Re: add AVX2 support to simd.h - Mailing list pgsql-hackers

From Nathan Bossart
Subject Re: add AVX2 support to simd.h
Date
Msg-id 20240319031601.GA828141@nathanxps13
Whole thread Raw
In response to Re: add AVX2 support to simd.h  (John Naylor <johncnaylorls@gmail.com>)
Responses Re: add AVX2 support to simd.h
List pgsql-hackers
On Tue, Mar 19, 2024 at 10:03:36AM +0700, John Naylor wrote:
> I took a brief look, and 0001 isn't quite what I had in mind. I can't
> quite tell what it's doing with the additional branches and "goto
> retry", but I meant something pretty simple:

Do you mean 0002?  0001 just adds a 2-register loop for remaining elements
once we've exhausted what can be processed with the 4-register loop.

> - if short, do one element at a time and return

0002 does this.

> - if long, do one block unconditionally, then round the start pointer
> up so that "end - start" is an exact multiple of blocks, and loop over
> them

0002 does the opposite of this.  That is, after we've completed as many
blocks as possible, we move the iterator variable back to "end -
block_size" and do one final iteration to cover all the remaining elements.

-- 
Nathan Bossart
Amazon Web Services: https://aws.amazon.com



pgsql-hackers by date:

Previous
From: John Naylor
Date:
Subject: Re: add AVX2 support to simd.h
Next
From: Masahiko Sawada
Date:
Subject: Re: [PoC] Improve dead tuple storage for lazy vacuum