[AArch64] Shifts cost 1

[dmgreen]

Summary

The costs of shifts was 2 as opposed to 1, as the nodes are marked custom. Fix this like the others and mark the nodes as cheap.

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

case ISD::MUL:
     // - two muls.
     // So, for a v2i64 with LT.First = 1 the cost is 8, and for a v4i64 with
     // LT.first = 2 the cost is 16.
     return LT.first * 8;
   case ISD::ADD:
   case ISD::XOR:
   case ISD::OR:
   case ISD::AND:
+  case ISD::SRL:
+  case ISD::SRA:
+  case ISD::SHL:
     // These nodes are marked as 'custom' for combining purposes only.
     // We know that they are legal. See LowerAdd in ISelLowering.
     return (Cost + 1) * LT.first;
 
   case ISD::FADD:
   case ISD::FSUB:
   case ISD::FMUL:
   case ISD::FDIV:

llvm/test/Analysis/CostModel/AArch64/arith-overflow.ll

 declare {i8, i1}                @llvm.smul.with.overflow.i8(i8, i8)
 declare {<16 x i8>, <16 x i1>}  @llvm.smul.with.overflow.v16i8(<16 x i8>, <16 x i8>)
 declare {<32 x i8>, <32 x i1>}  @llvm.smul.with.overflow.v32i8(<32 x i8>, <32 x i8>)
 declare {<64 x i8>, <64 x i1>}  @llvm.smul.with.overflow.v64i8(<64 x i8>, <64 x i8>)
 
 define i32 @smul(i32 %arg) {
 ; RECIP-LABEL: 'smul'
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 92 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SIZE-LABEL: 'smul'
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)

 
 define i32 @umul(i32 %arg) {
 ; RECIP-LABEL: 'umul'
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 50 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 100 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 92 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SIZE-LABEL: 'umul'
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)

llvm/test/Analysis/CostModel/AArch64/arith.ll

 }
 
 
 define void @vi8() {
 ; CHECK-LABEL: 'vi8'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %c2 = add <2 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %d2 = sub <2 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %e2 = mul <2 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f2 = ashr <2 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %g2 = lshr <2 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %h2 = shl <2 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f2 = ashr <2 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %g2 = lshr <2 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %h2 = shl <2 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i2 = and <2 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j2 = or <2 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k2 = xor <2 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %c4 = add <4 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %d4 = sub <4 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %e4 = mul <4 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f4 = ashr <4 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %g4 = lshr <4 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %h4 = shl <4 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f4 = ashr <4 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %g4 = lshr <4 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %h4 = shl <4 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i4 = and <4 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j4 = or <4 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k4 = xor <4 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %c8 = add <8 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %d8 = sub <8 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %e8 = mul <8 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f8 = ashr <8 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %g8 = lshr <8 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %h8 = shl <8 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f8 = ashr <8 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %g8 = lshr <8 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %h8 = shl <8 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i8 = and <8 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j8 = or <8 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k8 = xor <8 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %c16 = add <16 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %d16 = sub <16 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %e16 = mul <16 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f16 = ashr <16 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %g16 = lshr <16 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %h16 = shl <16 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f16 = ashr <16 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %g16 = lshr <16 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %h16 = shl <16 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i16 = and <16 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j16 = or <16 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k16 = xor <16 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %c2 = add <2 x i8> undef, undef
   %d2 = sub <2 x i8> undef, undef
   %e2 = mul <2 x i8> undef, undef
;
   ret void
 }
 
 define void @vi16() {
 ; CHECK-LABEL: 'vi16'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %c2 = add <2 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %d2 = sub <2 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %e2 = mul <2 x i16> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f2 = ashr <2 x i16> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %g2 = lshr <2 x i16> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %h2 = shl <2 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f2 = ashr <2 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %g2 = lshr <2 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %h2 = shl <2 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i2 = and <2 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j2 = or <2 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k2 = xor <2 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %c4 = add <4 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %d4 = sub <4 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %e4 = mul <4 x i16> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f4 = ashr <4 x i16> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %g4 = lshr <4 x i16> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %h4 = shl <4 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f4 = ashr <4 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %g4 = lshr <4 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %h4 = shl <4 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i4 = and <4 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j4 = or <4 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k4 = xor <4 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %c8 = add <8 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %d8 = sub <8 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %e8 = mul <8 x i16> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f8 = ashr <8 x i16> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %g8 = lshr <8 x i16> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %h8 = shl <8 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f8 = ashr <8 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %g8 = lshr <8 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %h8 = shl <8 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i8 = and <8 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j8 = or <8 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k8 = xor <8 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %c16 = add <16 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %d16 = sub <16 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %e16 = mul <16 x i16> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %f16 = ashr <16 x i16> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %g16 = lshr <16 x i16> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %h16 = shl <16 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f16 = ashr <16 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %g16 = lshr <16 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %h16 = shl <16 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %i16 = and <16 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %j16 = or <16 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %k16 = xor <16 x i16> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %c2 = add <2 x i16> undef, undef
   %d2 = sub <2 x i16> undef, undef
   %e2 = mul <2 x i16> undef, undef
;
   ret void
 }
 
