mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-15 10:37:44 +00:00
* add flush cache to device op
* add flush cache parameter to ckProfiler
* change calculate size a and b method
* chang evaluation time method foro AVERAGE to MEDIAN
* format code
* adjust some code
* fix core dumped
* remove loop call flush icache in kernel
* remove loop(outer) call flush icache
---------
Co-authored-by: letaoqin <letaoqin@amd.com>
[ROCm/composable_kernel commit: f448d179b7]
31 lines
879 B
C++
31 lines
879 B
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include <hip/hip_runtime.h>
|
|
|
|
namespace ck {
|
|
static __global__ void flush_icache()
|
|
{
|
|
asm __volatile__("s_icache_inv \n\t"
|
|
"s_nop 0 \n\t"
|
|
"s_nop 0 \n\t"
|
|
"s_nop 0 \n\t"
|
|
"s_nop 0 \n\t"
|
|
"s_nop 0 \n\t"
|
|
"s_nop 0 \n\t"
|
|
"s_nop 0 \n\t"
|
|
"s_nop 0 \n\t"
|
|
"s_nop 0 \n\t"
|
|
"s_nop 0 \n\t"
|
|
"s_nop 0 \n\t"
|
|
"s_nop 0 \n\t"
|
|
"s_nop 0 \n\t"
|
|
"s_nop 0 \n\t"
|
|
"s_nop 0 \n\t"
|
|
"s_nop 0 \n\t" ::
|
|
:);
|
|
}
|
|
} // namespace ck
|