Why the use of only 128 in GPU_GRP_SIZE as in KeyHuntCuda was 2048?
What's the relation between this constants?
// Number of random jumps
// Max 512 for the GPU
#define NB_JUMP 32
// GPU group size
#define GPU_GRP_SIZE 128
// GPU number of run per kernel call
#define NB_RUN 64
I think GPU_GRP_SIZE should be small as possible to fit to SM L1 cache, because it used most frequently.
2048 in KeyHuntCuda (rotorcuda) is too big and huge global memory pressure because of this.
As I understand more NB_RUN = less kernel calls from CPU code. It doing NB_RUNs of GPU_GRP_SIZE.
I'm using Nsight Compute and GPU-Z sensors data to experiment with different values.