mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 02:02:46 +00:00
7674eb6416
* 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]
71 lines
2.5 KiB
C++
71 lines
2.5 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_MEMORYBUFFER_H_
|
|
#define RAPIDJSON_MEMORYBUFFER_H_
|
|
|
|
#include "stream.h"
|
|
#include "internal/stack.h"
|
|
|
|
RAPIDJSON_NAMESPACE_BEGIN
|
|
|
|
//! Represents an in-memory output byte stream.
|
|
/*!
|
|
This class is mainly for being wrapped by EncodedOutputStream or AutoUTFOutputStream.
|
|
|
|
It is similar to FileWriteBuffer but the destination is an in-memory buffer instead of a file.
|
|
|
|
Differences between MemoryBuffer and StringBuffer:
|
|
1. StringBuffer has Encoding but MemoryBuffer is only a byte buffer.
|
|
2. StringBuffer::GetString() returns a null-terminated string. MemoryBuffer::GetBuffer() returns a buffer without terminator.
|
|
|
|
\tparam Allocator type for allocating memory buffer.
|
|
\note implements Stream concept
|
|
*/
|
|
template <typename Allocator = CrtAllocator>
|
|
struct GenericMemoryBuffer {
|
|
typedef char Ch; // byte
|
|
|
|
GenericMemoryBuffer(Allocator* allocator = 0, size_t capacity = kDefaultCapacity) : stack_(allocator, capacity) {}
|
|
|
|
void Put(Ch c) { *stack_.template Push<Ch>() = c; }
|
|
void Flush() {}
|
|
|
|
void Clear() { stack_.Clear(); }
|
|
void ShrinkToFit() { stack_.ShrinkToFit(); }
|
|
Ch* Push(size_t count) { return stack_.template Push<Ch>(count); }
|
|
void Pop(size_t count) { stack_.template Pop<Ch>(count); }
|
|
|
|
const Ch* GetBuffer() const {
|
|
return stack_.template Bottom<Ch>();
|
|
}
|
|
|
|
size_t GetSize() const { return stack_.GetSize(); }
|
|
|
|
static const size_t kDefaultCapacity = 256;
|
|
mutable internal::Stack<Allocator> stack_;
|
|
};
|
|
|
|
typedef GenericMemoryBuffer<> MemoryBuffer;
|
|
|
|
//! Implement specialized version of PutN() with memset() for better performance.
|
|
template<>
|
|
inline void PutN(MemoryBuffer& memoryBuffer, char c, size_t n) {
|
|
std::memset(memoryBuffer.stack_.Push<char>(n), c, n * sizeof(c));
|
|
}
|
|
|
|
RAPIDJSON_NAMESPACE_END
|
|
|
|
#endif // RAPIDJSON_MEMORYBUFFER_H_
|