AMDGPU: Add some baseline cost model tests #100797
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This stack of pull requests is managed by Graphite. Learn more about stacking. |
This was referenced Jul 26, 2024
|
@llvm/pr-subscribers-llvm-transforms @llvm/pr-subscribers-backend-amdgpu Author: Matt Arsenault (arsenm) ChangesPatch is 534.48 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/100797.diff 25 Files Affected:
diff --git a/llvm/test/Analysis/CostModel/AMDGPU/arith-fp.ll b/llvm/test/Analysis/CostModel/AMDGPU/arith-fp.ll
deleted file mode 100644
index 72a3392891592..0000000000000
--- a/llvm/test/Analysis/CostModel/AMDGPU/arith-fp.ll
+++ /dev/null
@@ -1,103 +0,0 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL %s
-; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL %s
-; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL %s
-; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL %s
-
-; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL-SIZE %s
-; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL-SIZE %s
-; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL-SIZE %s
-; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL-SIZE %s
-; END.
-
-define i32 @fcopysign(i32 %arg) {
-; ALL-LABEL: 'fcopysign'
-; 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 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 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 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 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 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: %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 10 for instruction: ret i32 undef
-;
-; ALL-SIZE-LABEL: 'fcopysign'
-; 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 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 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 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: %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 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: %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 1 for instruction: ret i32 undef
-;
- %F32 = call float @llvm.copysign.f32(float undef, float undef)
- %V4F32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
- %V8F32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
- %V16F32 = call <16 x float> @llvm.copysign.v16f32(<16 x float> undef, <16 x float> undef)
-
- %F64 = call double @llvm.copysign.f64(double undef, double undef)
- %V2F64 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
- %V4F64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
- %V8F64 = call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)
-
- ret i32 undef
-}
-
-define i32 @fsqrt(i32 %arg) {
-; ALL-LABEL: 'fsqrt'
-; ALL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
-; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
-; ALL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
-; ALL-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
-; ALL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
-; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
-; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
-; ALL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
-; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
-;
-; ALL-SIZE-LABEL: 'fsqrt'
-; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
-; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
-; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
-; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
-; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
-; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
-; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
-; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.sqrt.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.sqrt.f32(float undef)
- %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
- %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
- %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
-
- %F64 = call double @llvm.sqrt.f64(double undef)
- %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
- %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
- %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
-
- ret i32 undef
-}
-
-declare float @llvm.copysign.f32(float, float)
-declare <4 x float> @llvm.copysign.v4f32(<4 x float>, <4 x float>)
-declare <8 x float> @llvm.copysign.v8f32(<8 x float>, <8 x float>)
-declare <16 x float> @llvm.copysign.v16f32(<16 x float>, <16 x float>)
-
-declare double @llvm.copysign.f64(double, double)
-declare <2 x double> @llvm.copysign.v2f64(<2 x double>, <2 x double>)
-declare <4 x double> @llvm.copysign.v4f64(<4 x double>, <4 x double>)
-declare <8 x double> @llvm.copysign.v8f64(<8 x double>, <8 x double>)
-
-declare float @llvm.sqrt.f32(float)
-declare <4 x float> @llvm.sqrt.v4f32(<4 x float>)
