On Sat, Mar 1, 2025 at 1:23 PM Shankaran, Akash
wrote:
> Given the same x86-simdsort library is intended to optimize 1) list_sort 2)
> tuple sort, it didn't make sense to duplicate the work to integrate it in
> pg_vector for list_sort, and then again in postgres for tuple-sort.
Thank you for t
>> > I don't think "another extension might use it someday" makes a very strong
>> > case,
>> > particularly for something that requires a new dependency.
>>
>> The x86-simdsort library is an optional dependency in Postgres. Also the new
>> list sort implementation which uses the x86-simdsort lib
On Fri, Feb 28, 2025 at 12:43 PM R, Rakshit wrote:
> > I don't think "another extension might use it someday" makes a very strong
> > case,
> > particularly for something that requires a new dependency.
>
> The x86-simdsort library is an optional dependency in Postgres. Also the new
> list sort
Hi All,
Thank you so much for the feedback.
> I don't think "another extension might use it someday" makes a very strong
> case,
> particularly for something that requires a new dependency.
The x86-simdsort library is an optional dependency in Postgres. Also the new
list sort implementation
> Note that our current implemention is highly optimized for low-cardinality
> inputs.
> This is needed for aggregate queries. I found this write-up of a couple
> scalar and
> vectorized sorts, and they show this library doing very poorly on very-low
> cardinality inputs. I would look into that b
On Tue, Feb 18, 2025 at 1:49 PM R, Rakshit wrote:
>
> Hi All,
>
> Thank you very much for your feedback! We investigated the recommendations as
> we developed the current patch. Please refer to the comments below.
>
> > I'd suggest targeting pg_qsort() directly, instead of list_sort().
> > list_
gards,
-Original Message-
From: Andrei Lepikhov
Sent: Saturday, November 23, 2024 8:50 AM
To: Giacchino, Luca ;
pgsql-hackers@lists.postgresql.org
Cc: R, Rakshit ; Shankaran, Akash
; Devulapalli, Raghuveer
Subject: Re: SIMD optimization for list_sort
On 22/11/2024 06:27, Giacchino, Luca wrot
On 22/11/2024 06:27, Giacchino, Luca wrote:
We’d appreciate feedback on this approach. In the meantime, we will
complete the patch to share. We also plan to extend SIMD-based sort to
tuple sort in the future.
Nice! I continually see performance reports when sorting and group order
impact perfor
On Fri, Nov 22, 2024 at 6:27 AM Giacchino, Luca
wrote:
> We’d appreciate feedback on this approach. In the meantime, we will complete
> the patch to share. We also plan to extend SIMD-based sort to tuple sort in
> the future.
Coincidentally, I'll be prototyping a tuple sort that will take bette
On Fri, Nov 22, 2024 at 06:01:22PM +0200, Heikki Linnakangas wrote:
> On 22/11/2024 01:27, Giacchino, Luca wrote:
>> We´d appreciate feedback on this approach. In the meantime, we will
>> complete the patch to share. We also plan to extend SIMD-based sort to
>> tuple sort in the future.
>
> If you
On 22/11/2024 01:27, Giacchino, Luca wrote:
The existing list_sort takes a comparator function to compare pairs of
ListCell. On the other hand, x86-simd-sort requires an array of numeric
values to sort, and it returns an array of sorted indices. To enable
x86-simd-sort, we add new list_sort_sim
Hi All,
We propose enabling SIMD-based sort for list_sort using the x86-simd-sort
library (https://github.com/intel/x86-simd-sort).
The existing list_sort takes a comparator function to compare pairs of
ListCell. On the other hand, x86-simd-sort requires an array of numeric values
to sort, and
12 matches
Mail list logo
