; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 5
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx950 -mattr=+half-rate-64-ops < %s | FileCheck -check-prefix=GFX950-FASTF64 %s
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a -mattr=+half-rate-64-ops < %s | FileCheck -check-prefixes=ALL,GFX9,GFX90A-FASTF64 %s
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 -mattr=+half-rate-64-ops < %s | FileCheck -check-prefixes=ALL,GFX9,FASTF64 %s
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mattr=-half-rate-64-ops < %s | FileCheck -check-prefixes=ALL,SLOWF64 %s
; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx950 -mattr=+half-rate-64-ops < %s | FileCheck -check-prefixes=SIZE,GFX950-SIZE %s
; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a -mattr=+half-rate-64-ops < %s | FileCheck -check-prefixes=SIZE,GFX9-SIZE,GFX90A-SIZE %s
; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 -mattr=+half-rate-64-ops < %s | FileCheck -check-prefixes=SIZE,GFX9-SIZE %s
; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mattr=-half-rate-64-ops < %s | FileCheck -check-prefixes=SIZE,SLOW-SIZE %s

define void @maximum_f16() {
; GFX950-FASTF64-LABEL: 'maximum_f16'
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f16 = call half @llvm.maximum.f16(half undef, half undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2f16 = call <2 x half> @llvm.maximum.v2f16(<2 x half> undef, <2 x half> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v3f16 = call <3 x half> @llvm.maximum.v3f16(<3 x half> undef, <3 x half> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f16 = call <4 x half> @llvm.maximum.v4f16(<4 x half> undef, <4 x half> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f16 = call <8 x half> @llvm.maximum.v8f16(<8 x half> undef, <8 x half> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16f16 = call <16 x half> @llvm.maximum.v16f16(<16 x half> undef, <16 x half> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; GFX9-LABEL: 'maximum_f16'
; GFX9-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f16 = call half @llvm.maximum.f16(half undef, half undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %v2f16 = call <2 x half> @llvm.maximum.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.maximum.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.maximum.v4f16(<4 x half> undef, <4 x half> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f16 = call <8 x half> @llvm.maximum.v8f16(<8 x half> undef, <8 x half> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16f16 = call <16 x half> @llvm.maximum.v16f16(<16 x half> undef, <16 x half> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; SLOWF64-LABEL: 'maximum_f16'
; SLOWF64-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f16 = call half @llvm.maximum.f16(half undef, half undef)
; SLOWF64-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %v2f16 = call <2 x half> @llvm.maximum.v2f16(<2 x half> undef, <2 x half> undef)
; SLOWF64-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %v3f16 = call <3 x half> @llvm.maximum.v3f16(<3 x half> undef, <3 x half> undef)
; SLOWF64-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %v4f16 = call <4 x half> @llvm.maximum.v4f16(<4 x half> undef, <4 x half> undef)
; SLOWF64-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %v8f16 = call <8 x half> @llvm.maximum.v8f16(<8 x half> undef, <8 x half> undef)
; SLOWF64-NEXT:  Cost Model: Found an estimated cost of 176 for instruction: %v16f16 = call <16 x half> @llvm.maximum.v16f16(<16 x half> undef, <16 x half> undef)
; SLOWF64-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; GFX950-SIZE-LABEL: 'maximum_f16'
; GFX950-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f16 = call half @llvm.maximum.f16(half undef, half undef)
; GFX950-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2f16 = call <2 x half> @llvm.maximum.v2f16(<2 x half> undef, <2 x half> undef)
; GFX950-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v3f16 = call <3 x half> @llvm.maximum.v3f16(<3 x half> undef, <3 x half> undef)
; GFX950-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f16 = call <4 x half> @llvm.maximum.v4f16(<4 x half> undef, <4 x half> undef)
; GFX950-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f16 = call <8 x half> @llvm.maximum.v8f16(<8 x half> undef, <8 x half> undef)
; GFX950-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16f16 = call <16 x half> @llvm.maximum.v16f16(<16 x half> undef, <16 x half> undef)
; GFX950-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; GFX9-SIZE-LABEL: 'maximum_f16'
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.maximum.f16(half undef, half undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v2f16 = call <2 x half> @llvm.maximum.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.maximum.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.maximum.v4f16(<4 x half> undef, <4 x half> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f16 = call <8 x half> @llvm.maximum.v8f16(<8 x half> undef, <8 x half> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16f16 = call <16 x half> @llvm.maximum.v16f16(<16 x half> undef, <16 x half> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; SLOW-SIZE-LABEL: 'maximum_f16'
