17:19:14 tevador you might be interested: https://github.com/xmrig/xmrig/pull/1986 19:09:43 sech1: is it basically due to faster mov? dataset init only happens twice per week anyways 19:10:31 It's faster because it initializes 5 items at a time (1 item using integer registers, 4 items using AVX 256-bit registers) 19:10:42 so it also has more time to prefetch data from cache 19:10:50 5 parallel fetches per thread 19:11:24 but it's not faster on all CPUs... 19:15:12 It would've been much much faster if there were 64-bit multiplication instructions for AVX... 19:15:35 Basically main loop is ~4 times slower than the regular loop, but it initializes 5 elements 20:26:05 older CPUs with only 128bit pathways for AVX 22:37:16 I guess I could try to test AVX2 with HashX, it could be a bit faster there since it doesn't use mulh