 define void @vi32() {
 ; CHECK-LABEL: 'vi32'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %c2 = add <2 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %d2 = sub <2 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %e2 = mul <2 x i32> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f2 = ashr <2 x i32> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %g2 = lshr <2 x i32> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %h2 = shl <2 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f2 = ashr <2 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %g2 = lshr <2 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %h2 = shl <2 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i2 = and <2 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j2 = or <2 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k2 = xor <2 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %c4 = add <4 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %d4 = sub <4 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %e4 = mul <4 x i32> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f4 = ashr <4 x i32> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %g4 = lshr <4 x i32> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %h4 = shl <4 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f4 = ashr <4 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %g4 = lshr <4 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %h4 = shl <4 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i4 = and <4 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j4 = or <4 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k4 = xor <4 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %c8 = add <8 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %d8 = sub <8 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %e8 = mul <8 x i32> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %f8 = ashr <8 x i32> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %g8 = lshr <8 x i32> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %h8 = shl <8 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f8 = ashr <8 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %g8 = lshr <8 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %h8 = shl <8 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %i8 = and <8 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %j8 = or <8 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %k8 = xor <8 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %c16 = add <16 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %d16 = sub <16 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %e16 = mul <16 x i32> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %f16 = ashr <16 x i32> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %g16 = lshr <16 x i32> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %h16 = shl <16 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %f16 = ashr <16 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %g16 = lshr <16 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %h16 = shl <16 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %i16 = and <16 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %j16 = or <16 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %k16 = xor <16 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %c2 = add <2 x i32> undef, undef
   %d2 = sub <2 x i32> undef, undef
   %e2 = mul <2 x i32> undef, undef
;
   ret void
 }
 
 define void @vi64() {
 ; CHECK-LABEL: 'vi64'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %c2 = add <2 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %d2 = sub <2 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %e2 = mul <2 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f2 = ashr <2 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %g2 = lshr <2 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %h2 = shl <2 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f2 = ashr <2 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %g2 = lshr <2 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %h2 = shl <2 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %i2 = and <2 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %j2 = or <2 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %k2 = xor <2 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %c4 = add <4 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %d4 = sub <4 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %e4 = mul <4 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %f4 = ashr <4 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %g4 = lshr <4 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %h4 = shl <4 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f4 = ashr <4 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %g4 = lshr <4 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %h4 = shl <4 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %i4 = and <4 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %j4 = or <4 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %k4 = xor <4 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %c8 = add <8 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %d8 = sub <8 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %e8 = mul <8 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %f8 = ashr <8 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %g8 = lshr <8 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %h8 = shl <8 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %f8 = ashr <8 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %g8 = lshr <8 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %h8 = shl <8 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %i8 = and <8 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %j8 = or <8 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %k8 = xor <8 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %c16 = add <16 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %d16 = sub <16 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %e16 = mul <16 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %f16 = ashr <16 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %g16 = lshr <16 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %h16 = shl <16 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %f16 = ashr <16 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %g16 = lshr <16 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %h16 = shl <16 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %i16 = and <16 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %j16 = or <16 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %k16 = xor <16 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %c2 = add <2 x i64> undef, undef
   %d2 = sub <2 x i64> undef, undef
   %e2 = mul <2 x i64> undef, undef

llvm/test/Analysis/CostModel/AArch64/div.ll

 
 define i32 @sdiv_uniformconst() {
 ; CHECK-LABEL: 'sdiv_uniformconst'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I64 = sdiv i64 undef, 7
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 7, i64 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 216 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 432 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 440 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 880 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = sdiv i64 undef, 7
   %V2i64 = sdiv <2 x i64> undef, <i64 7, i64 7>
   %V4i64 = sdiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
   %V8i64 = sdiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>

 
 define i32 @udiv_uniformconst() {
 ; CHECK-LABEL: 'udiv_uniformconst'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I64 = udiv i64 undef, 7
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 7, i64 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 216 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 432 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 440 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 880 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = udiv i64 undef, 7
   %V2i64 = udiv <2 x i64> undef, <i64 7, i64 7>
   %V4i64 = udiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
   %V8i64 = udiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
;
   %V64i8 = udiv <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
 
   ret i32 undef
 }
 
 define i32 @sdiv_uniformconstpow2() {
 ; CHECK-LABEL: 'sdiv_uniformconstpow2'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I64 = sdiv i64 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 16, i64 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 16, i64 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I32 = sdiv i32 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 120 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 116 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I16 = sdiv i16 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 124 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 248 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 61 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 122 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 244 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I8 = sdiv i8 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 126 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 252 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 504 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 125 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 250 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 500 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = sdiv i64 undef, 16
   %V2i64 = sdiv <2 x i64> undef, <i64 16, i64 16>
   %V4i64 = sdiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
   %V8i64 = sdiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
 
