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

; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 5
; RUN: opt < %s -mtriple=amdgpu6.01-unknown-amdhsa -passes="print<cost-model>" -cost-kind=throughput 2>&1 -disable-output | FileCheck -check-prefixes=ALL,BASE %s
; RUN: opt < %s -mtriple=amdgpu8.03-unknown-amdhsa -passes="print<cost-model>" -cost-kind=throughput 2>&1 -disable-output | FileCheck -check-prefixes=ALL,GFX8 %s
; RUN: opt < %s -mtriple=amdgpu9.00-unknown-amdhsa -passes="print<cost-model>" -cost-kind=throughput 2>&1 -disable-output | FileCheck -check-prefixes=ALL,GFX9 %s
; RUN: opt < %s -mtriple=amdgpu10.30-unknown-amdhsa -passes="print<cost-model>" -cost-kind=throughput 2>&1 -disable-output | FileCheck -check-prefixes=ALL,GFX10 %s

; RUN: opt < %s -mtriple=amdgpu6.01-unknown-amdhsa -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output | FileCheck -check-prefixes=ALL-SIZE,BASE-SIZE %s
; RUN: opt < %s -mtriple=amdgpu8.03-unknown-amdhsa -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output | FileCheck -check-prefixes=ALL-SIZE,GFX8-SIZE %s
; RUN: opt < %s -mtriple=amdgpu9.00-unknown-amdhsa -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output | FileCheck -check-prefixes=ALL-SIZE,GFX9-SIZE %s
; RUN: opt < %s -mtriple=amdgpu10.30-unknown-amdhsa -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output | FileCheck -check-prefixes=ALL-SIZE,GFX10-SIZE %s

define void @copysign_f16() {
; BASE-LABEL: 'copysign_f16'
; BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.copysign.f16(half undef, half undef)
; BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2f16 = call <2 x half> @llvm.copysign.v2f16(<2 x half> undef, <2 x half> undef)
; BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v3f16 = call <3 x half> @llvm.copysign.v3f16(<3 x half> undef, <3 x half> undef)
; BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4f16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
; BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v5f16 = call <5 x half> @llvm.copysign.v5f16(<5 x half> undef, <5 x half> undef)
; BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8f16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef)
; BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v9f16 = call <9 x half> @llvm.copysign.v9f16(<9 x half> undef, <9 x half> undef)
; BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16f16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef)
; BASE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; GFX8-LABEL: 'copysign_f16'
; GFX8-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.copysign.f16(half undef, half undef)
; GFX8-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f16 = call <2 x half> @llvm.copysign.v2f16(<2 x half> undef, <2 x half> undef)
; GFX8-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v3f16 = call <3 x half> @llvm.copysign.v3f16(<3 x half> undef, <3 x half> undef)
; GFX8-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4f16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
; GFX8-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v5f16 = call <5 x half> @llvm.copysign.v5f16(<5 x half> undef, <5 x half> undef)
; GFX8-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8f16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef)
; GFX8-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v9f16 = call <9 x half> @llvm.copysign.v9f16(<9 x half> undef, <9 x half> undef)
; GFX8-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16f16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef)
; GFX8-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; GFX9-LABEL: 'copysign_f16'
; GFX9-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.copysign.f16(half undef, half undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2f16 = call <2 x half> @llvm.copysign.v2f16(<2 x half> undef, <2 x half> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v3f16 = call <3 x half> @llvm.copysign.v3f16(<3 x half> undef, <3 x half> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v5f16 = call <5 x half> @llvm.copysign.v5f16(<5 x half> undef, <5 x half> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8f16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v9f16 = call <9 x half> @llvm.copysign.v9f16(<9 x half> undef, <9 x half> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16f16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; GFX10-LABEL: 'copysign_f16'
; GFX10-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.copysign.f16(half undef, half undef)
; GFX10-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2f16 = call <2 x half> @llvm.copysign.v2f16(<2 x half> undef, <2 x half> undef)
; GFX10-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v3f16 = call <3 x half> @llvm.copysign.v3f16(<3 x half> undef, <3 x half> undef)
; GFX10-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
; GFX10-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v5f16 = call <5 x half> @llvm.copysign.v5f16(<5 x half> undef, <5 x half> undef)
; GFX10-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8f16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef)
; GFX10-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v9f16 = call <9 x half> @llvm.copysign.v9f16(<9 x half> undef, <9 x half> undef)
; GFX10-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16f16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef)
; GFX10-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; BASE-SIZE-LABEL: 'copysign_f16'
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.copysign.f16(half undef, half undef)
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2f16 = call <2 x half> @llvm.copysign.v2f16(<2 x half> undef, <2 x half> undef)
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v3f16 = call <3 x half> @llvm.copysign.v3f16(<3 x half> undef, <3 x half> undef)
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4f16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v5f16 = call <5 x half> @llvm.copysign.v5f16(<5 x half> undef, <5 x half> undef)
