The main problem i see with Bulldozer is that it has only fore floating point units,
Each pair of integer core`s share one FPU, even though the FPU`s have been `optimized` to take account of this and do have supprizing performance as they are,
With BOINC projects that are FPU intensive surely this will be a bottle neck for us,
And in the few tests so far published the 1100T can keep up in many of the ways we are likely to use them when the CPU is subjected to 24/7 100% load and the fact of eight work units trying to use the limited number of FPU`s at the same time, only time will tell and when someone is brave enough to buy one and put it on Rosetta to see what it can do in real world tests.
I would still like to buy one but will wait a bit longer to see how things work out.

There is also a thread on seti@home about Bulldozy
http://setiathome.berkeley.edu/forum_thread.php?id=65764

I'm fairly sure I recall someone stating that Rosetta has more integer work than float. Not sure if that's true, and I can't find the thread but have foudn this: http://boinc.bakerlab.org/rosetta/forum_thread.php?id=4907...

I got four tasks, one at a time, starting early yesterday even before the announcement on the home page. Each of them completed, uploaded and reported normally.

That changed today. I am now not getting any new tasks.

You can assume that this problem is related to the recent system failures, but I'm going to try to let the managers know when there is what might be a new problem. They have been most appreciative of my letting them know about such problems in the past, and that's what I'm doing now.

So I rejoin after almost 2 years of inactivity. I see 4 computers and only one of them with credit or perhaps another one with a little in the single figures. I can't remember there being 4 when I left. Could this be because of the backup? Anyway I try to merge them and they seem to have been disappeared instead. Is this from the outage or is it a bug in the software?

Only the newest show up and I can still access the other 3 with their numbers only they have now been anonymized, all with zero credit. My account still looks like it has the total credit. People will now think I cheated having the credit but no computers that actually did it. :D Though I don't see how one could. I seem to have rejoined at the worst time.

So is this something that will automatically be fixed or should I just leave it and forget about it?

So you haven't noticed that Rosetta@Home recently had a file system crash bad enough that they expect it to take some time to get everything back to normal?

You could always try doing at least one more workunit, and seeing if that's enough to restore whichever computer you use to your records. But note that a number of other people rejoined after an absence long enough they need to download a new version of the application software have had problems doing that download, since the restore from the file system crash hadn't proceded far enough to restore that software from the backup they're using.

Hopefully, they can fix whatever other problems you're seeing, once the restore from the backup gets far enough.

I don't really know if this is a 5.8 problem, a BOINC problem, or what..so..if I'm in the wrong thread, feel free to move this elsewhere.

Just happened to notice that a WU had just completed, so went to my results page to check credit, and in less than 5 minutes, the result was nowhere to be found. All my prior WU's from today's work are there, and my "in progress" work is there, but not this one. Here's the log (edited for brevity):

9/19/2007 2:33:13 PM|rosetta@home|Starting 1a68__SEARCH_PAIRINGS_ROUND2_RESCORE_150_SAVE_ALL_OUT_-1a68_-_BARCODE__2050_7166_0
9/19/2007 2:33:14 PM|rosetta@home|Starting task 1a68__SEARCH_PAIRINGS_ROUND2_RESCORE_150_SAVE_ALL_OUT_-1a68_-_BARCODE__2050_7166_0 using rosetta_beta version 580
9/19/2007 5:28:31 PM|rosetta@home|Computation for task 1a68__SEARCH_PAIRINGS_ROUND2_RESCORE_150_SAVE_ALL_OUT_-1a68_-_BARCODE__2050_7166_0 finished
9/19/2007 5:28:33 PM|rosetta@home|[file_xfer] Started upload of file 1a68__SEARCH_PAIRINGS_ROUND2_RESCORE_150_SAVE_ALL_OUT_-1a68_-_BARCODE__2050_7166_0_0
9/19/2007 5:28:40 PM|rosetta@home|[file_xfer] Finished upload of file 1a68__SEARCH_PAIRINGS_ROUND2_RESCORE_150_SAVE_ALL_OUT_-1a68_-_BARCODE__2050_7166_0_0
9/19/2007 5:28:40 PM|rosetta@home|[file_xfer] Throughput 4223 bytes/sec
9/19/2007 5:28:46 PM|rosetta@home|Sending scheduler request: To report completed tasks
9/19/2007 5:28:46 PM|rosetta@home|Reporting 1 tasks
9/19/2007 5:28:51 PM|rosetta@home|Scheduler RPC succeeded [server version 509]
9/19/2007 5:28:51 PM|rosetta@home|Deferring communication for 4 min 2 sec
9/19/2007 5:28:51 PM|rosetta@home|Reason: requested by project

By 5:33PM (PDT)(i.e., 00:33 UTC) this WU was not in my results list. Since I've never had one disappear THAT fast before, I'm wondering if something is amiss. Unfortunately I have no way to know the result # or WU#...

