Hacker News new | ask | show | jobs
by XorNot 1506 days ago
Why would it be irrelevant? Even the paucity of availability isn't really a problem - the big winners here are server users in data centers, not desktops or laptops. How much string parsing and munging is happening ingesting big datasets right now? If running a specially optimized function set on part of your fleet reduces utilization, that's direct cost savings you realize. If the AMD is then widening that support base, you're deeply favoring expanding usage while you scale up.
1 comments
_rtld_global_ro 1506 days ago
Given Intel's AVX extension could cause silent failures on servers (very high work load for prolonged time, compare to end user computers), I'm not sure it would be a big win for servers either: https://arxiv.org/pdf/2102.11245.pdf.
link
jcranmer 1506 days ago
I'm downvoting you because the assertion you're implying--that use of AVX increases soft failure rates more than using non-AVX instructions would--is not sustained by the source you use as reference.
link
tialaramex 1506 days ago
Indeed, I'd summarise that source as "At Facebook sometimes weird stuff happens. We postulate it's not because of all the buggy code written by Software Engineers like us, it must be hardware. As well as lots of speculation about hypothetical widespread problems that would show we're actually not writing buggy software, here's a single concrete example where it was hardware".

If anything I'd say that Core 59 is one of those exceptions that prove the rule. This is such a rare phenomenon that when it does happen you can do the work to pin it down and say yup, this CPU is busted - if it was really commonplace you'd constantly trip over these bugs and get nowhere. There probably isn't really, as that paper claims, a "systemic issue across generations" except that those generations are all running Facebook's buggy code.

link
janwas 1506 days ago
One interesting anecdote is that HPC planning for exascale included significant concern about machine failures and (silent) data corruption. When running at large enough scale, even seemingly small failure rates translate into "oh, there goes another one".
link