Message boards :
Number crunching :
Update on Linux 64 -Nividia-V8-MB ?????
Message board moderation
Previous · 1 . . . 3 · 4 · 5 · 6
Author | Message |
---|---|
jason_gee Send message Joined: 24 Nov 06 Posts: 7489 Credit: 91,093,184 RAC: 0 |
Sounds good. Yeah, fingers crossed and good luck. The motivation is that I need to understand all the possible failure modes of my own applications, even if that means some supporting layer underneath. Everyone needs a hobby I guess, lol. "Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions. |
OTS Send message Joined: 6 Jan 08 Posts: 369 Credit: 20,533,537 RAC: 0 |
Well that went well – not. I reseated the video card, the RAM, and two expansions cards. I aslo changed the mode to PCIe V2 and blew out what little dust there was and was still getting invalids. After a couple of weeks of thinking I about it I decided to upgrade the BIOS as the last logical step. After all, I had done at least 6 firmware changes over the past 20 years and not had any problems. I download the BIOS update and followed the instructions exactly as the README indicated. As I watched the screen, it indicated that in turn the boot block, main, nvram, and ncb were were all erased, updated, and verified. It then indicated Update Success, /FDT!!, /GBE:!!, and /MER!! followed by instructions to reboot. After clearing the CMOS as instructed I rebooted to a blank screen and a beep code of 2-9-7. I think if it weighed another 100 lbs it would now make a good boat anchor because it is now useless as a server. I have spent that last few hours turning a spare PC into a temporary server from backups. It does not have all the functionality of the bricked server but at least the two web sites are back up and sendmail is sending and receiving mail again. All I can say is thank goodness it was Linux and not Windows. The only thing that did not work from backups was an add-on PCI serial card even though everything was different from the CPU to the chipset. I well send Supermicro an email to determine what the beep code means but I am pretty certain a new MB is in my future. The only decision is whether or not to improve performance with a new CPU as well. One thing I do know is that it won't be a Supermicro MB! |
jason_gee Send message Joined: 24 Nov 06 Posts: 7489 Credit: 91,093,184 RAC: 0 |
I well send Supermicro an email to determine what the beep code means but I am pretty certain a new MB is in my future. The only decision is whether or not to improve performance with a new CPU as well. One thing I do know is that it won't be a Supermicro MB! Sorry to hear about the struggles. The manual does describe how to get the original BIOS back from nothing, however beep code sure implies some or another hardware failure outright. Will be interesting to find out what that code is. I suspect SuperMicro might be more helpful than their warnings imply. "Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions. |
OTS Send message Joined: 6 Jan 08 Posts: 369 Credit: 20,533,537 RAC: 0 |
I well send Supermicro an email to determine what the beep code means but I am pretty certain a new MB is in my future. The only decision is whether or not to improve performance with a new CPU as well. One thing I do know is that it won't be a Supermicro MB! Thanks. I saw the procedure but thought I would see if they could provide an older BIOS file, perhaps even a copy of my original vers. 1, that might stand a better chance of success. Right about now, a few invalids with vers. 1 doesn't seem that bad ;). Thanks again. |
tazzduke Send message Joined: 15 Sep 07 Posts: 190 Credit: 28,269,068 RAC: 5 |
Greetings Jason Okay managed to get CUDA42 and CUDA60 running on my linux system Ubuntu 15.10 - GTX 670 gpu The CUDA42 was easy to get up and going. Once I figured out a permission problem with the CUDA60, finally got time to get that up and going as well. Pulled down 100 tasks though, sorry about that. Are we still able to continue crunching this way or should we wait till the final release is ready??? Regards |
jason_gee Send message Joined: 24 Nov 06 Posts: 7489 Credit: 91,093,184 RAC: 0 |
My suggestion is if it's working, don't break it :D . I'm juggling some work and watching the GBT situation. Meanwhile currently roadmapping the best way to incorporate some optimisations supplied by Petri without sacrificing wider support. Also making Linux and Mac Development/deployment Easier and more automated, and preparing for the next generation of hardware. If that sounds like a lot, well it is no more than usual :), Things will be a bit clearer when I post a roadmap (Which I'll do) as soon as I figure out the Curveball NV just threw me a couple of days ago with a request to test Cuda 8, rofl. "Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions. |
tazzduke Send message Joined: 15 Sep 07 Posts: 190 Credit: 28,269,068 RAC: 5 |
Thanks Jason for the reply, I have a bit a time on my hand, so I will monitor a few of the tasks so see if all goes well and no -9 overflows pop up. Wish all the best in getting it all sorted and down on a roadmap lol. Regards One Happy Cruncher. |
jason_gee Send message Joined: 24 Nov 06 Posts: 7489 Credit: 91,093,184 RAC: 0 |
Thanks Jason for the reply, I have a bit a time on my hand, so I will monitor a few of the tasks so see if all goes well and no -9 overflows pop up. Thanks! Yeah a lot of changes happening, and on the horizon, so your vigilance is appreciated. Good times :D "Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions. |
©2024 University of California
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.