llvm-project.git/mlir/lib/Dialect/XeGPU/Transforms/XeGPUVectorLinearize.cpp, branch mainUnnamed repository; edit this file 'description' to name the repository.
[mlir][XeGPU][Transform] Add vectorlinearize transform pass. (#158084)2025-09-18T22:25:38+00:00Md Abdullah Shahneous Bari98356296+mshahneo@users.noreply.github.com2025-09-18T22:25:38+00:0004c4e9da133a5f206ded35c7eddd9e2ab34926c7
Use upstream patterns to create a vectorlinearize pass needed for
lowering to XeVM.
Linearizes n-D vectors to 1-D vectors.
This is needed because, `vector-to-llvm` does not linearize all the
vectors.
Use upstream patterns to create a vectorlinearize pass needed for
lowering to XeVM.
Linearizes n-D vectors to 1-D vectors.
This is needed because, `vector-to-llvm` does not linearize all the
vectors.