Tori Baker 97e35b677b [BACKEND] fix division by 0 pathway (#2412) ...

It was possible for multiDimWarpId[1] to be 0 which then gets translated
into a `urem 0, 0` and results in an unreachable when going through
llvm, an empty kernel, and nans. This PR uses ceiling to clamp the
result to be >=1.

chsigg is working on a fix to lower the unreachable in llvm to a trap
(https://github.com/llvm/llvm-project/pull/67478).

2023-09-30 10:53:43 -07:00

..

divide-by-0.mlir

[BACKEND] fix division by 0 pathway (#2412)

2023-09-30 10:53:43 -07:00

invalid.mlir

[FRONTEND][BACKEND] Add flag to control accumulation for fp8 (#2300)

2023-09-15 18:42:54 -07:00

triton_ops.mlir

[FRONTEND][BACKEND] Add flag to control accumulation for fp8 (#2300)

2023-09-15 18:42:54 -07:00

triton_to_tritongpu.mlir

[FRONTEND][BACKEND] Add flag to control accumulation for fp8 (#2300)

2023-09-15 18:42:54 -07:00

tritongpu_to_llvm_hopper.mlir

[BACKEND] turn on MMA V3 by default on Hopper (#2414)

2023-09-28 22:45:28 -07:00

tritongpu_to_llvm.mlir

Lit test to check for illegal st.shared.b1 llvmir (#2387)

2023-09-26 17:12:32 +00:00