| From: | Nathan Bossart <nathandbossart(at)gmail(dot)com> |
|---|---|
| To: | John Naylor <johncnaylorls(at)gmail(dot)com> |
| Cc: | Ants Aasma <ants(at)cybertec(dot)at>, pgsql-hackers(at)postgresql(dot)org |
| Subject: | Re: add AVX2 support to simd.h |
| Date: | 2024-03-25 15:21:21 |
| Message-ID: | 20240325152121.GB2662364@nathanxps13 |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Mon, Mar 25, 2024 at 10:03:27AM +0700, John Naylor wrote:
> Seems pretty good. It'd be good to see the results of 2- vs.
> 4-register before committing, because that might lead to some
> restructuring, but maybe it won't, and v8 is already an improvement
> over HEAD.
I tested this the other day [0] (only for x86). The results seemed to
indicate that the 4-register approach was still quite a bit better.
> /* Process the remaining elements one at a time. */
>
> This now does all of them if that path is taken, so "remaining" can be removed.
Right, will do.
[0] https://postgr.es/m/20240321183823.GA1800896%40nathanxps13
--
Nathan Bossart
Amazon Web Services: https://aws.amazon.com
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Peter Eisentraut | 2024-03-25 15:26:20 | Re: documentation structure |
| Previous Message | Amonson, Paul D | 2024-03-25 15:20:19 | RE: Popcount optimization using AVX512 |