Index: llvm/trunk/include/llvm/CodeGen/BasicTTIImpl.h
===================================================================
--- llvm/trunk/include/llvm/CodeGen/BasicTTIImpl.h
+++ llvm/trunk/include/llvm/CodeGen/BasicTTIImpl.h
@@ -1306,6 +1306,30 @@
                                               CondTy, nullptr);
       return Cost;
     }
+    case Intrinsic::smul_fix:
+    case Intrinsic::umul_fix: {
+      unsigned ExtSize = RetTy->getScalarSizeInBits() * 2;
+      Type *ExtTy = Type::getIntNTy(RetTy->getContext(), ExtSize);
+      if (RetVF > 1)
+        ExtTy = VectorType::get(ExtTy, RetVF);
+
+      unsigned ExtOp =
+          IID == Intrinsic::smul_fix ? Instruction::SExt : Instruction::ZExt;
+
+      unsigned Cost = 0;
+      Cost += 2 * ConcreteTTI->getCastInstrCost(ExtOp, ExtTy, RetTy);
+      Cost += ConcreteTTI->getArithmeticInstrCost(Instruction::Mul, ExtTy);
+      Cost +=
+          2 * ConcreteTTI->getCastInstrCost(Instruction::Trunc, RetTy, ExtTy);
+      Cost += ConcreteTTI->getArithmeticInstrCost(Instruction::LShr, RetTy,
+                                                  TTI::OK_AnyValue,
+                                                  TTI::OK_UniformConstantValue);
+      Cost += ConcreteTTI->getArithmeticInstrCost(Instruction::Shl, RetTy,
+                                                  TTI::OK_AnyValue,
+                                                  TTI::OK_UniformConstantValue);
+      Cost += ConcreteTTI->getArithmeticInstrCost(Instruction::Or, RetTy);
+      return Cost;
+    }
     case Intrinsic::sadd_with_overflow:
     case Intrinsic::ssub_with_overflow: {
       Type *SumTy = RetTy->getContainedType(0);
Index: llvm/trunk/test/Analysis/CostModel/X86/arith-fix.ll
===================================================================
--- llvm/trunk/test/Analysis/CostModel/X86/arith-fix.ll
+++ llvm/trunk/test/Analysis/CostModel/X86/arith-fix.ll
@@ -32,24 +32,195 @@
 declare <64 x i8>  @llvm.smul.fix.v64i8(<64 x i8>, <64 x i8>, i32)
 
 define i32 @smul(i32 %arg) {
-; CHECK-LABEL: 'smul'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.smul.fix.i64(i64 undef, i64 undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.smul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.smul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.smul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.smul.fix.i32(i32 undef, i32 undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.smul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.smul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.smul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.smul.fix.i16(i16 undef, i16 undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.smul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.smul.fix.i8(i8 undef, i8 undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V32I8 = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V64I8 = call <64 x i8> @llvm.smul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSSE3-LABEL: 'smul'
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.smul.fix.i64(i64 undef, i64 undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.smul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4I64 = call <4 x i64> @llvm.smul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8I64 = call <8 x i64> @llvm.smul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I32 = call i32 @llvm.smul.fix.i32(i32 undef, i32 undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V4I32 = call <4 x i32> @llvm.smul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V8I32 = call <8 x i32> @llvm.smul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V16I32 = call <16 x i32> @llvm.smul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.smul.fix.i16(i16 undef, i16 undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V8I16 = call <8 x i16> @llvm.smul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.smul.fix.i8(i8 undef, i8 undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16I8 = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32I8 = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V64I8 = call <64 x i8> @llvm.smul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE42-LABEL: 'smul'
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.smul.fix.i64(i64 undef, i64 undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.smul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4I64 = call <4 x i64> @llvm.smul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8I64 = call <8 x i64> @llvm.smul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I32 = call i32 @llvm.smul.fix.i32(i32 undef, i32 undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V4I32 = call <4 x i32> @llvm.smul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %V8I32 = call <8 x i32> @llvm.smul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16I32 = call <16 x i32> @llvm.smul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.smul.fix.i16(i16 undef, i16 undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8I16 = call <8 x i16> @llvm.smul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.smul.fix.i8(i8 undef, i8 undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16I8 = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V32I8 = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V64I8 = call <64 x i8> @llvm.smul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX1-LABEL: 'smul'
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.smul.fix.i64(i64 undef, i64 undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.smul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V4I64 = call <4 x i64> @llvm.smul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %V8I64 = call <8 x i64> @llvm.smul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I32 = call i32 @llvm.smul.fix.i32(i32 undef, i32 undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V4I32 = call <4 x i32> @llvm.smul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 81 for instruction: %V8I32 = call <8 x i32> @llvm.smul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 166 for instruction: %V16I32 = call <16 x i32> @llvm.smul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.smul.fix.i16(i16 undef, i16 undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V8I16 = call <8 x i16> @llvm.smul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 78 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.smul.fix.i8(i8 undef, i8 undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V16I8 = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V32I8 = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 118 for instruction: %V64I8 = call <64 x i8> @llvm.smul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX2-LABEL: 'smul'
