Date: Thu, 11 Dec 1997 00:12:24 -0800 (PST) From: Jaye Mathisen <mrcpu@cdsnet.net> To: Jason Evans <jasone@canonware.com> Cc: Alex <garbanzo@hooked.net>, Steve Passe <smp@csn.net>, current <current@FreeBSD.ORG> Subject: Re: -current, goliath, smp -- problems Message-ID: <Pine.NEB.3.95.971211000539.14624R-100000@mail.cdsnet.net> In-Reply-To: <Pine.LNX.3.95.971209231804.248N-100000@paladio>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, 9 Dec 1997, Jason Evans wrote: > On Mon, 8 Dec 1997, Alex wrote: > in the neighborhood of 500 MB/sec, which is enough to feed 4 processors, > but quite inadequate for 8. So, even though there are twice as many > processors, the performance gain is not impressive. > > If there's anyone else out there that knows any better, please correct me. > =) While I can't correct you, I have a couple DEC ZX6000's, that when using the add-on memory boards, so there's something like 4GB of SIMMS, the memory path becomes 256bit wide, 4 way interleaved, and runs at some hellacious rate, and I remember the memory bandwidth being significantly higher than 500MB/s. Heck, if somebody knows of some memory benchmarking software, I'd be happy to try it out.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.NEB.3.95.971211000539.14624R-100000>