mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 10:09:41 +00:00
* Adding RapidJson Library
* Adding Json Dumps in all CK_Tile Examples
Not verified yet
* Adding json to cktile Batched Transpose
* adding json dumps to layernorm2d_fwd
* Adding json dump to flatmm_basic
* Adding RapidJson Library
* Adding Json Dumps in all CK_Tile Examples
Not verified yet
* Adding json to cktile Batched Transpose
* adding json dumps to layernorm2d_fwd
* Adding json dump to flatmm_basic
* Adding json in 03_gemm
* Add json dump to 16_batched_gemm
* Add json dump to gemm_multi_d_fp16
* Add json dump to grouped_gemm
* fix fmha_bwd/fwd
* Fix clang-format errors
exclude include/rapidjson in jenkins as its a third-party library
* Saparating function and defination.
* Update Documentation of 03_gemm
* Refactoring as per code review
* Disable fp8 instances on unsupported targets (#2592)
* Restrict building of gemm_universal_preshuffle_f8 instances to specific targets in CMakeLists.txt
* Add condition to skip gemm_xdl_universal_preshuffle_f8 instances for unsupported targets in CMakeLists.txt
* Add conditions to skip unsupported targets for gemm_universal_preshuffle_f8 and gemm_xdl_universal_preshuffle_f8 instances in CMakeLists.txt
* Refine conditions to exclude gemm_universal_preshuffle_f8 instances for unsupported targets in CMakeLists.txt
---------
Co-authored-by: AviralGoelAMD <aviralgoel@amd.com>
* fix clang format
* remove duplicate lines of code from library/src/tensor_operation_instance/gpu/CMakeLists.txt
* Fixing Readme and unifying jsondumps
* adding moe_smoothquant
* adding fused_moe
* Fixing Readme for batched_gemm
* Fixing Readme for grouped_gemm
* adding flatmm
* adding gemm_multi_d_fp16
* adding elementwise
* adding File name when json is dumped
* Fixing Reduce after merge
* adding batched_transpose
* Adding Warptile in Gemm
* Fixing Clang Format
---------
Co-authored-by: Aviral Goel <aviral.goel@amd.com>
Co-authored-by: AviralGoelAMD <aviralgoel@amd.com>
Co-authored-by: illsilin_amdeng <Illia.Silin@amd.com>
[ROCm/composable_kernel commit: 4d041837ad]
105 lines
3.1 KiB
C++
105 lines
3.1 KiB
C++
// Tencent is pleased to support the open source community by making RapidJSON available.
|
|
//
|
|
// Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
|
|
//
|
|
// Licensed under the MIT License (the "License"); you may not use this file except
|
|
// in compliance with the License. You may obtain a copy of the License at
|
|
//
|
|
// http://opensource.org/licenses/MIT
|
|
//
|
|
// Unless required by applicable law or agreed to in writing, software distributed
|
|
// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
|
|
// CONDITIONS OF ANY KIND, either express or implied. See the License for the
|
|
// specific language governing permissions and limitations under the License.
|
|
|
|
#ifndef RAPIDJSON_FILEWRITESTREAM_H_
|
|
#define RAPIDJSON_FILEWRITESTREAM_H_
|
|
|
|
#include "stream.h"
|
|
#include <cstdio>
|
|
|
|
#ifdef __clang__
|
|
RAPIDJSON_DIAG_PUSH
|
|
RAPIDJSON_DIAG_OFF(unreachable-code)
|
|
#endif
|
|
|
|
RAPIDJSON_NAMESPACE_BEGIN
|
|
|
|
//! Wrapper of C file stream for output using fwrite().
|
|
/*!
|
|
\note implements Stream concept
|
|
*/
|
|
class FileWriteStream {
|
|
public:
|
|
typedef char Ch; //!< Character type. Only support char.
|
|
|
|
FileWriteStream(std::FILE* fp, char* buffer, size_t bufferSize) : fp_(fp), buffer_(buffer), bufferEnd_(buffer + bufferSize), current_(buffer_) {
|
|
RAPIDJSON_ASSERT(fp_ != 0);
|
|
}
|
|
|
|
void Put(char c) {
|
|
if (current_ >= bufferEnd_)
|
|
Flush();
|
|
|
|
*current_++ = c;
|
|
}
|
|
|
|
void PutN(char c, size_t n) {
|
|
size_t avail = static_cast<size_t>(bufferEnd_ - current_);
|
|
while (n > avail) {
|
|
std::memset(current_, c, avail);
|
|
current_ += avail;
|
|
Flush();
|
|
n -= avail;
|
|
avail = static_cast<size_t>(bufferEnd_ - current_);
|
|
}
|
|
|
|
if (n > 0) {
|
|
std::memset(current_, c, n);
|
|
current_ += n;
|
|
}
|
|
}
|
|
|
|
void Flush() {
|
|
if (current_ != buffer_) {
|
|
size_t result = std::fwrite(buffer_, 1, static_cast<size_t>(current_ - buffer_), fp_);
|
|
if (result < static_cast<size_t>(current_ - buffer_)) {
|
|
// failure deliberately ignored at this time
|
|
// added to avoid warn_unused_result build errors
|
|
}
|
|
current_ = buffer_;
|
|
}
|
|
}
|
|
|
|
// Not implemented
|
|
char Peek() const { RAPIDJSON_ASSERT(false); return 0; }
|
|
char Take() { RAPIDJSON_ASSERT(false); return 0; }
|
|
size_t Tell() const { RAPIDJSON_ASSERT(false); return 0; }
|
|
char* PutBegin() { RAPIDJSON_ASSERT(false); return 0; }
|
|
size_t PutEnd(char*) { RAPIDJSON_ASSERT(false); return 0; }
|
|
|
|
private:
|
|
// Prohibit copy constructor & assignment operator.
|
|
FileWriteStream(const FileWriteStream&);
|
|
FileWriteStream& operator=(const FileWriteStream&);
|
|
|
|
std::FILE* fp_;
|
|
char *buffer_;
|
|
char *bufferEnd_;
|
|
char *current_;
|
|
};
|
|
|
|
//! Implement specialized version of PutN() with memset() for better performance.
|
|
template<>
|
|
inline void PutN(FileWriteStream& stream, char c, size_t n) {
|
|
stream.PutN(c, n);
|
|
}
|
|
|
|
RAPIDJSON_NAMESPACE_END
|
|
|
|
#ifdef __clang__
|
|
RAPIDJSON_DIAG_POP
|
|
#endif
|
|
|
|
#endif // RAPIDJSON_FILESTREAM_H_
|