   %I32 = sdiv i32 undef, 16

 
 define i32 @udiv_uniformconstpow2() {
 ; CHECK-LABEL: 'udiv_uniformconstpow2'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I64 = udiv i64 undef, 16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 16, i64 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 216 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 432 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 440 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 880 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = udiv i64 undef, 16
   %V2i64 = udiv <2 x i64> undef, <i64 16, i64 16>
   %V4i64 = udiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
   %V8i64 = udiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>

 
 define i32 @sdiv_uniformconstnegpow2() {
 ; CHECK-LABEL: 'sdiv_uniformconstnegpow2'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I64 = sdiv i64 undef, -16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 -16, i64 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 216 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 432 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 440 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 880 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = sdiv i64 undef, -16
   %V2i64 = sdiv <2 x i64> undef, <i64 -16, i64 -16>
   %V4i64 = sdiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
   %V8i64 = sdiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>

 
 define i32 @udiv_uniformconstnegpow2() {
 ; CHECK-LABEL: 'udiv_uniformconstnegpow2'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I64 = udiv i64 undef, -16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 -16, i64 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 216 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 432 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 440 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 880 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = udiv i64 undef, -16
   %V2i64 = udiv <2 x i64> undef, <i64 -16, i64 -16>
   %V4i64 = udiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
   %V8i64 = udiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>

llvm/test/Analysis/CostModel/AArch64/div_cte.ll

 ; RUN: opt -passes='print<cost-model>' 2>&1 -disable-output -mtriple=aarch64-linux-gnu -mattr=+neon < %s | FileCheck %s
 
 ; Verify the cost of integer division by constant.
 
 define <16 x i8> @sdiv8xi16(<16 x i8> %x) {
 ; CHECK-LABEL: function 'sdiv8xi16'
-; CHECK: Found an estimated cost of 9 for instruction: %div = sdiv <16 x i8> %x, <i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9>
+; CHECK: Found an estimated cost of 7 for instruction: %div = sdiv <16 x i8> %x, <i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9>
   %div = sdiv <16 x i8> %x, <i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9>
   ret <16 x i8> %div
 }
 
 define <8 x i16> @sdiv16xi8(<8 x i16> %x) {
 ; CHECK-LABEL: function 'sdiv16xi8'
-; CHECK: Found an estimated cost of 9 for instruction: %div = sdiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
+; CHECK: Found an estimated cost of 7 for instruction: %div = sdiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
   %div = sdiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
   ret <8 x i16> %div
 }
 
 define <4 x i32> @sdiv32xi4(<4 x i32> %x) {
 ; CHECK-LABEL: function 'sdiv32xi4'
-; CHECK: Found an estimated cost of 9 for instruction: %div = sdiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
+; CHECK: Found an estimated cost of 7 for instruction: %div = sdiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
   %div = sdiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
   ret <4 x i32> %div
 }
 
 define <16 x i8> @udiv8xi16(<16 x i8> %x) {
 ; CHECK-LABEL: function 'udiv8xi16'
-; CHECK: Found an estimated cost of 9 for instruction: %div = udiv <16 x i8> %x, <i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9>
+; CHECK: Found an estimated cost of 7 for instruction: %div = udiv <16 x i8> %x, <i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9>
   %div = udiv <16 x i8> %x, <i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9>
   ret <16 x i8> %div
 }
 
 define <8 x i16> @udiv16xi8(<8 x i16> %x) {
 ; CHECK-LABEL: function 'udiv16xi8'
-; CHECK: Found an estimated cost of 9 for instruction:   %div = udiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
+; CHECK: Found an estimated cost of 7 for instruction:   %div = udiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
   %div = udiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
   ret <8 x i16> %div
 }
 
 define <4 x i32> @udiv32xi4(<4 x i32> %x) {
 ; CHECK-LABEL: function 'udiv32xi4'
-; CHECK: Found an estimated cost of 9 for instruction:   %div = udiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
+; CHECK: Found an estimated cost of 7 for instruction:   %div = udiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
   %div = udiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
   ret <4 x i32> %div
 }

llvm/test/Transforms/SLPVectorizer/AArch64/gather-cost.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -S -slp-vectorizer -instcombine -pass-remarks-output=%t | FileCheck %s
 ; RUN: cat %t | FileCheck -check-prefix=REMARK %s
 ; RUN: opt < %s -S -aa-pipeline=basic-aa -passes='slp-vectorizer,instcombine' -pass-remarks-output=%t | FileCheck %s
 ; RUN: cat %t | FileCheck -check-prefix=REMARK %s
 
 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
 target triple = "aarch64--linux-gnu"
 
 ; REMARK-LABEL: Function: gather_multiple_use
 ; REMARK:       Args:
 ; REMARK-NEXT:    - String: 'Vectorized horizontal reduction with cost '
-; REMARK-NEXT:    - Cost: '-6'
+; REMARK-NEXT:    - Cost: '-7'
 ;
 ; REMARK-NOT: Function: gather_load
 
 define internal i32 @gather_multiple_use(i32 %a, i32 %b, i32 %c, i32 %d) {
 ; CHECK-LABEL: @gather_multiple_use(
 ; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x i32> poison, i32 [[C:%.*]], i64 0
 ; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <4 x i32> [[TMP1]], i32 [[A:%.*]], i64 1
 ; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <4 x i32> [[TMP2]], i32 [[B:%.*]], i64 2