Index: llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -1858,15 +1858,15 @@
     // as elements are extracted from the vectors and the muls scalarized.
     // As getScalarizationOverhead is a bit too pessimistic, we estimate the
     // cost for a i64 vector directly here, which is:
-    // - four i64 extracts,
-    // - two i64 inserts, and
-    // - 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. If both operands are extensions it will not
+    // - four 2-cost i64 extracts,
+    // - two 2-cost i64 inserts, and
+    // - two 1-cost muls.
+    // So, for a v2i64 with LT.First = 1 the cost is 14, and for a v4i64 with
+    // LT.first = 2 the cost is 28. If both operands are extensions it will not
     // need to scalarize so the cost can be cheaper (smull or umull).
     if (LT.second != MVT::v2i64 || isWideningInstruction(Ty, Opcode, Args))
       return LT.first;
-    return LT.first * 8;
+    return LT.first * 14;
   }
   case ISD::ADD:
   case ISD::XOR:
Index: llvm/test/Analysis/CostModel/AArch64/arith-overflow.ll
===================================================================
--- llvm/test/Analysis/CostModel/AArch64/arith-overflow.ll
+++ llvm/test/Analysis/CostModel/AArch64/arith-overflow.ll
@@ -357,9 +357,9 @@
 ; 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 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 36 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 72 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 144 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 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)
@@ -439,9 +439,9 @@
 ; 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 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 35 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 70 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 140 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 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)
Index: llvm/test/Analysis/CostModel/AArch64/arith-widening.ll
===================================================================
--- llvm/test/Analysis/CostModel/AArch64/arith-widening.ll
+++ llvm/test/Analysis/CostModel/AArch64/arith-widening.ll
@@ -1554,15 +1554,15 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %zl2_8_32 = zext <2 x i8> %i8 to <2 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %azl_8_32 = mul <2 x i32> %zl1_8_32, %zl2_8_32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sw_8_64 = sext <2 x i8> %i8 to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %asw_8_64 = mul <2 x i64> %i64, %sw_8_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %asw_8_64 = mul <2 x i64> %i64, %sw_8_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sl1_8_64 = sext <2 x i8> %i8 to <2 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sl2_8_64 = sext <2 x i8> %i8 to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %asl_8_64 = mul <2 x i64> %sl1_8_64, %sl2_8_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %asl_8_64 = mul <2 x i64> %sl1_8_64, %sl2_8_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %zw_8_64 = zext <2 x i8> %i8 to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %azw_8_64 = mul <2 x i64> %i64, %zw_8_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %azw_8_64 = mul <2 x i64> %i64, %zw_8_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %zl1_8_64 = zext <2 x i8> %i8 to <2 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %zl2_8_64 = zext <2 x i8> %i8 to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %azl_8_64 = mul <2 x i64> %zl1_8_64, %zl2_8_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %azl_8_64 = mul <2 x i64> %zl1_8_64, %zl2_8_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sw_16_32 = sext <2 x i16> %i16 to <2 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %asw_16_32 = mul <2 x i32> %i32, %sw_16_32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sl1_16_32 = sext <2 x i16> %i16 to <2 x i32>
@@ -1574,22 +1574,22 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %zl2_16_32 = zext <2 x i16> %i16 to <2 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %azl_16_32 = mul <2 x i32> %zl1_16_32, %zl2_16_32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sw_16_64 = sext <2 x i16> %i16 to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %asw_16_64 = mul <2 x i64> %i64, %sw_16_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %asw_16_64 = mul <2 x i64> %i64, %sw_16_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sl1_16_64 = sext <2 x i16> %i16 to <2 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sl2_16_64 = sext <2 x i16> %i16 to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %asl_16_64 = mul <2 x i64> %sl1_16_64, %sl2_16_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %asl_16_64 = mul <2 x i64> %sl1_16_64, %sl2_16_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %zw_16_64 = zext <2 x i16> %i16 to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %azw_16_64 = mul <2 x i64> %i64, %zw_16_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %azw_16_64 = mul <2 x i64> %i64, %zw_16_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %zl1_16_64 = zext <2 x i16> %i16 to <2 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %zl2_16_64 = zext <2 x i16> %i16 to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %azl_16_64 = mul <2 x i64> %zl1_16_64, %zl2_16_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %azl_16_64 = mul <2 x i64> %zl1_16_64, %zl2_16_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sw_32_64 = sext <2 x i32> %i32 to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %asw_32_64 = mul <2 x i64> %i64, %sw_32_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %asw_32_64 = mul <2 x i64> %i64, %sw_32_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sl1_32_64 = sext <2 x i32> %i32 to <2 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sl2_32_64 = sext <2 x i32> %i32 to <2 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %asl_32_64 = mul <2 x i64> %sl1_32_64, %sl2_32_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %zw_32_64 = zext <2 x i32> %i32 to <2 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %azw_32_64 = mul <2 x i64> %i64, %zw_32_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %azw_32_64 = mul <2 x i64> %i64, %zw_32_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %zl1_32_64 = zext <2 x i32> %i32 to <2 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %zl2_32_64 = zext <2 x i32> %i32 to <2 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %azl_32_64 = mul <2 x i64> %zl1_32_64, %zl2_32_64
@@ -1693,15 +1693,15 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %zl2_8_32 = zext <4 x i8> %i8 to <4 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %azl_8_32 = mul <4 x i32> %zl1_8_32, %zl2_8_32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %sw_8_64 = sext <4 x i8> %i8 to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %asw_8_64 = mul <4 x i64> %i64, %sw_8_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %asw_8_64 = mul <4 x i64> %i64, %sw_8_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %sl1_8_64 = sext <4 x i8> %i8 to <4 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %sl2_8_64 = sext <4 x i8> %i8 to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %asl_8_64 = mul <4 x i64> %sl1_8_64, %sl2_8_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %asl_8_64 = mul <4 x i64> %sl1_8_64, %sl2_8_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %zw_8_64 = zext <4 x i8> %i8 to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %azw_8_64 = mul <4 x i64> %i64, %zw_8_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %azw_8_64 = mul <4 x i64> %i64, %zw_8_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %zl1_8_64 = zext <4 x i8> %i8 to <4 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %zl2_8_64 = zext <4 x i8> %i8 to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %azl_8_64 = mul <4 x i64> %zl1_8_64, %zl2_8_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %azl_8_64 = mul <4 x i64> %zl1_8_64, %zl2_8_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sw_16_32 = sext <4 x i16> %i16 to <4 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %asw_16_32 = mul <4 x i32> %i32, %sw_16_32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sl1_16_32 = sext <4 x i16> %i16 to <4 x i32>
@@ -1713,22 +1713,22 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %zl2_16_32 = zext <4 x i16> %i16 to <4 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %azl_16_32 = mul <4 x i32> %zl1_16_32, %zl2_16_32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sw_16_64 = sext <4 x i16> %i16 to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %asw_16_64 = mul <4 x i64> %i64, %sw_16_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %asw_16_64 = mul <4 x i64> %i64, %sw_16_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sl1_16_64 = sext <4 x i16> %i16 to <4 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sl2_16_64 = sext <4 x i16> %i16 to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %asl_16_64 = mul <4 x i64> %sl1_16_64, %sl2_16_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %asl_16_64 = mul <4 x i64> %sl1_16_64, %sl2_16_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %zw_16_64 = zext <4 x i16> %i16 to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %azw_16_64 = mul <4 x i64> %i64, %zw_16_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %azw_16_64 = mul <4 x i64> %i64, %zw_16_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %zl1_16_64 = zext <4 x i16> %i16 to <4 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %zl2_16_64 = zext <4 x i16> %i16 to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %azl_16_64 = mul <4 x i64> %zl1_16_64, %zl2_16_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %azl_16_64 = mul <4 x i64> %zl1_16_64, %zl2_16_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sw_32_64 = sext <4 x i32> %i32 to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %asw_32_64 = mul <4 x i64> %i64, %sw_32_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %asw_32_64 = mul <4 x i64> %i64, %sw_32_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sl1_32_64 = sext <4 x i32> %i32 to <4 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sl2_32_64 = sext <4 x i32> %i32 to <4 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %asl_32_64 = mul <4 x i64> %sl1_32_64, %sl2_32_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %zw_32_64 = zext <4 x i32> %i32 to <4 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %azw_32_64 = mul <4 x i64> %i64, %zw_32_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %azw_32_64 = mul <4 x i64> %i64, %zw_32_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %zl1_32_64 = zext <4 x i32> %i32 to <4 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %zl2_32_64 = zext <4 x i32> %i32 to <4 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %azl_32_64 = mul <4 x i64> %zl1_32_64, %zl2_32_64
