07:12:40 <p3rL> why xmrig 5.5.1 is crashing on x32 ?
07:12:45 <p3rL> how to feeexeeet
18:09:37 <cohcho> Is it safe to use std::atomic<uint32>::fetch_add(1) in real miner?
18:09:57 <cohcho> it's present in randomx-benchmark
18:11:27 <tevador> it is safe, but there are better ways to distribute nonces
18:11:49 <tevador> you can make many non-overlapping sequences
18:13:16 <cohcho> I've just get duplicate value from fetch_add(1) within the same thread. That's why asked here
18:15:31 <hyc> indeed, simpler to just divide nonce space by number of threads, and not worry about it
18:20:12 <cohcho> It's  iterating by N nonces within nonce space and assign i-th part to each thread. I'm trying to decrease delay of switching from previous job. It's up to N / (worker speed) now.
18:20:33 <cohcho> If that problem with atomic is real then I can't use them even for job notification.
18:21:15 <cohcho> Maybe it has happened due loading randomx library from memory buffer.
18:21:41 <cohcho> Can't reproduce it in c++ binary without sophisticated loading.
18:24:25 <cohcho> What efficient way will you use for new job notification except atomic and decreased threads's step within nonce space?
18:25:22 <cohcho> some structure under mutex?
18:34:31 <cohcho> again duplicate but in two different threads, something doesn't work
18:34:59 <sech1> atomic should just work
18:35:08 <sech1> returning same value twice is weird
20:53:57 <cohcho> if this is all required for fetch_add: "lock xadd QWORD PTR [rax],rdx" then it should really work even in jit with arbitrary memory address
21:01:18 <atoc> Yo
21:01:41 <tevador> cohcho: yes, just note that this instruction can take 20-50 CPU cycles
21:02:18 <atoc> tevador is there a paper on RandomX?
21:02:24 <atoc> i.e how it works?
21:02:36 <tevador> there are extensive docs on github
21:02:44 <atoc> cool, in the same repo?
21:02:58 <tevador> https://github.com/tevador/RandomX#documentation
21:03:09 <atoc> ooh found it
21:03:15 <atoc> this looks good too: https://github.com/tevador/RandomX/blob/master/doc/design.md
21:03:39 <atoc> (y)
21:03:57 <tevador> yes, there are two docs: the formal specs and the design comments
21:04:46 <atoc> thanks didn't know if it was all code or not and if there was a separate paper
21:06:38 <tevador> everything is in the github repo, including the audit reports
21:10:02 <atoc> Cool thanks. I did not know you hung out in this chat. I'll probably be back with questions,
21:11:23 <tevador> ok, this is the right channel for questions
21:12:43 <atoc> Sweet