Re: [PATCH] word-at-a-time: use the same return type for has_zero regardless of endianness

From: Arnd Bergmann
Date: Wed Aug 02 2023 - 02:00:27 EST

On Wed, Aug 2, 2023, at 03:07, Linus Torvalds wrote:
> On Tue, 1 Aug 2023 at 15:22, <ndesaulniers@xxxxxxxxxx> wrote:

> Who ends up being affected by this? Powerpc does its own
> word-at-a-time thing because the big-endian case is nasty and you can
> do better with special instructions that they have.

powerpc needs the same patch though.

> Who else is even BE any more? Some old 32-bit arm setup?
> I think the patch is fine, but I guess I'd like to know that people
> who are affected actually don't see any code generation changes (or
> possibly see improvements from not turning it into a bool until later)

s390 is the main one here, maintainers added to Cc.

Atheros and Realtek MIPS are older but still shipping in low-end
network equipment, and there are still users on old embedded
big-endian mips (broadcom, cavium, intel/lantiq and arm
(intel ixp4xx) hardware. All modern Arm hardware (v6/v7/v8/v9)
can do both big-endian and little-endian, but actual user numbers
for big-endian are close to zero -- I have not heard from anyone
actually using it in years.

And then there was a lot of the old-school workstation/server
hardware (m68k, mips, parisc and sparc, not alpha/ia64) that is
mostly big-endian and still maintained to some degree.