ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-12 01:10:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

added implicit gemm v4 (nchw, kcyx)

Browse Source
This commit is contained in:
Chao Liu
2019-05-30 20:28:01 -05:00
parent b2439ec9dd
commit cb78cc74b7
5 changed files with 40 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/include/ConstantTensorDescriptor.hip.hpp
View File

@@ -215,7 +215,7 @@ struct ConstantTensorDescriptor
// do carry check in reversed order, starting from lowest dimension
// don't check the highest dimension
static_for<0, nDim - 1, 1>{}([&](auto IDimReverse) {
static_for<0, nDim, 1>{}([&](auto IDimReverse) {
constexpr index_t idim = nDim - 1 - IDimReverse.Get();
constexpr auto IDim = Number<idim>{};
@@ -241,7 +241,7 @@ struct ConstantTensorDescriptor
// do borrow check in reversed order, starting from lowest dimension
// don't check the highest dimension
static_for<0, nDim - 1, 1>{}([&](auto IDimReverse) {
static_for<0, nDim, 1>{}([&](auto IDimReverse) {
constexpr index_t idim = nDim - 1 - IDimReverse.Get();
constexpr auto IDim = Number<idim>{};