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.maximum.f16(half undef, half undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2f16 = call <2 x half> @llvm.maximum.v2f16(<2 x half> undef, <2 x half> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v3f16 = call <3 x half> @llvm.maximum.v3f16(<3 x half> undef, <3 x half> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4f16 = call <4 x half> @llvm.maximum.v4f16(<4 x half> undef, <4 x half> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v8f16 = call <8 x half> @llvm.maximum.v8f16(<8 x half> undef, <8 x half> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v16f16 = call <16 x half> @llvm.maximum.v16f16(<16 x half> undef, <16 x half> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; SLOW-LABEL: 'maximum_f16'
; SLOW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f16 = call half @llvm.maximum.f16(half undef, half undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2f16 = call <2 x half> @llvm.maximum.v2f16(<2 x half> undef, <2 x half> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v3f16 = call <3 x half> @llvm.maximum.v3f16(<3 x half> undef, <3 x half> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4f16 = call <4 x half> @llvm.maximum.v4f16(<4 x half> undef, <4 x half> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v8f16 = call <8 x half> @llvm.maximum.v8f16(<8 x half> undef, <8 x half> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v16f16 = call <16 x half> @llvm.maximum.v16f16(<16 x half> undef, <16 x half> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
  %f16 = call half @llvm.maximum.f16(half undef, half undef)
  %v2f16 = call <2 x half> @llvm.maximum.v2f16(<2 x half> undef, <2 x half> undef)
  %v3f16 = call <3x half> @llvm.maximum.v3f16(<3 x half> undef, <3 x half> undef)
  %v4f16 = call <4 x half> @llvm.maximum.v4f16(<4 x half> undef, <4 x half> undef)
  %v8f16 = call <8 x half> @llvm.maximum.v8f16(<8 x half> undef, <8 x half> undef)
  %v16f16 = call <16 x half> @llvm.maximum.v16f16(<16 x half> undef, <16 x half> undef)
  ret void
}

define void @maximum_bf16() {
; GFX950-FASTF64-LABEL: 'maximum_bf16'
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.maximum.bf16(bfloat undef, bfloat undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v2bf16 = call <2 x bfloat> @llvm.maximum.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %v3bf16 = call <3 x bfloat> @llvm.maximum.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v4bf16 = call <4 x bfloat> @llvm.maximum.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v8bf16 = call <8 x bfloat> @llvm.maximum.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %v16bf16 = call <16 x bfloat> @llvm.maximum.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; GFX9-LABEL: 'maximum_bf16'
; GFX9-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.maximum.bf16(bfloat undef, bfloat undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v2bf16 = call <2 x bfloat> @llvm.maximum.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %v3bf16 = call <3 x bfloat> @llvm.maximum.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v4bf16 = call <4 x bfloat> @llvm.maximum.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v8bf16 = call <8 x bfloat> @llvm.maximum.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %v16bf16 = call <16 x bfloat> @llvm.maximum.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
; GFX9-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; SLOWF64-LABEL: 'maximum_bf16'
; SLOWF64-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %bf16 = call bfloat @llvm.maximum.bf16(bfloat undef, bfloat undef)
; SLOWF64-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %v2bf16 = call <2 x bfloat> @llvm.maximum.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
; SLOWF64-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %v3bf16 = call <3 x bfloat> @llvm.maximum.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef)
; SLOWF64-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %v4bf16 = call <4 x bfloat> @llvm.maximum.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
; SLOWF64-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %v8bf16 = call <8 x bfloat> @llvm.maximum.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
; SLOWF64-NEXT:  Cost Model: Found an estimated cost of 176 for instruction: %v16bf16 = call <16 x bfloat> @llvm.maximum.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
; SLOWF64-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; GFX950-SIZE-LABEL: 'maximum_bf16'
; GFX950-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.maximum.bf16(bfloat undef, bfloat undef)
