Date: Fri, 06 Feb 2015 22:32:27 +0000 From: bugzilla-noreply@freebsd.org To: freebsd-bugs@FreeBSD.org Subject: [Bug 135718] [patch] enhance qsort(3) to properly handle 32-bit aligned data on 64-bit systems Message-ID: <bug-135718-8-9tlfhOpJMp@https.bugs.freebsd.org/bugzilla/> In-Reply-To: <bug-135718-8@https.bugs.freebsd.org/bugzilla/> References: <bug-135718-8@https.bugs.freebsd.org/bugzilla/>
next in thread | previous in thread | raw e-mail | index | archive | help
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=135718 --- Comment #5 from Andrey A. Chernov <ache@FreeBSD.org> --- And the bug: on amd64 the patch always copy by 32bits instead of 64bits due to replacement of swapcode(long, a, b, n) by swapcode(int, a, b, n). It is possible that copy by 32bits is faster on amd64 (I don't check), but it is very architecture dependent and must be ifdefed. If we going to be architecture dependent and optimize just i386 and amd64 cases, the code should use int32_t and int64_t and use proper architecture-related ifdefs. -- You are receiving this mail because: You are the assignee for the bug.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-135718-8-9tlfhOpJMp>