AMDGPU: Add gfx950 cost model tests for minimum and maximum

[arsenm]

No description provided.

[arsenm]

• AMDGPU: Add gfx950 cost model tests for minimum and maximum #130029 👈 (View in Graphite)
• main

This stack of pull requests is managed by Graphite. Learn more about stacking.

[llvmbot]

@llvm/pr-subscribers-llvm-analysis

@llvm/pr-subscribers-backend-amdgpu

Author: Matt Arsenault (arsenm)

Changes

---

Full diff: https://github.com/llvm/llvm-project/pull/130029.diff

2 Files Affected:

• (modified) llvm/test/Analysis/CostModel/AMDGPU/maximum.ll (+37)
• (modified) llvm/test/Analysis/CostModel/AMDGPU/minimum.ll (+37)

diff --git a/llvm/test/Analysis/CostModel/AMDGPU/maximum.ll b/llvm/test/Analysis/CostModel/AMDGPU/maximum.ll
index 0f6f01b9c1d36..603e04fc7a7a7 100644
--- a/llvm/test/Analysis/CostModel/AMDGPU/maximum.ll
+++ b/llvm/test/Analysis/CostModel/AMDGPU/maximum.ll
@@ -1,4 +1,5 @@
 ; 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
@@ -7,6 +8,15 @@
 ; 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 8 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 11 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 23 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 47 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)
@@ -61,6 +71,15 @@ define void @maximum_f16() {
 }
 
 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)
@@ -115,6 +134,15 @@ define void @maximum_bf16() {
 }
 
 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)
@@ -143,6 +171,15 @@ define void @maximum_f32() {
 }
 
 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)
diff --git a/llvm/test/Analysis/CostModel/AMDGPU/minimum.ll b/llvm/test/Analysis/CostModel/AMDGPU/minimum.ll
index b6e52cfaaaada..4507ba4929f1b 100644
--- a/llvm/test/Analysis/CostModel/AMDGPU/minimum.ll
+++ b/llvm/test/Analysis/CostModel/AMDGPU/minimum.ll
@@ -1,4 +1,5 @@
 ; 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
@@ -7,6 +8,15 @@
 ; 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 @minimum_f16() {
+; GFX950-FASTF64-LABEL: 'minimum_f16'
+; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f16 = call half @llvm.minimum.f16(half undef, half undef)
+; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2f16 = call <2 x half> @llvm.minimum.v2f16(<2 x half> undef, <2 x half> undef)
+; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v3f16 = call <3 x half> @llvm.minimum.v3f16(<3 x half> undef, <3 x half> undef)
+; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v4f16 = call <4 x half> @llvm.minimum.v4f16(<4 x half> undef, <4 x half> undef)
+; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %v8f16 = call <8 x half> @llvm.minimum.v8f16(<8 x half> undef, <8 x half> undef)
+; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %v16f16 = call <16 x half> @llvm.minimum.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: 'minimum_f16'
 ; GFX9-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f16 = call half @llvm.minimum.f16(half undef, half undef)
 ; GFX9-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %v2f16 = call <2 x half> @llvm.minimum.v2f16(<2 x half> undef, <2 x half> undef)
@@ -61,6 +71,15 @@ define void @minimum_f16() {
 }
 
 define void @minimum_bf16() {
+; GFX950-FASTF64-LABEL: 'minimum_bf16'
+; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.minimum.bf16(bfloat undef, bfloat undef)
+; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v2bf16 = call <2 x bfloat> @llvm.minimum.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.minimum.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.minimum.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.minimum.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.minimum.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: 'minimum_bf16'
 ; GFX9-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.minimum.bf16(bfloat undef, bfloat undef)
 ; GFX9-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v2bf16 = call <2 x bfloat> @llvm.minimum.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
@@ -115,6 +134,15 @@ define void @minimum_bf16() {
 }
 
 define void @minimum_f32() {
+; GFX950-FASTF64-LABEL: 'minimum_f32'
+; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f32 = call float @llvm.minimum.f32(float undef, float undef)
+; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32 = call <2 x float> @llvm.minimum.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.minimum.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.minimum.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.minimum.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.minimum.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: 'minimum_f32'
 ; ALL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f32 = call float @llvm.minimum.f32(float undef, float undef)
 ; ALL-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %v2f32 = call <2 x float> @llvm.minimum.v2f32(<2 x float> undef, <2 x float> undef)
@@ -143,6 +171,15 @@ define void @minimum_f32() {
 }
 
 define void @minimum_f64() {
+; GFX950-FASTF64-LABEL: 'minimum_f64'
+; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f64 = call double @llvm.minimum.f64(double undef, double undef)
+; GFX950-FASTF64-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %v2f64 = call <2 x double> @llvm.minimum.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.minimum.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.minimum.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.minimum.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.minimum.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: 'minimum_f64'
 ; ALL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %f64 = call double @llvm.minimum.f64(double undef, double undef)
 ; ALL-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %v2f64 = call <2 x double> @llvm.minimum.v2f64(<2 x double> undef, <2 x double> undef)