abstract_cuda_task.h

Go to the documentation of this file.

 
// NIST-developed software is provided by NIST as a public service. You may use, copy and distribute copies of the
// software in any medium, provided that you keep intact this entire notice. You may improve, modify and create
// derivative works of the software or any portion of the software, and you may copy and distribute such modifications
// or works. Modified works should carry a notice stating that you changed the software and should note the date and
// nature of any such change. Please explicitly acknowledge the National Institute of Standards and Technology as the
// source of the software. NIST-developed software is expressly provided "AS IS." NIST MAKES NO WARRANTY OF ANY KIND,
// EXPRESS, IMPLIED, IN FACT OR ARISING BY OPERATION OF LAW, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTY OF
// MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, NON-INFRINGEMENT AND DATA ACCURACY. NIST NEITHER REPRESENTS NOR
// WARRANTS THAT THE OPERATION OF THE SOFTWARE WILL BE UNINTERRUPTED OR ERROR-FREE, OR THAT ANY DEFECTS WILL BE
// CORRECTED. NIST DOES NOT WARRANT OR MAKE ANY REPRESENTATIONS REGARDING THE USE OF THE SOFTWARE OR THE RESULTS
// THEREOF, INCLUDING BUT NOT LIMITED TO THE CORRECTNESS, ACCURACY, RELIABILITY, OR USEFULNESS OF THE SOFTWARE. You
// are solely responsible for determining the appropriateness of using and distributing the software and you assume
// all risks associated with its use, including but not limited to the risks and costs of program errors, compliance
// with applicable laws, damage to or loss of data, programs or equipment, and the unavailability or interruption of
// operation. This software is not intended to be used in any situation where a failure could cause risk of injury or
// damage to property. The software developed by NIST employees is not subject to copyright protection within the
// United States.
 
#ifndef HEDGEHOG_ABSTRACT_CUDA_TASK_H
#define HEDGEHOG_ABSTRACT_CUDA_TASK_H
#ifdef HH_USE_CUDA
 
#include <cuda_runtime.h>
#include <unordered_set>
 
#include "abstract_task.h"
#include "../../tools/cuda_debugging.h"
 
namespace hh {
 
template<size_t Separator, class ...AllTypes>
class AbstractCUDATask : public AbstractTask<Separator, AllTypes...> {
 private:
  bool enablePeerAccess_ = false;               
  std::unordered_set<int> peerDeviceIds_ = {};  
  cudaStream_t stream_ = {};                    
 
 public:
  AbstractCUDATask(std::string const &name, size_t numberThreads, bool enablePeerAccess, bool automaticStart = false)
      : AbstractTask<Separator, AllTypes...>(name, numberThreads, automaticStart),
        enablePeerAccess_(enablePeerAccess) {
    this->coreTask()->printOptions().background({0x76, 0xb9, 0x00, 0xff});
    this->coreTask()->printOptions().font({0xff, 0xff, 0xff, 0xff});
  }
 
  explicit AbstractCUDATask(std::string const name = "CudaTask", size_t numberThreads = 1) :
      AbstractCUDATask<Separator, AllTypes...>(name, numberThreads, false, false) {};
 
  AbstractCUDATask(std::shared_ptr<hh::core::CoreTask<Separator, AllTypes...>> coreTask, bool enablePeerAccess)
      : AbstractTask<Separator, AllTypes...>(std::shared_ptr<hh::core::CoreTask<Separator, AllTypes...>>(coreTask)),
        enablePeerAccess_(enablePeerAccess) {
    this->coreTask()->printOptions().background({0x76, 0xb9, 0x00, 0xff});
    this->coreTask()->printOptions().font({0xff, 0xff, 0xff, 0xff});
  }
 
  ~AbstractCUDATask() override {
    if (this->memoryManager() != nullptr) {
      checkCudaErrors(cudaSetDevice(this->memoryManager()->deviceId()));
    }
  }
 
  void initialize() final {
    int numGpus = 0;
    int canAccess = 0;
    checkCudaErrors(cudaGetDeviceCount(&numGpus));
    assert(this->deviceId() < numGpus);
    checkCudaErrors(cudaSetDevice(this->deviceId()));
    checkCudaErrors(cudaStreamCreate(&stream_));
 
    if (enablePeerAccess_) {
      for (int i = 0; i < numGpus; ++i) {
        if (i != this->deviceId()) {
          checkCudaErrors(cudaDeviceCanAccessPeer(&canAccess, this->deviceId(), i));
 
          if (canAccess) {
            auto ret = cudaDeviceEnablePeerAccess(i, 0);
            if (ret != cudaErrorPeerAccessAlreadyEnabled) {
              checkCudaErrors(ret);
            }
            peerDeviceIds_.insert(i);
          }
        }
      }
    }
    auto ret = cudaGetLastError();
    if (ret != cudaErrorPeerAccessAlreadyEnabled) {
      checkCudaErrors(ret);
    }
    this->initializeCuda();
  }
 
  void shutdown() final {
    this->shutdownCuda();
    checkCudaErrors(cudaStreamDestroy(stream_));
  }
 
  virtual void initializeCuda() {}
 
  virtual void shutdownCuda() {}
 
  bool enablePeerAccess() const { return enablePeerAccess_; }
 
  cudaStream_t stream() const { return stream_; }
 
  bool hasPeerAccess(int peerDeviceId) { return peerDeviceIds_.find(peerDeviceId) != peerDeviceIds_.end(); }
 
};
 
}
#endif //HH_USE_CUDA
#endif //HEDGEHOG_ABSTRACT_CUDA_TASK_H