[llvm] 3c4391b - Revert rG15de7aaae52ef4be9f9ff3b130804e5b5ccd29f4 "[CostModel][X86] Add CodeSize/SizeLatency handling for fadd/fsub/fmul/fsqrt ops"

Simon Pilgrim via llvm-commits llvm-commits at lists.llvm.org
Sun Aug 21 08:52:03 PDT 2022


Author: Simon Pilgrim
Date: 2022-08-21T16:51:45+01:00
New Revision: 3c4391b4bb1f2bff37fa3c4b7255f7feeaa5b90a

URL: https://github.com/llvm/llvm-project/commit/3c4391b4bb1f2bff37fa3c4b7255f7feeaa5b90a
DIFF: https://github.com/llvm/llvm-project/commit/3c4391b4bb1f2bff37fa3c4b7255f7feeaa5b90a.diff

LOG: Revert rG15de7aaae52ef4be9f9ff3b130804e5b5ccd29f4 "[CostModel][X86] Add CodeSize/SizeLatency handling for fadd/fsub/fmul/fsqrt ops"

This is unintentionally affecting some backend tests

Added: 
    

Modified: 
    llvm/lib/Target/X86/X86TargetTransformInfo.cpp
    llvm/test/Analysis/CostModel/X86/arith-fp-codesize.ll
    llvm/test/Analysis/CostModel/X86/arith-fp-sizelatency.ll
    llvm/test/Analysis/CostModel/X86/intrinsic-cost-kinds.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index eaf67512ad63..63a6dce6caaa 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -286,22 +286,10 @@ InstructionCost X86TTIImpl::getArithmeticInstrCost(
   }
 
   // TODO: Handle more cost kinds.
-  if (CostKind != TTI::TCK_RecipThroughput) {
-    // Handle some basic single instruction code size cases.
-    if (CostKind == TTI::TCK_CodeSize || CostKind == TTI::TCK_SizeAndLatency) {
-      switch (ISD) {
-      case ISD::FADD:
-      case ISD::FSUB:
-      case ISD::FMUL:
-        return LT.first;
-        break;
-      }
-    }
-
+  if (CostKind != TTI::TCK_RecipThroughput)
     return BaseT::getArithmeticInstrCost(Opcode, Ty, CostKind, Op1Info, Op2Info,
                                          Opd1PropInfo, Opd2PropInfo, Args,
                                          CxtI);
-  }
 
   static const CostTblEntry GLMCostTable[] = {
     { ISD::FDIV,  MVT::f32,   18 }, // divss
@@ -3439,10 +3427,6 @@ X86TTIImpl::getTypeBasedIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
       return LT.first * Cost;
     }
 
-    // FSQRT is a single instruction.
-    if (ISD == ISD::FSQRT && CostKind == TTI::TCK_CodeSize)
-      return LT.first;
-
     auto adjustTableCost = [](const CostTblEntry &Entry,
                               InstructionCost LegalizationCost,
                               FastMathFlags FMF) {

diff  --git a/llvm/test/Analysis/CostModel/X86/arith-fp-codesize.ll b/llvm/test/Analysis/CostModel/X86/arith-fp-codesize.ll
index 15b423137da4..5dccd4d59373 100644
--- a/llvm/test/Analysis/CostModel/X86/arith-fp-codesize.ll
+++ b/llvm/test/Analysis/CostModel/X86/arith-fp-codesize.ll
@@ -1,60 +1,27 @@
 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=x86_64-- -mattr=-sse2 | FileCheck %s --check-prefixes=CHECK,SSE1
 ; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=x86_64-- -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE2
-; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=x86_64-- -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE2
-; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=x86_64-- -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX
-; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=x86_64-- -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX
+; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=x86_64-- -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE42
+; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=x86_64-- -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
+; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=x86_64-- -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
 ; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=x86_64-- -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512
 ; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=x86_64-- -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512
 ;
-; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=x86_64-- -mcpu=slm | FileCheck %s --check-prefixes=CHECK,SSE2
-; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=x86_64-- -mcpu=goldmont | FileCheck %s --check-prefixes=CHECK,SSE2
-; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=x86_64-- -mcpu=btver2 | FileCheck %s --check-prefixes=CHECK,AVX
+; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=x86_64-- -mcpu=slm | FileCheck %s --check-prefixes=CHECK,SLM
+; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=x86_64-- -mcpu=goldmont | FileCheck %s --check-prefixes=CHECK,GLM
+; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=x86_64-- -mcpu=btver2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
 
