Re: introduce optimized linear search functions that return index of matching element

Поиск
Список
Период
Сортировка
От John Naylor
Тема Re: introduce optimized linear search functions that return index of matching element
Дата
Msg-id CAFBsxsFiC0gmaoJ54uJHubnTojzoL3ZYdt3PR-jNYpzgrgb1og@mail.gmail.com
обсуждение исходный текст
Ответ на introduce optimized linear search functions that return index of matching element  (Nathan Bossart <nathandbossart@gmail.com>)
Список pgsql-hackers
Дерево обсуждения

On Sat, Sep 17, 2022 at 12:29 PM Nathan Bossart <nathandbossart@gmail.com> wrote:
>
> On Fri, Sep 16, 2022 at 02:54:14PM +0700, John Naylor wrote:
> > v6 demonstrates why this should have been put off towards the end. (more below)
>
> Since the SIMD code is fresh in my mind, I wanted to offer my review for
> 0001 in the "Improve dead tuple storage for lazy vacuum" thread [0].
> However, I agree with John that the SIMD part of that work should be left
> for the end

As I mentioned in the radix tree thread, I don't believe this level of abstraction is appropriate for the intended use case. We'll want to incorporate some of the low-level simd.h improvements later, so you should get authorship credit for those.  I've marked the entry "returned with feedback".

--
John Naylor
EDB: http://www.enterprisedb.com

В списке pgsql-hackers по дате отправления:

Предыдущее
От: "kuroda.hayato@fujitsu.com"
Дата:
Сообщение: RE: test_decoding assertion failure for the loss of top-sub transaction relationship
Следующее
От: Michael Paquier
Дата:
Сообщение: Re: Expose Parallelism counters planned/execute in pg_stat_statements