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.smul.fix.i64(i64 undef, i64 undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.smul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V4I64 = call <4 x i64> @llvm.smul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %V8I64 = call <8 x i64> @llvm.smul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I32 = call i32 @llvm.smul.fix.i32(i32 undef, i32 undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V4I32 = call <4 x i32> @llvm.smul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V8I32 = call <8 x i32> @llvm.smul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 70 for instruction: %V16I32 = call <16 x i32> @llvm.smul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.smul.fix.i16(i16 undef, i16 undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V8I16 = call <8 x i16> @llvm.smul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.smul.fix.i8(i8 undef, i8 undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V32I8 = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V64I8 = call <64 x i8> @llvm.smul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX512F-LABEL: 'smul'
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.smul.fix.i64(i64 undef, i64 undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.smul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V4I64 = call <4 x i64> @llvm.smul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 79 for instruction: %V8I64 = call <8 x i64> @llvm.smul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I32 = call i32 @llvm.smul.fix.i32(i32 undef, i32 undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V4I32 = call <4 x i32> @llvm.smul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V8I32 = call <8 x i32> @llvm.smul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V16I32 = call <16 x i32> @llvm.smul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.smul.fix.i16(i16 undef, i16 undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.smul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.smul.fix.i8(i8 undef, i8 undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V32I8 = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V64I8 = call <64 x i8> @llvm.smul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX512BW-LABEL: 'smul'
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.smul.fix.i64(i64 undef, i64 undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.smul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V4I64 = call <4 x i64> @llvm.smul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 79 for instruction: %V8I64 = call <8 x i64> @llvm.smul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I32 = call i32 @llvm.smul.fix.i32(i32 undef, i32 undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V4I32 = call <4 x i32> @llvm.smul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V8I32 = call <8 x i32> @llvm.smul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V16I32 = call <16 x i32> @llvm.smul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.smul.fix.i16(i16 undef, i16 undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.smul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.smul.fix.i8(i8 undef, i8 undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64I8 = call <64 x i8> @llvm.smul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX512DQ-LABEL: 'smul'
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.smul.fix.i64(i64 undef, i64 undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.smul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V4I64 = call <4 x i64> @llvm.smul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 79 for instruction: %V8I64 = call <8 x i64> @llvm.smul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I32 = call i32 @llvm.smul.fix.i32(i32 undef, i32 undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4I32 = call <4 x i32> @llvm.smul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call <8 x i32> @llvm.smul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16I32 = call <16 x i32> @llvm.smul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.smul.fix.i16(i16 undef, i16 undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.smul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.smul.fix.i8(i8 undef, i8 undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V32I8 = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V64I8 = call <64 x i8> @llvm.smul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'smul'
+; SLM-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.smul.fix.i64(i64 undef, i64 undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.smul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4I64 = call <4 x i64> @llvm.smul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8I64 = call <8 x i64> @llvm.smul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I32 = call i32 @llvm.smul.fix.i32(i32 undef, i32 undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V4I32 = call <4 x i32> @llvm.smul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 90 for instruction: %V8I32 = call <8 x i32> @llvm.smul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 184 for instruction: %V16I32 = call <16 x i32> @llvm.smul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.smul.fix.i16(i16 undef, i16 undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V8I16 = call <8 x i16> @llvm.smul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 70 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.smul.fix.i8(i8 undef, i8 undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16I8 = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V32I8 = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V64I8 = call <64 x i8> @llvm.smul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'smul'
+; GLM-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.smul.fix.i64(i64 undef, i64 undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.smul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4I64 = call <4 x i64> @llvm.smul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8I64 = call <8 x i64> @llvm.smul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I32 = call i32 @llvm.smul.fix.i32(i32 undef, i32 undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V4I32 = call <4 x i32> @llvm.smul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %V8I32 = call <8 x i32> @llvm.smul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16I32 = call <16 x i32> @llvm.smul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.smul.fix.i16(i16 undef, i16 undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8I16 = call <8 x i16> @llvm.smul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.smul.fix.i8(i8 undef, i8 undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16I8 = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V32I8 = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V64I8 = call <64 x i8> @llvm.smul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; BTVER2-LABEL: 'smul'