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8f16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef)
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v9f16 = call <9 x half> @llvm.copysign.v9f16(<9 x half> undef, <9 x half> undef)
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16f16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef)
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; GFX8-SIZE-LABEL: 'copysign_f16'
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.copysign.f16(half undef, half undef)
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f16 = call <2 x half> @llvm.copysign.v2f16(<2 x half> undef, <2 x half> undef)
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v3f16 = call <3 x half> @llvm.copysign.v3f16(<3 x half> undef, <3 x half> undef)
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4f16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v5f16 = call <5 x half> @llvm.copysign.v5f16(<5 x half> undef, <5 x half> undef)
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8f16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef)
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v9f16 = call <9 x half> @llvm.copysign.v9f16(<9 x half> undef, <9 x half> undef)
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16f16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef)
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; GFX9-SIZE-LABEL: 'copysign_f16'
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.copysign.f16(half undef, half undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2f16 = call <2 x half> @llvm.copysign.v2f16(<2 x half> undef, <2 x half> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v3f16 = call <3 x half> @llvm.copysign.v3f16(<3 x half> undef, <3 x half> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v5f16 = call <5 x half> @llvm.copysign.v5f16(<5 x half> undef, <5 x half> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8f16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v9f16 = call <9 x half> @llvm.copysign.v9f16(<9 x half> undef, <9 x half> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16f16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; GFX10-SIZE-LABEL: 'copysign_f16'
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.copysign.f16(half undef, half undef)
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2f16 = call <2 x half> @llvm.copysign.v2f16(<2 x half> undef, <2 x half> undef)
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v3f16 = call <3 x half> @llvm.copysign.v3f16(<3 x half> undef, <3 x half> undef)
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v5f16 = call <5 x half> @llvm.copysign.v5f16(<5 x half> undef, <5 x half> undef)
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8f16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef)
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v9f16 = call <9 x half> @llvm.copysign.v9f16(<9 x half> undef, <9 x half> undef)
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16f16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef)
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
  %f16 = call half @llvm.copysign.f16(half undef, half undef)
  %v2f16 = call <2 x half> @llvm.copysign.v2f16(<2 x half> undef, <2 x half> undef)
  %v3f16 = call <3 x half> @llvm.copysign.v3f16(<3 x half> undef, <3 x half> undef)
  %v4f16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
  %v5f16 = call <5 x half> @llvm.copysign.v5f16(<5 x half> undef, <5 x half> undef)
  %v8f16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef)
  %v9f16 = call <9 x half> @llvm.copysign.v9f16(<9 x half> undef, <9 x half> undef)
  %v16f16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef)
  ret void
}

define void @copysign_f32() {
; ALL-LABEL: 'copysign_f32'
; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f32 = call float @llvm.copysign.f32(float undef, float undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32 = call <2 x float> @llvm.copysign.v2f32(<2 x float> undef, <2 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v3f32 = call <3 x float> @llvm.copysign.v3f32(<3 x float> undef, <3 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4f32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %v5f32 = call <5 x float> @llvm.copysign.v5f32(<5 x float> undef, <5 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8f32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %v9f32 = call <9 x float> @llvm.copysign.v9f32(<9 x float> undef, <9 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16f32 = call <16 x float> @llvm.copysign.v16f32(<16 x float> undef, <16 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; ALL-SIZE-LABEL: 'copysign_f32'
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f32 = call float @llvm.copysign.f32(float undef, float undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32 = call <2 x float> @llvm.copysign.v2f32(<2 x float> undef, <2 x float> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v3f32 = call <3 x float> @llvm.copysign.v3f32(<3 x float> undef, <3 x float> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4f32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %v5f32 = call <5 x float> @llvm.copysign.v5f32(<5 x float> undef, <5 x float> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8f32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %v9f32 = call <9 x float> @llvm.copysign.v9f32(<9 x float> undef, <9 x float> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16f32 = call <16 x float> @llvm.copysign.v16f32(<16 x float> undef, <16 x float> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
  %f32 = call float @llvm.copysign.f32(float undef, float undef)
  %v2f32 = call <2 x float> @llvm.copysign.v2f32(<2 x float> undef, <2 x float> undef)
  %v3f32 = call <3 x float> @llvm.copysign.v3f32(<3 x float> undef, <3 x float> undef)
  %v4f32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
  %v5f32 = call <5 x float> @llvm.copysign.v5f32(<5 x float> undef, <5 x float> undef)
  %v8f32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
  %v9f32 = call <9 x float> @llvm.copysign.v9f32(<9 x float> undef, <9 x float> undef)
