VF 8 For instruction: store float 0.000000e+00, float* %tmp3, align 4
+; VF_8-NEXT:     Found an estimated cost of 64 for VF 8 For instruction: store float 0.000000e+00, float* %tmp3, align 4
 ; VF_16-LABEL: Checking a loop in "f32_factor_4"
-; VF_16:         Found an estimated cost of 2112 for VF 16 For instruction: %tmp4 = load float, float* %tmp0, align 4
+; VF_16:         Found an estimated cost of 160 for VF 16 For instruction: %tmp4 = load float, float* %tmp0, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load float, float* %tmp1, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp6 = load float, float* %tmp2, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp7 = load float, float* %tmp3, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store float 0.000000e+00, float* %tmp0, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store float 0.000000e+00, float* %tmp1, align 4
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store float 0.000000e+00, float* %tmp2, align 4
-; VF_16-NEXT:    Found an estimated cost of 1088 for VF 16 For instruction: store float 0.000000e+00, float* %tmp3, align 4
+; VF_16-NEXT:    Found an estimated cost of 128 for VF 16 For instruction: store float 0.000000e+00, float* %tmp3, align 4
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %tmp0 = getelementptr inbounds %f32.4, %f32.4* %data, i64 %i, i32 0
@@ -1051,41 +1051,41 @@
   br label %for.body
 
 ; VF_2-LABEL:  Checking a loop in "f64_factor_4"
-; VF_2:          Found an estimated cost of 40 for VF 2 For instruction: %tmp4 = load double, double* %tmp0, align 8
+; VF_2:          Found an estimated cost of 24 for VF 2 For instruction: %tmp4 = load double, double* %tmp0, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load double, double* %tmp1, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp6 = load double, double* %tmp2, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: %tmp7 = load double, double* %tmp3, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store double 0.000000e+00, double* %tmp0, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store double 0.000000e+00, double* %tmp1, align 8
 ; VF_2-NEXT:     Found an estimated cost of 0 for VF 2 For instruction: store double 0.000000e+00, double* %tmp2, align 8
-; VF_2-NEXT:     Found an estimated cost of 24 for VF 2 For instruction: store double 0.000000e+00, double* %tmp3, align 8
+; VF_2-NEXT:     Found an estimated cost of 16 for VF 2 For instruction: store double 0.000000e+00, double* %tmp3, align 8
 ; VF_4-LABEL:  Checking a loop in "f64_factor_4"
-; VF_4:          Found an estimated cost of 144 for VF 4 For instruction: %tmp4 = load double, double* %tmp0, align 8
+; VF_4:          Found an estimated cost of 48 for VF 4 For instruction: %tmp4 = load double, double* %tmp0, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load double, double* %tmp1, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp6 = load double, double* %tmp2, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: %tmp7 = load double, double* %tmp3, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store double 0.000000e+00, double* %tmp0, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store double 0.000000e+00, double* %tmp1, align 8
 ; VF_4-NEXT:     Found an estimated cost of 0 for VF 4 For instruction: store double 0.000000e+00, double* %tmp2, align 8
-; VF_4-NEXT:     Found an estimated cost of 80 for VF 4 For instruction: store double 0.000000e+00, double* %tmp3, align 8
+; VF_4-NEXT:     Found an estimated cost of 32 for VF 4 For instruction: store double 0.000000e+00, double* %tmp3, align 8
 ; VF_8-LABEL:  Checking a loop in "f64_factor_4"
-; VF_8:          Found an estimated cost of 544 for VF 8 For instruction: %tmp4 = load double, double* %tmp0, align 8
