[CostModel][X86] Add SSE1 fp cost tests

llvm-svn: 350401

diff --git a/llvm/test/Analysis/CostModel/X86/arith-fp.ll b/llvm/test/Analysis/CostModel/X86/arith-fp.ll
index a6b5cf6..bd62bd9 100644 (file)
--- a/llvm/test/Analysis/CostModel/X86/arith-fp.ll
+++ b/llvm/test/Analysis/CostModel/X86/arith-fp.ll
@@ -1,4 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -enable-no-nans-fp-math  -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mattr=-sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE1
 ; RUN: opt < %s -enable-no-nans-fp-math  -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
 ; RUN: opt < %s -enable-no-nans-fp-math  -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
 ; RUN: opt < %s -enable-no-nans-fp-math  -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
@@ -14,6 +15,17 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f3
 target triple = "x86_64-apple-macosx10.8.0"
 
 define i32 @fadd(i32 %arg) {
+; SSE1-LABEL: 'fadd'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = fadd float undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fadd <4 x float> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fadd <8 x float> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = fadd <16 x float> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = fadd double undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = fadd <2 x double> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = fadd <4 x double> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = fadd <8 x double> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
 ; SSE2-LABEL: 'fadd'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = fadd float undef, undef
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fadd <4 x float> undef, undef
@@ -116,6 +128,17 @@ define i32 @fadd(i32 %arg) {
 }
 
 define i32 @fsub(i32 %arg) {
+; SSE1-LABEL: 'fsub'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = fsub float undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fsub <4 x float> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fsub <8 x float> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = fsub <16 x float> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = fsub double undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = fsub <2 x double> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = fsub <4 x double> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = fsub <8 x double> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
 ; SSE2-LABEL: 'fsub'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = fsub float undef, undef
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fsub <4 x float> undef, undef
@@ -218,6 +241,17 @@ define i32 @fsub(i32 %arg) {
 }
 
 define i32 @fmul(i32 %arg) {
+; SSE1-LABEL: 'fmul'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = fmul float undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fmul <4 x float> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fmul <8 x float> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = fmul <16 x float> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = fmul double undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = fmul <2 x double> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = fmul <4 x double> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = fmul <8 x double> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
 ; SSE2-LABEL: 'fmul'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = fmul float undef, undef
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fmul <4 x float> undef, undef
@@ -320,6 +354,17 @@ define i32 @fmul(i32 %arg) {
 }
 
 define i32 @fdiv(i32 %arg) {
+; SSE1-LABEL: 'fdiv'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %F32 = fdiv float undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V4F32 = fdiv <4 x float> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V8F32 = fdiv <8 x float> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V16F32 = fdiv <16 x float> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = fdiv double undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = fdiv <2 x double> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = fdiv <4 x double> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = fdiv <8 x double> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
 ; SSE2-LABEL: 'fdiv'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %F32 = fdiv float undef, undef
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V4F32 = fdiv <4 x float> undef, undef
@@ -422,16 +467,38 @@ define i32 @fdiv(i32 %arg) {
 }
 
 define i32 @frem(i32 %arg) {
-; SSE-LABEL: 'frem'
-; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = frem float undef, undef
-; SSE-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F32 = frem <4 x float> undef, undef
-; SSE-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F32 = frem <8 x float> undef, undef
-; SSE-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V16F32 = frem <16 x float> undef, undef
-; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = frem double undef, undef
-; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = frem <2 x double> undef, undef
-; SSE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4F64 = frem <4 x double> undef, undef
-; SSE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8F64 = frem <8 x double> undef, undef
-; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSE1-LABEL: 'frem'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = frem float undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F32 = frem <4 x float> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F32 = frem <8 x float> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V16F32 = frem <16 x float> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = frem double undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = frem <2 x double> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = frem <4 x double> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = frem <8 x double> undef, undef
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE2-LABEL: 'frem'
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = frem float undef, undef
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F32 = frem <4 x float> undef, undef
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F32 = frem <8 x float> undef, undef
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V16F32 = frem <16 x float> undef, undef
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = frem double undef, undef
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = frem <2 x double> undef, undef
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4F64 = frem <4 x double> undef, undef
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8F64 = frem <8 x double> undef, undef
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE42-LABEL: 'frem'
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = frem float undef, undef
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F32 = frem <4 x float> undef, undef
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F32 = frem <8 x float> undef, undef
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V16F32 = frem <16 x float> undef, undef
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = frem double undef, undef
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = frem <2 x double> undef, undef
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4F64 = frem <4 x double> undef, undef
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8F64 = frem <8 x double> undef, undef
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX-LABEL: 'frem'
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = frem float undef, undef
@@ -502,6 +569,17 @@ define i32 @frem(i32 %arg) {
 }
 
 define i32 @fsqrt(i32 %arg) {
+; SSE1-LABEL: 'fsqrt'
+; 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 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 0 for instruction: ret i32 undef
+;
 ; SSE2-LABEL: 'fsqrt'
 ; 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)
@@ -604,16 +682,38 @@ define i32 @fsqrt(i32 %arg) {
 }
 
 define i32 @fabs(i32 %arg) {
-; SSE-LABEL: 'fabs'
-; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.fabs.f32(float undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.fabs.f64(double undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSE1-LABEL: 'fabs'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.fabs.f32(float undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.fabs.f64(double undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE2-LABEL: 'fabs'
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.fabs.f32(float undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.fabs.f64(double undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
+; 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 0 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 0 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)
@@ -684,16 +784,38 @@ define i32 @fabs(i32 %arg) {
 }
 
 define i32 @fcopysign(i32 %arg) {
-; SSE-LABEL: 'fcopysign'
-; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.copysign.f32(float undef, float undef)
-; SSE-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)
-; SSE-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)
-; SSE-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)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.copysign.f64(double undef, double undef)
-; SSE-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)
-; SSE-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)
-; SSE-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)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSE1-LABEL: 'fcopysign'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.copysign.f32(float undef, float undef)
+; SSE1-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)
+; SSE1-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)
+; SSE1-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)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.copysign.f64(double undef, double undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V2F64 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V4F64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V8F64 = call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE2-LABEL: 'fcopysign'
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.copysign.f32(float undef, float undef)
+; SSE2-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)
+; SSE2-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)
+; SSE2-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)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.copysign.f64(double undef, double undef)
+; SSE2-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)
+; SSE2-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)
+; 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 0 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 0 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)
@@ -764,16 +886,38 @@ define i32 @fcopysign(i32 %arg) {
 }
 
 define i32 @fma(i32 %arg) {
-; SSE-LABEL: 'fma'
-; SSE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %V16F32 = call <16 x float> @llvm.fma.v16f32(<16 x float> undef, <16 x float> undef, <16 x float> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %V8F64 = call <8 x double> @llvm.fma.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSE1-LABEL: 'fma'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %V16F32 = call <16 x float> @llvm.fma.v16f32(<16 x float> undef, <16 x float> undef, <16 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V8F64 = call <8 x double> @llvm.fma.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE2-LABEL: 'fma'
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %V16F32 = call <16 x float> @llvm.fma.v16f32(<16 x float> undef, <16 x float> undef, <16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 84 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 0 for instruction: ret i32 undef
+;
+; SSE42-LABEL: 'fma'
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 43 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 86 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 172 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 10 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 21 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 42 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 84 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 0 for instruction: ret i32 undef
 ;
 ; AVX-LABEL: 'fma'
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)