There was an error fetching the commit references. Please try again later.
cuda: implement cryptonight_v8
- introduce a new schema where two threads work together on one hash - update autoadjustment - remove an mistake where shared memory was shrinked for gpus < sm_70
Showing
- xmrstak/backend/nvidia/minethd.cpp 0 additions, 5 deletionsxmrstak/backend/nvidia/minethd.cpp
- xmrstak/backend/nvidia/nvcc_code/cuda_core.cu 301 additions, 164 deletionsxmrstak/backend/nvidia/nvcc_code/cuda_core.cu
- xmrstak/backend/nvidia/nvcc_code/cuda_extra.cu 21 additions, 6 deletionsxmrstak/backend/nvidia/nvcc_code/cuda_extra.cu
Loading
Please register or sign in to comment