Hey JeanLuc
tried on linux got no compilation error even with CCAP=8.6 ... windows is driving me nuts
on the illegal memory access issue when searching complete addresses..
does it help you to know that every gridsize x1 is working but every x2 x128 whatever is throwing that error?
i can take 83968x1 and it is working (slow but working) 1x1 working 1x2 error
cuda-memcheck.. same func call comp_keys_comp
GPU: GPU #0 GeForce RTX 3090 (82x0 cores) Grid(656x128)
========= Misaligned Shared or Local Address
========= at 0x00008980 in comp_keys_comp(unsigned short*, unsigned int*, unsigned long*, unsigned int, unsigned int*)
========= by thread (86,0,0) in block (300,0,0)
i'm still not good enough to degug that correctly
Apparently JeanLucPons is busy with other things - which I quite understand.
Updated VanitySearch to support the latest NVIDIA architecture.
Please here is the link:
https://github.com/zielar2/VanitySearchIMPORTANT! To compile you need the latest CUDA Toolkit, version 11.1!
Soon I will try to upload the compiled version to my repository.
Let me know if it helped and show off your performance.