Skip to content

[mlir][vector] Disable BreakDownVectorBitCast for scalable vectors #122725

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
Jan 24, 2025
+18 −0
Merged

[mlir][vector] Disable BreakDownVectorBitCast for scalable vectors #122725

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
7 changes: 7 additions & 0 deletions mlir/lib/Dialect/Vector/Transforms/VectorTransforms.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -906,6 +906,13 @@ struct BreakDownVectorBitCast : public OpRewritePattern<vector::BitCastOp> {
VectorType castDstType = bitcastOp.getResultVectorType();
assert(castSrcType.getRank() == castDstType.getRank());

// This transformation builds on top of
// vector.{extract|insert}_strided_slice, which do not support
// extracting/inserting "scallable sub-vectors". Bail out.
if (castSrcType.isScalable())
return rewriter.notifyMatchFailure(bitcastOp,
"Scalable vectors are not supported");

// Only support rank 1 case for now.
if (castSrcType.getRank() != 1)
return failure();
Expand Down
11 changes: 11 additions & 0 deletions mlir/test/Dialect/Vector/vector-break-down-bitcast.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,3 +39,14 @@ func.func @bitcast_i8_to_i32(%input: vector<16xi8>) -> vector<4xi32> {
// CHECK: %[[CAST3:.+]] = vector.bitcast %[[EXTRACT3]] : vector<4xi8> to vector<1xi32>
// CHECK: %[[INSERT3:.+]] = vector.insert_strided_slice %[[CAST3]], %[[INSERT2]] {offsets = [3], strides = [1]} : vector<1xi32> into vector<4xi32>
// CHECK: return %[[INSERT3]]

// -----

// Scalable vectors are not supported!

// CHECK-LABEL: func.func @bitcast_scalable_negative
// CHECK: vector.bitcast
func.func @bitcast_scalable_negative(%input: vector<[8]xf16>) -> vector<[4]xf32> {
%0 = vector.bitcast %input : vector<[8]xf16> to vector<[4]xf32>
return %0: vector<[4]xf32>
}
Loading