ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-03 13:11:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add fp8 @ bf8 gemm support and example (#933)

Browse Source 
* Add f8 bf8 gemm example

* Add element-wise ops

* Add intrinsics

* Update reference calculation

* Add an additional type option for xdlops gemm

* Fix build process

* Add bf8 to buffer addressing

* Update blockwise op, split typeA and typeB

* Update for compatibility

* Uppdate naming to f8->fp8

* Update naming

* Format
This commit is contained in:
Rostyslav Geyyer
2023-10-02 16:39:03 -05:00
committed by GitHub
parent 59dbb01fd1
commit bd09b5c538
36 changed files with 475 additions and 159 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle.hpp
View File

@@ -66,7 +66,8 @@ template <typename ALayout,
index_t CShuffleBlockTransferScalarPerVector_NPerBlock,
LoopScheduler LoopSched = make_default_loop_scheduler(),
PipelineVersion PipelineVer = PipelineVersion::v1,
typename ComputeType = CDataType>
typename ComputeTypeA = CDataType,
typename ComputeTypeB = ComputeTypeA>
struct DeviceGemm_Xdl_CShuffle : public DeviceGemm<ALayout,
BLayout,
CLayout,
@@ -131,7 +132,8 @@ struct DeviceGemm_Xdl_CShuffle : public DeviceGemm<ALayout,
CShuffleBlockTransferScalarPerVector_NPerBlock,
LoopSched,
PipelineVer,
ComputeType>;
ComputeTypeA,
ComputeTypeB>;
using Argument = typename GridwiseGemm::Argument;