On Tue, 4 Jan 2022 01:47:21 +0000
<eagost...@nvidia.com> wrote:
> static int
> -cuda_mem_alloc(struct rte_gpu *dev, size_t size, void **ptr)
> +cuda_mem_alloc(struct rte_gpu *dev, size_t size, void **ptr, unsigned int
> align)
> {
> CUresult res;
> const char *err_string;
> @@ -610,8 +612,10 @@ cuda_mem_alloc(struct rte_gpu *dev, size_t size, void
> **ptr)
>
> /* Allocate memory */
> mem_alloc_list_tail->size = size;
> - res = pfn_cuMemAlloc(&(mem_alloc_list_tail->ptr_d),
> - mem_alloc_list_tail->size);
> + mem_alloc_list_tail->size_orig = size + align;
> +
> + res = pfn_cuMemAlloc(&(mem_alloc_list_tail->ptr_orig_d),
> + mem_alloc_list_tail->size_orig);
> if (res != 0) {
> pfn_cuGetErrorString(res, &(err_string));
> rte_cuda_log(ERR, "cuCtxSetCurrent current failed with %s",
> @@ -620,6 +624,13 @@ cuda_mem_alloc(struct rte_gpu *dev, size_t size, void
> **ptr)
> return -rte_errno;
> }
>
> +
> + /* Align memory address */
> + mem_alloc_list_tail->ptr_d = mem_alloc_list_tail->ptr_orig_d;
> + if (align && ((uintptr_t)mem_alloc_list_tail->ptr_d) % align)
> + mem_alloc_list_tail->ptr_d += (align -
> + (((uintptr_t)mem_alloc_list_tail->ptr_d) %
> align));
Posix memalign takes size_t for both size and alignment.
Better to put the input parameters first, and then the resulting output
parameter last
for consistency; follows the Rusty API design manifesto.
Alignment only makes sense if power of two. The code should check that and
optimize
for that.
