Slashdot Mirror
Modding The Barton XP To A Barton MP
Dr. Jackie Lee writes "Don't have the budget for an AMD Opteron? There's always a cheaper alternative with AMD's current Barton processors. In this article, we'll show you how to run these new Barton XP processors in SMP mode."
Or, maybe, its for those of us who can't afford the hugely expensive 'multiprocessor' chips, but would still like to be able to run a dual-processor system.
As a programmer, it's always a good idea to have access to a dual-processor system, because there are all sorts of lockups that just wont happen on a single-processor system, but will lock your program up on a multi-processor one. Having a hugely expensive system just to debug an application isn't feasible - if you're able to fool a 'single processor' chip into thinking it's a 'multiprocessor' one, then you've got an essential debugging machine at a fraction of the price
why SMP nowadays?
Sadly, there's still a lot of dog-slow apps. Example: ask Macromedia Dreamweaver MX to test a stored procedure with a hundred parameters, and it'll freeze for 30-90 seconds on all of the P4's I've tried it on, pegging the CPU at 100%. On dual-CPU boxes, that means you can still be productive with the other CPU, and do things like whine on Macromedia user groups while it runs.
SMP also helps a lot if your box is both a testbed and a design system: mine runs SQL Server, IIS, and I do my design on it, so while I'm working, there's a ton of processes running.
Don't get me wrong, I still buy the "real" SMP systems with warranties, but just pointing out why I'm doing it, and I'm not rendering.
What's your damage, Heather?
Guess what? You can't guarantee they'll work - people on LKML have refused to help users who have done this, as it simply makes it impossible to determine whether problems are the fault of the kernel or of the CPU itself.
Bah. You don't know anything for sure, neither to these LKML people. They're just trying to eliminate unknow quantities from their debugging (not like I blame them). For all we know right now (being that the article is slashdotted) there is no difference between the XP and MP except a jumper setting. I honestly wouldn't be suprised if it's true. Why go through all the trouble to fab seperate chips when you can just use external jumpers?
This wouldn't be the first time someone could upgrade their hardware by connecting two contacts.
What really matters is determining if there is any actual difference between an XP and an MP. If there is none, then this isn't just for "the overclockers who couldn't care less about stability". There are plenty of others who would love to save $40/cpu.
Since you don't know either way. You're not really contributing much to the discussion. Yeah, without any testing I wouldn't use a modded chip for critical data, but it's not impossible to verify whether or not the modded chip is stable. "it simply makes it impossible to determine whether problems are the fault of the kernel or of the CPU itself" No, it doesn't. There's a simple solution. Test with both modded XPs and regular MPs.
What needs to happen is testing. Without that, we don't really know how useful this mod will be.
Life is too short to proofread.