; 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=+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

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
;
  %F32 = fadd float undef, undef
  %V4F32 = fadd <4 x float> undef, undef
  %V8F32 = fadd <8 x float> undef, undef
  %V16F32 = fadd <16 x float> undef, undef

  %F64 = fadd double undef, undef
  %V2F64 = fadd <2 x double> undef, undef
  %V4F64 = fadd <4 x double> undef, undef
  %V8F64 = fadd <8 x double> undef, undef

  ret i32 undef
}

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
;
  %F32 = fsub float undef, undef
  %V4F32 = fsub <4 x float> undef, undef
  %V8F32 = fsub <8 x float> undef, undef
  %V16F32 = fsub <16 x float> undef, undef

  %F64 = fsub double undef, undef
  %V2F64 = fsub <2 x double> undef, undef
  %V4F64 = fsub <4 x double> undef, undef
  %V8F64 = fsub <8 x double> undef, undef

  ret i32 undef
}

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
;
  %F32 = fsub float -0.0, undef
  %V4F32 = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, undef
  %V8F32 = fsub <8 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, undef
  %V16F32 = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, undef

  %F64 = fsub double -0.0, undef
  %V2F64 = fsub <2 x double> <double -0.0, double -0.0>, undef
  %V4F64 = fsub <4 x double> <double -0.0, double -0.0, double -0.0, double -0.0>, undef
  %V8F64 = fsub <8 x double> <double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0>, undef

  ret i32 undef
}

define i32 @fneg(i32 %arg) {
; SSE1-LABEL: 'fneg'
; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fneg float undef
; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fneg <4 x float> undef
; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fneg <8 x float> undef
; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fneg <16 x float> undef
; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fneg double undef
; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fneg <2 x double> undef
; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fneg <4 x double> undef
; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = fneg <8 x double> undef
; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; SSE2-LABEL: 'fneg'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fneg float undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fneg <4 x float> undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fneg <8 x float> undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fneg <16 x float> undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fneg double undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fneg <2 x double> undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fneg <4 x double> undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fneg <8 x double> undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; AVX-LABEL: 'fneg'
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fneg float undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fneg <4 x float> undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fneg <8 x float> undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F32 = fneg <16 x float> undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fneg double undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fneg <2 x double> undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fneg <4 x double> undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F64 = fneg <8 x double> undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; AVX512-LABEL: 'fneg'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fneg float undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fneg <4 x float> undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fneg <8 x float> undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fneg <16 x float> undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fneg double undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fneg <2 x double> undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fneg <4 x double> undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fneg <8 x double> undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
  %F32 = fneg float undef
  %V4F32 = fneg <4 x float> undef
  %V8F32 = fneg <8 x float> undef
  %V16F32 = fneg <16 x float> undef

  %F64 = fneg double undef
  %V2F64 = fneg <2 x double> undef
  %V4F64 = fneg <4 x double> undef
  %V8F64 = fneg <8 x double> undef

  ret i32 undef
}

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
;
  %F32 = fmul float undef, undef
  %V4F32 = fmul <4 x float> undef, undef
  %V8F32 = fmul <8 x float> undef, undef
  %V16F32 = fmul <16 x float> undef, undef

  %F64 = fmul double undef, undef
  %V2F64 = fmul <2 x double> undef, undef
  %V4F64 = fmul <4 x double> undef, undef
  %V8F64 = fmul <8 x double> undef, undef

  ret i32 undef
}

define i32 @fdiv(i32 %arg) {
; SSE1-LABEL: 'fdiv'
; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fdiv float undef, undef
; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fdiv <4 x float> undef, undef
; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fdiv <8 x float> undef, undef
; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fdiv <16 x float> undef, undef
; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fdiv double undef, undef
; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fdiv <2 x double> undef, undef
; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fdiv <4 x double> undef, undef
; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = fdiv <8 x double> undef, undef
; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; SSE2-LABEL: 'fdiv'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fdiv float undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fdiv <4 x float> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fdiv <8 x float> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fdiv <16 x float> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fdiv double undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fdiv <2 x double> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fdiv <4 x double> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fdiv <8 x double> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; AVX-LABEL: 'fdiv'
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fdiv float undef, undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fdiv <4 x float> undef, undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fdiv <8 x float> undef, undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F32 = fdiv <16 x float> undef, undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fdiv double undef, undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fdiv <2 x double> undef, undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fdiv <4 x double> undef, undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F64 = fdiv <8 x double> undef, undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; AVX512-LABEL: 'fdiv'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fdiv float undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fdiv <4 x float> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fdiv <8 x float> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = fdiv <16 x float> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fdiv double undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fdiv <2 x double> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fdiv <4 x double> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = fdiv <8 x double> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
  %F32 = fdiv float undef, undef
  %V4F32 = fdiv <4 x float> undef, undef
  %V8F32 = fdiv <8 x float> undef, undef
  %V16F32 = fdiv <16 x float> undef, undef

  %F64 = fdiv double undef, undef
  %V2F64 = fdiv <2 x double> undef, undef
  %V4F64 = fdiv <4 x double> undef, undef
  %V8F64 = fdiv <8 x double> undef, undef

  ret i32 undef
}

define i32 @frem(i32 %arg) {
; CHECK-LABEL: 'frem'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %F32 = frem float undef, undef
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = frem <4 x float> undef, undef
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = frem <8 x float> undef, undef
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = frem <16 x float> undef, undef
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %F64 = frem double undef, undef
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = frem <2 x double> undef, undef
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = frem <4 x double> undef, undef
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = frem <8 x double> undef, undef
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
  %F32 = frem float undef, undef
  %V4F32 = frem <4 x float> undef, undef
  %V8F32 = frem <8 x float> undef, undef
  %V16F32 = frem <16 x float> undef, undef