@@ -1832,15 +1832,15 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %zl2_8_32 = zext <8 x i8> %i8 to <8 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %azl_8_32 = mul <8 x i32> %zl1_8_32, %zl2_8_32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %sw_8_64 = sext <8 x i8> %i8 to <8 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %asw_8_64 = mul <8 x i64> %i64, %sw_8_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %asw_8_64 = mul <8 x i64> %i64, %sw_8_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %sl1_8_64 = sext <8 x i8> %i8 to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %sl2_8_64 = sext <8 x i8> %i8 to <8 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %asl_8_64 = mul <8 x i64> %sl1_8_64, %sl2_8_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %asl_8_64 = mul <8 x i64> %sl1_8_64, %sl2_8_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %zw_8_64 = zext <8 x i8> %i8 to <8 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %azw_8_64 = mul <8 x i64> %i64, %zw_8_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %azw_8_64 = mul <8 x i64> %i64, %zw_8_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %zl1_8_64 = zext <8 x i8> %i8 to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %zl2_8_64 = zext <8 x i8> %i8 to <8 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %azl_8_64 = mul <8 x i64> %zl1_8_64, %zl2_8_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %azl_8_64 = mul <8 x i64> %zl1_8_64, %zl2_8_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sw_16_32 = sext <8 x i16> %i16 to <8 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %asw_16_32 = mul <8 x i32> %i32, %sw_16_32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sl1_16_32 = sext <8 x i16> %i16 to <8 x i32>
@@ -1852,22 +1852,22 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %zl2_16_32 = zext <8 x i16> %i16 to <8 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %azl_16_32 = mul <8 x i32> %zl1_16_32, %zl2_16_32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %sw_16_64 = sext <8 x i16> %i16 to <8 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %asw_16_64 = mul <8 x i64> %i64, %sw_16_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %asw_16_64 = mul <8 x i64> %i64, %sw_16_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %sl1_16_64 = sext <8 x i16> %i16 to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %sl2_16_64 = sext <8 x i16> %i16 to <8 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %asl_16_64 = mul <8 x i64> %sl1_16_64, %sl2_16_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %asl_16_64 = mul <8 x i64> %sl1_16_64, %sl2_16_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %zw_16_64 = zext <8 x i16> %i16 to <8 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %azw_16_64 = mul <8 x i64> %i64, %zw_16_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %azw_16_64 = mul <8 x i64> %i64, %zw_16_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %zl1_16_64 = zext <8 x i16> %i16 to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %zl2_16_64 = zext <8 x i16> %i16 to <8 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %azl_16_64 = mul <8 x i64> %zl1_16_64, %zl2_16_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %azl_16_64 = mul <8 x i64> %zl1_16_64, %zl2_16_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %sw_32_64 = sext <8 x i32> %i32 to <8 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %asw_32_64 = mul <8 x i64> %i64, %sw_32_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %asw_32_64 = mul <8 x i64> %i64, %sw_32_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sl1_32_64 = sext <8 x i32> %i32 to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sl2_32_64 = sext <8 x i32> %i32 to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %asl_32_64 = mul <8 x i64> %sl1_32_64, %sl2_32_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %zw_32_64 = zext <8 x i32> %i32 to <8 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %azw_32_64 = mul <8 x i64> %i64, %zw_32_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %azw_32_64 = mul <8 x i64> %i64, %zw_32_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %zl1_32_64 = zext <8 x i32> %i32 to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %zl2_32_64 = zext <8 x i32> %i32 to <8 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %azl_32_64 = mul <8 x i64> %zl1_32_64, %zl2_32_64
@@ -1971,15 +1971,15 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %zl2_8_32 = zext <16 x i8> %i8 to <16 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %azl_8_32 = mul <16 x i32> %zl1_8_32, %zl2_8_32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %sw_8_64 = sext <16 x i8> %i8 to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %asw_8_64 = mul <16 x i64> %i64, %sw_8_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %asw_8_64 = mul <16 x i64> %i64, %sw_8_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %sl1_8_64 = sext <16 x i8> %i8 to <16 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %sl2_8_64 = sext <16 x i8> %i8 to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %asl_8_64 = mul <16 x i64> %sl1_8_64, %sl2_8_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %asl_8_64 = mul <16 x