diff --git a/src/cuda/CUDAStream.h b/src/cuda/CUDAStream.h index bb3f866..83b8c66 100644 --- a/src/cuda/CUDAStream.h +++ b/src/cuda/CUDAStream.h @@ -22,7 +22,7 @@ #endif #define TBSIZE 1024 -#define DOT_NUM_BLOCKS 1024 +#define DOT_NUM_BLOCKS 256 template class CUDAStream : public Stream