+; VF_8:          Found an estimated cost of 96 for VF 8 For instruction: %tmp4 = load double, double* %tmp0, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load double, double* %tmp1, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp6 = load double, double* %tmp2, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp7 = load double, double* %tmp3, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store double 0.000000e+00, double* %tmp0, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store double 0.000000e+00, double* %tmp1, align 8
 ; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: store double 0.000000e+00, double* %tmp2, align 8
-; VF_8-NEXT:     Found an estimated cost of 288 for VF 8 For instruction: store double 0.000000e+00, double* %tmp3, align 8
+; VF_8-NEXT:     Found an estimated cost of 64 for VF 8 For instruction: store double 0.000000e+00, double* %tmp3, align 8
 ; VF_16-LABEL: Checking a loop in "f64_factor_4"
-; VF_16:         Found an estimated cost of 2112 for VF 16 For instruction: %tmp4 = load double, double* %tmp0, align 8
+; VF_16:         Found an estimated cost of 192 for VF 16 For instruction: %tmp4 = load double, double* %tmp0, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load double, double* %tmp1, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp6 = load double, double* %tmp2, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp7 = load double, double* %tmp3, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store double 0.000000e+00, double* %tmp0, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store double 0.000000e+00, double* %tmp1, align 8
 ; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: store double 0.000000e+00, double* %tmp2, align 8
-; VF_16-NEXT:    Found an estimated cost of 1088 for VF 16 For instruction: store double 0.000000e+00, double* %tmp3, align 8
+; VF_16-NEXT:    Found an estimated cost of 128 for VF 16 For instruction: store double 0.000000e+00, double* %tmp3, align 8
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %tmp0 = getelementptr inbounds %f64.4, %f64.4* %data, i64 %i, i32 0
diff --git a/llvm/test/Transforms/LoopVectorize/ARM/mve-saddsatcost.ll b/llvm/test/Transforms/LoopVectorize/ARM/mve-saddsatcost.ll
--- a/llvm/test/Transforms/LoopVectorize/ARM/mve-saddsatcost.ll
+++ b/llvm/test/Transforms/LoopVectorize/ARM/mve-saddsatcost.ll
@@ -8,7 +8,7 @@
 
 ; CHECK-COST-LABEL: arm_offset_q15
 ; CHECK-COST: Found an estimated cost of 10 for VF 1 For instruction:   %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
-; CHECK-COST: Found an estimated cost of 28 for VF 2 For instruction:   %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
+; CHECK-COST: Found an estimated cost of 36 for VF 2 For instruction:   %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
 ; CHECK-COST: Found an estimated cost of 8 for VF 4 For instruction:   %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
 ; CHECK-COST: Found an estimated cost of 2 for VF 8 For instruction:   %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
 
diff --git a/llvm/test/Transforms/LoopVectorize/ARM/pointer_iv.ll b/llvm/test/Transforms/LoopVectorize/ARM/pointer_iv.ll
--- a/llvm/test/Transforms/LoopVectorize/ARM/pointer_iv.ll
+++ b/llvm/test/Transforms/LoopVectorize/ARM/pointer_iv.ll
@@ -688,19 +688,37 @@
 define hidden void @pointer_phi_v4half_add3(half* noalias nocapture readonly %A, half* noalias nocapture %B, half %y) {
 ; CHECK-LABEL: @pointer_phi_v4half_add3(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK-NEXT:    [[IND_END:%.*]] = getelementptr half, half* [[A:%.*]], i32 2976
+; CHECK-NEXT:    [[IND_END3:%.*]] = getelementptr half, half* [[B:%.*]], i32 992
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x half> poison, half [[Y:%.*]], i32 0
+; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x half> [[BROADCAST_SPLATINSERT]], <8 x half> poison, <8 x i32> zeroinitializer
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = mul i32 [[INDEX]], 3
+; CHECK-NEXT:    [[NEXT_GEP:%.*]] = getelementptr half, half* [[A]], i32 [[TMP0]]
+; CHECK-NEXT:    [[NEXT_GEP4:%.*]] = getelementptr half, half* [[B]], i32 [[INDEX]]
+; CHECK-NEXT:    [[TMP1:%.*]] = bitcast half* [[NEXT_GEP]] to <24 x half>*
+; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <24 x half>, <24 x half>* [[TMP1]], align 4
+; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = shufflevector <24 x half> [[WIDE_VEC]], <24 x half> poison, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd fast <8 x half> [[STRIDED_VEC]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast half* [[NEXT_GEP4]] to <8 x half>*
+; CHECK-NEXT:    store <8 x half> [[TMP2]], <8 x half>* [[TMP3]], align 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 8
+; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[INDEX_NEXT]], 992
+; CHECK-NEXT:    br i1 [[TMP4]], label [[FOR_BODY:%.*]], label [[VECTOR_BODY]], [[LOOP22:!llvm.loop !.*]]
 ; CHECK:       for.body:
-; CHECK-NEXT:    [[A_ADDR_09:%.*]] = phi half* [ [[ADD_PTR:%.*]], [[FOR_BODY]] ], [ [[A:%.*]], [[ENTRY:%.*]] ]
-; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY]] ]
-; CHECK-NEXT:    [[B_ADDR_07:%.*]] = phi half* [ [[INCDEC_PTR:%.*]], [[FOR_BODY]] ], [ [[B:%.*]], [[ENTRY]] ]
-; CHECK-NEXT:    [[TMP0:%.*]] = load half, half* [[A_ADDR_09]], align 4
+; CHECK-NEXT:    [[A_ADDR_09:%.*]] = phi half* [ [[ADD_PTR:%.*]], [[FOR_BODY]] ], [ [[IND_END]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ 992, [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[B_ADDR_07:%.*]] = phi half* [ [[INCDEC_PTR:%.*]], [[FOR_BODY]] ], [ [[IND_END3]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP5:%.*]] = load half, half* [[A_ADDR_09]], align 4
 ; CHECK-NEXT:    [[ADD_PTR]] = getelementptr inbounds half, half* [[A_ADDR_09]], i32 3
-; CHECK-NEXT:    [[ADD:%.*]] = fadd fast half [[TMP0]], [[Y:%.*]]
+; CHECK-NEXT:    [[ADD:%.*]] = fadd fast half [[TMP5]], [[Y]]
 ; CHECK-NEXT:    store half [[ADD]], half* [[B_ADDR_07]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR]] = getelementptr inbounds half, half* [[B_ADDR_07]], i32 1
 ; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], 1000
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[END:%.*]], label [[FOR_BODY]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[END:%.*]], label [[FOR_BODY]], [[LOOP23:!llvm.loop !.*]]
 ; CHECK:       end:
 ; CHECK-NEXT:    ret void
 ;
@@ -753,7 +771,7 @@
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 8
 ; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i32 [[INDEX_NEXT]], 9992
 ; CHECK-NEXT:    [[PTR_IND]] = getelementptr i32, i32* [[POINTER_PHI]], i32 48
-; CHECK-NEXT:    br i1 [[TMP7]], label [[FOR_BODY:%.*]], label [[VECTOR_BODY]], [[LOOP22:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[TMP7]], label [[FOR_BODY:%.*]], label [[VECTOR_BODY]], [[LOOP24:!llvm.loop !.*]]
 ; CHECK:       for.cond.cleanup:
 ; CHECK-NEXT:    ret void
 ; CHECK:       for.body:
@@ -767,7 +785,7 @@
 ; CHECK-NEXT:    [[INCDEC_PTR]] = getelementptr inbounds i32, i32* [[B_ADDR_06]], i32 1
 ; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_07]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], 10000
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]], [[LOOP23:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]], [[LOOP25:!llvm.loop !.*]]
 ;
 
 entry:
@@ -837,7 +855,7 @@
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 16
 ; CHECK-NEXT:    [[TMP15:%.*]] = icmp eq i32 [[INDEX_NEXT]], 9984
 ; CHECK-NEXT:    [[PTR_IND]] = getelementptr i32, i32* [[POINTER_PHI]], i32 96
-; CHECK-NEXT:    br i1 [[TMP15]], label [[FOR_BODY:%.*]], label [[VECTOR_BODY]], [[LOOP24:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[TMP15]], label [[FOR_BODY:%.*]], label [[VECTOR_BODY]], [[LOOP26:!llvm.loop !.*]]
 ; CHECK:       for.cond.cleanup:
 ; CHECK-NEXT:    ret void
 ; CHECK:       for.body:
@@ -851,7 +869,7 @@
 ; CHECK-NEXT:    [[INCDEC_PTR]] = getelementptr inbounds i32, i32* [[B_ADDR_06]], i32 1
 ; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_07]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], 10000
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]], [[LOOP25:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]], [[LOOP27:!llvm.loop !.*]]
 ;
 entry:
   br label %for.body
@@ -893,23 +911,23 @@
 ; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr i8, i8* [[POINTER_PHI]], <4 x i32> <i32 0, i32 3, i32 6, i32 9>
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr i8, i8* [[POINTER_PHI5]], <4 x i32> <i32 0, i32 3, i32 6, i32 9>
 ; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i8, <4 x i8*> [[TMP0]], i32 1
-; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*> [[TMP0]], i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i8> undef), !alias.scope !26
+; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*> [[TMP0]], i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i8> undef), !alias.scope !28
 ; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i8, <4 x i8*> [[TMP0]], i32 2
-; CHECK-NEXT:    [[WIDE_MASKED_GATHER7:%.*]] = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*> [[TMP2]], i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i8> undef), !alias.scope !26
-; CHECK-NEXT:    [[WIDE_MASKED_GATHER8:%.*]] = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*> [[TMP3]], i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i8> undef), !alias.scope !26
+; CHECK-NEXT:    [[WIDE_MASKED_GATHER7:%.*]] = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*> [[TMP2]], i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i8> undef), !alias.scope !28
+; CHECK-NEXT:    [[WIDE_MASKED_GATHER8:%.*]] = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*> [[TMP3]], i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i8> undef), !alias.scope !28
 ; CHECK-NEXT:    [[TMP4:%.*]] = mul <4 x i8> [[WIDE_MASKED_GATHER]], <i8 10, i8 10, i8 10, i8 10>
 ; CHECK-NEXT:    [[TMP5:%.*]] = mul <4 x i8> [[WIDE_MASKED_GATHER]], [[WIDE_MASKED_GATHER7]]
 ; CHECK-NEXT:    [[TMP6:%.*]] = mul <4 x i8> [[WIDE_MASKED_GATHER]], [[WIDE_MASKED_GATHER8]]
 ; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i8, <4 x i8*> [[TMP1]], i32 1
-; CHECK-NEXT:    call void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8> [[TMP4]], <4 x i8*> [[TMP1]], i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>), !alias.scope !29, !noalias !26
+; CHECK-NEXT:    call void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8> [[TMP4]], <4 x i8*> [[TMP1]], i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>), !alias.scope !31, !noalias !28
 ; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i8, <4 x i8*> [[TMP1]], i32 2
-; CHECK-NEXT:    call void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8> [[TMP5]], <4 x i8*> [[TMP7]], i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>), !alias.scope !29, !noalias !26
-; CHECK-NEXT:    call void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8> [[TMP6]], <4 x i8*> [[TMP8]], i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>), !alias.scope !29, !noalias !26
+; CHECK-NEXT:    call void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8> [[TMP5]], <4 x i8*> [[TMP7]], i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>), !alias.scope !31, !noalias !28
+; CHECK-NEXT:    call void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8> [[TMP6]], <4 x i8*> [[TMP8]], i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>), !alias.scope !31, !noalias !28
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1000
 ; CHECK-NEXT:    [[PTR_IND]] = getelementptr i8, i8* [[POINTER_PHI]], i32 12
 ; CHECK-NEXT:    [[PTR_IND6]] = getelementptr i8, i8* [[POINTER_PHI5]], i32 12
-; CHECK-NEXT:    br i1 [[TMP9]], label [[END:%.*]], label [[VECTOR_BODY]], [[LOOP31:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[TMP9]], label [[END:%.*]], label [[VECTOR_BODY]], [[LOOP33:!llvm.loop !.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[X_ADDR_050:%.*]] = phi i8* [ [[INCDEC_PTR2:%.*]], [[FOR_BODY]] ], [ [[X]], [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    [[Z_ADDR_049:%.*]] = phi i8* [ [[INCDEC_PTR34:%.*]], [[FOR_BODY]] ], [ [[Z]], [[ENTRY]] ]
@@ -931,7 +949,7 @@
 ; CHECK-NEXT:    store i8 [[MUL2]], i8* [[INCDEC_PTR33]], align 1
 ; CHECK-NEXT:    [[INC]] = add nuw i32 [[I_048]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], 1000
