donproc 5eee738df7 [Triton-MLIR][FRONTEND] [BACKEND] fix atomics (#879) ...

minor fix to backend and frontend of atomics, we can pass 1 test without
mask and the shape aligned with CTA size now

Co-authored-by: dongdongl <dongdongl@nvidia.com>

2022-11-16 12:25:15 +08:00

..

__init__.py

[FRONTEND] Expose end-to-end compile to python frontend (#58)

2022-08-17 10:42:48 -07:00

printf_helper.py

[Triton-MLIR]Add ptx vprintf support (#825)

2022-11-02 16:39:09 +08:00

test_compiler.py

[FRONTEND] Backport new runtime from master (#706)

2022-09-23 16:09:43 -07:00

test_core.py

[Triton-MLIR][FRONTEND] [BACKEND] fix atomics (#879)

2022-11-16 12:25:15 +08:00

test_elementwise.py

[Triton-MLIR] Add ex2.approx implementation for ExpOp and fix smem allocation for ReduceOpConversion (#875)

2022-11-15 01:27:32 +00:00

test_ext_elemwise.py

[Triton-MLIR][BACKEND] Add elementwise ops and tests (#804)

2022-10-28 05:26:29 +00:00

test_gemm.py

[Triton-MLIR][Backend] Fix convert_layout blocked->shared in non-default order (#876)

2022-11-15 09:02:46 +08:00

test_printf.py

[Triton-MLIR]Add ptx vprintf support (#825)

2022-11-02 16:39:09 +08:00

test_reduce.py

[BACKEND] Added support for mma layouts in reductions (#863)

2022-11-10 09:58:07 -08:00

test_transpose.py

[triton-mlir][BACKEND] Support masked load/store (#657)

2022-10-10 13:29:53 +08:00

test_vecadd.py

[Triton-MLIR] Fix some typos (#874)

2022-11-13 18:15:53 -08:00