Date: Fri, 11 Jul 1997 18:51:37 +0200 From: Stefan Esser <se@FreeBSD.ORG> To: Narvi <narvi@haldjas.folklore.ee> Cc: mika ruohotie <bsdhack@shadows.aeon.net>, hackers@FreeBSD.ORG, Stefan Esser <se@FreeBSD.ORG> Subject: Re: PQ_LARGECACHE and page colouring Message-ID: <19970711185137.42296@mi.uni-koeln.de> In-Reply-To: <Pine.BSF.3.96.970710111052.19833B-100000@haldjas.folklore.ee>; from Narvi on Thu, Jul 10, 1997 at 11:18:23AM %2B0300 References: <199707092048.XAA24685@shadows.aeon.net> <Pine.BSF.3.96.970710111052.19833B-100000@haldjas.folklore.ee>
next in thread | previous in thread | raw e-mail | index | archive | help
On Jul 10, Narvi <narvi@haldjas.folklore.ee> wrote: > > > > > if I add options PQ_LARGECACHE to the kernel config file. > > > > something we with 512K cache should use or not? > I have about the same (asus fx motherboard + 512K pipline burst cache in > the form of a coast module). > > I don't know if it is direct-mapped or not - there is no documentation I > can get my hands on. But it does help. All current chip sets for Pentium class processors support only a direct mapped secondary cache, AFAIK. 2-way or 4-way mapped caches on the motherboard were common in the 386 days, and may have been supported by some 486 chip set (I don't really know), but made sense mostly because of the much smaller cache size than common today. Regards, STefan
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19970711185137.42296>