mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-05 06:01:23 +00:00
4d041837ad
* 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>
47 lines
1.4 KiB
C++
47 lines
1.4 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_INTERNAL_SWAP_H_
|
|
#define RAPIDJSON_INTERNAL_SWAP_H_
|
|
|
|
#include "../rapidjson.h"
|
|
|
|
#if defined(__clang__)
|
|
RAPIDJSON_DIAG_PUSH
|
|
RAPIDJSON_DIAG_OFF(c++98-compat)
|
|
#endif
|
|
|
|
RAPIDJSON_NAMESPACE_BEGIN
|
|
namespace internal {
|
|
|
|
//! Custom swap() to avoid dependency on C++ <algorithm> header
|
|
/*! \tparam T Type of the arguments to swap, should be instantiated with primitive C++ types only.
|
|
\note This has the same semantics as std::swap().
|
|
*/
|
|
template <typename T>
|
|
inline void Swap(T& a, T& b) RAPIDJSON_NOEXCEPT {
|
|
T tmp = a;
|
|
a = b;
|
|
b = tmp;
|
|
}
|
|
|
|
} // namespace internal
|
|
RAPIDJSON_NAMESPACE_END
|
|
|
|
#if defined(__clang__)
|
|
RAPIDJSON_DIAG_POP
|
|
#endif
|
|
|
|
#endif // RAPIDJSON_INTERNAL_SWAP_H_
|