mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-01 20:21:23 +00:00
Support Wave32 in CK_TILE - Part 1 (#2594)
* Support wave32/wave64 in CK_TILE - Part 1 * remove blocksize in kernel launch * fix build error * fix clang format * fix clang format 2 * fix clang format 3 * fix fmha build error * fix fmha build 2 * fix fmha build 3 * fix build error 4 * address review comment * update change log * replace KernelBlockSize with kBlockSize * fix CI fail * fix clang format * address review comment and rebase code. * fix universal test fail --------- Co-authored-by: Lin, Qun <Quentin.Lin+amdeng@amd.com> Co-authored-by: Thomas Ning <Thomas.Ning@amd.com>
This commit is contained in:
@@ -112,17 +112,17 @@ bool run(const ck_tile::ArgParser& arg_parser)
|
||||
}
|
||||
|
||||
// 4. Run the kernel
|
||||
float ave_time = launch_kernel(ck_tile::stream_config{nullptr, true, 0, warmup, repeat},
|
||||
ck_tile::make_kernel<kBlockSize, kBlockPerCu>(
|
||||
Kernel{},
|
||||
kGridSize,
|
||||
kBlockSize,
|
||||
0, // Shared memory
|
||||
op_lengths, // Logical dimensions for the operation (M, N)
|
||||
input_strides, // Strides for input tensor(s)
|
||||
output_strides, // Strides for output tensor (N, M)
|
||||
input_tensors,
|
||||
static_cast<YDataType*>(y_buf.GetDeviceBuffer())));
|
||||
float ave_time = launch_kernel(
|
||||
ck_tile::stream_config{nullptr, true, 0, warmup, repeat},
|
||||
ck_tile::make_kernel<kBlockPerCu>(Kernel{},
|
||||
kGridSize,
|
||||
kBlockSize,
|
||||
0, // Shared memory
|
||||
op_lengths, // Logical dimensions for the operation (M, N)
|
||||
input_strides, // Strides for input tensor(s)
|
||||
output_strides, // Strides for output tensor (N, M)
|
||||
input_tensors,
|
||||
static_cast<YDataType*>(y_buf.GetDeviceBuffer())));
|
||||
|
||||
std::cout << "Average time: " << ave_time << " ms" << std::endl;
|
||||
|
||||
|
||||
Reference in New Issue
Block a user