-declare <8 x float> @llvm.sqrt.v8f32(<8 x float>)
-declare <16 x float> @llvm.sqrt.v16f32(<16 x float>)
-
-declare double @llvm.sqrt.f64(double)
-declare <2 x double> @llvm.sqrt.v2f64(<2 x double>)
-declare <4 x double> @llvm.sqrt.v4f64(<4 x double>)
-declare <8 x double> @llvm.sqrt.v8f64(<8 x double>)
diff --git a/llvm/test/Analysis/CostModel/AMDGPU/arithmetic_fence.ll b/llvm/test/Analysis/CostModel/AMDGPU/arithmetic_fence.ll
new file mode 100644
index 0000000000000..2cee15193a503
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AMDGPU/arithmetic_fence.ll
@@ -0,0 +1,139 @@
+; 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 < %s | FileCheck -check-prefixes=ALL %s
+; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL-SIZE %s
+
+define void @arithmetic_fence_f16() {
+; ALL-LABEL: 'arithmetic_fence_f16'
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %f16 = call half @llvm.arithmetic.fence.f16(half undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2f16 = call <2 x half> @llvm.arithmetic.fence.v2f16(<2 x half> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v3f16 = call <3 x half> @llvm.arithmetic.fence.v3f16(<3 x half> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4f16 = call <4 x half> @llvm.arithmetic.fence.v4f16(<4 x half> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v5f16 = call <5 x half> @llvm.arithmetic.fence.v5f16(<5 x half> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f16 = call <8 x half> @llvm.arithmetic.fence.v8f16(<8 x half> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f16 = call <16 x half> @llvm.arithmetic.fence.v16f16(<16 x half> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v17f16 = call <17 x half> @llvm.arithmetic.fence.v17f16(<17 x half> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; ALL-SIZE-LABEL: 'arithmetic_fence_f16'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %f16 = call half @llvm.arithmetic.fence.f16(half undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2f16 = call <2 x half> @llvm.arithmetic.fence.v2f16(<2 x half> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v3f16 = call <3 x half> @llvm.arithmetic.fence.v3f16(<3 x half> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4f16 = call <4 x half> @llvm.arithmetic.fence.v4f16(<4 x half> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v5f16 = call <5 x half> @llvm.arithmetic.fence.v5f16(<5 x half> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f16 = call <8 x half> @llvm.arithmetic.fence.v8f16(<8 x half> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f16 = call <16 x half> @llvm.arithmetic.fence.v16f16(<16 x half> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v17f16 = call <17 x half> @llvm.arithmetic.fence.v17f16(<17 x half> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+ %f16 = call half @llvm.arithmetic.fence.f16(half undef)
+ %v2f16 = call <2 x half> @llvm.arithmetic.fence.v2f16(<2 x half> undef)
+ %v3f16 = call <3 x half> @llvm.arithmetic.fence.v3f16(<3 x half> undef)
+ %v4f16 = call <4 x half> @llvm.arithmetic.fence.v4f16(<4 x half> undef)
+ %v5f16 = call <5 x half> @llvm.arithmetic.fence.v5f16(<5 x half> undef)
+ %v8f16 = call <8 x half> @llvm.arithmetic.fence.v8f16(<8 x half> undef)
+ %v16f16 = call <16 x half> @llvm.arithmetic.fence.v16f16(<16 x half> undef)
+ %v17f16 = call <17 x half> @llvm.arithmetic.fence.v17f16(<17 x half> undef)
+ ret void
+}
+
+define void @arithmetic_fence_bf16() {
+; ALL-LABEL: 'arithmetic_fence_bf16'
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %bf16 = call bfloat @llvm.arithmetic.fence.bf16(bfloat undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2bf16 = call <2 x bfloat> @llvm.arithmetic.fence.v2bf16(<2 x bfloat> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v3bf16 = call <3 x bfloat> @llvm.arithmetic.fence.v3bf16(<3 x bfloat> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4bf16 = call <4 x bfloat> @llvm.arithmetic.fence.v4bf16(<4 x bfloat> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v5bf16 = call <5 x bfloat> @llvm.arithmetic.fence.v5bf16(<5 x bfloat> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8bf16 = call <8 x bfloat> @llvm.arithmetic.fence.v8bf16(<8 x bfloat> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16bf16 = call <16 x bfloat> @llvm.arithmetic.fence.v16bf16(<16 x bfloat> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v17bf16 = call <17 x bfloat> @llvm.arithmetic.fence.v17bf16(<17 x bfloat> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; ALL-SIZE-LABEL: 'arithmetic_fence_bf16'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %bf16 = call bfloat @llvm.arithmetic.fence.bf16(bfloat undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2bf16 = call <2 x bfloat> @llvm.arithmetic.fence.v2bf16(<2 x bfloat> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v3bf16 = call <3 x bfloat> @llvm.arithmetic.fence.v3bf16(<3 x