Ceci est une ancienne révision du document !
Tesla T10
- Trois cartes GPU réparties sur deux noeuds.
- File d'attente
tesla - Version de CUDA 4
Caractéristique
Type de chaque carte
Major revision number: 1 Minor revision number: 3 Name: Tesla T10 Processor Total global memory: 4294770688 Total shared memory per block: 16384 Total registers per block: 16384 Warp size: 32 Maximum memory pitch: 2147483647 Maximum threads per block: 512 Maximum dimension 0 of block: 512 Maximum dimension 1 of block: 512 Maximum dimension 2 of block: 64 Maximum dimension 0 of grid: 65535 Maximum dimension 1 of grid: 65535 Maximum dimension 2 of grid: 1 Clock rate: 1296000 Total constant memory: 65536 Texture alignment: 256 Concurrent copy and execution: Yes Number of multiprocessors: 30 Kernel execution timeout: Yes
Mode interactif
On se connecte sur les noeuds tesla en utilisant SGE (en mode interactif) depuis la machine login mesocluster.univ-fcomte.fr.
Attention : Comme la queue tesla dispose de 16 coeurs, on ne peut avoir plus de 16 sessions interactives.
$ qlogin -q tesla
Une fois connecté, on charge le module cuda pour pouvoir compiler et exécuter les programmes CUDA/OpenCL.
$ cd WORK
$ module load cuda
Exemple de programme
- VectorAdd.c
#include <stdio.h> #include <cuda.h> #include <stdlib.h> #define N 4096 // size of array __global__ void vectorAdd(int *a,int *b, int *c) { int tid = blockIdx.x * blockDim.x + threadIdx.x; if(tid < N){ c[tid] = a[tid]+b[tid]; } } int main(int argc, char *argv[]) { int T = 10, B = 1; // threads per block and blocks per grid int a[N],b[N],c[N]; int *dev_a, *dev_b, *dev_c; printf("Size of array = %d\n", N); do { printf("Enter number of threads per block (1024 max, comp. cap. 2.x) "); scanf("%d",&T); printf("\nEnter nuumber of blocks per grid: "); scanf("%d",&B); if (T * B < N) printf("Error T x B < N, try again\n"); } while (T * B < N); cudaEvent_t start, stop; // using cuda events to measure time float elapsed_time_ms; // which is applicable for asynchronous code also cudaSetDevice(0); cudaMalloc((void**)&dev_a,N * sizeof(int)); cudaMalloc((void**)&dev_b,N * sizeof(int)); cudaMalloc((void**)&dev_c,N * sizeof(int)); for(int i=0;i<N;i++) { // load arrays with some numbers a[i] = i; b[i] = i; } cudaMemcpy(dev_a, a , N*sizeof(int),cudaMemcpyHostToDevice); cudaMemcpy(dev_b, b , N*sizeof(int),cudaMemcpyHostToDevice); cudaMemcpy(dev_c, c , N*sizeof(int),cudaMemcpyHostToDevice); cudaEventCreate( &start ); // instrument code to measure start time cudaEventCreate( &stop ); cudaEventRecord( start, 0 ); vectorAdd<<<B,T>>>(dev_a,dev_b,dev_c); cudaMemcpy(c,dev_c,N*sizeof(int),cudaMemcpyDeviceToHost); cudaEventRecord( stop, 0 ); // instrument code to measue end time cudaEventSynchronize( stop ); cudaEventElapsedTime( &elapsed_time_ms, start, stop ); for(int i=0;i<N;i++) { printf("%d+%d=%d\n",a[i],b[i],c[i]); } printf("Time to calculate results: %f ms.\n", elapsed_time_ms); // print out execution time // clean up cudaFree(dev_a); cudaFree(dev_b); cudaFree(dev_c); cudaEventDestroy(start); cudaEventDestroy(stop); return 0; }
Compilation
$ nvcc VectorAdd.cu -o VectorAdd
On exécute le programme :
./VectorAdd
Mode passif
Vous pouvez utiliser SGE pour compiler et/ou exécuter un code CUDA ou OpenCL :
- cuda.sge
#!/bin/bash -l #$ -l h_rt=2:00:0 #$ -o $JOB_NAME.o$JOB_ID #$ -e $JOB_NAME.e$JOB_ID #$ -N job_cuda #$ -q tesla #$ -V #$ -l h_vmem=1.5G module load cuda ################################# ### Pour compiler ### ################################# nvcc monprogramme.cu -o monprogramme ################################# ### Pour executer #### ################################# ./monprogramme