Star3
37
代码
代码
Issues3
Pull Requests20
流水线
项目讨论
Wiki
分析
Star3
37
GGitHub[MLIR][Conversion] XeGPU to XeVM: Use adaptor for getting base address from memref. (#168610)
7de59f0b创建于 2025年11月20日历史提交
文件最后提交记录最后更新时间
create_nd_tdesc.mlir
[MLIR][Conversion] XeGPU to XeVM: Use adaptor for getting base address from memref. (#168610) adaptor already lowers memref to base address. Conversion patterns should use it instead of generating code to get base address from memref.
8 个月前
dpas.mlir
[MLIR][XeGPU] XeVM lowering support for load_matrix/store_matrix + fix sanitizer issue (#163858) This PR fix the sanitizer issue reported post-merge for https://github.com/llvm/llvm-project/pull/162780
9 个月前
fence.mlir
[MLIR][Conversion][XeGPU][XeVM] Add XeGPUToXeVM conversion pass and tests. (#154556) Add XeGPU to XeVM conversion pass and tests.
11 个月前
loadstore_1d.mlir
[MLIR][Conversion] XeGPU to XeVM: Use adaptor for getting base address from memref. (#168610) adaptor already lowers memref to base address. Conversion patterns should use it instead of generating code to get base address from memref.
8 个月前
loadstore_matrix.mlir
[MLIR][XeGPU] Allow create mem desc from 2d memref (#167767) This PR relax the create_mem_desc's restriction on source memref, allowing it to be a 2d memref.
8 个月前
loadstore_nd.mlir
[MLIR][Conversion] XeGPU to XeVM: Use adaptor for getting base address from memref. (#168610) adaptor already lowers memref to base address. Conversion patterns should use it instead of generating code to get base address from memref.
8 个月前
loadstoreprefetch.mlir
[MLIR][XeVM] Update XeVM prefetch ops. (#166445) xevm.blockprefetch2d op has pointer operand marked as MemRead. And that causes the op got get folded away be canonicalize pass. Remove the side effect mark and update XeGPU to XeVM prefetch op conversion test cases to use canonicalize pass.
9 个月前
materializecast.mlir
[MLIR][Conversion] Convert XeGPU to XeVM pass: Remove lowering support for tensor descriptor with offsets. (#157550) And update load/store/prefetch test cases to use direct offsets. Tensor descriptors with offsets are getting deprecated.
10 个月前
prefetch_nd.mlir
[MLIR][XeVM] Update XeVM prefetch ops. (#166445) xevm.blockprefetch2d op has pointer operand marked as MemRead. And that causes the op got get folded away be canonicalize pass. Remove the side effect mark and update XeGPU to XeVM prefetch op conversion test cases to use canonicalize pass.
9 个月前