CUDA: Using realloc inside kernel

Question

I know that it is possible to use malloc inside the kernel to allocate memory on GPU's global memory. Is it also possible to use realloc?

Where did you get that information? AFAIK there is no such thing as memory management inside a kernel. You have to prepare everything upfront. — Jonas Bötel, Mar 16 '11 at 16:33
malloc and free are supported according to the 3.2 programming guide. — Ade Miller, Mar 23 '11 at 05:16

YesThatIsMyName · Answer 1 · 2017-08-22T09:25:24.800

5

You could write you own realloc device function for your data type.

Just allocate the new space for a new array, copy the old values to the new, free the old array space, return the new with more space.

Approximately like the following code fragment:

__device__ MY_TYPE* myrealloc(int oldsize, int newsize, MY_TYPE* old)
{
    MY_TYPE* newT = (MY_TYPE*) malloc (newsize*sizeof(MY_TYPE));

    int i;

    for(i=0; i<oldsize; i++)
    {
        newT[i] = old[i];
    }

    free(old);
    return newT;
}

But be sure to call it, if you really need it. Also add proper error checking.

edited Aug 22 '17 at 09:25

answered May 29 '12 at 14:44

YesThatIsMyName

1,585
3
23
30

2

if newsize < oldsize, the loop should be until newsize right? also, old can be null. – shaoyl85 Feb 02 '14 at 18:44

score 4 · Answer 2 · answered Mar 16 '11 at 09:07

4

In the Cuda Programming Guide, when they introduce malloc and free functions, there is no mention of realloc. I would assume that it does not exist.

If you want to know it for sure, why don't you write a simple kernel and try using it?

answered Mar 16 '11 at 09:07

CygnusX1

20,968
5
65
109

CUDA: Using realloc inside kernel

2 Answers2

Linked