ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-04 05:31:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

Contraction multi abd (#957)

Browse Source 
* add gridwise_multi_abd

* move element_op into RunRead

* merge element_wise op with data read

* add multiABD example

* allow packed elementwise_op

* changed example

* clean

* clean

* add is_detected

* fix

* minor fix

* add scaleAdd_vec4 example

* init commit for contraction_multi_ABD

* add examples

* add examples of multiA and broadcast

* update example

* fixed comments

* Update cmake-ck-dev.sh

* Update cmake-ck-dev.sh

* Add comments into the example

---------

Co-authored-by: Jing Zhang <jizha@amd.com>
This commit is contained in:
zjing14
2023-10-02 09:18:36 -05:00
committed by GitHub
parent 6b5f647371
commit 9d58c42103
7 changed files with 1618 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_abd_xdl_cshuffle.hpp
View File

@@ -428,7 +428,7 @@ struct GridwiseGemmMultipleABD_xdl_cshuffle
[&](auto i) {
using ALayout = remove_cvref_t<tuple_element_t<i.value, AsLayout>>;
return MakeEGridDescriptor_M_N<ALayout, GemmSpec>(MRaws[i], KRaws[i], AsStride[i]);
return MakeAGridDescriptor_M_K<ALayout, GemmSpec>(MRaws[i], KRaws[i], AsStride[i]);
},
Number<NumATensor>{});
}