On Thu, Aug 25, 2022 at 11:57 AM Nathan Bossart
<nathandbossart@gmail.com> wrote:
>
> On Thu, Aug 25, 2022 at 10:38:34AM +0700, John Naylor wrote:
> > On Thu, Aug 25, 2022 at 1:01 AM Nathan Bossart <nathandbossart@gmail.com> wrote:
> >> On Wed, Aug 24, 2022 at 11:07:03AM +0700, John Naylor wrote:
> >> > - Can a user on ARM64 ever get a runtime fault if the machine attempts
> >> > to execute NEON instructions?
> >>
> >> IIUC yes, although I'm not sure how likely it is in practice.
> >
> > Given the quoted part above, it doesn't seem likely, but we should try
> > to find out for sure, because a runtime fault is surely not acceptable
> > even on a toy system.
>
> The ARM literature appears to indicate that Neon support is pretty standard
> on aarch64, and AFAICT it's pretty common to just assume it's available.
This doesn't exactly rise to the level of "find out for sure", so I
went looking myself. This is the language I found [1]:
"Both floating-point and NEON are required in all standard ARMv8
implementations. However, implementations targeting specialized
markets may support the following combinations:
No NEON or floating-point.
Full floating-point and SIMD support with exception trapping.
Full floating-point and SIMD support without exception trapping."
Since we assume floating-point, I see no reason not to assume NEON,
but a case could be made for documenting that we require NEON on
aarch64, in addition to exception trapping (for CRC runtime check) and
floating point on any Arm. Or even just say "standard". I don't
believe anyone will want to run Postgres on specialized hardware
lacking these features, so maybe it's a moot point.
[1] https://developer.arm.com/documentation/den0024/a/AArch64-Floating-point-and-NEON
--
John Naylor
EDB: http://www.enterprisedb.com