NVProf for NCCL program

Accelerated Computing GPU-Accelerated Libraries
1

Hi, All

When I want to use NVProf for NCCL problem with --metrics all, The profiling results always return me like

==2781== NVPROF is profiling process 2781, command: ./nccl_example 2 16
==2781== Profiling application: ./nccl_example 2 16
==2781== Profiling result:
No events/metrics were profiled.

My simple nccl program

#include <stdio.h>
#include "cuda_runtime.h"
#include "nccl.h"

#define CUDACHECK(cmd) do {                         \
  cudaError_t e = cmd;                              \
  if( e != cudaSuccess ) {                          \
    printf("Failed: Cuda error %s:%d '%s'\n",             \
        __FILE__,__LINE__,cudaGetErrorString(e));   \
    exit(EXIT_FAILURE);                             \
  }                                                 \
} while(0)


#define NCCLCHECK(cmd) do {                         \
  ncclResult_t r = cmd;                             \
  if (r!= ncclSuccess) {                            \
    printf("Failed, NCCL error %s:%d '%s'\n",             \
        __FILE__,__LINE__,ncclGetErrorString(r));   \
    exit(EXIT_FAILURE);                             \
  }                                                 \
} while(0)


int main(int argc, char* argv[])
{
  ncclComm_t comms[4];


  //managing 4 devices
  int nDev = 3;
  int size = 32*1024*1024;
  int devs[4] = {0, 1, 2};

  //allocating and initializing device buffers
  float** sendbuff = (float**)malloc(nDev * sizeof(float*));
  float** recvbuff = (float**)malloc(nDev * sizeof(float*));
  cudaStream_t* s = (cudaStream_t*)malloc(sizeof(cudaStream_t)*nDev);


  for (int i = 0; i < nDev; ++i) {
    CUDACHECK(cudaSetDevice(i));
    CUDACHECK(cudaMalloc(sendbuff + i, size * sizeof(float)));
    CUDACHECK(cudaMalloc(recvbuff + i, size * sizeof(float)));
    CUDACHECK(cudaMemset(sendbuff[i], 1, size * sizeof(float)));
    CUDACHECK(cudaMemset(recvbuff[i], 0, size * sizeof(float)));
    CUDACHECK(cudaStreamCreate(s+i));
  }


  //initializing NCCL
  NCCLCHECK(ncclCommInitAll(comms, nDev, devs));
//   printf("1--- \n");

   //calling NCCL communication API. Group API is required when using
   //multiple devices per thread
  NCCLCHECK(ncclGroupStart());
  for (int i = 0; i < nDev; ++i)
    NCCLCHECK(ncclAllReduce((const void*)sendbuff[i], (void*)recvbuff[i], 
                                size, ncclFloat, ncclSum, comms[i], s[i]));
  NCCLCHECK(ncclGroupEnd());


  //synchronizing on CUDA streams to wait for completion of NCCL operation
  for (int i = 0; i < nDev; ++i) {
    CUDACHECK(cudaSetDevice(i));
    CUDACHECK(cudaStreamSynchronize(s[i]));
  }

//   printf("2--- \n");

  //free device buffers
  for (int i = 0; i < nDev; ++i) {
    CUDACHECK(cudaSetDevice(i));
    CUDACHECK(cudaFree(sendbuff[i]));
    CUDACHECK(cudaFree(recvbuff[i]));
  }


  //finalizing NCCL
  for(int i = 0; i < nDev; ++i)
      ncclCommDestroy(comms[i]);

  printf("Success \n");
  return 0;
}

Because I need to know the detailed metrics of NCCL APIs.
Thanks!

2

Have you tried Nsight Systems?

3