  %F64 = frem double undef, undef
  %V2F64 = frem <2 x double> undef, undef
  %V4F64 = frem <4 x double> undef, undef
  %V8F64 = frem <8 x double> undef, undef

  ret i32 undef
}

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 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 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 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
;
; 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 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 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
;
  %F32 = call float @llvm.sqrt.f32(float undef)
  %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
  %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
  %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)

  %F64 = call double @llvm.sqrt.f64(double undef)
  %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
  %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
  %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)

  ret i32 undef
}

define i32 @fabs(i32 %arg) {
; 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 1 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 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)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.fabs.f64(double undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; AVX512-LABEL: 'fabs'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.fabs.f32(float undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F32 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.fabs.f64(double undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
; 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
;
  %F32 = call float @llvm.fabs.f32(float undef)
  %V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
  %V8F32 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
  %V16F32 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)

  %F64 = call double @llvm.fabs.f64(double undef)
  %V2F64 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
  %V4F64 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
  %V8F64 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)

  ret i32 undef
}

define i32 @fcopysign(i32 %arg) {
; 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 1 for instruction: %F64 = call double @llvm.copysign.f64(double undef, double undef)
; SSE1-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)
; SSE1-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)
; SSE1-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)
; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 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 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)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = call <16 x float> @llvm.copysign.v16f32(<16 x float> undef, <16 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.copysign.f64(double undef, double undef)
; AVX-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)
; AVX-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)
; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; AVX512-LABEL: 'fcopysign'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.copysign.f32(float undef, float undef)
; AVX512-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)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F32 = call <16 x float> @llvm.copysign.v16f32(<16 x float> undef, <16 x float> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.copysign.f64(double undef, double undef)
; AVX512-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)
; 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
;
  %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)
  %V8F32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
  %V16F32 = call <16 x float> @llvm.copysign.v16f32(<16 x float> undef, <16 x float> undef)

  %F64 = call double @llvm.copysign.f64(double undef, double undef)
  %V2F64 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
  %V4F64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
  %V8F64 = call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)

  ret i32 undef
}

define i32 @fma(i32 %arg) {
; SSE1-LABEL: 'fma'
; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
; SSE1-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)
; SSE1-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)
; SSE1-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)
; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 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 4 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 8 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 1 for instruction: ret i32 undef
;
; SSE2-LABEL: 'fma'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
; SSE2-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)
; SSE2-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)
; SSE2-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)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
; SSE2-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)
; SSE2-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)
; 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
;
; 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)
; AVX-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V16F32 = call <16 x float> @llvm.fma.v16f32(<16 x float> undef, <16 x float> undef, <16 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
; AVX-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)
; AVX-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V8F64 = call <8 x double> @llvm.fma.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; AVX512-LABEL: 'fma'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = call <16 x float> @llvm.fma.v16f32(<16 x float> undef, <16 x float> undef, <16 x float> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
; 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
;
  %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)
  %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
  %V16F32 = call <16 x float> @llvm.fma.v16f32(<16 x float> undef, <16 x float> undef, <16 x float> undef)

  %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
  %V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
  %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
  %V8F64 = call <8 x double> @llvm.fma.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)

  ret i32 undef
}

declare float @llvm.sqrt.f32(float)
declare <4 x float> @llvm.sqrt.v4f32(<4 x float>)
declare <8 x float> @llvm.sqrt.v8f32(<8 x float>)
declare <16 x float> @llvm.sqrt.v16f32(<16 x float>)

declare double @llvm.sqrt.f64(double)
declare <2 x double> @llvm.sqrt.v2f64(<2 x double>)
declare <4 x double> @llvm.sqrt.v4f64(<4 x double>)
declare <8 x double> @llvm.sqrt.v8f64(<8 x double>)

declare float @llvm.fabs.f32(float)
declare <4 x float> @llvm.fabs.v4f32(<4 x float>)
declare <8 x float> @llvm.fabs.v8f32(<8 x float>)
declare <16 x float> @llvm.fabs.v16f32(<16 x float>)

declare double @llvm.fabs.f64(double)
declare <2 x double> @llvm.fabs.v2f64(<2 x double>)
declare <4 x double> @llvm.fabs.v4f64(<4 x double>)
declare <8 x double> @llvm.fabs.v8f64(<8 x double>)

declare float @llvm.copysign.f32(float, float)
declare <4 x float> @llvm.copysign.v4f32(<4 x float>, <4 x float>)
declare <8 x float> @llvm.copysign.v8f32(<8 x float>, <8 x float>)
declare <16 x float> @llvm.copysign.v16f32(<16 x float>, <16 x float>)

declare double @llvm.copysign.f64(double, double)
declare <2 x double> @llvm.copysign.v2f64(<2 x double>, <2 x double>)
declare <4 x double> @llvm.copysign.v4f64(<4 x double>, <4 x double>)
declare <8 x double> @llvm.copysign.v8f64(<8 x double>, <8 x double>)

declare float @llvm.fma.f32(float, float, float)
declare <4 x float> @llvm.fma.v4f32(<4 x float>, <4 x float>, <4 x float>)
declare <8 x float> @llvm.fma.v8f32(<8 x float>, <8 x float>, <8 x float>)
declare <16 x float> @llvm.fma.v16f32(<16 x float>, <16 x float>, <16 x float>)

declare double @llvm.fma.f64(double, double, double)
declare <2 x double> @llvm.fma.v2f64(<2 x double>, <2 x double>, <2 x double>)
declare <4 x double> @llvm.fma.v4f64(<4 x double>, <4 x double>, <4 x double>)
declare <8 x double> @llvm.fma.v8f64(<8 x double>, <8 x double>, <8 x double>)