TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

AVX-512, what’s useful for us

93 pointsby rbultjeover 7 years ago

6 comments

raphlinusover 7 years ago
If I'm understanding it correctly, they're not actually using the 512 bit (ZMM) registers, because using them can cause overall system slowdown. It seems to me they're only really useful if you're doing an AVX-512 intensive workload. And do those really exist? For something like bulk matrix multiplications, GPGPU is going to be much better, both in throughput and in operations per joule. I'm remaining to be convinced that the ecological niche occupied by SIMD is significant, let alone expanding.
评论 #15989618 未加载
评论 #15991321 未加载
评论 #15990719 未加载
评论 #15989653 未加载
dragontamerover 7 years ago
It will be a while before AVX-512 becomes practical however. AMD doesn&#x27;t support it (so any RyZen or Threadripper fans will miss out), and even Intel 8th Gen Coffee-lake doesn&#x27;t support it.<p>Only Intel Extreme i9 and Xeon Silver &#x2F; Gold &#x2F; Platinum seems to support it. So the market for this instruction set is quite limited.
评论 #15988771 未加载
评论 #15989226 未加载
评论 #15989572 未加载
minxomatover 7 years ago
<p><pre><code> document.querySelector(&#x27;#k2Container&#x27;).style.color = &#x27;black&#x27;; </code></pre> and the blog post becomes almost readable.<p>Other than that, nice intro.
评论 #15988341 未加载
pkayeover 7 years ago
I changed some Golang code to AVX in my last project. In isolation that code ran like 2-4x faster but as part of the full program, the program was 5% slower overall. Could never make a sense of it. Any thoughts on how to determine the cause?
评论 #15990178 未加载
评论 #15990233 未加载
评论 #15992433 未加载
评论 #15990106 未加载
评论 #15993615 未加载
gokover 7 years ago
Doesn&#x27;t mention what I find the coolest part of AVX-512: the conflict detection instructions. Finally a way to vectorize loops with indirect loads!
ninegunpiover 7 years ago
for slowing down awkward code?