I declare two 16x16 matries represented in 1D and do the addition. In the kernel, I make a thead process N elements(N = 1, 2,4,.....) , when N is less than 16, it works fine, but when it reaches 16, some kind of runtime error happens. I can not figure it out.
The code is as below(main.cpp and locate.br):
main.cpp:
#include <stdio.h>
#include <stdlib.h>
#include "brookgenfiles/locate.h"
using namespace brook;
#define SIZE 16
#define SIZE2 256
void printMatrix(int len, float m[])
{
int i, j;
for (i = 0; i < len; i++)
{
for (j = 0; j < len; j++)
{
printf("%f, ", m[i * len + j]);
}
printf("\n");
}
}
int main()
{
//array a, b and c
float a[SIZE2];
float b[SIZE2];
float c[SIZE2];
int i;
for (i = 0; i< SIZE2; i++)
{
a = 1.0;
b = 2.0;
}
unsigned int msize = SIZE2;
Stream<float> sa(1, &msize);
Stream<float> sb(1, &msize);
Stream<float> sc(1, &msize);
sa.read(a);
sb.read(b);
uint4 domainSize = uint4(SIZE2, 1, 1, 1);
blockAdd.domainSize(domainSize);
blockAdd(sa, sb, sc);
sc.write(c);
if (sc.error())
{
printf("Error occured! %s\n", sc.errorLog());
return 1;
}
printMatrix(SIZE, c);
getchar();
return 0;
}
locate.br:
Attribute[GroupSize(64, 1, 1)]
kernel void
blockAdd(float a[], float b[], out float c[])
{
int tid = instance().x;
//every thread process len elements, len = 1, 2, 4, 6, 8, 16, ....
//when len = 16, come the error
int len= 16;
int start = tid * len;
int i;
int index;
for (i = 0; i < len; i++)
{
c[start + i] = a[start + i] + b[start + i];
}
}
