Re: __sync_lock_test_and_set on ARM

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

To: "Andrew Haley" <aph-gcc@xxxxxxxxxxxxxxxxxxx>
Subject: Re: __sync_lock_test_and_set on ARM
From: "Phil Endecott" <spam_from_gcc_help_2@xxxxxxxxxxxx>
Date: Thu, 13 Sep 2007 14:34:47 +0100
Cc: "Phil Endecott" <spam_from_gcc_help_2@xxxxxxxxxxxx>, <gcc-help@xxxxxxxxxxx>, "David Daney" <ddaney@xxxxxxxxxx>
In-reply-to: <18153.14521.717519.504892@xxxxxxxxxxxx>
References: <18153.14521.717519.504892@xxxxxxxxxxxx>

Andrew Haley wrote:

pre-ARM v6 the builtins can't be done in userland


__sync_lock_test_and_set can be doing in userland; it is a single SWP instruction.

I am only asking that this one builtin be implemented.


Phil.

References:
- Re: __sync_lock_test_and_set on ARM
  - From: Andrew Haley

Prev by Date: Re: __sync_lock_test_and_set on ARM
Next by Date: gcc: installation problem, cannot exec `cc1': No such file or directory
Previous by thread: Re: __sync_lock_test_and_set on ARM
Next by thread: Re: __sync_lock_test_and_set on ARM
Index(es):
- Date
- Thread

[Index of Archives] [Linux C Programming] [Linux Kernel] [eCos] [Fedora Development] [Fedora Announce] [Autoconf] [The DWARVES Debugging Tools] [Yosemite Campsites] [Yosemite News] [Linux GCC]

Powered by Linux