Refactor elementwise kernels (#1222)

* Refactor elementwise kernels

* Instances fixes

* Fix cmake

* Fix max pool bwd test

* Update two stage gemm split k

* Restore elementwise scale for hiptensor backward compatiblity

* Fix Acc data type check in conv fwd multiple abd

* Disable conv fp64 fwd example

* Update grouped conv weight multi d
This commit is contained in:
Bartłomiej Kocot
2024-04-19 13:31:17 +02:00
committed by GitHub
parent e0f3f918f1
commit ad1597c499
38 changed files with 513 additions and 2502 deletions

View File

@@ -6,7 +6,7 @@
#include <iostream>
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_elementwise_3d_impl.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_elementwise_dynamic_vector_dims_impl.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
#include "ck/library/tensor_operation_instance/gpu/transpose_3d.hpp"