Revision as of 15:55, 30 January 2017

Programming Details

CUDA is a parallel computing platform and application programming interface (API) model created by Nvidia. It allows you to program a CUDA-enabled graphics processing unit (GPU) for general purpose processing.

The CUDA platform is designed to work with programming languages such as C, C++, and Fortran

Programming example

#include <stdio.h>

__global__
void saxpy(int n, float a, float *x, float *y)
{
  int i = blockIdx.x*blockDim.x + threadIdx.x;
  if (i < n)
        y[i] = a*x[i] + y[i];
}

int main(void)
{
  int N = 1<<31;

  float *x, *y, *d_x, *d_y;
  x = (float*)malloc(N*sizeof(float));
  y = (float*)malloc(N*sizeof(float));

  cudaMalloc(&d_x, N*sizeof(float));
  cudaMalloc(&d_y, N*sizeof(float));

        for (int i = 0; i < N; i++)
        {
                x[i] = 1.0f;
                y[i] = 2.0f;
        }

  cudaMemcpy(d_x, x, N*sizeof(float), cudaMemcpyHostToDevice);
  cudaMemcpy(d_y, y, N*sizeof(float), cudaMemcpyHostToDevice);

  // Perform SAXPY on 1M elements
  saxpy<<<(N+255)/256, 256>>>(N, 2.0f, d_x, d_y);

  cudaMemcpy(y, d_y, N*sizeof(float), cudaMemcpyDeviceToHost);

  float maxError = 0.0f;
  for (int i = 0; i < N; i++)
    maxError = max(maxError, abs(y[i]-4.0f));
  printf("Max error: %fn", maxError);
}

Compilation

The program would be compiled in the following way, optional Intel compiler available too:

module load cuda/7.5.18
nvcc -o testGPU testGPU.cu

Usage Examples

Batch example

#!/bin/bash

#SBATCH -J gpu-cuda
#SBATCH -N 1
#SBATCH --ntasks-per-node 1
#SBATCH -D /home/user/CUDA
#SBATCH -o %N.%j.%a.out
#SBATCH -e %N.%j.%a.err
#SBATCH -p gpu
#SBATCH --gres=gpu:tesla
#SBATCH --exclusive

module load cuda/7.5.18

/home/user/CUDA/testGPU

[username@login01 ~]$ sbatch demoCUDA.job
Submitted batch job 290552