Date: Tue, 10 Jun 1997 21:39:13 +0200 From: Stefan Esser <se@FreeBSD.ORG> To: Howard Lew <hlew@www2.shoppersnet.com> Cc: Craig Johnston <craig@gnofn.org>, hardware@FreeBSD.ORG Subject: Re: poor memory bandwidth on ABIT IT5H rev 1.5 Message-ID: <19970610213913.46089@mi.uni-koeln.de> In-Reply-To: <Pine.BSF.3.91.970610101234.23498C-100000@www2.shoppersnet.com>; from Howard Lew on Tue, Jun 10, 1997 at 10:37:24AM -0700 References: <19970610112536.48352@mi.uni-koeln.de> <Pine.BSF.3.91.970610101234.23498C-100000@www2.shoppersnet.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Jun 10, Howard Lew <hlew@www2.shoppersnet.com> wrote: > On Tue, 10 Jun 1997, Stefan Esser wrote: > > > On Jun 9, Howard Lew <hlew@www2.shoppersnet.com> wrote: > > > I thought the TX was better than the VX, so I compared several > > > motherboards with dd if=/dev/zero of=/dev/null bs=1m count=1000 > > > > > > CPU is AMD K5-PR133 > > > > > > FIC PT2006 (Intel VX) with 256K PB Cache & FreeBSD-2.1.7.1R > > > Got 65MB/s > > > > > > FreeTech F63T (Intel VX) with 256K PB Cache & FreeBSD-2.1.7.1R > > > Got 62MB/s > > > > > > FreeTech F79 (Intel TX) with 512K PB Cache & FreeBSD-3.0SNAP-6/6/97 > > > Got 43MB/s > > You won't see much of a difference between 2.1.x and -current, with > > regard to chip-set support. The TX does not need any specific code, > > and I doubt that the EIDE code in -current know about the TX IDE > > chip ... > > > > uh oh.. Then I think the upgrade was more of a downgrade except I have a > few more memory slots and better cpu support... The funny thing is that > Win95 seems to run faster. On Mode 3 EIDE, it gets about 8MB/sec on the > MB according to coretest. No, the TX should be faster than the VX (which is slow, unless you got SDRAM). The TX is (kind of) an enhanced version of the VX, and is assumed to be faster than the Triton 2 (it got deeper PCI buffers and supports new PCI 2.1 features that should improve throughput if multiple PCI bus-masters demand high bandwidth and the CPU is accessing high latency devices at the same time.) > Gee I should have asked that earlier... 2.1.7.1R was super stable > although it felt a little slower and I thought it was because of the "no > driver assigned messages". I think that USB device steals an IRQ now, so > now every IRQ available is being used. I think the next great chipset > should support more IRQs (Is that possible)? You can have as many interrupts as you want, with PCI, but PCI on PC-compatible hardware is restricted to the PC interrupt structure (for backwards compatibility reasons if some PCI card that completely emulates some ISA card is installed, and to be used with the ISA driver). > So the TX is even slower than the VX for EDO? This gives me a very bad > feeling... No, I don't think I wrote that (at least I didn't want to ... :) The TX should be better than the VX, which was slow with EDO, but slightly faster than the Triton 2 with SDRAM. The major limitation of the VX chip set is that it only supports 64MB of DRAM covered by secondary cache, so it is no good for server machines with a few hundred MB of RAM ... Regards, STefan
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19970610213913.46089>