  %v16f32 = call <16 x float> @llvm.copysign.v16f32(<16 x float> undef, <16 x float> undef)
  ret void
}

define void @copysign_bf16() {
; BASE-LABEL: 'copysign_bf16'
; BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.copysign.bf16(bfloat undef, bfloat undef)
; BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2bf16 = call <2 x bfloat> @llvm.copysign.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
; BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v3bf16 = call <3 x bfloat> @llvm.copysign.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef)
; BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4bf16 = call <4 x bfloat> @llvm.copysign.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
; BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v5bf16 = call <5 x bfloat> @llvm.copysign.v5bf16(<5 x bfloat> undef, <5 x bfloat> undef)
; BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8bf16 = call <8 x bfloat> @llvm.copysign.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
; BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v9bf16 = call <9 x bfloat> @llvm.copysign.v9bf16(<9 x bfloat> undef, <9 x bfloat> undef)
; BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16bf16 = call <16 x bfloat> @llvm.copysign.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
; BASE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; GFX8-LABEL: 'copysign_bf16'
; GFX8-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.copysign.bf16(bfloat undef, bfloat undef)
; GFX8-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2bf16 = call <2 x bfloat> @llvm.copysign.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
; GFX8-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v3bf16 = call <3 x bfloat> @llvm.copysign.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef)
; GFX8-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4bf16 = call <4 x bfloat> @llvm.copysign.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
; GFX8-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v5bf16 = call <5 x bfloat> @llvm.copysign.v5bf16(<5 x bfloat> undef, <5 x bfloat> undef)
; GFX8-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8bf16 = call <8 x bfloat> @llvm.copysign.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
; GFX8-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v9bf16 = call <9 x bfloat> @llvm.copysign.v9bf16(<9 x bfloat> undef, <9 x bfloat> undef)
; GFX8-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16bf16 = call <16 x bfloat> @llvm.copysign.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
; GFX8-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; GFX9-LABEL: 'copysign_bf16'
; GFX9-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.copysign.bf16(bfloat undef, bfloat undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2bf16 = call <2 x bfloat> @llvm.copysign.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v3bf16 = call <3 x bfloat> @llvm.copysign.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4bf16 = call <4 x bfloat> @llvm.copysign.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v5bf16 = call <5 x bfloat> @llvm.copysign.v5bf16(<5 x bfloat> undef, <5 x bfloat> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8bf16 = call <8 x bfloat> @llvm.copysign.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v9bf16 = call <9 x bfloat> @llvm.copysign.v9bf16(<9 x bfloat> undef, <9 x bfloat> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16bf16 = call <16 x bfloat> @llvm.copysign.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; GFX10-LABEL: 'copysign_bf16'
; GFX10-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.copysign.bf16(bfloat undef, bfloat undef)
; GFX10-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2bf16 = call <2 x bfloat> @llvm.copysign.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
; GFX10-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v3bf16 = call <3 x bfloat> @llvm.copysign.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef)
; GFX10-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4bf16 = call <4 x bfloat> @llvm.copysign.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
; GFX10-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v5bf16 = call <5 x bfloat> @llvm.copysign.v5bf16(<5 x bfloat> undef, <5 x bfloat> undef)
; GFX10-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8bf16 = call <8 x bfloat> @llvm.copysign.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
; GFX10-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v9bf16 = call <9 x bfloat> @llvm.copysign.v9bf16(<9 x bfloat> undef, <9 x bfloat> undef)
; GFX10-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16bf16 = call <16 x bfloat> @llvm.copysign.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
; GFX10-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; BASE-SIZE-LABEL: 'copysign_bf16'
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.copysign.bf16(bfloat undef, bfloat undef)
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2bf16 = call <2 x bfloat> @llvm.copysign.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v3bf16 = call <3 x bfloat> @llvm.copysign.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef)
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4bf16 = call <4 x bfloat> @llvm.copysign.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v5bf16 = call <5 x bfloat> @llvm.copysign.v5bf16(<5 x bfloat> undef, <5 x bfloat> undef)
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8bf16 = call <8 x bfloat> @llvm.copysign.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v9bf16 = call <9 x bfloat> @llvm.copysign.v9bf16(<9 x bfloat> undef, <9 x bfloat> undef)
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16bf16 = call <16 x bfloat> @llvm.copysign.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
; BASE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; GFX8-SIZE-LABEL: 'copysign_bf16'
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.copysign.bf16(bfloat undef, bfloat undef)