Thoughts, anyone?

I am quite curious as to the relative success rate of the Capri14 WUs versus WUs of all other types.

My personal experience is that a Capri14 WU is nearly doomed to failure, no matter the Rosetta version on which it is running, while nearly all other WUs will succeed...

I sincerely hope that the CPU time that (to my layman's perspective) I seem to be wasting on Capri14 is not representative of the experience of the general population of Rosetta crunchers.

Respectfully,
David Emigh

David I believe you are having a bad run of luck on the WUs. I also have had several fail but overall better than 95% have finished with valid results. Like a few others I have had to make adjustments to memory allocations on my old machines but the CAPRI14 project will soon be over and we can get back to the same old boring number crunching.
I also don't like the "client error" result either it does give me a since of loss.

Cheers Jim

This is puzzling -- those jobs arent taking long. We'll look into it. In the meanwhile, can your or other post links to the appropriate results that were killed?

I have now done several CAPRI14 WUs with 5.80: Only one has a problem:
http://boinc.bakerlab.org/rosetta/workunit.php?wuid=95775480
with this result:
http://boinc.bakerlab.org/rosetta/result.php?resultid=105522388
I don't have a clue as to why it failed to Validate. It seems to have run the full length of time I have set for processing.

Thanks,
Jim

I agree. Did you happen to view the graphic prior to it getting ended by the watch dog? I'm wondering if it was one of those that took the whole 3.5hrs on that first model, and therefore never completed one and had no completed results to report... or if it was one of those running 6 models an hour, and so it had completed 20 models or whatever prior to the problem. If the ladder, then definately there is room for improvement.

Most WU types will report the completed models and the failure and show "success", and issue credit accordingly. But I'm not certain if these are proving the exception to the rule.

If it were really stuck, the watch dog should detect that and end it. But there are cases where progress is slow to come and the watch dog knows that. More then an hour for a single step... ya that sounds a bit high. That was one of Rhiju's questions was "did you happen to notice if the screen looked totally stuck before the crash?" ... but then THAT one didn't "crash" with the stuck after 900 seconds condition.

Do you know? Was it still using CPU after that hour? There have been issues where BOINC shows a status of "running", but no CPU is being used.

I made changes to three of my systems last week. One did not require merging, but two did. I was able to successfully merge one system, but not the other. Here are the three scenarios.

Computer 177211 was upgraded from a 2.4Ghz P4 to a 3.2GHz Dual Core P4. While Windows XP and some software required reregistration, I did nothing to the BOINC client. The Rosetta site reflects the new and correct hardware/OS configuration that is now in 177211.

Computer 203481 was running Windows XP Home, and I installed Windows XP Pro. The installation wiped the hard drive, and I installed the latest version of BOINC. This created computer 486792, and I was able to merge the results of 203481 into 486792. The merge results reflect the proper and current OS on this hardware.

Computer 297677 is running Red Hat Linux on a dual core P4 whose hostname is redhat. Last week I ran the "update" to apply the latest patches. The Kernel version changed from 2.6.9-42.0.10.ELsmp to 2.6.9-55.ELsmp. During the update, I also had to use the Logical Volument Management tool to extend my root and /var file systems. After patching, my /usr/local file system disappeared, and that is where the BOINC client was installed. This time I installed the latest version of BOINC under the /home filesystem and it created computer 486792. When I attempt to merge computer 486792, no computers appear in the merge list. However, if I attempt to merge computer 297677, it displays the same hostname or hardware in its various incarnations, but not the current configuration for 486792. The merge list for 297677 includes a system named fedora that was running on a Pentium III. Fedora was later replaced with redhat on the same P3. Redhat was later upgraded from a P3 to a Dual Core P4, and configuration also appears in the merge list. However, I cannot merge 297677 into 486792.