; 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,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
; RUN: opt < %s -enable-no-nans-fp-math  -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
; RUN: opt < %s -enable-no-nans-fp-math  -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
; RUN: opt < %s -enable-no-nans-fp-math  -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BW
;
; RUN: opt < %s -enable-no-nans-fp-math  -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=slm | FileCheck %s --check-prefixes=SLM
; RUN: opt < %s -enable-no-nans-fp-math  -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=goldmont | FileCheck %s --check-prefixes=GLM
; RUN: opt < %s -enable-no-nans-fp-math  -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=btver2 | FileCheck %s --check-prefixes=BTVER2

target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.8.0"

define i32 @fadd(i32 %arg) {
; 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
; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fadd <8 x float> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = fadd <16 x float> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = fadd double undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fadd <2 x double> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fadd <4 x double> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = fadd <8 x double> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 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 0 for instruction: ret i32 undef
;
; AVX1-LABEL: 'fadd'
; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fadd <8 x float> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fadd <16 x float> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fadd <2 x double> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fadd <4 x double> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fadd <8 x double> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX2-LABEL: 'fadd'
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fadd <8 x float> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F32 = fadd <16 x float> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fadd <2 x double> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fadd <4 x double> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F64 = fadd <8 x double> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 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 0 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 2 for instruction: %V2F64 = fadd <2 x double> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fadd <4 x double> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = fadd <8 x double> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 0 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 0 for instruction: ret i32 undef
;
; BTVER2-LABEL: 'fadd'
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fadd <8 x float> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fadd <16 x float> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fadd <2 x double> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fadd <4 x double> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fadd <8 x double> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 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) {
; 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
; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fsub <8 x float> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = fsub <16 x float> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = fsub double undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fsub <2 x double> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fsub <4 x double> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = fsub <8 x double> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 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 0 for instruction: ret i32 undef
;
; AVX1-LABEL: 'fsub'
; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fsub <16 x float> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fsub <4 x double> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fsub <8 x double> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX2-LABEL: 'fsub'
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fsub <8 x float> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F32 = fsub <16 x float> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fsub <4 x double> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F64 = fsub <8 x double> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 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 0 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 2 for instruction: %V2F64 = fsub <2 x double> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fsub <4 x double> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = fsub <8 x double> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 0 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 0 for instruction: ret i32 undef
;
; BTVER2-LABEL: 'fsub'
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fsub <16 x float> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fsub <4 x double> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fsub <8 x double> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 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 @fmul(i32 %arg) {
; 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
; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fmul <8 x float> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = fmul <16 x float> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = fmul double undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fmul <2 x double> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fmul <4 x double> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = fmul <8 x double> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 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 0 for instruction: ret i32 undef
;
; AVX1-LABEL: 'fmul'
; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fmul float undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fmul <4 x float> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fmul <8 x float> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fmul <16 x float> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fmul double undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fmul <2 x double> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fmul <4 x double> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fmul <8 x double> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX2-LABEL: 'fmul'
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fmul float undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fmul <4 x float> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fmul <8 x float> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F32 = fmul <16 x float> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fmul double undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fmul <2 x double> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fmul <4 x double> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F64 = fmul <8 x double> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 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 0 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 2 for instruction: %V4F32 = fmul <4 x float> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fmul <8 x float> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = fmul <16 x float> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = fmul double undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = fmul <2 x double> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = fmul <4 x double> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = fmul <8 x double> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 0 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 0 for instruction: ret i32 undef
;
; BTVER2-LABEL: 'fmul'
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = fmul float undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fmul <4 x float> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fmul <8 x float> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fmul <16 x float> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = fmul double undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fmul <2 x double> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fmul <4 x double> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fmul <8 x double> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 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) {
; 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
; SSE2-NEXT:  Cost Model: Found an estimated cost of 78 for instruction: %V8F32 = fdiv <8 x float> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 156 for instruction: %V16F32 = fdiv <16 x float> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %F64 = fdiv double undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V2F64 = fdiv <2 x double> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 138 for instruction: %V4F64 = fdiv <4 x double> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 276 for instruction: %V8F64 = fdiv <8 x double> undef, undef
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SSE42-LABEL: 'fdiv'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %F32 = fdiv float undef, undef
; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F32 = fdiv <4 x float> undef, undef
; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F32 = fdiv <8 x float> undef, undef
; SSE42-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V16F32 = fdiv <16 x float> undef, undef
; SSE42-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %F64 = fdiv double undef, undef
; SSE42-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2F64 = fdiv <2 x double> undef, undef
; SSE42-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V4F64 = fdiv <4 x double> undef, undef
; SSE42-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8F64 = fdiv <8 x double> undef, undef
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX1-LABEL: 'fdiv'
; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %F32 = fdiv float undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F32 = fdiv <4 x float> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F32 = fdiv <8 x float> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V16F32 = fdiv <16 x float> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %F64 = fdiv double undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2F64 = fdiv <2 x double> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V4F64 = fdiv <4 x double> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8F64 = fdiv <8 x double> undef, undef
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX2-LABEL: 'fdiv'
; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %F32 = fdiv float undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = fdiv <4 x float> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V8F32 = fdiv <8 x float> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V16F32 = fdiv <16 x float> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %F64 = fdiv double undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2F64 = fdiv <2 x double> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4F64 = fdiv <4 x double> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8F64 = fdiv <8 x double> undef, undef
