mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-04-20 06:49:15 +00:00
Batched gemm and reduction (#156)
* adding batched_gemm_and_reduction * batched_gemm_reduce works with bactch_count=1 * fix a bug in grid_size; batched_gemm_reduce works for batch_count > 1 * adding profiler for batched_gemm_fp16 * fixed a bug in declaration of d1 and d0; both example and profiler work * clang-format * cleanup * batched_gemm_reduce: add test * minor change * fixed some typo in function names
This commit is contained in:
@@ -5,11 +5,9 @@
|
||||
#include <stdlib.h>
|
||||
#include <half.hpp>
|
||||
#include "config.hpp"
|
||||
#include "print.hpp"
|
||||
#include "device.hpp"
|
||||
#include "host_tensor.hpp"
|
||||
#include "host_tensor_generator.hpp"
|
||||
#include "host_gemm.hpp"
|
||||
#include "device_tensor.hpp"
|
||||
#include "device_gemm_xdl.hpp"
|
||||
#include "device_gemm_xdl_c_shuffle.hpp"
|
||||
|
||||
Reference in New Issue
Block a user