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.smul.fix.i64(i64 undef, i64 undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.smul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V4I64 = call <4 x i64> @llvm.smul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %V8I64 = call <8 x i64> @llvm.smul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I32 = call i32 @llvm.smul.fix.i32(i32 undef, i32 undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V4I32 = call <4 x i32> @llvm.smul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 81 for instruction: %V8I32 = call <8 x i32> @llvm.smul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 166 for instruction: %V16I32 = call <16 x i32> @llvm.smul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.smul.fix.i16(i16 undef, i16 undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V8I16 = call <8 x i16> @llvm.smul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 78 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.smul.fix.i8(i8 undef, i8 undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V16I8 = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V32I8 = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 118 for instruction: %V64I8 = call <64 x i8> @llvm.smul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = call i64 @llvm.smul.fix.i64(i64 undef, i64 undef, i32 3)
   %V2I64 = call <2 x i64> @llvm.smul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
@@ -95,24 +266,195 @@
 declare <64 x i8>  @llvm.umul.fix.v64i8(<64 x i8>, <64 x i8>, i32)
 
 define i32 @umul(i32 %arg) {
-; CHECK-LABEL: 'umul'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.umul.fix.i64(i64 undef, i64 undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.umul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.umul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.umul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.umul.fix.i32(i32 undef, i32 undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.umul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.umul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.umul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.umul.fix.i16(i16 undef, i16 undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.umul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.umul.fix.i8(i8 undef, i8 undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V32I8 = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V64I8 = call <64 x i8> @llvm.umul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSSE3-LABEL: 'umul'
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.umul.fix.i64(i64 undef, i64 undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.umul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4I64 = call <4 x i64> @llvm.umul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8I64 = call <8 x i64> @llvm.umul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.umul.fix.i32(i32 undef, i32 undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V4I32 = call <4 x i32> @llvm.umul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V8I32 = call <8 x i32> @llvm.umul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 120 for instruction: %V16I32 = call <16 x i32> @llvm.umul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.umul.fix.i16(i16 undef, i16 undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V8I16 = call <8 x i16> @llvm.umul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.umul.fix.i8(i8 undef, i8 undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16I8 = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V32I8 = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V64I8 = call <64 x i8> @llvm.umul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE42-LABEL: 'umul'
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.umul.fix.i64(i64 undef, i64 undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.umul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4I64 = call <4 x i64> @llvm.umul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8I64 = call <8 x i64> @llvm.umul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.umul.fix.i32(i32 undef, i32 undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V4I32 = call <4 x i32> @llvm.umul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %V8I32 = call <8 x i32> @llvm.umul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16I32 = call <16 x i32> @llvm.umul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.umul.fix.i16(i16 undef, i16 undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8I16 = call <8 x i16> @llvm.umul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.umul.fix.i8(i8 undef, i8 undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16I8 = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V32I8 = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V64I8 = call <64 x i8> @llvm.umul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX1-LABEL: 'umul'
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.umul.fix.i64(i64 undef, i64 undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.umul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V4I64 = call <4 x i64> @llvm.umul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %V8I64 = call <8 x i64> @llvm.umul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.umul.fix.i32(i32 undef, i32 undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V4I32 = call <4 x i32> @llvm.umul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 81 for instruction: %V8I32 = call <8 x i32> @llvm.umul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 166 for instruction: %V16I32 = call <16 x i32> @llvm.umul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.umul.fix.i16(i16 undef, i16 undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V8I16 = call <8 x i16> @llvm.umul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 78 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.umul.fix.i8(i8 undef, i8 undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V16I8 = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V32I8 = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 118 for instruction: %V64I8 = call <64 x i8> @llvm.umul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX2-LABEL: 'umul'
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.umul.fix.i64(i64 undef, i64 undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.umul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V4I64 = call <4 x i64> @llvm.umul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %V8I64 = call <8 x i64> @llvm.umul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.umul.fix.i32(i32 undef, i32 undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V4I32 = call <4 x i32> @llvm.umul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V8I32 = call <8 x i32> @llvm.umul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 70 for instruction: %V16I32 = call <16 x i32> @llvm.umul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.umul.fix.i16(i16 undef, i16 undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V8I16 = call <8 x i16> @llvm.umul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.umul.fix.i8(i8 undef, i8 undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V32I8 = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V64I8 = call <64 x i8> @llvm.umul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX512F-LABEL: 'umul'
