Hashcat using CUDA over OPENCL, why? - Printable Version +- hashcat Forum (https://hashcat.net/forum) +-- Forum: Support (https://hashcat.net/forum/forum-3.html) +--- Forum: hashcat (https://hashcat.net/forum/forum-45.html) +--- Thread: Hashcat using CUDA over OPENCL, why? (/thread-9537.html) |
Hashcat using CUDA over OPENCL, why? - sp00ks - 09-30-2020 I'm using hashcat 6 with a single GTX1080Ti, and just noticed that when the cuda device is being used over opencl. Is there a switch I'm missing to always use opencl over cuda? hashcat (v6.1.1-29-ga72ba6fa) starting... CUDA API (CUDA 10.2) ==================== * Device #1: GeForce GTX 1080 Ti, 8265/11178 MB, 28MCU OpenCL API (OpenCL 1.2 CUDA 10.2.185) - Platform #1 [NVIDIA Corporation] ======================================================================== * Device #2: GeForce GTX 1080 Ti, skipped OS: Debian Buster RE: Hashcat using CUDA over OPENCL, why? - atom - 09-30-2020 Yes, a simple -d 2 in your case will do the trick. RE: Hashcat using CUDA over OPENCL, why? - sp00ks - 09-30-2020 (09-30-2020, 02:33 PM)atom Wrote: Yes, a simple -d 2 in your case will do the trick. Thanks I thought that would work. I was wondering if there is a way of hashcat always selecting opencl as the preferred? I have hashcat automated in a lot of scripts so it might not always be device 2 you see. RE: Hashcat using CUDA over OPENCL, why? - atom - 09-30-2020 You can also use --backend-ignore-cuda |