[GPUToXeVMPipeline][Pipeline] Modify pipeline to add convert-vector-to-llvm.
#166204
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
Member
|
@llvm/pr-subscribers-mlir Author: Md Abdullah Shahneous Bari (mshahneo) ChangesFull diff: https://github.com/llvm/llvm-project/pull/166204.diff 1 Files Affected:
diff --git a/mlir/lib/Dialect/GPU/Pipelines/GPUToXeVMPipeline.cpp b/mlir/lib/Dialect/GPU/Pipelines/GPUToXeVMPipeline.cpp
index 1a1485ba2e02c..1c46fa518dd99 100644
--- a/mlir/lib/Dialect/GPU/Pipelines/GPUToXeVMPipeline.cpp
+++ b/mlir/lib/Dialect/GPU/Pipelines/GPUToXeVMPipeline.cpp
@@ -85,6 +85,7 @@ void buildGPUPassPipeline(OpPassManager &pm,
pm.addNestedPass<gpu::GPUModuleOp>(
createConvertGpuOpsToLLVMSPVOps(gpuToLLVMSPVOptions));
}
+ pm.addNestedPass<gpu::GPUModuleOp>(createConvertToLLVMPass());
pm.addNestedPass<gpu::GPUModuleOp>(createCSEPass());
pm.addNestedPass<gpu::GPUModuleOp>(createReconcileUnrealizedCastsPass());
}
@@ -106,6 +107,8 @@ void buildPostGPUCommonPassPipeline(
pm.addPass(createLowerAffinePass());
pm.addPass(createConvertToLLVMPass());
pm.addPass(createReconcileUnrealizedCastsPass());
+ pm.addNestedPass<gpu::GPUModuleOp>(createCanonicalizerPass());
+ pm.addNestedPass<gpu::GPUModuleOp>(createCSEPass());
// gpu-module-to-binary
{
GpuModuleToBinaryPassOptions gpuToModuleBinOptions;
|
Member
|
@llvm/pr-subscribers-mlir-gpu Author: Md Abdullah Shahneous Bari (mshahneo) ChangesFull diff: https://github.com/llvm/llvm-project/pull/166204.diff 1 Files Affected:
diff --git a/mlir/lib/Dialect/GPU/Pipelines/GPUToXeVMPipeline.cpp b/mlir/lib/Dialect/GPU/Pipelines/GPUToXeVMPipeline.cpp
index 1a1485ba2e02c..1c46fa518dd99 100644
--- a/mlir/lib/Dialect/GPU/Pipelines/GPUToXeVMPipeline.cpp
+++ b/mlir/lib/Dialect/GPU/Pipelines/GPUToXeVMPipeline.cpp
@@ -85,6 +85,7 @@ void buildGPUPassPipeline(OpPassManager &pm,
pm.addNestedPass<gpu::GPUModuleOp>(
createConvertGpuOpsToLLVMSPVOps(gpuToLLVMSPVOptions));
}
+ pm.addNestedPass<gpu::GPUModuleOp>(createConvertToLLVMPass());
pm.addNestedPass<gpu::GPUModuleOp>(createCSEPass());
pm.addNestedPass<gpu::GPUModuleOp>(createReconcileUnrealizedCastsPass());
}
@@ -106,6 +107,8 @@ void buildPostGPUCommonPassPipeline(
pm.addPass(createLowerAffinePass());
pm.addPass(createConvertToLLVMPass());
pm.addPass(createReconcileUnrealizedCastsPass());
+ pm.addNestedPass<gpu::GPUModuleOp>(createCanonicalizerPass());
+ pm.addNestedPass<gpu::GPUModuleOp>(createCSEPass());
// gpu-module-to-binary
{
GpuModuleToBinaryPassOptions gpuToModuleBinOptions;
|
mshahneo
changed the title
convert-vector-to-llvm.
The `convert-vector-to-llvm` pass applies a set of vector transformation patterns that are not included in the standard `convert-to-llvm` pass interface. These additional transformations are required to properly lower MLIR vector operations. Since not all vector ops have direct `llvm` dialect lowering, many of them must first be progressively rewritten into simpler or more canonical vector ops, which are then lowered to `llvm`. Therefore, running `convert-vector-to-llvm` is necessary to ensure a complete and correct lowering of vector operations to the `llvm` dialect.
