Date: Fri, 13 Jul 2007 07:17:06 -0400 From: John Baldwin <jhb@freebsd.org> To: freebsd-arch@freebsd.org Cc: Dag-Erling =?utf-8?q?Sm=C3=B8rgrav?= <des@des.no>, "Sean C. Farley" <scf@freebsd.org> Subject: Re: Assembly string functions in i386 libc Message-ID: <200707130717.07585.jhb@freebsd.org> In-Reply-To: <86d4yw649m.fsf@dwp.des.no> References: <20070711134721.D2385@thor.farley.org> <20070712170748.W8789@thor.farley.org> <86d4yw649m.fsf@dwp.des.no>
next in thread | previous in thread | raw e-mail | index | archive | help
On Friday 13 July 2007 05:29:09 am Dag-Erling Sm=C3=B8rgrav wrote: > "Sean C. Farley" <scf@FreeBSD.org> writes: > > I never claimed to succeed; I only tried. The two types of tests I can > > think would be useful were execution of strlen() by itself and within a > > common program. I had thought I had tested the first type of test. >=20 > You did, but it's worthless. >=20 > If you wrote a test program that did nothing but add two numbers > together, then profiled that program, would you then conclude that > addition needs optimizing? Um, des, he's asking to _remove_ the assembly optimization on i386 and just= =20 use the C version that other archs use. Unless there is a compelling reaso= n=20 to keep the asm versions I agree that the C version should just be used=20 instead. =2D-=20 John Baldwin
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200707130717.07585.jhb>