[jeffbee]

On Ice Lake Xeon the penalty for using the AVX-512 features on a single core is -100MHz. If we pessimistically use the slowest part Intel sells, that is a 5% performance penalty (2% on their fastest parts). The speedup from this work is 40-60% compared to AVX2. So you'd be a fool to take the side of the folk myth. AVX-512 works.

By the way the performance penalty for using AVX-512 on multiple cores when the multiple cores were already active is zero. There is no penalty in most server scenarios.

[MontyCarloHall]

>On Ice Lake Xeon the penalty for using the AVX-512 features on a single core is -100MHz.

That is a penalty due to licensing [0], not thermal throttling. As I wrote elsewhere, I’ve seen my clockspeed get cut in half across all cores on a physical die when running AVX-heavy operations for a sustained period of time, due to thermal throttling.

[0] https://travisdowns.github.io/blog/2020/08/19/icl-avx512-fre...

[mcronce]

The default AVX offset for Ice Lake is indeed only 100MHz (and it doesn't exist starting with Rocket Lake), but 512b SIMD instructions use a lot of power, and as a result generate a lot of heat - so they certainly can cause thermal throttling or throttling due to power limits

[ahh]

It's the transition that kills you. Are you doing this full time?

[jeffbee]

My full-time thing is more search-y and takes tens of milliseconds so I'm not really sweating power state transitions that take a few micros.