kekonn

kernel void matrixTranspose( global float *a, global float *b, constant float *c, constant int size )
{
	int idx = get_global_id(0);
	int idy = get_global_id(1);
	b[idx * size + idy] = a[idy * size + idx];
	int BLOCKSIZE = 0;
	
	int loops;
	for (loops=0;loops<50;loops++)
	{

kekonn

/********************************************************************
*  sample.cu
*  This is a example of the CUDA program.
*********************************************************************/

#define MATRIX_SIZE 200
#define BLOCKSIZE 200
#define BLOCKDIM 200
#define BENCH_LOOP 100

kekonn

------------------
System Information
------------------
Time of this report: 5/20/2015, 20:05:09
       Machine name: JONAS-8
   Operating System: Windows 8 Pro 64-bit (6.2, Build 9200) (9200.win8_gdr.150316-1542)
           Language: Dutch (Regional Setting: Dutch)
System Manufacturer: System manufacturer
       System Model: System Product Name
               BIOS: 3603