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[END]], label [[FOR_BODY]], [[LOOP32:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[END]], label [[FOR_BODY]], [[LOOP34:!llvm.loop !.*]]
 ; CHECK:       end:
 ; CHECK-NEXT:    ret void
 ;
diff --git a/llvm/test/Transforms/LoopVectorize/ARM/tail-folding-not-allowed.ll b/llvm/test/Transforms/LoopVectorize/ARM/tail-folding-not-allowed.ll
--- a/llvm/test/Transforms/LoopVectorize/ARM/tail-folding-not-allowed.ll
+++ b/llvm/test/Transforms/LoopVectorize/ARM/tail-folding-not-allowed.ll
@@ -465,25 +465,58 @@
 define void @fptrunc_not_allowed(float* noalias nocapture %A, float* noalias nocapture readonly %B, float* noalias nocapture readonly %C, half* noalias nocapture %D) #0 {
 ; CHECK-LABEL: @fptrunc_not_allowed(
 ; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds float, float* [[B:%.*]], i32 [[TMP0]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds float, float* [[TMP1]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[TMP2]] to <4 x float>*
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x float>, <4 x float>* [[TMP3]], align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds float, float* [[C:%.*]], i32 [[TMP0]]
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds float, float* [[TMP4]], i32 0
+; CHECK-NEXT:    [[TMP6:%.*]] = bitcast float* [[TMP5]] to <4 x float>*
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <4 x float>, <4 x float>* [[TMP6]], align 4
+; CHECK-NEXT:    [[TMP7:%.*]] = fadd fast <4 x float> [[WIDE_LOAD1]], [[WIDE_LOAD]]
+; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds float, float* [[A:%.*]], i32 [[TMP0]]
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds float, float* [[TMP8]], i32 0
+; CHECK-NEXT:    [[TMP10:%.*]] = bitcast float* [[TMP9]] to <4 x float>*
+; CHECK-NEXT:    store <4 x float> [[TMP7]], <4 x float>* [[TMP10]], align 4
+; CHECK-NEXT:    [[TMP11:%.*]] = fptrunc <4 x float> [[TMP7]] to <4 x half>
+; CHECK-NEXT:    [[TMP12:%.*]] = fmul fast <4 x half> [[TMP11]], <half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000>
+; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr inbounds half, half* [[D:%.*]], i32 [[TMP0]]
+; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds half, half* [[TMP13]], i32 0
+; CHECK-NEXT:    [[TMP15:%.*]] = bitcast half* [[TMP14]] to <4 x half>*
+; CHECK-NEXT:    store <4 x half> [[TMP12]], <4 x half>* [[TMP15]], align 2
+; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
+; CHECK-NEXT:    [[TMP16:%.*]] = icmp eq i32 [[INDEX_NEXT]], 428
+; CHECK-NEXT:    br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP12:!llvm.loop !.*]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 431, 428
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 428, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.cond.cleanup:
 ; CHECK-NEXT:    ret void
 ; CHECK:       for.body:
-; CHECK-NEXT:    [[I_017:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[ADD6:%.*]], [[FOR_BODY]] ]
-; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds float, float* [[B:%.*]], i32 [[I_017]]
-; CHECK-NEXT:    [[TMP0:%.*]] = load float, float* [[ARRAYIDX]], align 4
-; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds float, float* [[C:%.*]], i32 [[I_017]]
-; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* [[ARRAYIDX1]], align 4
-; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[TMP1]], [[TMP0]]
-; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds float, float* [[A:%.*]], i32 [[I_017]]
+; CHECK-NEXT:    [[I_017:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[ADD6:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds float, float* [[B]], i32 [[I_017]]
+; CHECK-NEXT:    [[TMP17:%.*]] = load float, float* [[ARRAYIDX]], align 4
+; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds float, float* [[C]], i32 [[I_017]]
+; CHECK-NEXT:    [[TMP18:%.*]] = load float, float* [[ARRAYIDX1]], align 4
+; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[TMP18]], [[TMP17]]
+; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds float, float* [[A]], i32 [[I_017]]
 ; CHECK-NEXT:    store float [[ADD]], float* [[ARRAYIDX2]], align 4
 ; CHECK-NEXT:    [[CONV:%.*]] = fptrunc float [[ADD]] to half
 ; CHECK-NEXT:    [[FACTOR:%.*]] = fmul fast half [[CONV]], 0xH4000
-; CHECK-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds half, half* [[D:%.*]], i32 [[I_017]]
+; CHECK-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds half, half* [[D]], i32 [[I_017]]
 ; CHECK-NEXT:    store half [[FACTOR]], half* [[ARRAYIDX5]], align 2
 ; CHECK-NEXT:    [[ADD6]] = add nuw nsw i32 [[I_017]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[ADD6]], 431
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], [[LOOP13:!llvm.loop !.*]]
 ;
 entry:
   br label %for.body
@@ -591,7 +624,7 @@
 ; CHECK-NEXT:    [[TMP5]] = select <4 x i1> [[TMP4]], <4 x i32> [[VEC_PHI]], <4 x i32> [[WIDE_LOAD]]
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP12:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP14:!llvm.loop !.*]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> [[TMP5]])
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
@@ -609,7 +642,7 @@
 ; CHECK-NEXT:    [[ADD]] = select i1 [[C]], i32 [[R_07]], i32 [[TMP8]]
 ; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], [[LOOP13:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], [[LOOP15:!llvm.loop !.*]]
 ; CHECK:       for.cond.cleanup.loopexit:
 ; CHECK-NEXT:    [[ADD_LCSSA:%.*]] = phi i32 [ [[ADD]], [[FOR_BODY]] ], [ [[TMP7]], [[MIDDLE_BLOCK]] ]
 ; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
@@ -661,7 +694,7 @@
 ; CHECK-NEXT:    [[TMP5]] = select <4 x i1> [[TMP4]], <4 x i32> [[VEC_PHI]], <4 x i32> [[WIDE_LOAD]]
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP14:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP16:!llvm.loop !.*]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> [[TMP5]])
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
@@ -679,7 +712,7 @@
 ; CHECK-NEXT:    [[ADD]] = select i1 [[C]], i32 [[R_07]], i32 [[TMP8]]
 ; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], [[LOOP15:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], [[LOOP17:!llvm.loop !.*]]
 ; CHECK:       for.cond.cleanup.loopexit:
 ; CHECK-NEXT:    [[ADD_LCSSA:%.*]] = phi i32 [ [[ADD]], [[FOR_BODY]] ], [ [[TMP7]], [[MIDDLE_BLOCK]] ]
 ; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
@@ -731,7 +764,7 @@
 ; CHECK-NEXT:    [[TMP5]] = select <4 x i1> [[TMP4]], <4 x i32> [[VEC_PHI]], <4 x i32> [[WIDE_LOAD]]
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP16:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP18:!llvm.loop !.*]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.vector.reduce.umin.v4i32(<4 x i32> [[TMP5]])
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
@@ -749,7 +782,7 @@
 ; CHECK-NEXT:    [[ADD]] = select i1 [[C]], i32 [[R_07]], i32 [[TMP8]]
 ; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], [[LOOP17:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], [[LOOP19:!llvm.loop !.*]]
 ; CHECK:       for.cond.cleanup.loopexit:
 ; CHECK-NEXT:    [[ADD_LCSSA:%.*]] = phi i32 [ [[ADD]], [[FOR_BODY]] ], [ [[TMP7]], [[MIDDLE_BLOCK]] ]
 ; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
@@ -801,7 +834,7 @@
 ; CHECK-NEXT:    [[TMP5]] = select <4 x i1> [[TMP4]], <4 x i32> [[VEC_PHI]], <4 x i32> [[WIDE_LOAD]]
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP18:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP20:!llvm.loop !.*]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> [[TMP5]])
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
@@ -819,7 +852,7 @@
 ; CHECK-NEXT:    [[ADD]] = select i1 [[C]], i32 [[R_07]], i32 [[TMP8]]
 ; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], [[LOOP19:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], [[LOOP21:!llvm.loop !.*]]
 ; CHECK:       for.cond.cleanup.loopexit:
 ; CHECK-NEXT:    [[ADD_LCSSA:%.*]] = phi i32 [ [[ADD]], [[FOR_BODY]] ], [ [[TMP7]], [[MIDDLE_BLOCK]] ]
 ; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]