ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-01 20:21:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK_TILE] support group from cmdline (#1295)

Browse Source 
* support cmdline seqlen decode

* silent print

* update readme

* update kernel launch 3d

* update tile partitioner

* fix spill for bf16

* modify based on comment

* modify payload_t

* fix bug for alibi mode

* fix alibi test err

* refactor kernel launch, support select timer

* add missing file

* remove useless code

* add some comments
This commit is contained in:
carlushuang
2024-05-28 11:13:21 +08:00
committed by GitHub
parent 02fa2c298b
commit 5055b3bdcb
16 changed files with 534 additions and 261 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
include/ck_tile/host/stream_config.hpp
View File

@@ -6,6 +6,22 @@
#include <hip/hip_runtime.h>
namespace ck_tile {
/*
* construct this structure with behavior as:
*
* // create stream config with default stream(NULL), and not timing the kernel
* stream_config s = stream_config{};
*
* // create stream config with _some_stream_id_, and not timing the kernel
* stream_config s = stream_config{_some_stream_id_};
*
* // create stream config with _some_stream_id_, and benchmark with warmup/repeat as default
* stream_config s = stream_config{_some_stream_id_, true};
*
* // create stream config with _some_stream_id_, and benchmark using cpu timer
* stream_config s = stream_config{_some_stream_id_, true, 0, 3, 10, false};
**/
struct stream_config
{
hipStream_t stream_id_ = nullptr;
@@ -13,5 +29,6 @@ struct stream_config
int log_level_ = 0;
int cold_niters_ = 3;
int nrepeat_ = 10;
bool is_gpu_timer_ = true; // keep compatible
};
} // namespace ck_tile