Re: autovectorize page checksum code included elsewhere

On Thu, Nov 23, 2023 at 1:49 AM Nathan Bossart <nathandbossart(at)gmail(dot)com> wrote:
>
> On Wed, Nov 22, 2023 at 02:54:13PM +0200, Ants Aasma wrote:
> > On Wed, 22 Nov 2023 at 11:44, John Naylor <johncnaylorls(at)gmail(dot)com> wrote:
> >> Poking in those files a bit, I also see references to building with
> >> SSE 4.1. Maybe that's an avenue that we should pursue? (an indirect
> >> function call is surely worth it for page-sized data)
>
> Yes, I think we should, but we also need to be careful not to hurt
> performance on platforms that aren't able to benefit [0] [1].

Well, yes (see popcount using a direct function call on non-x86), but
I don't think it's as important for page-sized data. Also, sse4.1 is
~10 years old, I think.

> There are a couple of other threads about adding support for newer
> instructions [2] [3], and properly detecting the availability of these
> instructions seems to be a common obstacle. We have a path forward for
> stuff that's already using a runtime check (e.g., CRC32C), but I think
> we're still trying to figure out what to do for things that must be inlined
> (e.g., simd.h).
>
> One half-formed idea I have is to introduce some sort of ./configure flag
> that enables all the newer instructions that your CPU understands.

That's not doable, but we should consider taking advantage of
x86-64-v2, which RedHat 9 builds with. That would allow inlining CRC
and popcount there. Not sure how to detect that easily.