diff options
author | Isaac Nudelman <62861466+nuudlman@users.noreply.github.com> | 2025-10-08 16:09:50 -0500 |
---|---|---|
committer | GitHub <noreply@github.com> | 2025-10-08 16:09:50 -0500 |
commit | cc14b589659b6c6c9fb65de7a274287f2490d345 (patch) | |
tree | 62d305ca7e9e95d0812588edea0c684c608b80d6 /llvm/tools/llvm-offload-binary/llvm-offload-binary.cpp | |
parent | 1395d4315bf49be64817b79e3863d183bb28c3e1 (diff) | |
download | llvm-cc14b589659b6c6c9fb65de7a274287f2490d345.zip llvm-cc14b589659b6c6c9fb65de7a274287f2490d345.tar.gz llvm-cc14b589659b6c6c9fb65de7a274287f2490d345.tar.bz2 |
[MLIR][Linalg] Fix winograd op lowering for types smaller than f32 (#158500)
The winograd transform constant array is always emitted as f32, but
previously the creation would pass through the original type. If this
type was smaller (like f16), you would get an assertion failure during
attribute creation.
This fixes this by ensuring that the types match and adding a test for
this case.
Diffstat (limited to 'llvm/tools/llvm-offload-binary/llvm-offload-binary.cpp')
0 files changed, 0 insertions, 0 deletions