Date: Thu, 02 Apr 1998 11:52:52 +0800 From: Stephen Hocking-Senior Programmer PGS Tensor Perth <shocking@prth.pgs.com> To: freebsd-current@FreeBSD.ORG Cc: shocking@quokka.prth.tensor.pgs.com Subject: Re: current-digest V4 #79 Message-ID: <199804020352.LAA01292@ariadne.tensor.pgs.com> In-Reply-To: Your message of "Thu, 02 Apr 1998 13:38:17 %2B1000." <35230829.78DAA808@scitec.com.au>
next in thread | previous in thread | raw e-mail | index | archive | help
> Gregory P. Smith wrote: > > I think that would violate the Kernel's "never use floating point" rule > > because MMX uses the FP registers. (and on Intel's MMX implementation > > supposedly has a "large" context switch time between MMX and floating > > point mode). > Much of this alledgedly large time comes from manually saving and restoring all the FP registers. If you don't have to save them, then it becomes much less costly. On the other hand, the AMD K6 has far less penalty for saving them, but its MMX instruction set apparently runs at about 1/2 the speed of an equivalently clocked P5-MMX. I think Tom's Hardware page & x86.org have some hard numbers for all this. Stephen To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199804020352.LAA01292>