| From: | "David E(dot) Wheeler" <david(at)justatheory(dot)com> |
|---|---|
| To: | Andrew Dunstan <andrew(at)dunslane(dot)net> |
| Cc: | PostgreSQL Hackers <pgsql-hackers(at)lists(dot)postgresql(dot)org> |
| Subject: | Re: Add ASCII fast path to Unicode normalization functions |
| Date: | 2026-09-14 15:01:10 |
| Message-ID: | 088274BE-E09C-40F3-A57D-A5C9070B5456@justatheory.com |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Sep 14, 2026, at 10:50, Andrew Dunstan <andrew(at)dunslane(dot)net> wrote:
> Benchmarked with data sized to fit comfortably under shared_buffers rather
> than triggering the seqscan ring-buffer bypass, which otherwise swamps the
> comparison at larger table sizes: ~10x on pure ASCII, ~4x on an 85/15
> ASCII/non-ASCII mix, and no measurable regression on non-ASCII input
> that still needs the full decode-and-quickcheck path.
Well this looks super simple and like a very nice speedup! Thanks for digging into that!
D
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Greg Burd | 2026-09-14 15:08:48 | Re: ExecForceStoreHeapTuple() loses tts_tid, so ORDER BY-op index scans project an invalid ctid |
| Previous Message | Melanie Plageman | 2026-09-14 14:57:44 | Re: eliminate xl_heap_visible to reduce WAL (and eventually set VM on-access) |