 define i32 @fadd(i32 %arg) {
-; SSE1-LABEL: 'fadd'
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fadd <8 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fadd <16 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fadd <2 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fadd <4 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = fadd <8 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE2-LABEL: 'fadd'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fadd <8 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fadd <16 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fadd <2 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fadd <4 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fadd <8 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX-LABEL: 'fadd'
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fadd <8 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F32 = fadd <16 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fadd <2 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fadd <4 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F64 = fadd <8 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512-LABEL: 'fadd'
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fadd <8 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fadd <16 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fadd <2 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fadd <4 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fadd <8 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fadd'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fadd <8 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fadd <16 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fadd <2 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fadd <4 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fadd <8 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %F32 = fadd float undef, undef
   %V4F32 = fadd <4 x float> undef, undef
@@ -70,49 +37,16 @@ define i32 @fadd(i32 %arg) {
 }
 
 define i32 @fsub(i32 %arg) {
-; SSE1-LABEL: 'fsub'
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fsub <16 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fsub <2 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fsub <4 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = fsub <8 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE2-LABEL: 'fsub'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fsub <16 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fsub <4 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fsub <8 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX-LABEL: 'fsub'
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fsub <8 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F32 = fsub <16 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fsub <4 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F64 = fsub <8 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512-LABEL: 'fsub'
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fsub <8 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fsub <16 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fsub <4 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fsub <8 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fsub'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fsub <8 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fsub <16 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fsub <4 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fsub <8 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %F32 = fsub float undef, undef
   %V4F32 = fsub <4 x float> undef, undef
@@ -128,49 +62,16 @@ define i32 @fsub(i32 %arg) {
 }
 
 define i32 @fneg_idiom(i32 %arg) {
-; SSE1-LABEL: 'fneg_idiom'
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float -0.000000e+00, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double -0.000000e+00, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE2-LABEL: 'fneg_idiom'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float -0.000000e+00, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double -0.000000e+00, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX-LABEL: 'fneg_idiom'
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float -0.000000e+00, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F32 = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double -0.000000e+00, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F64 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512-LABEL: 'fneg_idiom'
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float -0.000000e+00, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double -0.000000e+00, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fneg_idiom'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float -0.000000e+00, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double -0.000000e+00, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %F32 = fsub float -0.0, undef
   %V4F32 = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, undef
@@ -211,49 +112,16 @@ define i32 @fneg(i32 %arg) {
 }
 
 define i32 @fmul(i32 %arg) {
-; SSE1-LABEL: 'fmul'
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fmul float undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fmul <4 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fmul <8 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fmul <16 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fmul double undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fmul <2 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fmul <4 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = fmul <8 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE2-LABEL: 'fmul'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fmul float undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fmul <4 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fmul <8 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fmul <16 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fmul double undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fmul <2 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fmul <4 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fmul <8 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX-LABEL: 'fmul'
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fmul float undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fmul <4 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fmul <8 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F32 = fmul <16 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fmul double undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fmul <2 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fmul <4 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F64 = fmul <8 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512-LABEL: 'fmul'
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fmul float undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fmul <4 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fmul <8 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fmul <16 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fmul double undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fmul <2 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fmul <4 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fmul <8 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fmul'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fmul float undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fmul <4 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fmul <8 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fmul <16 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fmul double undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fmul <2 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fmul <4 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fmul <8 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %F32 = fmul float undef, undef
   %V4F32 = fmul <4 x float> undef, undef
@@ -320,48 +188,92 @@ define i32 @frem(i32 %arg) {
 
