llvm/test/Analysis/CostModel/AMDGPU/fround.ll

; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL,FAST %s
; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL,FAST %s
; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL,FAST %s
; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL,SLOW %s

; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL-SIZE,FAST-SIZE %s
; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL-SIZE,FAST-SIZE %s
; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL-SIZE,FAST-SIZE %s
; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL-SIZE,SLOW-SIZE %s
; END.

define i32 @ceil(i32 %arg) {
; FAST-LABEL: 'ceil'
; FAST-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.ceil.f32(float undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.ceil.v4f32(<4 x float> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.ceil.f64(double undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.ceil.v2f64(<2 x double> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
;
; SLOW-LABEL: 'ceil'
; SLOW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.ceil.f32(float undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.ceil.v4f32(<4 x float> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.ceil.f64(double undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.ceil.v2f64(<2 x double> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
;
; FAST-SIZE-LABEL: 'ceil'
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.ceil.f32(float undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.ceil.v4f32(<4 x float> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.ceil.f64(double undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.ceil.v2f64(<2 x double> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; SLOW-SIZE-LABEL: 'ceil'
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.ceil.f32(float undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.ceil.v4f32(<4 x float> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.ceil.f64(double undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.ceil.v2f64(<2 x double> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
  %F32 = call float @llvm.ceil.f32(float undef)
  %V4F32 = call <4 x float> @llvm.ceil.v4f32(<4 x float> undef)
  %V8F32 = call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
  %V16F32 = call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)

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

  ret i32 undef
}

define i32 @floor(i32 %arg) {
; ALL-LABEL: 'floor'
; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.floor.f32(float undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.floor.v4f32(<4 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.floor.v8f32(<8 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.floor.v16f32(<16 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.floor.f64(double undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.floor.v2f64(<2 x double> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.floor.v4f64(<4 x double> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.floor.v8f64(<8 x double> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
;
; ALL-SIZE-LABEL: 'floor'
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.floor.f32(float undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.floor.v4f32(<4 x float> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.floor.v8f32(<8 x float> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.floor.v16f32(<16 x float> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.floor.f64(double undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.floor.v2f64(<2 x double> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.floor.v4f64(<4 x double> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.floor.v8f64(<8 x double> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
  %F32 = call float @llvm.floor.f32(float undef)
  %V4F32 = call <4 x float> @llvm.floor.v4f32(<4 x float> undef)
  %V8F32 = call <8 x float> @llvm.floor.v8f32(<8 x float> undef)
  %V16F32 = call <16 x float> @llvm.floor.v16f32(<16 x float> undef)

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

  ret i32 undef
}

define i32 @nearbyint(i32 %arg) {
; ALL-LABEL: 'nearbyint'
; ALL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.nearbyint.f32(float undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x float> @llvm.nearbyint.v4f32(<4 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x float> @llvm.nearbyint.v8f32(<8 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x float> @llvm.nearbyint.v16f32(<16 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.nearbyint.f64(double undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.nearbyint.v2f64(<2 x double> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.nearbyint.v4f64(<4 x double> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.nearbyint.v8f64(<8 x double> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
;
; ALL-SIZE-LABEL: 'nearbyint'
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.nearbyint.f32(float undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x float> @llvm.nearbyint.v4f32(<4 x float> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x float> @llvm.nearbyint.v8f32(<8 x float> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x float> @llvm.nearbyint.v16f32(<16 x float> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.nearbyint.f64(double undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.nearbyint.v2f64(<2 x double> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.nearbyint.v4f64(<4 x double> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.nearbyint.v8f64(<8 x double> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
  %F32 = call float @llvm.nearbyint.f32(float undef)
  %V4F32 = call <4 x float> @llvm.nearbyint.v4f32(<4 x float> undef)
  %V8F32 = call <8 x float> @llvm.nearbyint.v8f32(<8 x float> undef)
  %V16F32 = call <16 x float> @llvm.nearbyint.v16f32(<16 x float> undef)

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

  ret i32 undef
}

define i32 @rint(i32 %arg) {
; FAST-LABEL: 'rint'
; FAST-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
;
; SLOW-LABEL: 'rint'
; SLOW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.rint.f64(double undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
;
; FAST-SIZE-LABEL: 'rint'
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; SLOW-SIZE-LABEL: 'rint'
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.rint.f64(double undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
  %F32 = call float @llvm.rint.f32(float undef)
  %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
  %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
  %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)

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

  ret i32 undef
}

define i32 @trunc(i32 %arg) {
; FAST-LABEL: 'trunc'
; FAST-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.trunc.f32(float undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.trunc.v4f32(<4 x float> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.trunc.f64(double undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.trunc.v2f64(<2 x double> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
; FAST-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
;
; SLOW-LABEL: 'trunc'
; SLOW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.trunc.f32(float undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.trunc.v4f32(<4 x float> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.trunc.f64(double undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.trunc.v2f64(<2 x double> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
;
; FAST-SIZE-LABEL: 'trunc'
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.trunc.f32(float undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.trunc.v4f32(<4 x float> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.trunc.f64(double undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.trunc.v2f64(<2 x double> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
; FAST-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; SLOW-SIZE-LABEL: 'trunc'
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.trunc.f32(float undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.trunc.v4f32(<4 x float> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.trunc.f64(double undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.trunc.v2f64(<2 x double> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
  %F32 = call float @llvm.trunc.f32(float undef)
  %V4F32 = call <4 x float> @llvm.trunc.v4f32(<4 x float> undef)
  %V8F32 = call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
  %V16F32 = call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)

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

  ret i32 undef
}

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

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

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

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

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

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

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

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

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

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