There was a mistake in my query, so the macOS speedup column was wrong
(was accidentally comparing Linux number with macOS master, sorry for
the noise). I also forgot to mention that you don't actually get the
speedup on PostgreSQL 17 on a Mac, because Peter only recently
implemented the needed re
On Fri, Sep 6, 2024 at 4:28 PM Thomas Munro wrote:
> Without this
> patch for PostgreSQL, it reads 1, 2, 4, 7 blocks (= 16 in total)
> before it has to take a break to hop to a new page, and then it start
> again at 1. Oops.
Erm, correction: 1, 2, 4, 8, 1 (because it runs out due to m == 16 and
On Wed, Jun 12, 2024 at 3:37 AM Jonathan S. Katz wrote:
> If you're curious, I can fire up some of my more serious benchmarks on
> this to do a before/after to see if there's anything interesting. I have
> a few large datasets (10s of millions) of larger vectors (1536dim => 6KB
> payloads) that co
On 6/11/24 12:53 AM, Thomas Munro wrote:
Hi,
I was looking around for an exotic index type to try the experience of
streamifying an extension, ie out-of-core code. I am totally new to
pgvector, but since everyone keeps talking about it, I could not avoid
picking up some basic facts in the pgcon
On 11/06/2024 07:53, Thomas Munro wrote:
Someone involved in that project mentioned that it's probably not a
great topic to research in practice, because real world users of HNSW
use fully cached ie prewarmed indexes, because the performance is so
bad otherwise. (Though maybe that argument is a
