Using simd properly(I think) and lowering the nonce text, I went from that 7MH/s to 10MH/s
I have a bunch of other ideas to get me to my goal of 20, but I am happy to let this run for a bit! Thanks for the suggestion!
1 karma · joined June 21, 2024
I have a bunch of other ideas to get me to my goal of 20, but I am happy to let this run for a bit! Thanks for the suggestion!
Time to comb through this code :D
I couldn't get wgsl to work properly, as it would need to have a sha256 implementation, and that's a bit heavy for a buzzed coding session. So, I used the simd commands, and that got me up to around 7mh/s on the m1, and a whole lot more on my desktop.
I will share the code once I get all the other optimizations I want in!