关于NVIDIA的MPS 执行

MPS的执行：主要看手册，https://docs.nvidia.com/deploy/pdf/CUDA_Multi_Process_Service_Overview.pdf

这里说一下，我需要的命令：

启动 mps-control

export CUDA_VISIBLE_DEVICES=0

export CUDA_MPS_PIPE_DIRECTORY=/tmp/nvidia-mps

export CUDA_MPS_LOG_DIRECTORY=/tmp/nvidia-log 

nvidia-cuda-mps-control -d

 

关闭mps-control

echo quit | nvidia-cuda-mps-control

执行完了，可以查看log 文件。

 

从这个链接摘抄的关于验证mps 的程序

http://stackoverflow.com/questions/34709749/how-do-i-use-nvidia-multi-process-service-mps-to-run-multiple-non-mpi-cuda-app

$ cat t1034.cu
#include <stdio.h>
#include <stdlib.h>

#define MAX_DELAY 30

#define cudaCheckErrors(msg) \
  do { \
    cudaError_t __err = cudaGetLastError(); \
    if (__err != cudaSuccess) { \
        fprintf(stderr, "Fatal error: %s (%s at %s:%d)\n", \
            msg, cudaGetErrorString(__err), \
            __FILE__, __LINE__); \
        fprintf(stderr, "*** FAILED - ABORTING\n"); \
        exit(1); \
    } \
  } while (0)


#include <time.h>
#include <sys/time.h>
#define USECPSEC 1000000ULL

unsigned long long dtime_usec(unsigned long long start){

  timeval tv;
  gettimeofday(&tv, 0);
  return ((tv.tv_sec*USECPSEC)+tv.tv_usec)-start;
}

#define APPRX_CLKS_PER_SEC 1000000000ULL
__global__ void delay_kernel(unsigned seconds){

  unsigned long long dt = clock64();
  while (clock64() < (dt + (seconds*APPRX_CLKS_PER_SEC)));
}

int main(int argc, char *argv[]){

  unsigned delay_t = 5; // seconds, approximately
  unsigned delay_t_r;
  if (argc > 1) delay_t_r = atoi(argv[1]);
  if ((delay_t_r > 0) && (delay_t_r < MAX_DELAY)) delay_t = delay_t_r;
  unsigned long long difft = dtime_usec(0);
  delay_kernel<<<1,1>>>(delay_t);
  cudaDeviceSynchronize();
  cudaCheckErrors("kernel fail");
  difft = dtime_usec(difft);
  printf("kernel duration: %fs\n", difft/(float)USECPSEC);
  return 0;
}

$ nvcc -arch=sm_35 -o t1034 t1034.cu
$ ./t1034
kernel duration: 6.528574s
$

 

$ cat start_as_root.bash
#!/bin/bash
# the following must be performed with root privilege
export CUDA_VISIBLE_DEVICES="0"
nvidia-smi -i 0 -c EXCLUSIVE_PROCESS
nvidia-cuda-mps-control -d

$ cat mps_run
#!/bin/bash
./t1034 &
./t1034
$

 

$ cat stop_as_root.bash
#!/bin/bash
echo quit | nvidia-cuda-mps-control
nvidia-smi -i 2 -c DEFAULT
$

 

$ ./mps_run
kernel duration: 6.409399s
kernel duration: 12.078304s
$

$ ./start_as_root.bash
$ ./mps_run
kernel duration: 6.167079s
kernel duration: 6.263062s

 

转载于:https://www.cnblogs.com/xingzifei/p/6136095.html