triton

Author	SHA1	Message	Date
Yan Chunwei	e419781978	[Triton-MLIR][BACKEND] Make mmav1 works on basic cases (#944 ) TODO: - Add more cases - Currently, we just set vec to 4 to make the basic cases pass Issue: - the vec in shared layout is different compared to master branch - when vec=1, it encounters CUDA misalignment error, it doesn't work in master branch as well - when setting vec to the value identical to master branch, the MMA works	2022-12-06 10:57:08 +08:00
Qingyi Liu	661be523c0	[Triton-MLIR][BACKEND] Minor fixes of shared memory in ReduceOpConversion (#924 )	2022-11-29 11:50:31 +08:00
Yan Chunwei	c87fbf886e	[Triton-MLIR][BACKEND] Remove static and unnamed namespace in Utility.h (#923 ) Reference https://wiki.sei.cmu.edu/confluence/display/cplusplus/DCL59-CPP.+Do+not+define+an+unnamed+namespace+in+a+header+file	2022-11-29 01:06:06 +00:00
Qingyi Liu	9d31998a9d	[Triton-MLIR][BACKEND] Add argmin / argmax implementation for ReduceOp (#918 )	2022-11-27 22:59:27 -08:00
Yan Chunwei	04ec5deb41	[Triton-MLIR][BACKEND] decouple the dot code (#921 ) This PR - apply minimal modification to decouple the Dot helper related code from TritonGPUToLLVM.cpp to a separate local header file to make it easier to share some data structure for Dot - add some patch necessary for transA and transB - add some patch necessary for MMA v1 execution in backend	2022-11-28 13:30:27 +08:00