Conversation

Notices

1. Embed this notice
   Fabian Giesen (rygorous@mastodon.gamedev.place)'s status on Thursday, 22-May-2025 09:10:57 JST Fabian Giesen

   What's that mysterious workaround?

   Core Huff6 decode step is described in https://fgiesen.wordpress.com/2023/10/29/entropy-decoding-in-oodle-data-x86-64-6-stream-huffman-decoders/

   A customer managed to get a fairly consistent repro for transient decode errors by overclocking an i7-14700KF by about 5% from stock settings ("performance" multiplier 56->59).

   It took weeks of back and forth and forensic debugging to figure out what actually happens, but TL;DR: the observed decode errors are all consistent with a single instruction misbehaving.

   • scriptjunkie repeated this.
   • Embed this notice
     Fabian Giesen (rygorous@mastodon.gamedev.place)'s status on Thursday, 22-May-2025 09:11:02 JST Fabian Giesen

     in reply to

     This instruction:
     mov [rDest + <index>], ch

     under these conditions, when overclocked a bit, once the machine has "warmed up", seems to have around a 1/10000 chance of actually storing the contents of CL instead of CH to memory.

     (this was "fun" to debug.)

     The workaround: when we detect Raptor Lake CPUs, we now do

     shr ecx, 8
     mov [rDest + <index>], cl

     instead. This takes more FE and uop bandwidth, but this loop is mainly latency-limited, and this is off the critical path.

   • Embed this notice
     Rich Felker (dalias@hachyderm.io)'s status on Thursday, 22-May-2025 12:58:41 JST Rich Felker

     in reply to

     • 🇺🇦 haxadecimal
     • Per Vognsen

     @pervognsen @brouhaha @rygorous I mean I'd just take that as indication you need to underclock these pieces of shit by 20% or treat them as ewaste. 🤷

   • Embed this notice
     🇺🇦 haxadecimal (brouhaha@mastodon.social)'s status on Thursday, 22-May-2025 12:58:42 JST 🇺🇦 haxadecimal

     in reply to

     @rygorous
     Or don't overclock?
     But definitely mad props on the detective work.

   • Embed this notice
     Per Vognsen (pervognsen@mastodon.social)'s status on Thursday, 22-May-2025 12:58:42 JST Per Vognsen

     in reply to

     • 🇺🇦 haxadecimal

     @brouhaha @rygorous Fabian can clarify further but I thought it did happen without overclocking, just with extreme rarity? The overclocking is used to make it reproducible in a lab setting.