Date: Wed, 19 Aug 1998 12:37:36 +1000 From: "Andrew Reilly" <reilly@zeta.org.au> To: =?iso-8859-1?Q?Dag-Erling_Coidan_Sm=F8rgrav?= <dag-erli@ifi.uio.no>, Chen Hsiung Chan <frankch@waru.life.nthu.edu.tw> Cc: hackers@FreeBSD.ORG Subject: Re: Dual Celerons - anyone tried this? Message-ID: <19980819123736.A3980@reilly.home> In-Reply-To: =?iso-8859-1?Q?=3Cxzpu33a5mca=2Efsf=40skejdbrimir=2Eifi=2Euio=2Eno=3E=3B?= =?iso-8859-1?Q?_from_Dag-Erling_Coidan_Sm=F8rgrav__on_Tue=2C_Aug_18=2C_1?= =?iso-8859-1?Q?998_at_03:41:25PM_%2B0000?= References: <19980818221129.30050@waru.life.nthu.edu.tw> <xzpu33a5mca.fsf@skejdbrimir.ifi.uio.no>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, Aug 18, 1998 at 03:41:25PM +0000, Dag-Erling Coidan Smørgrav wrote: > Chen Hsiung Chan <frankch@waru.life.nthu.edu.tw> writes: > > In the report they mentioned that one can overclock celeron > > to 448MHz, combined with the dual capability, the machine is > > certainly screaming. > > No matter how you shake it, a cache-less CPU does not scream except > from anguish. It does depend a lot on what you're doing. You are probably right if your workload is "make buildworld", but for most multi-media applications L2-cache is not interestingly different from raw DRAM, (because of the data volumes), and the only useful caching performed is that done in function kernels, by the L1-cache. I believe that the Celeron has as much L1-cache as any other processor out there at the moment (more or less). -- Andrew To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19980819123736.A3980>