Re:Intel Publishes Fast AVX-512 Sorting Library, 10~17x Fast...
by jeffbee on Wednesday February 15, 2023 @05:36PM
(#34811805)
Numpy is something you could expect to find running on a workstation and Intel's workstation CPU line has had AVX-512 continuously since 2017.
[ Parent
| on HN ]
Re:Intel Publishes Fast AVX-512 Sorting Library, 10~17x Fast...
by mumumu on Wednesday February 15, 2023 @05:52PM
(#34812065)
Alder Lake and Raptor Lake workstation (W680 Chipset) doesn't have AVX512 enabled.
Re:Intel Publishes Fast AVX-512 Sorting Library, 10~17x Fast...
by sliken on Wednesday February 15, 2023 @06:34PM
(#34812572)
Sad, big win for the Ryzen or future Zen 4 threadripper.
Re:Intel Publishes Fast AVX-512 Sorting Library, 10~17x Fast...
by jeffbee on Wednesday February 15, 2023 @06:00PM
(#34812150)
Fair. The "entry workstation" thing from Intel is baffling. I was thinking Xeon W, but then of course there was the Xeon W-12xx that lacked AVX-512.
In short, I was wrong. It would have been more correct to say that Intel has offered a workstation part with AVX-512 continuously since Skylake.
Re:Intel Publishes Fast AVX-512 Sorting Library, 10~17x Fast...
by bXVsbGVy on Friday February 17, 2023 @02:42PM
(#34839384)
Intel released a couple days ago new Xeon-W CPUs with AVX-512.
The wx-24xx uses the same p-cores as alder lake, but with avx-521 enabled. Same for wx-34xx but with raptor lake's p-core.
The entry levels xeon are believed to be identical to Core ix, with the e-cores disabled and avx-512 enabled. The extra I/O and ECC support is done by the chipset.
In summary, they just went to support avx-512 only on xeon w.
This makes sense, since must be hard to schedule between cores with and w/o avx (the e-cores doesn't have avx).
Re:Intel Publishes Fast AVX-512 Sorting Library, 10~17x Fast...
by cbsmith on Wednesday February 15, 2023 @06:09PM
(#34812285)
There was a longstanding issue where AVX-512 would trigger frequency throttling on a number of Intel CPUs, resulting in a net performance penalty for mixed workloads.
Re:Intel Publishes Fast AVX-512 Sorting Library, 10~17x Fast...
by saagarjha on Wednesday February 15, 2023 @06:11PM
(#34812309)
Ok, but that hasn’t been a problem in a while.
Re:Intel Publishes Fast AVX-512 Sorting Library, 10~17x Fast...
by cbsmith on Wednesday February 15, 2023 @06:38PM
(#34812608)
Yeah, but the mystique still lingers on.
Re:Intel Publishes Fast AVX-512 Sorting Library, 10~17x Fast...
by Rimintil on Wednesday February 15, 2023 @06:31PM
(#34812518)
Hasn't been a problem because software corrected for that, or hasn't been a problem because Intel resolved the underlying throttling issues with AVX-512?
Re:Intel Publishes Fast AVX-512 Sorting Library, 10~17x Fast...
by mhh__ on Wednesday February 15, 2023 @06:36PM
(#34812582)
Both
Re:Intel Publishes Fast AVX-512 Sorting Library, 10~17x Fast...
by jackmott42 on Wednesday February 15, 2023 @08:05PM
(#34813520)
It was never really a problem.
Re:Intel Publishes Fast AVX-512 Sorting Library, 10~17x Fast...
by rurban on Thursday February 16, 2023 @01:29AM
(#34815747)
It was only useful in a couple of corner cases, but not in general library functions.
Intel could never fix its thermal issues, AMD did.
Re:Intel Publishes Fast AVX-512 Sorting Library, 10~17x Fast...
by jackmott42 on Wednesday February 15, 2023 @08:05PM
(#34813516)
No, there was a longstanding issue of people worrying that it would result in a net performance penalty for mixed workloads. Meanwhile people actually using AVX-512 dealt with that by making sure mixed workloads were batched appropriately and it is usually a big net win even if you don't worry about it.
Re:Intel Publishes Fast AVX-512 Sorting Library, 10~17x Fast...
by stephencanon on Thursday February 16, 2023 @10:35AM
(#34820002)
“Longstanding” here means “really only in a single CPU generation (SKX), and even then only if you were dumb and used like 50 AVX-512 instructions in isolation for no reason at all.”