Closed lezcano closed 1 day ago
We unify it and simplify its API (it was taking an unused shape parameter). While doing this, we found that the previous implementation was incorrect at least for AMDWmmaEncodingAttr, as this layout was using the shape parameter.
shape
AMDWmmaEncodingAttr
Interestingly enough the doc in the header file for this function noted that the function is indeed independent of the tensor shape, even though the function does take a shape as an input! https://github.com/triton-lang/triton/blob/0bd30a2f3192204c5a50d5ffde27ad8493f6c026/include/triton/Dialect/TritonGPU/IR/Dialect.h#L113-L114
We unify it and simplify its API (it was taking an unused
shape
parameter). While doing this, we found that the previous implementation was incorrect at least forAMDWmmaEncodingAttr
, as this layout was using the shape parameter.Interestingly enough the doc in the header file for this function noted that the function is indeed independent of the tensor shape, even though the function does take a shape as an input! https://github.com/triton-lang/triton/blob/0bd30a2f3192204c5a50d5ffde27ad8493f6c026/include/triton/Dialect/TritonGPU/IR/Dialect.h#L113-L114