Re: [HACKERS] Broken atomics code on PPC with FreeBSD 10.3

Поиск
Список
Период
Сортировка
От Andres Freund
Тема Re: [HACKERS] Broken atomics code on PPC with FreeBSD 10.3
Дата
Msg-id 9E4EBC01-A299-4122-9416-32E5377253F8@anarazel.de
обсуждение исходный текст
Ответ на Re: [HACKERS] Broken atomics code on PPC with FreeBSD 10.3  (Tom Lane <tgl@sss.pgh.pa.us>)
Ответы Re: [HACKERS] Broken atomics code on PPC with FreeBSD 10.3  (Tom Lane <tgl@sss.pgh.pa.us>)
Список pgsql-hackers

On December 30, 2016 4:48:22 PM GMT+01:00, Tom Lane <tgl@sss.pgh.pa.us> wrote:
>and got no warnings and the attached output.  I'm not very good at
>reading
>PPC assembler, but I think what is happening in the "char" case is that
>gcc is trying to emulate a byte-wide operation using a word-wide one,
>ie an lwarx/stwcx. loop. 

Hm.  This seems to suggest a straight out code generation bug in that compiler, not a failure in intrinsic detection.

I'll note that there's certainly ppc64 machine with that intrinsic working (tested that on the community hydra during
atomicsdevelopment).  So either it's a bug specific to some compiler version,  or 32bit ppc.
 

I assume there's no trivial way to get a newer compiler on that machine?
Andres
-- 
Sent from my Android device with K-9 Mail. Please excuse my brevity.



В списке pgsql-hackers по дате отправления:

Предыдущее
От: Pavel Stehule
Дата:
Сообщение: Re: [HACKERS] proposal: session server side variables
Следующее
От: Tom Lane
Дата:
Сообщение: Re: [HACKERS] Broken atomics code on PPC with FreeBSD 10.3