Skip to content

[MLIR] fix shape.broadcast canonicalize with all empty shape operands #118941

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.

Sign up for GitHub

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

Merged
merged 2 commits into from
Dec 20, 2024
Merged

[MLIR] fix shape.broadcast canonicalize with all empty shape operands #118941

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0375983
[MLIR] fix shape.broadcast canonicalize all empty shape operands
YellowHCH Dec 6, 2024
1f3e26a
Merge branch 'main' into fix_shape_canonicalize
Lewuathe Dec 20, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions mlir/lib/Dialect/Shape/IR/Shape.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -698,6 +698,14 @@ struct RemoveEmptyShapeOperandsPattern : public OpRewritePattern<OpTy> {
auto newOperands = llvm::filter_to_vector<8>(op->getOperands(),
isPotentiallyNonEmptyShape);

// Replace the op with empty shape constant if all operants are reduced to
// be empty.
if (newOperands.empty()) {
rewriter.replaceOpWithNewOp<ConstShapeOp>(
op, op->getResultTypes().front(), rewriter.getIndexTensorAttr({}));
return success();
}

// Reduce op to equivalent without empty shape operands.
if (newOperands.size() < op.getNumOperands()) {
rewriter.replaceOpWithNewOp<OpTy>(op, op->getResultTypes(), newOperands,
Expand Down
16 changes: 16 additions & 0 deletions mlir/test/Dialect/Shape/canonicalize.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
// RUN: mlir-opt -split-input-file -allow-unregistered-dialect -canonicalize="test-convergence" %s | FileCheck %s
// RUN: mlir-opt -split-input-file -allow-unregistered-dialect -canonicalize="test-convergence top-down=0" %s | FileCheck %s

// CHECK-LABEL: func @f
func.func @f(%arg0: tensor<2x3x4xf32>) -> tensor<3xindex> {
Expand Down Expand Up @@ -134,6 +135,21 @@ func.func @all_but_one_empty(%arg0 : !shape.shape) -> !shape.shape {

// -----

// All operands are known empty shapes.
// CHECK-LABEL: @all_empty
// CHECK-SAME: (%[[ARG_0:.*]]: tensor<f32>, %[[ARG_1:.*]]: tensor<i1>)
func.func @all_empty(%arg0: tensor<f32>, %arg1: tensor<i1>) -> tensor<0xindex> {
// CHECK: %[[CST:.*]] = shape.const_shape [] : tensor<0xindex>
// CHECK: return %[[CST]] : tensor<0xindex>
%1 = shape.shape_of %arg0 : tensor<f32> -> tensor<0xindex>
%2 = shape.shape_of %arg1 : tensor<i1> -> tensor<0xindex>
%3 = shape.const_shape [] : tensor<0xindex>
%4 = shape.broadcast %1, %2, %3 : tensor<0xindex>, tensor<0xindex>, tensor<0xindex> -> tensor<0xindex>
return %4 : tensor<0xindex>
}

// -----

// Partial folding.
// CHECK-LABEL: @partial_folding
// CHECK-SAME: (%[[ARG:.*]]: !shape.shape)
Expand Down
Loading