 define i32 @fsqrt(i32 %arg) {
 ; SSE1-LABEL: 'fsqrt'
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
 ; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
 ; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
 ; SSE2-LABEL: 'fsqrt'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
-; AVX-LABEL: 'fsqrt'
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; SSE42-LABEL: 'fsqrt'
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX1-LABEL: 'fsqrt'
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX2-LABEL: 'fsqrt'
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'fsqrt'
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'fsqrt'
+; SLM-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 70 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 280 for instruction: %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'fsqrt'
+; GLM-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 148 for instruction: %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 67 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 134 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 268 for instruction: %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %F32 = call float @llvm.sqrt.f32(float undef)
   %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
@@ -399,6 +311,17 @@ define i32 @fabs(i32 %arg) {
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
+; SSE42-LABEL: 'fabs'
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.fabs.f32(float undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.fabs.f64(double undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
 ; AVX-LABEL: 'fabs'
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.fabs.f32(float undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
@@ -420,6 +343,28 @@ define i32 @fabs(i32 %arg) {
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F64 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'fabs'
+; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.fabs.f32(float undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.fabs.f64(double undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'fabs'
+; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.fabs.f32(float undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.fabs.f64(double undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %F32 = call float @llvm.fabs.f32(float undef)
   %V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
@@ -457,6 +402,17 @@ define i32 @fcopysign(i32 %arg) {
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
+; SSE42-LABEL: 'fcopysign'
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.copysign.f32(float undef, float undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.copysign.v16f32(<16 x float> undef, <16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.copysign.f64(double undef, double undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
 ; AVX-LABEL: 'fcopysign'
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.copysign.f32(float undef, float undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
@@ -478,6 +434,28 @@ define i32 @fcopysign(i32 %arg) {
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F64 = call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'fcopysign'
+; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.copysign.f32(float undef, float undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.copysign.v16f32(<16 x float> undef, <16 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.copysign.f64(double undef, double undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'fcopysign'
+; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.copysign.f32(float undef, float undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.copysign.v16f32(<16 x float> undef, <16 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.copysign.f64(double undef, double undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %F32 = call float @llvm.copysign.f32(float undef, float undef)
   %V4F32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
@@ -515,6 +493,17 @@ define i32 @fma(i32 %arg) {
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8F64 = call <8 x double> @llvm.fma.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
+; SSE42-LABEL: 'fma'
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V16F32 = call <16 x float> @llvm.fma.v16f32(<16 x float> undef, <16 x float> undef, <16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8F64 = call <8 x double> @llvm.fma.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
 ; AVX-LABEL: 'fma'
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
@@ -536,6 +525,28 @@ define i32 @fma(i32 %arg) {
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = call <8 x double> @llvm.fma.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'fma'
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V16F32 = call <16 x float> @llvm.fma.v16f32(<16 x float> undef, <16 x float> undef, <16 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8F64 = call <8 x double> @llvm.fma.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'fma'
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V16F32 = call <16 x float> @llvm.fma.v16f32(<16 x float> undef, <16 x float> undef, <16 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8F64 = call <8 x double> @llvm.fma.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
   %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)

diff  --git a/llvm/test/Analysis/CostModel/X86/arith-fp-sizelatency.ll b/llvm/test/Analysis/CostModel/X86/arith-fp-sizelatency.ll
index 0a73faaf2d39..bbeff8a8f852 100644
--- a/llvm/test/Analysis/CostModel/X86/arith-fp-sizelatency.ll
+++ b/llvm/test/Analysis/CostModel/X86/arith-fp-sizelatency.ll
@@ -12,82 +12,16 @@
 ; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=size-latency -mtriple=x86_64-- -mcpu=btver2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
 
 define i32 @fadd(i32 %arg) {
-; SSE1-LABEL: 'fadd'
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fadd <8 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fadd <16 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fadd <2 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fadd <4 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = fadd <8 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE2-LABEL: 'fadd'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fadd <8 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fadd <16 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fadd <2 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fadd <4 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fadd <8 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE42-LABEL: 'fadd'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fadd <8 x float> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fadd <16 x float> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fadd <2 x double> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fadd <4 x double> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fadd <8 x double> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX-LABEL: 'fadd'
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fadd <8 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F32 = fadd <16 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fadd <2 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fadd <4 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F64 = fadd <8 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512-LABEL: 'fadd'
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fadd <8 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fadd <16 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fadd <2 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fadd <4 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fadd <8 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SLM-LABEL: 'fadd'
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fadd <8 x float> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fadd <16 x float> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fadd <2 x double> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fadd <4 x double> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fadd <8 x double> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; GLM-LABEL: 'fadd'
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fadd <8 x float> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fadd <16 x float> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fadd <2 x double> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fadd <4 x double> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fadd <8 x double> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fadd'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fadd <8 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fadd <16 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fadd <2 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fadd <4 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fadd <8 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %F32 = fadd float undef, undef
   %V4F32 = fadd <4 x float> undef, undef
@@ -103,82 +37,16 @@ define i32 @fadd(i32 %arg) {
 }
 
 define i32 @fsub(i32 %arg) {
-; SSE1-LABEL: 'fsub'
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fsub <16 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fsub <2 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fsub <4 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = fsub <8 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE2-LABEL: 'fsub'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fsub <16 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fsub <4 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fsub <8 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE42-LABEL: 'fsub'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fsub <16 x float> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fsub <4 x double> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fsub <8 x double> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX-LABEL: 'fsub'
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fsub <8 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F32 = fsub <16 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fsub <4 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F64 = fsub <8 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512-LABEL: 'fsub'
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fsub <8 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fsub <16 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fsub <4 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fsub <8 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SLM-LABEL: 'fsub'
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fsub <16 x float> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fsub <4 x double> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fsub <8 x double> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; GLM-LABEL: 'fsub'
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fsub <16 x float> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fsub <4 x double> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fsub <8 x double> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fsub'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fsub <8 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fsub <16 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fsub <4 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fsub <8 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %F32 = fsub float undef, undef
   %V4F32 = fsub <4 x float> undef, undef
@@ -194,82 +62,16 @@ define i32 @fsub(i32 %arg) {
 }
 
