mirror of
https://github.com/open-mmlab/mmdeploy.git
synced 2025-01-14 08:09:43 +08:00
36124f6205
* check in cmake * move backend_ops to csrc/backend_ops * check in preprocess, model, some codebase and their c-apis * check in CMakeLists.txt * check in parts of test_csrc * commit everything else * add readme * update core's BUILD_INTERFACE directory * skip codespell on third_party * update trt_net and ort_net's CMakeLists * ignore clion's build directory * check in pybind11 * add onnx.proto. Remove MMDeploy's dependency on ncnn's source code * export MMDeployTargets only when MMDEPLOY_BUILD_SDK is ON * remove useless message * target include directory is wrong * change target name from mmdeploy_ppl_net to mmdeploy_pplnn_net * skip install directory * update project's cmake * remove useless code * set CMAKE_BUILD_TYPE to Release by force if it isn't set by user * update custom ops CMakeLists * pass object target's source lists * fix lint end-of-file * fix lint: trailing whitespace * fix codespell hook * remove bicubic_interpolate to csrc/backend_ops/ * set MMDEPLOY_BUILD_SDK OFF * change custom ops build command * add spdlog installation command * update docs on how to checkout pybind11 * move bicubic_interpolate to backend_ops/tensorrt directory * remove useless code * correct cmake * fix typo * fix typo * fix install directory * correct sdk's readme * set cub dir when cuda version < 11.0 * change directory where clang-format will apply to * fix build command * add .clang-format * change clang-format style from google to file * reformat csrc/backend_ops * format sdk's code * turn off clang-format for some files * add -Xcompiler=-fno-gnu-unique * fix trt topk initialize * check in config for sdk demo * update cmake script and csrc's readme * correct config's path * add cuda include directory, otherwise compile failed in case of tensorrt8.2 * clang-format onnx2ncnn.cpp Co-authored-by: zhangli <lzhang329@gmail.com> Co-authored-by: grimoire <yaoqian@sensetime.com>
70 lines
2.1 KiB
C++
70 lines
2.1 KiB
C++
// Copyright (c) OpenMMLab. All rights reserved.
|
|
|
|
#ifndef MMDEPLOY_SRC_DEVICE_CUDA_DEFAULT_ALLOCATOR_H_
|
|
#define MMDEPLOY_SRC_DEVICE_CUDA_DEFAULT_ALLOCATOR_H_
|
|
|
|
#include <cuda_runtime.h>
|
|
|
|
#include <atomic>
|
|
#include <chrono>
|
|
|
|
#include "core/logger.h"
|
|
|
|
namespace mmdeploy::cuda {
|
|
|
|
class DefaultAllocator {
|
|
public:
|
|
DefaultAllocator() = default;
|
|
~DefaultAllocator() {
|
|
ERROR("=== CUDA Default Allocator ===");
|
|
ERROR(" Allocation: count={}, size={}MB, time={}ms", alloc_count_,
|
|
alloc_size_ / (1024 * 1024.f), alloc_time_ / 1000000.f);
|
|
ERROR("Deallocation: count={}, size={}MB, time={}ms", dealloc_count_,
|
|
dealloc_size_ / (1024 * 1024.f), dealloc_time_ / 1000000.f);
|
|
}
|
|
[[nodiscard]] void* Allocate(std::size_t n) {
|
|
void* p{};
|
|
auto t0 = std::chrono::high_resolution_clock::now();
|
|
auto ret = cudaMalloc(&p, n);
|
|
auto t1 = std::chrono::high_resolution_clock::now();
|
|
alloc_time_ += (int64_t)std::chrono::duration<double, std::nano>(t1 - t0).count();
|
|
if (ret != cudaSuccess) {
|
|
ERROR("error allocating cuda memory: {}", cudaGetErrorString(ret));
|
|
return nullptr;
|
|
}
|
|
alloc_count_ += 1;
|
|
alloc_size_ += n;
|
|
return p;
|
|
}
|
|
void Deallocate(void* p, std::size_t n) {
|
|
(void)n;
|
|
auto t0 = std::chrono::high_resolution_clock::now();
|
|
auto ret = cudaFree(p);
|
|
auto t1 = std::chrono::high_resolution_clock::now();
|
|
dealloc_time_ += (int64_t)std::chrono::duration<double, std::nano>(t1 - t0).count();
|
|
if (ret != cudaSuccess) {
|
|
ERROR("error deallocating cuda memory: {}", cudaGetErrorString(ret));
|
|
return;
|
|
}
|
|
dealloc_count_ += 1;
|
|
dealloc_size_ += n;
|
|
}
|
|
|
|
private:
|
|
std::atomic<std::size_t> alloc_count_;
|
|
std::atomic<std::size_t> alloc_size_;
|
|
std::atomic<std::size_t> alloc_time_;
|
|
std::atomic<std::size_t> dealloc_count_;
|
|
std::atomic<std::size_t> dealloc_size_;
|
|
std::atomic<std::size_t> dealloc_time_;
|
|
};
|
|
|
|
inline DefaultAllocator& gDefaultAllocator() {
|
|
static DefaultAllocator v;
|
|
return v;
|
|
}
|
|
|
|
} // namespace mmdeploy::cuda
|
|
|
|
#endif // MMDEPLOY_SRC_DEVICE_CUDA_DEFAULT_ALLOCATOR_H_
|