i64> %sl1_8_64, %sl2_8_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %zw_8_64 = zext <16 x i8> %i8 to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %azw_8_64 = mul <16 x i64> %i64, %zw_8_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %azw_8_64 = mul <16 x i64> %i64, %zw_8_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %zl1_8_64 = zext <16 x i8> %i8 to <16 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %zl2_8_64 = zext <16 x i8> %i8 to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %azl_8_64 = mul <16 x i64> %zl1_8_64, %zl2_8_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %azl_8_64 = mul <16 x i64> %zl1_8_64, %zl2_8_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %sw_16_32 = sext <16 x i16> %i16 to <16 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %asw_16_32 = mul <16 x i32> %i32, %sw_16_32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sl1_16_32 = sext <16 x i16> %i16 to <16 x i32>
@@ -1991,22 +1991,22 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %zl2_16_32 = zext <16 x i16> %i16 to <16 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %azl_16_32 = mul <16 x i32> %zl1_16_32, %zl2_16_32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %sw_16_64 = sext <16 x i16> %i16 to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %asw_16_64 = mul <16 x i64> %i64, %sw_16_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %asw_16_64 = mul <16 x i64> %i64, %sw_16_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %sl1_16_64 = sext <16 x i16> %i16 to <16 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %sl2_16_64 = sext <16 x i16> %i16 to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %asl_16_64 = mul <16 x i64> %sl1_16_64, %sl2_16_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %asl_16_64 = mul <16 x i64> %sl1_16_64, %sl2_16_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %zw_16_64 = zext <16 x i16> %i16 to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %azw_16_64 = mul <16 x i64> %i64, %zw_16_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %azw_16_64 = mul <16 x i64> %i64, %zw_16_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %zl1_16_64 = zext <16 x i16> %i16 to <16 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %zl2_16_64 = zext <16 x i16> %i16 to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %azl_16_64 = mul <16 x i64> %zl1_16_64, %zl2_16_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %azl_16_64 = mul <16 x i64> %zl1_16_64, %zl2_16_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %sw_32_64 = sext <16 x i32> %i32 to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %asw_32_64 = mul <16 x i64> %i64, %sw_32_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %asw_32_64 = mul <16 x i64> %i64, %sw_32_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sl1_32_64 = sext <16 x i32> %i32 to <16 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sl2_32_64 = sext <16 x i32> %i32 to <16 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %asl_32_64 = mul <16 x i64> %sl1_32_64, %sl2_32_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %zw_32_64 = zext <16 x i32> %i32 to <16 x i64>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %azw_32_64 = mul <16 x i64> %i64, %zw_32_64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %azw_32_64 = mul <16 x i64> %i64, %zw_32_64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %zl1_32_64 = zext <16 x i32> %i32 to <16 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %zl2_32_64 = zext <16 x i32> %i32 to <16 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %azl_32_64 = mul <16 x i64> %zl1_32_64, %zl2_32_64
Index: llvm/test/Analysis/CostModel/AArch64/arith.ll
===================================================================
--- llvm/test/Analysis/CostModel/AArch64/arith.ll
+++ llvm/test/Analysis/CostModel/AArch64/arith.ll
@@ -368,7 +368,7 @@
 ; 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 14 for instruction: %e2 = mul <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
@@ -377,7 +377,7 @@
 ; 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 28 for instruction: %e4 = mul <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
@@ -386,7 +386,7 @@
 ; 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 56 for instruction: %e8 = mul <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
@@ -395,7 +395,7 @@
 ; 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 112 for instruction: %e16 = mul <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
Index: llvm/test/Analysis/CostModel/AArch64/mul.ll
===================================================================
--- llvm/test/Analysis/CostModel/AArch64/mul.ll
+++ llvm/test/Analysis/CostModel/AArch64/mul.ll
@@ -113,7 +113,7 @@
 
 define <2 x i64> @t13(<2 x i64> %a, <2 x i64> %b)  {
 ; THROUGHPUT-LABEL: 't13'
-; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %1 = mul nsw <2 x i64> %a, %b
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %1 = mul nsw <2 x i64> %a, %b
 ; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %1
 ;
   %1 = mul nsw <2 x i64> %a, %b
@@ -122,7 +122,7 @@
 
 define <4 x i64> @t14(<4 x i64> %a, <4 x i64> %b)  {
 ; THROUGHPUT-LABEL: 't14'
-; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %1 = mul nsw <4 x i64> %a, %b
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %1 = mul nsw <4 x i64> %a, %b
 ; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %1
 ;
   %1 = mul nsw <4 x i64> %a, %b