mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-18 03:49:41 +00:00
Fused GEMM+GEMM (#351)
* initial stub for gemm_gemm_xdl_cshuffle
* set up example code
* compiles
* prevent integer overflow
* harmonize interface between ref_gemm and ref_batched_gemm
* batched_gemm_gemm
* fix example
* host tensor gen: diagonal pattern in lowest two-dimensions only
* make c descriptors containing only integral constants
* clean up
* add BlockwiseGemmXdlops_v2 while exploring an unified approach
* implement proper interface
* tidy up example
* fix compilation warnings
* coarsely controlled 2nd gemm padding
* remove rocm-cmake's hard requirement for certain revision
* clang-format
* resolve merge conflict
* fix compilation error on gfx10
* adds acc0 elementwise op to interface
* add gemm_gemm instances and tests
* avoid LDS data hazard
* fix build
Co-authored-by: Chao Liu <chao.liu2@amd.com>
[ROCm/composable_kernel commit: c20a75b07d]
This commit is contained in:
@@ -10,9 +10,9 @@
|
||||
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
|
||||
|
||||
#include "ck/library/utility/check_err.hpp"
|
||||
#include "ck/library/host_tensor/device_memory.hpp"
|
||||
#include "ck/library/host_tensor/host_tensor.hpp"
|
||||
#include "ck/library/host_tensor/host_tensor_generator.hpp"
|
||||
#include "ck/library/utility/device_memory.hpp"
|
||||
#include "ck/library/utility/host_tensor.hpp"
|
||||
#include "ck/library/utility/host_tensor_generator.hpp"
|
||||
#include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
|
||||
|
||||
template <ck::index_t... Is>
|
||||
@@ -186,9 +186,9 @@ int main(int argc, char* argv[])
|
||||
b_k_n.GenerateTensorValue(GeneratorTensor_1<ADataType>{1});
|
||||
}
|
||||
|
||||
DeviceMem a_m_k_device_buf(sizeof(ADataType) * a_m_k.mDesc.GetElementSpace());
|
||||
DeviceMem b_k_n_device_buf(sizeof(BDataType) * b_k_n.mDesc.GetElementSpace());
|
||||
DeviceMem c_m_n_device_buf(sizeof(CDataType) * c_m_n_device_result.mDesc.GetElementSpace());
|
||||
DeviceMem a_m_k_device_buf(sizeof(ADataType) * a_m_k.mDesc.GetElementSpaceSize());
|
||||
DeviceMem b_k_n_device_buf(sizeof(BDataType) * b_k_n.mDesc.GetElementSpaceSize());
|
||||
DeviceMem c_m_n_device_buf(sizeof(CDataType) * c_m_n_device_result.mDesc.GetElementSpaceSize());
|
||||
|
||||
a_m_k_device_buf.ToDevice(a_m_k.mData.data());
|
||||
b_k_n_device_buf.ToDevice(b_k_n.mData.data());
|
||||
|
||||
Reference in New Issue
Block a user