[mlir][nvvm] Add conversion for math.erfc #129329
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
clementval
requested review from
sherhut,
rscottmanley,
ftynse,
matthias-springer and
joker-eph
|
@llvm/pr-subscribers-mlir Author: Valentin Clement (バレンタイン クレメン) (clementval) ChangesAdd missing pattern to convert Full diff: https://github.com/llvm/llvm-project/pull/129329.diff 2 Files Affected:
diff --git a/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp b/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
index 61b73f546b5da..159a6afd4a917 100644
--- a/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
+++ b/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
@@ -540,6 +540,8 @@ void mlir::populateLibDeviceConversionPatterns(
"__nv_cosh");
populateOpPatterns<math::ErfOp>(converter, patterns, benefit, "__nv_erff",
"__nv_erf");
+ populateOpPatterns<math::ErfcOp>(converter, patterns, benefit, "__nv_erfcf",
+ "__nv_erfc");
populateOpPatterns<math::ExpOp>(converter, patterns, benefit, "__nv_expf",
"__nv_exp", "__nv_fast_expf");
populateOpPatterns<math::Exp2Op>(converter, patterns, benefit, "__nv_exp2f",
diff --git a/mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir b/mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
index 7b5b11ec02724..14594cd6badb1 100644
--- a/mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
+++ b/mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
@@ -1095,3 +1095,16 @@ gpu.module @test_module_54 {
return %0, %1, %2, %3, %4, %5 : i1, i1, i1, i1, i1, i1
}
}
+
+gpu.module @test_module_55 {
+ // CHECK: llvm.func @__nv_erfcf(f32) -> f32
+ // CHECK: llvm.func @__nv_erfc(f64) -> f64
+ // CHECK-LABEL: func @gpu_erf
+ func.func @gpu_erfc(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
+ %result32 = math.erfc %arg_f32 : f32
+ // CHECK: llvm.call @__nv_erfcf(%{{.*}}) : (f32) -> f32
+ %result64 = math.erfc %arg_f64 : f64
+ // CHECK: llvm.call @__nv_erfc(%{{.*}}) : (f64) -> f64
+ func.return %result32, %result64 : f32, f64
+ }
+}
|
|
@llvm/pr-subscribers-mlir-gpu Author: Valentin Clement (バレンタイン クレメン) (clementval) ChangesAdd missing pattern to convert Full diff: https://github.com/llvm/llvm-project/pull/129329.diff 2 Files Affected:
diff --git a/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp b/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
index 61b73f546b5da..159a6afd4a917 100644
--- a/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
+++ b/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
@@ -540,6 +540,8 @@ void mlir::populateLibDeviceConversionPatterns(
"__nv_cosh");
populateOpPatterns<math::ErfOp>(converter, patterns, benefit, "__nv_erff",
"__nv_erf");
+ populateOpPatterns<math::ErfcOp>(converter, patterns, benefit, "__nv_erfcf",
+ "__nv_erfc");
populateOpPatterns<math::ExpOp>(converter, patterns, benefit, "__nv_expf",
"__nv_exp", "__nv_fast_expf");
populateOpPatterns<math::Exp2Op>(converter, patterns, benefit, "__nv_exp2f",
diff --git a/mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir b/mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
index 7b5b11ec02724..14594cd6badb1 100644
--- a/mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
+++ b/mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
@@ -1095,3 +1095,16 @@ gpu.module @test_module_54 {
return %0, %1, %2, %3, %4, %5 : i1, i1, i1, i1, i1, i1
}
}
+
+gpu.module @test_module_55 {
+ // CHECK: llvm.func @__nv_erfcf(f32) -> f32
+ // CHECK: llvm.func @__nv_erfc(f64) -> f64
+ // CHECK-LABEL: func @gpu_erf
+ func.func @gpu_erfc(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
+ %result32 = math.erfc %arg_f32 : f32
+ // CHECK: llvm.call @__nv_erfcf(%{{.*}}) : (f32) -> f32
+ %result64 = math.erfc %arg_f64 : f64
+ // CHECK: llvm.call @__nv_erfc(%{{.*}}) : (f64) -> f64
+ func.return %result32, %result64 : f32, f64
+ }
+}
|
ftynse
approved these changes
Feb 28, 2025
asb
added a commit
that referenced
this pull request
Mar 12, 2025
… memset.pattern lowering As noted during review of #129329.
frederik-h
pushed a commit
to frederik-h/llvm-project
that referenced
this pull request
Mar 18, 2025
… memset.pattern lowering As noted during review of llvm#129329.
jph-13
pushed a commit
to jph-13/llvm-project
that referenced
this pull request
Mar 21, 2025
Add missing pattern to convert `math.erfc` operation to `__nv_erfcf` or `__nv_erfc` function call.
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.
Add missing pattern to convert
math.erfcoperation to__nv_erfcfor__nv_erfcfunction call.