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.umul.fix.i64(i64 undef, i64 undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.umul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V4I64 = call <4 x i64> @llvm.umul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 79 for instruction: %V8I64 = call <8 x i64> @llvm.umul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.umul.fix.i32(i32 undef, i32 undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V4I32 = call <4 x i32> @llvm.umul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V8I32 = call <8 x i32> @llvm.umul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V16I32 = call <16 x i32> @llvm.umul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.umul.fix.i16(i16 undef, i16 undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.umul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.umul.fix.i8(i8 undef, i8 undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V32I8 = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V64I8 = call <64 x i8> @llvm.umul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX512BW-LABEL: 'umul'
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.umul.fix.i64(i64 undef, i64 undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.umul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V4I64 = call <4 x i64> @llvm.umul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 79 for instruction: %V8I64 = call <8 x i64> @llvm.umul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.umul.fix.i32(i32 undef, i32 undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V4I32 = call <4 x i32> @llvm.umul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V8I32 = call <8 x i32> @llvm.umul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V16I32 = call <16 x i32> @llvm.umul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.umul.fix.i16(i16 undef, i16 undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.umul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.umul.fix.i8(i8 undef, i8 undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64I8 = call <64 x i8> @llvm.umul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX512DQ-LABEL: 'umul'
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.umul.fix.i64(i64 undef, i64 undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.umul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V4I64 = call <4 x i64> @llvm.umul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 79 for instruction: %V8I64 = call <8 x i64> @llvm.umul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.umul.fix.i32(i32 undef, i32 undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4I32 = call <4 x i32> @llvm.umul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call <8 x i32> @llvm.umul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16I32 = call <16 x i32> @llvm.umul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.umul.fix.i16(i16 undef, i16 undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.umul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.umul.fix.i8(i8 undef, i8 undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V32I8 = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V64I8 = call <64 x i8> @llvm.umul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'umul'
+; SLM-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.umul.fix.i64(i64 undef, i64 undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.umul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4I64 = call <4 x i64> @llvm.umul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8I64 = call <8 x i64> @llvm.umul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.umul.fix.i32(i32 undef, i32 undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V4I32 = call <4 x i32> @llvm.umul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 90 for instruction: %V8I32 = call <8 x i32> @llvm.umul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 184 for instruction: %V16I32 = call <16 x i32> @llvm.umul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.umul.fix.i16(i16 undef, i16 undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V8I16 = call <8 x i16> @llvm.umul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 70 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.umul.fix.i8(i8 undef, i8 undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16I8 = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V32I8 = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V64I8 = call <64 x i8> @llvm.umul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'umul'
+; GLM-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.umul.fix.i64(i64 undef, i64 undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.umul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4I64 = call <4 x i64> @llvm.umul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8I64 = call <8 x i64> @llvm.umul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.umul.fix.i32(i32 undef, i32 undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V4I32 = call <4 x i32> @llvm.umul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %V8I32 = call <8 x i32> @llvm.umul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16I32 = call <16 x i32> @llvm.umul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.umul.fix.i16(i16 undef, i16 undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8I16 = call <8 x i16> @llvm.umul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.umul.fix.i8(i8 undef, i8 undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16I8 = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V32I8 = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V64I8 = call <64 x i8> @llvm.umul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; BTVER2-LABEL: 'umul'
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = call i64 @llvm.umul.fix.i64(i64 undef, i64 undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call <2 x i64> @llvm.umul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V4I64 = call <4 x i64> @llvm.umul.fix.v4i64(<4 x i64> undef, <4 x i64> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %V8I64 = call <8 x i64> @llvm.umul.fix.v8i64(<8 x i64> undef, <8 x i64> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.umul.fix.i32(i32 undef, i32 undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V4I32 = call <4 x i32> @llvm.umul.fix.v4i32(<4 x i32> undef, <4 x i32> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 81 for instruction: %V8I32 = call <8 x i32> @llvm.umul.fix.v8i32(<8 x i32> undef, <8 x i32> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 166 for instruction: %V16I32 = call <16 x i32> @llvm.umul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.umul.fix.i16(i16 undef, i16 undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V8I16 = call <8 x i16> @llvm.umul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 78 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.umul.fix.i8(i8 undef, i8 undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V16I8 = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V32I8 = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 118 for instruction: %V64I8 = call <64 x i8> @llvm.umul.fix.v64i8(<64 x i8> undef, <64 x i8> undef, i32 3)
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = call i64 @llvm.umul.fix.i64(i64 undef, i64 undef, i32 3)
   %V2I64 = call <2 x i64> @llvm.umul.fix.v2i64(<2 x i64> undef, <2 x i64> undef, i32 3)