ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-07-01 04:07:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

clang format

Browse Source
This commit is contained in:
aska-0096
2024-09-04 15:11:51 +00:00
parent 99475cf8f9
commit 41fcfbc64e
13 changed files with 232 additions and 487 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
example/01_gemm/run_gemm_example_v2.inc
View File

@@ -272,7 +272,8 @@ bool run_gemm(const ProblemType& problem_size, const ExecutionConfig& config)
if(config.time_kernel)
{
ave_time = invoker.Run(argument, StreamConfig{nullptr, config.time_kernel, 0, 10, 5, true, 5});
ave_time =
invoker.Run(argument, StreamConfig{nullptr, config.time_kernel, 0, 10, 5, true, 5});
std::size_t flop = 2_uz * M * N * K;
std::size_t num_btype =

61
example/02_gemm_bilinear/gemm_bilinear_xdl_fp16_v3.cpp
View File

@@ -65,22 +65,51 @@ using CDEElementOp = AlphaBetaAdd;
static constexpr auto GemmSpec = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
using DeviceOpInstance =
ck::tensor_operation::device::DeviceGemmMultiD_Xdl_CShuffle_V3<
ALayout, BLayout, DsLayout, ELayout,
ADataType, BDataType, DsDataType, EDataType, AccDataType, CShuffleDataType,
AElementOp, BElementOp, CDEElementOp, GemmDefault,
256,
128, 128,
64, 8, 8,
16, 16,
4, 4,
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>,
2, 8, 8, 0,
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>,
2, 8, 8, 0,
1, 2, S<1, 32, 1, 8>, S<8, 8, 1>,
ck::BlockGemmPipelineScheduler::Intrawave,ck::BlockGemmPipelineVersion::v3>;
using DeviceOpInstance = ck::tensor_operation::device::DeviceGemmMultiD_Xdl_CShuffle_V3<
ALayout,
BLayout,
DsLayout,
ELayout,
ADataType,
BDataType,
DsDataType,
EDataType,
AccDataType,
CShuffleDataType,
AElementOp,
BElementOp,
CDEElementOp,
GemmDefault,
256,
128,
128,
64,
8,
8,
16,
16,
4,
4,
S<8, 32, 1>,
S<1, 0, 2>,
S<1, 0, 2>,
2,
8,
8,
0,
S<8, 32, 1>,
S<1, 0, 2>,
S<1, 0, 2>,
2,
8,
8,
0,
1,
2,
S<1, 32, 1, 8>,
S<8, 8, 1>,
ck::BlockGemmPipelineScheduler::Intrawave,
ck::BlockGemmPipelineVersion::v3>;
int main(int argc, char* argv[])
{