bfloat> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4bf16 = call <4 x bfloat> @llvm.arithmetic.fence.v4bf16(<4 x bfloat> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v5bf16 = call <5 x bfloat> @llvm.arithmetic.fence.v5bf16(<5 x bfloat> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8bf16 = call <8 x bfloat> @llvm.arithmetic.fence.v8bf16(<8 x bfloat> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16bf16 = call <16 x bfloat> @llvm.arithmetic.fence.v16bf16(<16 x bfloat> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v17bf16 = call <17 x bfloat> @llvm.arithmetic.fence.v17bf16(<17 x bfloat> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+ %bf16 = call bfloat @llvm.arithmetic.fence.bf16(bfloat undef)
+ %v2bf16 = call <2 x bfloat> @llvm.arithmetic.fence.v2bf16(<2 x bfloat> undef)
+ %v3bf16 = call <3 x bfloat> @llvm.arithmetic.fence.v3bf16(<3 x bfloat> undef)
+ %v4bf16 = call <4 x bfloat> @llvm.arithmetic.fence.v4bf16(<4 x bfloat> undef)
+ %v5bf16 = call <5 x bfloat> @llvm.arithmetic.fence.v5bf16(<5 x bfloat> undef)
+ %v8bf16 = call <8 x bfloat> @llvm.arithmetic.fence.v8bf16(<8 x bfloat> undef)
+ %v16bf16 = call <16 x bfloat> @llvm.arithmetic.fence.v16bf16(<16 x bfloat> undef)
+ %v17bf16 = call <17 x bfloat> @llvm.arithmetic.fence.v17bf16(<17 x bfloat> undef)
+ ret void
+}
+
+define void @arithmetic_fence_f32() {
+; ALL-LABEL: 'arithmetic_fence_f32'
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %f32 = call float @llvm.arithmetic.fence.f32(float undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2f32 = call <2 x float> @llvm.arithmetic.fence.v2f32(<2 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v3f32 = call <3 x float> @llvm.arithmetic.fence.v3f32(<3 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4f32 = call <4 x float> @llvm.arithmetic.fence.v4f32(<4 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v5f32 = call <5 x float> @llvm.arithmetic.fence.v5f32(<5 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f32 = call <8 x float> @llvm.arithmetic.fence.v8f32(<8 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f32 = call <16 x float> @llvm.arithmetic.fence.v16f32(<16 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v17f32 = call <17 x float> @llvm.arithmetic.fence.v17f32(<17 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; ALL-SIZE-LABEL: 'arithmetic_fence_f32'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %f32 = call float @llvm.arithmetic.fence.f32(float undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2f32 = call <2 x float> @llvm.arithmetic.fence.v2f32(<2 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v3f32 = call <3 x float> @llvm.arithmetic.fence.v3f32(<3 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4f32 = call <4 x float> @llvm.arithmetic.fence.v4f32(<4 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v5f32 = call <5 x float> @llvm.arithmetic.fence.v5f32(<5 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f32 = call <8 x float> @llvm.arithmetic.fence.v8f32(<8 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f32 = call <16 x float> @llvm.arithmetic.fence.v16f32(<16 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v17f32 = call <17 x float> @llvm.arithmetic.fence.v17f32(<17 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+ %f32 = call float @llvm.arithmetic.fence.f32(float undef)
+ %v2f32 = call <2 x float> @llvm.arithmetic.fence.v2f32(<2 x float> undef)
+ %v3f32 = call <3 x float> @llvm.arithmetic.fence.v3f32(<3 x float> undef)
+ %v4f32 = call <4 x float> @llvm.arithmetic.fence.v4f32(<4 x float> undef)
+ %v5f32 = call <5 x float> @llvm.arithmetic.fence.v5f32(<5 x float> undef)
+ %v8f32 = call <8 x float> @llvm.arithmetic.fence.v8f32(<8 x float> undef)
+ %v16f32 = call <16 x float> @llvm.arithmetic.fence.v16f32(<16 x float> undef)
+ %v17f32 = call <17 x float> @llvm.arithmetic.fence.v17f32(<17 x float> undef)
+ ret void
+}
+
+define void @arithmetic_fence_f64() {
+; ALL-LABEL: 'arithmetic_fence_f64'
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %f64 = call double @llvm.arithmetic.fence.f64(double undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2f64 = call <2 x double> @llvm.arithmetic.fence.v2f64(<2 x double> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v3f64 = call <3 x double> @llvm.arithmetic.fence.v3f64(<3 x double> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4f64 = call <4 x double> @llvm.arithmetic.fence.v4f64(<4 x double> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v5f64 = call <5 x double> @llvm.arithmetic.fence.v5f64(<5 x double> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f64 = call <8 x double> @llvm.arithmetic.fence.v8f64(<8 x double> undef)
+; ALL-NEXT: Cost Model: Found an estimated cos...
[truncated]
|
llvmbot
added
llvm:analysis
rovka
approved these changes
Jul 29, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.