On 2026-10-11 10:38, Willy Tarreau wrote:
> On Sun, Oct 11, 2026 at 07:19:46PM +0200, Sebastian Andrzej Siewior wrote:
>> On 2026-10-09 20:13:55 [-0600], Tancred wrote:
>>>
>>>
>>> On 10/8/26 03:07, Sebastian Andrzej Siewior wrote:
>>>> where certain workloads widely
>>>> move to x32 and use it exclusively. In the meantime Debian introduced a
>>>> patch to disable x32 by default (so it has to be enabled at boot time on
>>>> the command line) because they are afraid of the increased attack
>>>> surface. Fedora as far as I tell has X32 disabled (looking at 7.0-rc5
>>>> rpm in rawhide).
>>>>
>>>> Since there is practically no real use for x32
>>>
>>> I only recently discovered x32 and built a Desktop (with all daemons and
>>> utilities running 10-30% smaller and some a bit faster, with 64 bit
>>> libraries for eg. Firefox.) My experiment should definitely not decide
>>> anything, but how much real-world use would be sufficient to justify
>>> continued presence (more complex compat code)?
>>
>> "a bit faster" needs actual numbers to justify. One examples was quicker
>> gcc but I don't see a x32 compile farm leveraging this benefit.
>
> FWIW I do build my ARM cross-compilers in a32 because they're generally
> ~10-15% faster than in a64. I wouldn't be surprised if that was the same
> on x86 because tools such as compilers very likely use pointers a lot. In
> a build farm it certainly makes a difference, possibly not sufficient to
> justify keeping a kernel port, but it's just to illustrate one valid use
> case.
>
Compilers is known to be significantly faster with x32, because compilers use
a *lot* of pointers. However, even compilers are starting to need > 4 GiB of
memory in many configurations, especially when using LTO.
-hpa
