[nvvm] Include llvm-optimize-for-nvvm-target pass in gpu-lower-to-nvvm-pipeline
#107102
Conversation
This file contains 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
llvmbot
added
mlir:gpu
mlir
bazel
|
@llvm/pr-subscribers-mlir-gpu Author: Christian Sigg (chsigg) ChangesThe generic pass pipeline to lower to NVVM should apply these optimizations. Full diff: https://github.com/llvm/llvm-project/pull/107102.diff 3 Files Affected:
diff --git a/mlir/lib/Dialect/GPU/Pipelines/CMakeLists.txt b/mlir/lib/Dialect/GPU/Pipelines/CMakeLists.txt
index 70a9c77a6d796a..5e5003e0e4a329 100644
--- a/mlir/lib/Dialect/GPU/Pipelines/CMakeLists.txt
+++ b/mlir/lib/Dialect/GPU/Pipelines/CMakeLists.txt
@@ -11,6 +11,7 @@ add_mlir_dialect_library(MLIRGPUPipelines
MLIRTransforms
MLIRLinalgTransforms
MLIRAffineToStandard
+ MLIRLLVMIRTransforms
MLIRGPUToNVVMTransforms
MLIRIndexToLLVM
MLIRMathToLLVM
diff --git a/mlir/lib/Dialect/GPU/Pipelines/GPUToNVVMPipeline.cpp b/mlir/lib/Dialect/GPU/Pipelines/GPUToNVVMPipeline.cpp
index fb440756e0c1d5..6051d232b2ddc1 100644
--- a/mlir/lib/Dialect/GPU/Pipelines/GPUToNVVMPipeline.cpp
+++ b/mlir/lib/Dialect/GPU/Pipelines/GPUToNVVMPipeline.cpp
@@ -30,6 +30,7 @@
#include "mlir/Dialect/GPU/Pipelines/Passes.h"
#include "mlir/Dialect/GPU/Transforms/Passes.h"
#include "mlir/Dialect/LLVMIR/LLVMDialect.h"
+#include "mlir/Dialect/LLVMIR/Transforms/OptimizeForNVVM.h"
#include "mlir/Dialect/Linalg/Passes.h"
#include "mlir/Dialect/MemRef/Transforms/Passes.h"
#include "mlir/Pass/PassManager.h"
@@ -78,6 +79,7 @@ void buildGpuPassPipeline(OpPassManager &pm,
opt.useBarePtrCallConv = options.kernelUseBarePtrCallConv;
opt.indexBitwidth = options.indexBitWidth;
pm.addNestedPass<gpu::GPUModuleOp>(createConvertGpuOpsToNVVMOps(opt));
+ pm.addNestedPass<gpu::GPUModuleOp>(NVVM::createOptimizeForTargetPass());
pm.addNestedPass<gpu::GPUModuleOp>(createCanonicalizerPass());
pm.addNestedPass<gpu::GPUModuleOp>(createCSEPass());
pm.addNestedPass<gpu::GPUModuleOp>(createReconcileUnrealizedCastsPass());
diff --git a/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel b/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel
index ddb08f12f04976..c19345ea378a00 100644
--- a/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel
+++ b/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel
@@ -5636,6 +5636,7 @@ cc_library(
":GPUTransforms",
":IndexToLLVM",
":LLVMDialect",
+ ":LLVMIRTransforms",
":LinalgTransforms",
":MathToLLVM",
":MemRefToLLVM",
|
|
@llvm/pr-subscribers-mlir Author: Christian Sigg (chsigg) ChangesThe generic pass pipeline to lower to NVVM should apply these optimizations. Full diff: https://github.com/llvm/llvm-project/pull/107102.diff 3 Files Affected:
diff --git a/mlir/lib/Dialect/GPU/Pipelines/CMakeLists.txt b/mlir/lib/Dialect/GPU/Pipelines/CMakeLists.txt
index 70a9c77a6d796a..5e5003e0e4a329 100644
--- a/mlir/lib/Dialect/GPU/Pipelines/CMakeLists.txt
+++ b/mlir/lib/Dialect/GPU/Pipelines/CMakeLists.txt
@@ -11,6 +11,7 @@ add_mlir_dialect_library(MLIRGPUPipelines
MLIRTransforms
MLIRLinalgTransforms
MLIRAffineToStandard
+ MLIRLLVMIRTransforms
MLIRGPUToNVVMTransforms
MLIRIndexToLLVM
MLIRMathToLLVM
diff --git a/mlir/lib/Dialect/GPU/Pipelines/GPUToNVVMPipeline.cpp b/mlir/lib/Dialect/GPU/Pipelines/GPUToNVVMPipeline.cpp
index fb440756e0c1d5..6051d232b2ddc1 100644
--- a/mlir/lib/Dialect/GPU/Pipelines/GPUToNVVMPipeline.cpp
+++ b/mlir/lib/Dialect/GPU/Pipelines/GPUToNVVMPipeline.cpp
@@ -30,6 +30,7 @@
#include "mlir/Dialect/GPU/Pipelines/Passes.h"
#include "mlir/Dialect/GPU/Transforms/Passes.h"
#include "mlir/Dialect/LLVMIR/LLVMDialect.h"
+#include "mlir/Dialect/LLVMIR/Transforms/OptimizeForNVVM.h"
#include "mlir/Dialect/Linalg/Passes.h"
#include "mlir/Dialect/MemRef/Transforms/Passes.h"
#include "mlir/Pass/PassManager.h"
@@ -78,6 +79,7 @@ void buildGpuPassPipeline(OpPassManager &pm,
opt.useBarePtrCallConv = options.kernelUseBarePtrCallConv;
opt.indexBitwidth = options.indexBitWidth;
pm.addNestedPass<gpu::GPUModuleOp>(createConvertGpuOpsToNVVMOps(opt));
+ pm.addNestedPass<gpu::GPUModuleOp>(NVVM::createOptimizeForTargetPass());
pm.addNestedPass<gpu::GPUModuleOp>(createCanonicalizerPass());
pm.addNestedPass<gpu::GPUModuleOp>(createCSEPass());
pm.addNestedPass<gpu::GPUModuleOp>(createReconcileUnrealizedCastsPass());
diff --git a/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel b/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel
index ddb08f12f04976..c19345ea378a00 100644
--- a/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel
+++ b/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel
@@ -5636,6 +5636,7 @@ cc_library(
":GPUTransforms",
":IndexToLLVM",
":LLVMDialect",
+ ":LLVMIRTransforms",
":LinalgTransforms",
":MathToLLVM",
":MemRefToLLVM",
|
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.
The generic pass pipeline to lower to NVVM should apply these optimizations.