Should we compile x86-64 ld.so with -mno-sse -mno-sse?
H.J. Lu
hjl.tools@gmail.com
Thu Nov 1 23:17:00 GMT 2012
On Wed, Oct 31, 2012 at 10:18 PM, Andreas Jaeger <aj@suse.com> wrote:
> On 11/01/2012 12:18 AM, H.J. Lu wrote:
>>
>> On Wed, Oct 31, 2012 at 3:59 PM, Richard Henderson <rth@twiddle.net>
>> wrote:
>>>
>>> On 2012-11-01 03:10, Carlos O'Donell wrote:
>>>>
>>>> What use case is there for not wanting to touch SEE in ld.so?
>>>
>>>
>>> I can only imagine HJL is worried about AVX performance if the
>>> dynamic linker uses SSE insns.
>>>
>>
>> That is not the main reason. We make sure that ld.so string/memory
>> functions never touch SSE/AVX registers. It is not for performance,
>> but for correctness. Otherwise callee will get random values in
>> vector registers,
>
>
> And as you mention elsewhere, we test already for it - so is that test
> failing now for you? Under which condition?
>
We are depending on pure luck. Adding -mno-sse -mno-mmx should
ensure that ld.so doesn't use SSE nor MMX registers.
--
H.J.
More information about the Libc-alpha
mailing list