 define i32 @fneg_idiom(i32 %arg) {
-; SSE1-LABEL: 'fneg_idiom'
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float -0.000000e+00, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double -0.000000e+00, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE2-LABEL: 'fneg_idiom'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float -0.000000e+00, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double -0.000000e+00, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE42-LABEL: 'fneg_idiom'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float -0.000000e+00, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double -0.000000e+00, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX-LABEL: 'fneg_idiom'
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float -0.000000e+00, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F32 = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double -0.000000e+00, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F64 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512-LABEL: 'fneg_idiom'
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float -0.000000e+00, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double -0.000000e+00, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SLM-LABEL: 'fneg_idiom'
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float -0.000000e+00, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double -0.000000e+00, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; GLM-LABEL: 'fneg_idiom'
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float -0.000000e+00, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double -0.000000e+00, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fneg_idiom'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float -0.000000e+00, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double -0.000000e+00, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %F32 = fsub float -0.0, undef
   %V4F32 = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, undef
@@ -310,82 +112,16 @@ define i32 @fneg(i32 %arg) {
 }
 
 define i32 @fmul(i32 %arg) {
-; SSE1-LABEL: 'fmul'
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fmul float undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fmul <4 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fmul <8 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fmul <16 x float> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fmul double undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fmul <2 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fmul <4 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = fmul <8 x double> undef, undef
-; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE2-LABEL: 'fmul'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fmul float undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fmul <4 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fmul <8 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fmul <16 x float> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fmul double undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fmul <2 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fmul <4 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fmul <8 x double> undef, undef
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE42-LABEL: 'fmul'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fmul float undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fmul <4 x float> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fmul <8 x float> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fmul <16 x float> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fmul double undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fmul <2 x double> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fmul <4 x double> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fmul <8 x double> undef, undef
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX-LABEL: 'fmul'
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fmul float undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fmul <4 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fmul <8 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F32 = fmul <16 x float> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fmul double undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fmul <2 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fmul <4 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F64 = fmul <8 x double> undef, undef
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512-LABEL: 'fmul'
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fmul float undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fmul <4 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fmul <8 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fmul <16 x float> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fmul double undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fmul <2 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fmul <4 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fmul <8 x double> undef, undef
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SLM-LABEL: 'fmul'
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fmul float undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fmul <4 x float> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fmul <8 x float> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fmul <16 x float> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fmul double undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fmul <2 x double> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fmul <4 x double> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fmul <8 x double> undef, undef
-; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; GLM-LABEL: 'fmul'
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fmul float undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fmul <4 x float> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fmul <8 x float> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fmul <16 x float> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fmul double undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fmul <2 x double> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fmul <4 x double> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fmul <8 x double> undef, undef
-; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fmul'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fmul float undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fmul <4 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fmul <8 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fmul <16 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fmul double undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fmul <2 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fmul <4 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fmul <8 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %F32 = fmul float undef, undef
   %V4F32 = fmul <4 x float> undef, undef

diff  --git a/llvm/test/Analysis/CostModel/X86/intrinsic-cost-kinds.ll b/llvm/test/Analysis/CostModel/X86/intrinsic-cost-kinds.ll
index 70de98a6f602..8f96c850809c 100644
--- a/llvm/test/Analysis/CostModel/X86/intrinsic-cost-kinds.ll
+++ b/llvm/test/Analysis/CostModel/X86/intrinsic-cost-kinds.ll
@@ -139,12 +139,12 @@ define void @fmuladd(float %a, float %b, float %c, <16 x float> %va, <16 x float
 ;
 ; SIZE-LABEL: 'fmuladd'
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %s = call float @llvm.fmuladd.f32(float %a, float %b, float %c)
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v = call <16 x float> @llvm.fmuladd.v16f32(<16 x float> %va, <16 x float> %vb, <16 x float> %vc)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v = call <16 x float> @llvm.fmuladd.v16f32(<16 x float> %va, <16 x float> %vb, <16 x float> %vc)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE_LATE-LABEL: 'fmuladd'
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %s = call float @llvm.fmuladd.f32(float %a, float %b, float %c)
-; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v = call <16 x float> @llvm.fmuladd.v16f32(<16 x float> %va, <16 x float> %vb, <16 x float> %vc)
+; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v = call <16 x float> @llvm.fmuladd.v16f32(<16 x float> %va, <16 x float> %vb, <16 x float> %vc)
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   %s = call float @llvm.fmuladd.f32(float %a, float %b, float %c)


        


More information about the llvm-commits mailing list