Dual Processor Box
-
OK pop-pickers, Any recommendations for companies that I should choose/avoid for a Dual Processor box. I'd like Athlon, but I think realistically its going to be PIII for a few months. I'm not interested in a P4 dual box at present (if you can get one). Spin those 78s. Stephen Kellett -- C++/Java/Win NT/Unix variants Memory leaks/corruptions/performance/system problems. UK based. Problems with RSI/WRULD? Contact me for advice.
-
OK pop-pickers, Any recommendations for companies that I should choose/avoid for a Dual Processor box. I'd like Athlon, but I think realistically its going to be PIII for a few months. I'm not interested in a P4 dual box at present (if you can get one). Spin those 78s. Stephen Kellett -- C++/Java/Win NT/Unix variants Memory leaks/corruptions/performance/system problems. UK based. Problems with RSI/WRULD? Contact me for advice.
I built my own dual box not too far back.. Used dual P3 750s. Also has 512MB of ram on it and it moves VERY fast espcially while compiling this nasty 250,000 line code base I work with.. I've heard mixed feeling from a lot of people about the athlons. Something very important to remember about building your dual machine though is making sure you get a good mobo too. I would recommend supermicro or tyan boards. They are very stable and have pretty good speed. Joseph Dempsey jdempsey@cox.rr.com Joseph.Dempsey@thermobio.com "Software Engineering is a race between the programmers, trying to make bigger and better fool-proof software, and the universe trying to make bigger fools. So far the Universe in winning." --anonymous
-
OK pop-pickers, Any recommendations for companies that I should choose/avoid for a Dual Processor box. I'd like Athlon, but I think realistically its going to be PIII for a few months. I'm not interested in a P4 dual box at present (if you can get one). Spin those 78s. Stephen Kellett -- C++/Java/Win NT/Unix variants Memory leaks/corruptions/performance/system problems. UK based. Problems with RSI/WRULD? Contact me for advice.
At work, I have had two dual processor Dell machines and haven't had a single problem. I highly recommend Dell machines, they are top notch. Chris Hafey PS - My home machine is a dual processor box based on a SuperMicro motherboard. It works flawlessly!
-
OK pop-pickers, Any recommendations for companies that I should choose/avoid for a Dual Processor box. I'd like Athlon, but I think realistically its going to be PIII for a few months. I'm not interested in a P4 dual box at present (if you can get one). Spin those 78s. Stephen Kellett -- C++/Java/Win NT/Unix variants Memory leaks/corruptions/performance/system problems. UK based. Problems with RSI/WRULD? Contact me for advice.
I've got an Asus Dual-processor board. Don't have many problems with it. I bought it '99, and now it's happily running PIII-600's. It's also got a dual-channel SCSI LVD controller built on-board (this ROCKS!). Getting dual P4's is cool and all, but make sure that you don't let the bottleneck of your system be your hard disks. BTW: For all others reading this: do all forms of IDE require CPU cycles to read data from disks? I got into a discussion with the prof in my OS/hardware systems class about this topic. He said a SCSI system is alwasy going to lead to a faster system than an IDE, because IDE requires CPU cycles while SCSI chipsets have their own mini-processor built-in. Has anyone had experience with this? What about Firewire (IEEE 1394)? -- Russell Morris Georgia Institute of Technology "Lisa, just because I don't care doesn't mean I'm not listening..." - Homer
-
I've got an Asus Dual-processor board. Don't have many problems with it. I bought it '99, and now it's happily running PIII-600's. It's also got a dual-channel SCSI LVD controller built on-board (this ROCKS!). Getting dual P4's is cool and all, but make sure that you don't let the bottleneck of your system be your hard disks. BTW: For all others reading this: do all forms of IDE require CPU cycles to read data from disks? I got into a discussion with the prof in my OS/hardware systems class about this topic. He said a SCSI system is alwasy going to lead to a faster system than an IDE, because IDE requires CPU cycles while SCSI chipsets have their own mini-processor built-in. Has anyone had experience with this? What about Firewire (IEEE 1394)? -- Russell Morris Georgia Institute of Technology "Lisa, just because I don't care doesn't mean I'm not listening..." - Homer
do all forms of IDE require CPU cycles to read data from disks? I got into a discussion with the prof in my OS/hardware systems class about this topic. He said a SCSI system is alwasy going to lead to a faster system than an IDE, because IDE requires CPU cycles while SCSI chipsets have their own mini-processor built-in. That is correct (and why I only have SCSI-drives in my home-machine :)) - Anders Money talks, but all mine ever says is "Goodbye!"
