On Sat, 2002-03-23 at 23:48, Felix Miata wrote: > Lyvim Xaphir wrote: > > > On Sat, 2002-03-23 at 16:49, Felix Miata wrote: > > > > I currently have four machines with AMD chips and one (486) with Intel. > > > If I had to buy a motherboard today, it would probably be one that uses > > > an Intel CPU. Most AMD motherboards use performance crippled VIA > > > chipsets. How good the CPU is matters little when the primary bottleneck > > > is the I/O bus. > > > I don't have a problem with your bottleneck statement; but I do have a > > problem with it being applied to VIA chipsets. My research does not > > substantiate what you are saying. I have a VIA based Abit KT7A-RAID > > What research?
Your own research, for one. You disproved your own self in one post, and saved me the trouble of digging through my bookmarks. Thanks. > > mobo and have been running it for over a year with an Athlon 800 T-bird > > That would seem to be a statistically invalid sample size of one. An isolated case I am not. But even if I was, it's still superior to your "statistically invalid" sample of zero, which is what you have, assuming you're not planning to invest in another socket 7. > > overclocked to 964 mhz. If you've got more URL's backing up what you > > I don't overclock anything. I want bulletproof. Heh. I've got both. But that's only because I did'nt start out misinformed or prejudiced. Maybe I have an edge because I actually RTFM. > I spent quite some time looking for the URL I provided. I started first > at Tom's Hardware, thinking that's where I had seen it. My mistake. > Nowhere there could I find a relevant comparo of chipset performance at > Tom's. There was a chipset link there, but quite ancient. I spent a > bunch more time at Google extracting what I was after to show the list. You spend time finding them, writing about them, posting it to the expert list here, but then you don't check them to make sure you've backed your advice up properly? What kind of logic is that? > Games garbage. My computers aren't toys. It'll be a while before I can > afford yet another new memory type the way they've been changing so fast > lately and keeping prices up. Then when URL's are handed to you on a silver platter cut up into bite sized pieces fit for even a baby's palate, you still don't read. There is a complete set of benchmarks at the URL that I gave you; it was just accident that the OpenGL benchmarks were the first ones. Nobody told you to make the OpenGL benches your sole requsite; there were also business and application benches there for your perusal; what exactly is your excuse for ignoring those? NOT LOOKING? Hell, I guess if you don't even review your own URL's you're sure not going to review somebody elses. I also could relate the stupidity of ignoring the Opengl benches with relation to the efficiency and power of the system at large; but I consider it a waste of time. Casting pearls, as it were. > > Since you seem to be currently doing some research, I suggest that you > > go here and look at what the experts are saying about the pentium 4 > > architecture. > > > http://www.emulators.com/pentium4.htm#Pentium 4 > > Looks like an excellent reason to keep my Socket 7 systems running and > wait for wider availability of unflawed AMD support. Hmmmm. It's evident that even your own informaton does not percolate through. There's already "unflawed AMD support" available with the VIA chipset that YOUR authors wrote about. > > Oh, and by the way, I checked out your link to the url "that led to your > > comment." I'm kind of surprised, because it does not look like you've > > read it yourself. The article states that by using the latest VIA > > patches, the PCI bus performance is raised to equal that provided by > > Intel's chipset. > > > Don't you read your own research? > > I didn't read it today. I read it when I was researching weeks ago. You posted it to the expert list today, the article was marked as having been updated by the authors, you verified it was the correct URL today, and yet you didn't read it today? Not even a once-over? After reflecting on the totality of this thread, I actually believe you. > > In case you missed it the first time, I've copied and pasted it here for > > your convenience. Complete content, at this URL: > > > http://www.tecchannel.de/hardware/817/11.html > > > Text only excerpt for whomever it may concern here: > > > ______________________________________________________________________ > > Update: VIAs official patch, Version 1.04 > > [mucho patch stuff snipped] > > I'm confused about this patch business. What do they patch, device BIOS > code? Drivers? Surely if drivers they would be windoze only, no? You are confused about a great deal more than the patch business. > I > didn't see anything in what I snipped that indicated the patches applied > regardless of OS, which to me means windoze only and therefore useless > when I boot into Linux or OS/2. THE BENCHMARKS ON *YOUR* URL WERE WINDOZE BENCHES. Therefore, by your own logic they have no relation to Linux performance ! Also by your own logic they have no relation with regard to how Linux kernel/driver code handles the VIA chipset, which in the case of the KT266A supports Athlon CPU's fine. _________________________________________________________ Do You Yahoo!? Get your free @yahoo.com address at http://mail.yahoo.com
Want to buy your Pack or Services from MandrakeSoft? Go to http://www.mandrakestore.com
