libera #monero-pow

15 Jan 2026

Monero's Proof of Work algorithm (RandomX) and related topics. Use #p2pool-log and #p2pool-mini for P2Pool discussions. Anti-spam active: PM hyc for voice.

• 19:30
  sech1
  RandomX v2 testing has started: gist.github.com/SChernykh/6058ecf01c929883b9d19c7eeadc8809
• 19:30
  sech1
  More CPUs will be added soon (tm)
• 19:34
  DataHoarder
  how does this feel on your orangepi sech1 :D
• 19:34
  sech1
  I need to test it, actually
• 19:34
  sech1
  It's heavily memory limited, it doesn't have L3
• 19:36
  sech1
  I don't have a way to measure power though
• 19:36
  DataHoarder
  usb power meter? :D
• 19:39
  sech1
  I have a regular power meter, but it will show 4-5 watts, I guess. It's too rough measurement
• 19:41
  DataHoarder
  ah. I have one that does mA and mV precision on their own
• 19:42
  DataHoarder
  it is quite precise when I measured it against known samples HOWEVER you literally need to record the screen to get the data out
• 19:42
  sech1
  I have go-pro to record the screen at 120 FPS :D
• 19:43
  sech1
  Orange Pi RV2 (Ky X1 CPU, software AES): v1 99.3 h/s, v2 67.1 h/s
• 19:43
  sech1
  AES hits hard when it's not supported
• 19:43
  sech1
  XMRig could do 110 h/s on v1 though
• 19:44
  sech1
  This thing has unstable hashrate between launches
• 19:44
  DataHoarder
  start measuring 10s after starting :D
• 19:44
  sech1
  Even XMRig alternates between 110 and 85 h/s on v1, after each launch
• 19:44
  DataHoarder
  damn
• 19:44
  sech1
  No, I mean hashrate can be either 85 or 110 in XMRig, and it's stable for hours
• 19:45
  sech1
  But you need to restart it several times to get "lucky"
• 19:45
  DataHoarder
  that's very odd
• 19:45
  sech1
  Same behavior in randomx-benchmark, just with a bit lower hashrates
• 19:45
  DataHoarder
  no identifiable cause?
• 19:45
  sech1
  Probably memory allocation
• 19:45
  sech1
  Maybe some parts of RAM are slower there
• 19:45
  DataHoarder
  I wonder if it's due to how - yeah
• 19:46
  DataHoarder
  like if some core section crosses a specific physical boundary
• 19:46
  DataHoarder
  like scratchpad, allocated on big pages or similar but it's laid out across regions that cause that hit
• 19:46
  sech1
  It's a 8 GB model. Maybe the upper 4 GB are slower
• 19:46
  DataHoarder
  time to allocate it all
• 19:46
  DataHoarder
  and test all regions :P
• 19:47
  DataHoarder
  when efi randomx
• 19:47
  DataHoarder
  maybe we can make a small kernel module to expose contiguous physical memory allocations via specific rules
• 19:48
  DataHoarder
  afaik pagemap tells you where in physical memory your virtual memory map landed at
• 19:48
  DataHoarder
  so you can start gathering data for when it's slow/fast via pagemap (can inspect this externally while it's running)