FedoraThis forum is for the discussion of the Fedora Project.
Notices
Welcome to LinuxQuestions.org, a friendly and active Linux Community.
You are currently viewing LQ as a guest. By joining our community you will have the ability to post topics, receive our newsletter, use the advanced search, subscribe to threads and access many other special features. Registration is quick, simple and absolutely free. Join our community today!
Note that registered members see fewer ads, and ContentLink is completely disabled once you log in.
If you have any problems with the registration process or your account login, please contact us. If you need to reset your password, click here.
Having a problem logging in? Please visit this page to clear all LQ-related cookies.
Get a virtual cloud desktop with the Linux distro that you want in less than five minutes with Shells! With over 10 pre-installed distros to choose from, the worry-free installation life is here! Whether you are a digital nomad or just looking for flexibility, Shells can put your Linux machine on the device that you want to use.
Exclusive for LQ members, get up to 45% off per month. Click here for more info.
I am working on completing a FC4 build out using a Gigabyte motherboard and Athlon X2 processor and encountered a strange problem. During initial testing, using super_pi on processor 1 and glxgears on processor 2, performance was increased when both cores were loaded. Merely loading one processor at 100% resulted in worse performance for a single application than when both processors were under load.
Since this whole SMP type thing is new to me, I am guessing that Powernow-k8 is somehow playing a part in throttling the cores. Is there a way to change this behavior? If so, please point me to the proper documentation.
Thanks,
DQ
UPDATE: I am using a GA-k8n Ultra-9 motherboard. I decided to flash the bios to the F6 bios and now things seem to work (i.e. each core can run full tilt independent of the other). Grepping DMESG now indicates that 2 Athlon 64 processors are detected as opposed to a single Athlon Processor. The wording in DMESG is "correct" no matter how you read it.
Originally posted by DualQuad I am working on completing a FC4 build out using a Gigabyte motherboard and Athlon X2 processor and encountered a strange problem. During initial testing, using super_pi on processor 1 and glxgears on processor 2, performance was increased when both cores were loaded. Merely loading one processor at 100% resulted in worse performance for a single application than when both processors were under load.
Since this whole SMP type thing is new to me, I am guessing that Powernow-k8 is somehow playing a part in throttling the cores. Is there a way to change this behavior? If so, please point me to the proper documentation.
Thanks,
DQ
UPDATE: I am using a GA-k8n Ultra-9 motherboard. I decided to flash the bios to the F6 bios and now things seem to work (i.e. each core can run full tilt independent of the other). Grepping DMESG now indicates that 2 Athlon 64 processors are detected as opposed to a single Athlon Processor. The wording in DMESG is "correct" no matter how you read it.
I'm also interested in the Cool N Quite features of the Athlon 64. Can you tell me a little bit about your setup, and how you got it working.
I have an Athlon 64 3200+ (Socket 754) with an ABit mobo, and I'm running Fedora Core 4 for x86-64.
Is the Powernow kernel code already compiled into Fedora 4, or do I have to recompile the kernel myself to enable that?
Where can you see the clock throttling? Do you see it in the procinfo file (I think thats the file, I'm workign from memory), cause I never see mine at anything but full load.
The problem that DualQuad reported above, i.e., that performance is slow when only one processor is used and that performance is normal when both processors are being used, has also been plaguing me for some time as well. I have the same motherboard, a gigabyte GA-K8N Ultra-9 (Bios F6). I have tried several linuxes (FC3 with all updates, FC4 with all updates, both 32 bit and 64 bit, Suse 10), and I have also tried a range of kernel options (noapic, acpi=off, no_timer_check (for a runaway clock problem in FC4 64 bit)). Has anyone encountered and possibly solved this problem (custom kernel, or perhaps a different motherboard)?
Thanks!
I have an AMD Athlong 64 X2 4400
Last edited by BlueBright; 10-08-2005 at 02:03 PM.
LinuxQuestions.org is looking for people interested in writing
Editorials, Articles, Reviews, and more. If you'd like to contribute
content, let us know.