Collaborator
|
LLVM Buildbot has detected a new failure on builder Full details are available at: https://lab.llvm.org/buildbot/#/builders/203/builds/30172 Here is the relevant piece of the build log for the reference |
Collaborator
|
LLVM Buildbot has detected a new failure on builder Full details are available at: https://lab.llvm.org/buildbot/#/builders/205/builds/28962 Here is the relevant piece of the build log for the reference |
Collaborator
|
LLVM Buildbot has detected a new failure on builder Full details are available at: https://lab.llvm.org/buildbot/#/builders/204/builds/28983 Here is the relevant piece of the build log for the reference |
llvm-sync bot
pushed a commit
to arm/arm-toolchain
that referenced
this pull request
Nov 25, 2025
…dd `convert-vector-to-llvm`." (#169570) Reverts llvm/llvm-project#166204 There was a build issue due to a missing dependency.
mshahneo
added a commit
that referenced
this pull request
Nov 26, 2025
…-vector-to-llvm`. (#169573) `convert-vector-to-llvm` pass applies a set of vector transformation patterns that are not included in the standard `convert-to-llvm` pass interface. These additional transformations are required to properly lower MLIR vector operations. Since not all vector ops have direct `llvm` dialect lowering, many of them must first be progressively rewritten into simpler or more canonical vector ops, which are then lowered to `llvm`. Therefore, running `convert-vector-to-llvm` is necessary to ensure a complete and correct lowering of vector operations to the `llvm` dialect. Original PR: #166204 + post-commit failure fixes.
llvm-sync bot
pushed a commit
to arm/arm-toolchain
that referenced
this pull request
Nov 26, 2025
…dd `convert-vector-to-llvm`. (#169573) `convert-vector-to-llvm` pass applies a set of vector transformation patterns that are not included in the standard `convert-to-llvm` pass interface. These additional transformations are required to properly lower MLIR vector operations. Since not all vector ops have direct `llvm` dialect lowering, many of them must first be progressively rewritten into simpler or more canonical vector ops, which are then lowered to `llvm`. Therefore, running `convert-vector-to-llvm` is necessary to ensure a complete and correct lowering of vector operations to the `llvm` dialect. Original PR: llvm/llvm-project#166204 + post-commit failure fixes.
tanji-dg
pushed a commit
to tanji-dg/llvm-project
that referenced
this pull request
Nov 27, 2025
…-vector-to-llvm`. (llvm#169573) `convert-vector-to-llvm` pass applies a set of vector transformation patterns that are not included in the standard `convert-to-llvm` pass interface. These additional transformations are required to properly lower MLIR vector operations. Since not all vector ops have direct `llvm` dialect lowering, many of them must first be progressively rewritten into simpler or more canonical vector ops, which are then lowered to `llvm`. Therefore, running `convert-vector-to-llvm` is necessary to ensure a complete and correct lowering of vector operations to the `llvm` dialect. Original PR: llvm#166204 + post-commit failure fixes.
GeneraluseAI
pushed a commit
to GeneraluseAI/llvm-project
that referenced
this pull request
Nov 27, 2025
…-vector-to-llvm`. (llvm#169573) `convert-vector-to-llvm` pass applies a set of vector transformation patterns that are not included in the standard `convert-to-llvm` pass interface. These additional transformations are required to properly lower MLIR vector operations. Since not all vector ops have direct `llvm` dialect lowering, many of them must first be progressively rewritten into simpler or more canonical vector ops, which are then lowered to `llvm`. Therefore, running `convert-vector-to-llvm` is necessary to ensure a complete and correct lowering of vector operations to the `llvm` dialect. Original PR: llvm#166204 + post-commit failure fixes.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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
convert-vector-to-llvmpass applies a set of vector transformation patterns that are not included in the standardconvert-to-llvmpass interface. These additional transformations are required to properly lower MLIR vector operations. Since not all vector ops have directllvmdialect lowering, many of them must first be progressively rewritten into simpler or more canonical vector ops, which are then lowered tollvm. Therefore, runningconvert-vector-to-llvmis necessary to ensure a complete and correct lowering of vector operations to thellvmdialect.