; GFX950-SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v2bf16 = call <2 x bfloat> @llvm.maximum.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
; GFX950-SIZE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %v3bf16 = call <3 x bfloat> @llvm.maximum.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef)
; GFX950-SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v4bf16 = call <4 x bfloat> @llvm.maximum.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
; GFX950-SIZE-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v8bf16 = call <8 x bfloat> @llvm.maximum.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
; GFX950-SIZE-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %v16bf16 = call <16 x bfloat> @llvm.maximum.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
; GFX950-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; GFX9-SIZE-LABEL: 'maximum_bf16'
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.maximum.bf16(bfloat undef, bfloat undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v2bf16 = call <2 x bfloat> @llvm.maximum.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %v3bf16 = call <3 x bfloat> @llvm.maximum.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v4bf16 = call <4 x bfloat> @llvm.maximum.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v8bf16 = call <8 x bfloat> @llvm.maximum.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %v16bf16 = call <16 x bfloat> @llvm.maximum.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; SLOW-SIZE-LABEL: 'maximum_bf16'
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.maximum.bf16(bfloat undef, bfloat undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2bf16 = call <2 x bfloat> @llvm.maximum.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v3bf16 = call <3 x bfloat> @llvm.maximum.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4bf16 = call <4 x bfloat> @llvm.maximum.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v8bf16 = call <8 x bfloat> @llvm.maximum.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v16bf16 = call <16 x bfloat> @llvm.maximum.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
; SLOW-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; SLOW-LABEL: 'maximum_bf16'
; SLOW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bf16 = call bfloat @llvm.maximum.bf16(bfloat undef, bfloat undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2bf16 = call <2 x bfloat> @llvm.maximum.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v3bf16 = call <3 x bfloat> @llvm.maximum.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4bf16 = call <4 x bfloat> @llvm.maximum.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v8bf16 = call <8 x bfloat> @llvm.maximum.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v16bf16 = call <16 x bfloat> @llvm.maximum.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
; SLOW-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
  %bf16 = call bfloat @llvm.maximum.bf16(bfloat undef, bfloat undef)
  %v2bf16 = call <2 x bfloat> @llvm.maximum.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
  %v3bf16 = call <3x bfloat> @llvm.maximum.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef)
  %v4bf16 = call <4 x bfloat> @llvm.maximum.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
  %v8bf16 = call <8 x bfloat> @llvm.maximum.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
  %v16bf16 = call <16 x bfloat> @llvm.maximum.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
  ret void
}

define void @maximum_f32() {
; GFX950-FASTF64-LABEL: 'maximum_f32'
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f32 = call float @llvm.maximum.f32(float undef, float undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32 = call <2 x float> @llvm.maximum.v2f32(<2 x float> undef, <2 x float> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v3f32 = call <3 x float> @llvm.maximum.v3f32(<3 x float> undef, <3 x float> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4f32 = call <4 x float> @llvm.maximum.v4f32(<4 x float> undef, <4 x float> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8f32 = call <8 x float> @llvm.maximum.v8f32(<8 x float> undef, <8 x float> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16f32 = call <16 x float> @llvm.maximum.v16f32(<16 x float> undef, <16 x float> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; ALL-LABEL: 'maximum_f32'
; ALL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f32 = call float @llvm.maximum.f32(float undef, float undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %v2f32 = call <2 x float> @llvm.maximum.v2f32(<2 x float> undef, <2 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %v3f32 = call <3 x float> @llvm.maximum.v3f32(<3 x float> undef, <3 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %v4f32 = call <4 x float> @llvm.maximum.v4f32(<4 x float> undef, <4 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %v8f32 = call <8 x float> @llvm.maximum.v8f32(<8 x float> undef, <8 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %v16f32 = call <16 x float> @llvm.maximum.v16f32(<16 x float> undef, <16 x float> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; SIZE-LABEL: 'maximum_f32'
; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f32 = call float @llvm.maximum.f32(float undef, float undef)
; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32 = call <2 x float> @llvm.maximum.v2f32(<2 x float> undef, <2 x float> undef)
; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v3f32 = call <3 x float> @llvm.maximum.v3f32(<3 x float> undef, <3 x float> undef)
; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4f32 = call <4 x float> @llvm.maximum.v4f32(<4 x float> undef, <4 x float> undef)
; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8f32 = call <8 x float> @llvm.maximum.v8f32(<8 x float> undef, <8 x float> undef)
; SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16f32 = call <16 x float> @llvm.maximum.v16f32(<16 x float> undef, <16 x float> undef)
; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
  %f32 = call float @llvm.maximum.f32(float undef, float undef)
  %v2f32 = call <2 x float> @llvm.maximum.v2f32(<2 x float> undef, <2 x float> undef)
  %v3f32 = call <3x float> @llvm.maximum.v3f32(<3 x float> undef, <3 x float> undef)
  %v4f32 = call <4 x float> @llvm.maximum.v4f32(<4 x float> undef, <4 x float> undef)
  %v8f32 = call <8 x float> @llvm.maximum.v8f32(<8 x float> undef, <8 x float> undef)
  %v16f32 = call <16 x float> @llvm.maximum.v16f32(<16 x float> undef, <16 x float> undef)
  ret void
}

define void @maximum_f64() {
; GFX950-FASTF64-LABEL: 'maximum_f64'
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f64 = call double @llvm.maximum.f64(double undef, double undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %v2f64 = call <2 x double> @llvm.maximum.v2f64(<2 x double> undef, <2 x double> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %v3f64 = call <3 x double> @llvm.maximum.v3f64(<3 x double> undef, <3 x double> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %v4f64 = call <4 x double> @llvm.maximum.v4f64(<4 x double> undef, <4 x double> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %v8f64 = call <8 x double> @llvm.maximum.v8f64(<8 x double> undef, <8 x double> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %v16f64 = call <16 x double> @llvm.maximum.v16f64(<16 x double> undef, <16 x double> undef)
; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; ALL-LABEL: 'maximum_f64'
; ALL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f64 = call double @llvm.maximum.f64(double undef, double undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %v2f64 = call <2 x double> @llvm.maximum.v2f64(<2 x double> undef, <2 x double> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %v3f64 = call <3 x double> @llvm.maximum.v3f64(<3 x double> undef, <3 x double> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %v4f64 = call <4 x double> @llvm.maximum.v4f64(<4 x double> undef, <4 x double> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %v8f64 = call <8 x double> @llvm.maximum.v8f64(<8 x double> undef, <8 x double> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %v16f64 = call <16 x double> @llvm.maximum.v16f64(<16 x double> undef, <16 x double> undef)
; ALL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
;
; SIZE-LABEL: 'maximum_f64'
; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f64 = call double @llvm.maximum.f64(double undef, double undef)
; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f64 = call <2 x double> @llvm.maximum.v2f64(<2 x double> undef, <2 x double> undef)
; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v3f64 = call <3 x double> @llvm.maximum.v3f64(<3 x double> undef, <3 x double> undef)
; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4f64 = call <4 x double> @llvm.maximum.v4f64(<4 x double> undef, <4 x double> undef)
; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8f64 = call <8 x double> @llvm.maximum.v8f64(<8 x double> undef, <8 x double> undef)
; SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16f64 = call <16 x double> @llvm.maximum.v16f64(<16 x double> undef, <16 x double> undef)
; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
;
  %f64 = call double @llvm.maximum.f64(double undef, double undef)
  %v2f64 = call <2 x double> @llvm.maximum.v2f64(<2 x double> undef, <2 x double> undef)
  %v3f64 = call <3x double> @llvm.maximum.v3f64(<3 x double> undef, <3 x double> undef)
  %v4f64 = call <4 x double> @llvm.maximum.v4f64(<4 x double> undef, <4 x double> undef)
  %v8f64 = call <8 x double> @llvm.maximum.v8f64(<8 x double> undef, <8 x double> undef)
  %v16f64 = call <16 x double> @llvm.maximum.v16f64(<16 x double> undef, <16 x double> undef)
  ret void
}
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; FASTF64: {{.*}}
; GFX90A-FASTF64: {{.*}}
; GFX90A-SIZE: {{.*}}