Skip to content

[MLIR][GPU] Fix memref.dim folding with out-of-bound index #118890

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 1 commit into from
Dec 6, 2024
Merged

[MLIR][GPU] Fix memref.dim folding with out-of-bound index #118890

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 2 additions & 1 deletion mlir/lib/Dialect/GPU/IR/GPUDialect.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2075,7 +2075,8 @@ struct SimplifyDimOfAllocOp : public OpRewritePattern<memref::DimOp> {
return failure();

auto memrefType = llvm::dyn_cast<MemRefType>(dimOp.getSource().getType());
if (!memrefType || !memrefType.isDynamicDim(index.value()))
if (!memrefType || index.value() >= memrefType.getRank() ||
!memrefType.isDynamicDim(index.value()))
return failure();

auto alloc = dimOp.getSource().getDefiningOp<AllocOp>();
Expand Down
11 changes: 11 additions & 0 deletions mlir/test/Dialect/GPU/canonicalize.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -152,6 +152,17 @@ func.func @gpu_dim_of_alloc(%size: index) -> index {

// -----

// CHECK-LABEL: func @out_of_bound_memref.dim
// CHECK: %[[MEMREF:.[a-z0-9A-Z_]+]] = memref.dim
// CHECK: return %[[MEMREF]] : index
func.func @out_of_bound_memref.dim(%arg : memref<?xi8>, %size: index) -> index {
%c2 = arith.constant 2 : index
%1 = memref.dim %arg, %c2 : memref<?xi8>
return %1 : index
}

// -----

// CHECK-LABEL: func @simplify_gpu_launch
func.func @simplify_gpu_launch() attributes {llvm.emit_c_interface} {
%cst = arith.constant 0.000000e+00 : f32
Expand Down
Loading