-
I've got an Asus Dual-processor board. Don't have many problems with it. I bought it '99, and now it's happily running PIII-600's. It's also got a dual-channel SCSI LVD controller built on-board (this ROCKS!). Getting dual P4's is cool and all, but make sure that you don't let the bottleneck of your system be your hard disks. BTW: For all others reading this: do all forms of IDE require CPU cycles to read data from disks? I got into a discussion with the prof in my OS/hardware systems class about this topic. He said a SCSI system is alwasy going to lead to a faster system than an IDE, because IDE requires CPU cycles while SCSI chipsets have their own mini-processor built-in. Has anyone had experience with this? What about Firewire (IEEE 1394)? -- Russell Morris Georgia Institute of Technology "Lisa, just because I don't care doesn't mean I'm not listening..." - Homer
He said a SCSI system is alwasy going to lead to a faster system than an IDE, because IDE requires CPU cycles Um... no. IDE controllers all use DMA nowdays, as opposed to the older PIO (programmed I/O) method which did use the CPU. --Mike-- http://home.inreach.com/mdunn/ "Holding the away team at bay with a non-functioning phaser was an act of unmitigated gall. I admire gall." Lt. Cmdr. Worf
-
I've got an Asus Dual-processor board. Don't have many problems with it. I bought it '99, and now it's happily running PIII-600's. It's also got a dual-channel SCSI LVD controller built on-board (this ROCKS!). Getting dual P4's is cool and all, but make sure that you don't let the bottleneck of your system be your hard disks. BTW: For all others reading this: do all forms of IDE require CPU cycles to read data from disks? I got into a discussion with the prof in my OS/hardware systems class about this topic. He said a SCSI system is alwasy going to lead to a faster system than an IDE, because IDE requires CPU cycles while SCSI chipsets have their own mini-processor built-in. Has anyone had experience with this? What about Firewire (IEEE 1394)? -- Russell Morris Georgia Institute of Technology "Lisa, just because I don't care doesn't mean I'm not listening..." - Homer
No, he is wrong. It used to be that way, but it was a long time ago. Modern IDE system use DMA transfers and doesn't put any more strain on the CPU than a SCSI system does. http://www.storagereview.com/welcome.pl/http://www.storagereview.com/guide2000/ref/hdd/if/comp.html /Mike [NOTE: A modern SCSI disc *will* probably be faster than a modern IDE disc, but the reason for that is not the CPU load, it is more because of the lower access time for the SCSI disc.]
-
He said a SCSI system is alwasy going to lead to a faster system than an IDE, because IDE requires CPU cycles Um... no. IDE controllers all use DMA nowdays, as opposed to the older PIO (programmed I/O) method which did use the CPU. --Mike-- http://home.inreach.com/mdunn/ "Holding the away team at bay with a non-functioning phaser was an act of unmitigated gall. I admire gall." Lt. Cmdr. Worf
From what I have read, you can stack SCSI requests asynchronously (i.e., perform operations on one disk, while another is busy), which you cannot do with IDE. This is said to make SCSI significantly faster in a RAID configuration, even for equal spindle speeds and bus bandwidth. Can anyone more knowledgeable comment here?
-
OK pop-pickers, Any recommendations for companies that I should choose/avoid for a Dual Processor box. I'd like Athlon, but I think realistically its going to be PIII for a few months. I'm not interested in a P4 dual box at present (if you can get one). Spin those 78s. Stephen Kellett -- C++/Java/Win NT/Unix variants Memory leaks/corruptions/performance/system problems. UK based. Problems with RSI/WRULD? Contact me for advice.
Tyan do a Dual processor Athlon board, but is aimed at the server market. Other Manufacturers cannot be that far behind (I Hope:) ) Even if you're not paranoid, they might still be watching you.
-
OK pop-pickers, Any recommendations for companies that I should choose/avoid for a Dual Processor box. I'd like Athlon, but I think realistically its going to be PIII for a few months. I'm not interested in a P4 dual box at present (if you can get one). Spin those 78s. Stephen Kellett -- C++/Java/Win NT/Unix variants Memory leaks/corruptions/performance/system problems. UK based. Problems with RSI/WRULD? Contact me for advice.
Thanks for the replies folks. Stephen Kellett -- C++/Java/Win NT/Unix variants Memory leaks/corruptions/performance/system problems. UK based. Problems with RSI/WRULD? Contact me for advice.