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2bf16 = call <2 x bfloat> @llvm.copysign.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v3bf16 = call <3 x bfloat> @llvm.copysign.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef)
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4bf16 = call <4 x bfloat> @llvm.copysign.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v5bf16 = call <5 x bfloat> @llvm.copysign.v5bf16(<5 x bfloat> undef, <5 x bfloat> undef)
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8bf16 = call <8 x bfloat> @llvm.copysign.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v9bf16 = call <9 x bfloat> @llvm.copysign.v9bf16(<9 x bfloat> undef, <9 x bfloat> undef)
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16bf16 = call <16 x bfloat> @llvm.copysign.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
; GFX8-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; GFX9-SIZE-LABEL: 'copysign_bf16'
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.copysign.bf16(bfloat undef, bfloat undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2bf16 = call <2 x bfloat> @llvm.copysign.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v3bf16 = call <3 x bfloat> @llvm.copysign.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4bf16 = call <4 x bfloat> @llvm.copysign.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v5bf16 = call <5 x bfloat> @llvm.copysign.v5bf16(<5 x bfloat> undef, <5 x bfloat> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8bf16 = call <8 x bfloat> @llvm.copysign.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v9bf16 = call <9 x bfloat> @llvm.copysign.v9bf16(<9 x bfloat> undef, <9 x bfloat> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16bf16 = call <16 x bfloat> @llvm.copysign.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; GFX10-SIZE-LABEL: 'copysign_bf16'
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.copysign.bf16(bfloat undef, bfloat undef)
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2bf16 = call <2 x bfloat> @llvm.copysign.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v3bf16 = call <3 x bfloat> @llvm.copysign.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef)
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4bf16 = call <4 x bfloat> @llvm.copysign.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v5bf16 = call <5 x bfloat> @llvm.copysign.v5bf16(<5 x bfloat> undef, <5 x bfloat> undef)
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8bf16 = call <8 x bfloat> @llvm.copysign.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v9bf16 = call <9 x bfloat> @llvm.copysign.v9bf16(<9 x bfloat> undef, <9 x bfloat> undef)
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16bf16 = call <16 x bfloat> @llvm.copysign.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
; GFX10-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
  %bf16 = call bfloat @llvm.copysign.bf16(bfloat undef, bfloat undef)
  %v2bf16 = call <2 x bfloat> @llvm.copysign.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
  %v3bf16 = call <3 x bfloat> @llvm.copysign.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef)
  %v4bf16 = call <4 x bfloat> @llvm.copysign.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
  %v5bf16 = call <5 x bfloat> @llvm.copysign.v5bf16(<5 x bfloat> undef, <5 x bfloat> undef)
  %v8bf16 = call <8 x bfloat> @llvm.copysign.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
  %v9bf16 = call <9 x bfloat> @llvm.copysign.v9bf16(<9 x bfloat> undef, <9 x bfloat> undef)
  %v16bf16 = call <16 x bfloat> @llvm.copysign.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
  ret void
}

define void @copysign_f64() {
; ALL-LABEL: 'copysign_f64'
; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f64 = call double @llvm.copysign.f64(double undef, double undef)
; ALL-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)
; ALL-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v3f64 = call <3 x double> @llvm.copysign.v3f64(<3 x double> undef, <3 x double> undef)
; ALL-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)
; ALL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v5f64 = call <5 x double> @llvm.copysign.v5f64(<5 x double> undef, <5 x double> undef)
; ALL-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)
; ALL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v9f64 = call <9 x double> @llvm.copysign.v9f64(<9 x double> undef, <9 x double> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16f64 = call <16 x double> @llvm.copysign.v16f64(<16 x double> undef, <16 x double> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; ALL-SIZE-LABEL: 'copysign_f64'
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f64 = call double @llvm.copysign.f64(double undef, double undef)
; ALL-SIZE-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)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v3f64 = call <3 x double> @llvm.copysign.v3f64(<3 x double> undef, <3 x double> undef)
; ALL-SIZE-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)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v5f64 = call <5 x double> @llvm.copysign.v5f64(<5 x double> undef, <5 x double> undef)
; ALL-SIZE-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)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v9f64 = call <9 x double> @llvm.copysign.v9f64(<9 x double> undef, <9 x double> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16f64 = call <16 x double> @llvm.copysign.v16f64(<16 x double> undef, <16 x double> undef)
; ALL-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
  %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)
  %v3f64 = call <3 x double> @llvm.copysign.v3f64(<3 x double> undef, <3 x double> undef)
  %v4f64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
  %v5f64 = call <5 x double> @llvm.copysign.v5f64(<5 x double> undef, <5 x double> undef)
  %v8f64 = call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)
  %v9f64 = call <9 x double> @llvm.copysign.v9f64(<9 x double> undef, <9 x double> undef)
  %v16f64 = call <16 x double> @llvm.copysign.v16f64(<16 x double> undef, <16 x double> undef)
  ret void
}