Date: Wed, 26 Apr 2006 10:52:02 -0400 From: Mike Jakubik <mikej@rogers.com> To: David Gilbert <dgilbert@dclg.ca> Cc: freebsd-performance@freebsd.org, Steven Hartland <killing@multiplay.co.uk>, Bill Moran <wmoran@collaborativefusion.com> Subject: Re: Dual-core CPU vs. very large cache Message-ID: <444F8912.4010604@rogers.com> In-Reply-To: <17487.34074.833134.823847@canoe.dclg.ca> References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca>
next in thread | previous in thread | raw e-mail | index | archive | help
David Gilbert wrote: > This isn't random. As I understand the issue, the Opteron HT bus > handles synchronization much faster. So for a game --- this doesn't > matter ... games don't (usually) need sync. Databases, however, live > on synchonizaton. If you're a Dell man (and already paying the Dell > tax), consider the Sun 1U's. They offer up to 4 cores in a 1U. > Sure, the HTT bus is wonderful. Intel will raise the FSB to 1067, but i still think we will see significant performance improvements on the new Core architecture. The Conroe CPU throughly trashes an AMD Athlon-X2 at a "higher" frequency. For those interested: http://www.anandtech.com/tradeshows/showdoc.aspx?i=2713 As much as i love AMDs cpus, the availability of good server motherboards and chipsets stinks, hopefully that will change when socket AM2 comes out.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?444F8912.4010604>