-
Notifications
You must be signed in to change notification settings - Fork 12.6k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[mlir][sparse] remove sparse encoding propagation pass. #93593
Merged
Merged
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
This reverts commit 4962148.
yinying-lisa-li
approved these changes
May 28, 2024
@llvm/pr-subscribers-mlir-sparse @llvm/pr-subscribers-mlir Author: Peiming Liu (PeimingLiu) ChangesThis reverts commit 4962148. Full diff: https://github.com/llvm/llvm-project/pull/93593.diff 3 Files Affected:
diff --git a/mlir/include/mlir/Dialect/SparseTensor/Transforms/Passes.h b/mlir/include/mlir/Dialect/SparseTensor/Transforms/Passes.h
index bb49d6c256f21..d6d038ef65bdf 100644
--- a/mlir/include/mlir/Dialect/SparseTensor/Transforms/Passes.h
+++ b/mlir/include/mlir/Dialect/SparseTensor/Transforms/Passes.h
@@ -65,12 +65,6 @@ void populateSparseAssembler(RewritePatternSet &patterns, bool directOut);
std::unique_ptr<Pass> createSparseAssembler();
std::unique_ptr<Pass> createSparseAssembler(bool directOut);
-//===----------------------------------------------------------------------===//
-// The SparseEncodingPropagation pass.
-//===----------------------------------------------------------------------===//
-
-std::unique_ptr<Pass> createSparseEncodingPropagationPass();
-
//===----------------------------------------------------------------------===//
// The SparseReinterpretMap pass.
//===----------------------------------------------------------------------===//
diff --git a/mlir/include/mlir/Dialect/SparseTensor/Transforms/Passes.td b/mlir/include/mlir/Dialect/SparseTensor/Transforms/Passes.td
index 94c3ca60030ee..2f844cee5ff52 100644
--- a/mlir/include/mlir/Dialect/SparseTensor/Transforms/Passes.td
+++ b/mlir/include/mlir/Dialect/SparseTensor/Transforms/Passes.td
@@ -40,42 +40,6 @@ def SparseAssembler : Pass<"sparse-assembler", "ModuleOp"> {
];
}
-def SparseEncodingPropagation : Pass<"sparse-encoding-propagation", "func::FuncOp"> {
- let summary = "Propagate sparse tensor encodings";
- let description = [{
- A pass that propagates sparse tensor encodings.
-
- Background: To avoid introducing repetitive operations, sparse tensors
- in MLIR try to reuse tensor operations whenever available. However, most
- tensor operations are canonicalized/transformed without the knowledge
- of sparsity. The pass tries to propagate missing sparse encodings.
-
- For example:
- ```mlir
- %s = tensor.extract_slice %input[0, 0,] [2, 1] [1, 1]
- : tensor<2x3xf32, #sparse> to tensor<2x1xf32, #sparse>
-
- // After rank reducing (by tensor dialect transformation)
- %t = tensor.extract_slice %input[0, 0,] [2, 1] [1, 1]
- : tensor<2x3xf32, #sparse> to tensor<2xf32>
- %s = tensor.expand_shape [[0, 1]] %t
- : tensor<2xf32> to tensor<2x1xf32, #sparse>
-
- // After sparsity propagation
- %t = tensor.extract_slice %input[0, 0,] [2, 1] [1, 1]
- : tensor<2x3xf32, #sparse> to tensor<2xf32, #sparse1>
- %s = tensor.expand_shape [[0, 1]] %t
- : tensor<2xf32, #sparse1> to tensor<2x1xf32, #sparse>
- ```
- }];
-
- let constructor = "mlir::createSparseEncodingPropagationPass()";
- let dependentDialects = [
- "sparse_tensor::SparseTensorDialect",
- "tensor::TensorDialect",
- ];
-}
-
def SparseReinterpretMap : Pass<"sparse-reinterpret-map", "ModuleOp"> {
let summary = "Reinterprets sparse tensor type mappings";
let description = [{
diff --git a/mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorPasses.cpp b/mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorPasses.cpp
index f57353b5892b5..b42d58634a36c 100644
--- a/mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorPasses.cpp
+++ b/mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorPasses.cpp
@@ -23,7 +23,6 @@
namespace mlir {
#define GEN_PASS_DEF_SPARSEASSEMBLER
-#define GEN_PASS_DEF_SPARSEENCODINGPROPAGATION
#define GEN_PASS_DEF_SPARSEREINTERPRETMAP
#define GEN_PASS_DEF_PRESPARSIFICATIONREWRITE
#define GEN_PASS_DEF_SPARSIFICATIONPASS
@@ -61,14 +60,6 @@ struct SparseAssembler : public impl::SparseAssemblerBase<SparseAssembler> {
}
};
-struct SparseEncodingPropagation
- : public impl::SparseEncodingPropagationBase<SparseEncodingPropagation> {
- SparseEncodingPropagation() = default;
- SparseEncodingPropagation(const SparseEncodingPropagation &pass) = default;
-
- void runOnOperation() override {}
-};
-
struct SparseReinterpretMap
: public impl::SparseReinterpretMapBase<SparseReinterpretMap> {
SparseReinterpretMap() = default;
@@ -407,10 +398,6 @@ std::unique_ptr<Pass> mlir::createSparseAssembler() {
return std::make_unique<SparseAssembler>();
}
-std::unique_ptr<Pass> mlir::createSparseEncodingPropagationPass() {
- return std::make_unique<SparseEncodingPropagation>();
-}
-
std::unique_ptr<Pass> mlir::createSparseReinterpretMapPass() {
return std::make_unique<SparseReinterpretMap>();
}
|
vg0204
pushed a commit
to vg0204/llvm-project
that referenced
this pull request
May 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.
This reverts commit 4962148.