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512-LABEL: 'fdiv'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %F32 = fdiv float undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = fdiv <4 x float> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V8F32 = fdiv <8 x float> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F32 = fdiv <16 x float> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %F64 = fdiv double undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2F64 = fdiv <2 x double> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4F64 = fdiv <4 x double> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F64 = fdiv <8 x double> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SLM-LABEL: 'fdiv'
; SLM-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %F32 = fdiv float undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V4F32 = fdiv <4 x float> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 78 for instruction: %V8F32 = fdiv <8 x float> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 156 for instruction: %V16F32 = fdiv <16 x float> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %F64 = fdiv double undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V2F64 = fdiv <2 x double> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 138 for instruction: %V4F64 = fdiv <4 x double> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 276 for instruction: %V8F64 = fdiv <8 x double> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; GLM-LABEL: 'fdiv'
; GLM-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %F32 = fdiv float undef, undef
; GLM-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V4F32 = fdiv <4 x float> undef, undef
; GLM-NEXT:  Cost Model: Found an estimated cost of 70 for instruction: %V8F32 = fdiv <8 x float> undef, undef
; GLM-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V16F32 = fdiv <16 x float> undef, undef
; GLM-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %F64 = fdiv double undef, undef
; GLM-NEXT:  Cost Model: Found an estimated cost of 65 for instruction: %V2F64 = fdiv <2 x double> undef, undef
; GLM-NEXT:  Cost Model: Found an estimated cost of 130 for instruction: %V4F64 = fdiv <4 x double> undef, undef
; GLM-NEXT:  Cost Model: Found an estimated cost of 260 for instruction: %V8F64 = fdiv <8 x double> undef, undef
; GLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; BTVER2-LABEL: 'fdiv'
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %F32 = fdiv float undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F32 = fdiv <4 x float> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F32 = fdiv <8 x float> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V16F32 = fdiv <16 x float> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %F64 = fdiv double undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2F64 = fdiv <2 x double> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V4F64 = fdiv <4 x double> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8F64 = fdiv <8 x double> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 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) {
; 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
;
; AVX-LABEL: 'frem'
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = frem float undef, undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F32 = frem <4 x float> undef, undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V8F32 = frem <8 x float> undef, undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V16F32 = frem <16 x float> undef, undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = frem double undef, undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = frem <2 x double> undef, undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F64 = frem <4 x double> undef, undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F64 = frem <8 x double> undef, undef
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512-LABEL: 'frem'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = frem float undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F32 = frem <4 x float> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V8F32 = frem <8 x float> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %V16F32 = frem <16 x float> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = frem double undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = frem <2 x double> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F64 = frem <4 x double> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V8F64 = frem <8 x double> undef, undef
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SLM-LABEL: 'frem'
; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = frem float undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F32 = frem <4 x float> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F32 = frem <8 x float> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V16F32 = frem <16 x float> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = frem double undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = frem <2 x double> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4F64 = frem <4 x double> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8F64 = frem <8 x double> undef, undef
; SLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; GLM-LABEL: 'frem'
; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = frem float undef, undef
; GLM-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F32 = frem <4 x float> undef, undef
; GLM-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F32 = frem <8 x float> undef, undef
; GLM-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V16F32 = frem <16 x float> undef, undef
; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = frem double undef, undef
; GLM-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = frem <2 x double> undef, undef
; GLM-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4F64 = frem <4 x double> undef, undef
; GLM-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8F64 = frem <8 x double> undef, undef
; GLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; BTVER2-LABEL: 'frem'
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = frem float undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F32 = frem <4 x float> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V8F32 = frem <8 x float> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V16F32 = frem <16 x float> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = frem double undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = frem <2 x double> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F64 = frem <4 x double> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F64 = frem <8 x double> undef, undef
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 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) {
; 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)
; 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 0 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 0 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 0 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 0 for instruction: ret i32 undef
;
; AVX512-LABEL: 'fsqrt'
; 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 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 0 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 0 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 0 for instruction: ret i32 undef
;
; BTVER2-LABEL: 'fsqrt'
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 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) {
; 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
;
; 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 0 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 0 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 0 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 0 for instruction: ret i32 undef
;
; BTVER2-LABEL: 'fabs'
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.fabs.f32(float undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.fabs.f64(double undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 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) {
; 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
;
; 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 0 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 0 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 0 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 0 for instruction: ret i32 undef
;
; BTVER2-LABEL: 'fcopysign'
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.copysign.f32(float undef, float undef)
; BTVER2-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)
; BTVER2-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)
; BTVER2-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)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.copysign.f64(double undef, double undef)
; BTVER2-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)
; BTVER2-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)
; BTVER2-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)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 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) {
; 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
;
; 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)
; AVX-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)
; AVX-NEXT:  Cost Model: Found an estimated cost of 87 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 174 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 10 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
; AVX-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)
; AVX-NEXT:  Cost Model: Found an estimated cost of 43 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 86 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 0 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 0 for instruction: ret i32 undef
;
; SLM-LABEL: 'fma'
; SLM-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
; SLM-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)
; SLM-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)
; SLM-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)
; SLM-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
; SLM-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)
; SLM-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)
; SLM-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)
; SLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; GLM-LABEL: 'fma'
; GLM-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
; GLM-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)
; GLM-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)
; GLM-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)
; GLM-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
; GLM-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)
; GLM-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)
; GLM-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)
; GLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; BTVER2-LABEL: 'fma'
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
; BTVER2-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)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 87 for instruction: %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 174 for instruction: %V16F32 = call <16 x float> @llvm.fma.v16f32(<16 x float> undef, <16 x float> undef, <16 x float> undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
; BTVER2-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)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V8F64 = call <8 x double> @llvm.fma.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 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>)