Welcome to MilkyWay@home

Posts by Jesse Viviano

21) Questions and Answers : Windows : OpenCL tasks on Haswell? (Message 60792)
Posted 22 Jan 2014 by Jesse Viviano
Post:
No. OpenCL below version 2.0 requires that either the developer compile for each GPU vendor's architectures using the GPU vendor's OpenCL library or ship source code that would be used by the platform's compiler. The second approach would be ideal if all operating systems came with a compiler, but most Windows installations do not have any compilers installed. Therefore, you would need the developers to compile using Intel's OpenCL library before you can use your GPU for MilkyWay@home.
22) Message boards : MilkyWay@home Science : Has the science page of this website been hacked and vandalized? (Repost from website Q&A forum) (Message 60791)
Posted 22 Jan 2014 by Jesse Viviano
Post:
In the Milkyway@home science page, the statement "Recently, it was determined that the bulge contains a prominent bar." looks like Wikipedia-style vandalism because it implies that there is a place to get some food and alcoholic drinks in the Milky Way's bulge. Could an administrator look into the issue and plug any security holes to carry out this vandalism if they are discovered, or is there some meaning to the word "bar" that I do not understand?

This is a repost from the website question and answers forum at http://milkyway.cs.rpi.edu/milkyway/forum_thread.php?id=3454, because I am not sure that anyone is paying attention to that forum as the last post in there was around 4-5 years ago until I made my original post there. Please post replies there as that is the proper forum for this topic.
23) Questions and Answers : Web site : Has the science page of this website been hacked and vandalized? (Message 60790)
Posted 22 Jan 2014 by Jesse Viviano
Post:
In the Milkyway@home science page, the statement "Recently, it was determined that the bulge contains a prominent bar." looks like Wikipedia-style vandalism because it implies that there is a place to get some food and alcoholic drinks in the Milky Way's bulge. Could an administrator look into the issue and plug any security holes to carry out this vandalism if they are discovered, or is there some meaning to the word "bar" that I do not understand?
24) Message boards : Number crunching : Having downloaded wus in jobs list that are not listed and running in client? (Message 51946)
Posted 13 Dec 2011 by Jesse Viviano
Post:
I have had this problem. What you need to do is to select No new work for MW@Home, let all of your work units that you have on your computer finish, update the project to report the finished work units, and then reset the project. This will let the server know that the other work units failed. They will be listed as "Abandoned", and hopefully will be passed to someone who was able to download the N-Body application.

I don't know why BOINC is failing to report download errors for these bad work units because the executable for N-Body version 0.80 for 64-bit Windows apparently cannot be downloaded. It is just silently discarding those work units instead of reporting errors to the server.
25) Message boards : Number crunching : Error message from n-body (Message 51913)
Posted 11 Dec 2011 by Jesse Viviano
Post:
I am getting the same problems here. I will have to detach until this is fixed to prevent pollution of the MilkyWay database with any more bad work units. We all know how problematic the database is, and I do not want to add to its troubles by filling it up with invalid work. I have tried resetting the project and a manual detach and reattach. Nothing I know of works.
12/10/2011 7:17:31 PM | Milkyway@home | Detaching from project
12/10/2011 7:17:55 PM |  | Fetching configuration file from http://milkyway.cs.rpi.edu/milkyway/get_project_config.php
12/10/2011 7:18:12 PM | Milkyway@home | Master file download succeeded
12/10/2011 7:18:17 PM | Milkyway@home | Sending scheduler request: Project initialization.
12/10/2011 7:18:17 PM | Milkyway@home | Requesting new tasks for CPU and ATI GPU
12/10/2011 7:18:19 PM | Milkyway@home | Scheduler request completed: got 0 new tasks
12/10/2011 7:18:19 PM | Milkyway@home | Not sending work - last request too recent: 53 sec
12/10/2011 7:18:19 PM | Milkyway@home | General prefs: from Milkyway@home (last modified 30-Oct-2011 20:40:00)
12/10/2011 7:18:19 PM | Milkyway@home | Host location: none
12/10/2011 7:18:19 PM | Milkyway@home | General prefs: using your defaults
12/10/2011 7:18:19 PM |  | Preferences:
12/10/2011 7:18:19 PM |  |    max memory usage when active: 9207.97MB
12/10/2011 7:18:19 PM |  |    max memory usage when idle: 11049.56MB
12/10/2011 7:18:19 PM |  |    max disk usage: 931.40GB
12/10/2011 7:18:19 PM |  |    (to change preferences, visit the web site of an attached project, or select Preferences in the Manager)
12/10/2011 7:18:24 PM | SZTAKI Desktop Grid | Sending scheduler request: To fetch work.
12/10/2011 7:18:24 PM | SZTAKI Desktop Grid | Requesting new tasks for ATI GPU
12/10/2011 7:18:26 PM | SZTAKI Desktop Grid | Scheduler request completed: got 0 new tasks
12/10/2011 7:18:26 PM | SZTAKI Desktop Grid | No work sent
12/10/2011 7:18:49 PM | ABC@home | update requested by user
12/10/2011 7:18:51 PM | ABC@home | Sending scheduler request: Requested by user.
12/10/2011 7:18:51 PM | ABC@home | Reporting 1 completed tasks, requesting new tasks for ATI GPU
12/10/2011 7:18:55 PM | ABC@home | Scheduler request completed: got 0 new tasks
12/10/2011 7:18:55 PM | ABC@home | No work sent
12/10/2011 7:19:36 PM | Milkyway@home | update requested by user
12/10/2011 7:19:40 PM | Milkyway@home | Sending scheduler request: Requested by user.
12/10/2011 7:19:40 PM | Milkyway@home | Requesting new tasks for CPU and ATI GPU
12/10/2011 7:19:41 PM | Milkyway@home | Scheduler request completed: got 13 new tasks
12/10/2011 7:19:41 PM | Milkyway@home | [error] State file error: missing application file milkyway_nbody_0.80_windows_x86_64__mt
12/10/2011 7:19:41 PM | Milkyway@home | [error] No app version found for app milkyway_nbody platform windows_x86_64 ver 80 classmt; discarding nbody-Plum_Embedded_92656_1
12/10/2011 7:19:43 PM | Milkyway@home | Started download of milkyway_separation_0.82_windows_x86_64__ati14.exe
12/10/2011 7:19:43 PM | Milkyway@home | Started download of plum_slice_model_good.lua
12/10/2011 7:19:46 PM | Milkyway@home | Finished download of plum_slice_model_good.lua
12/10/2011 7:19:46 PM | Milkyway@home | Started download of plum_slice_model_good.hist
12/10/2011 7:19:48 PM | Milkyway@home | Finished download of milkyway_separation_0.82_windows_x86_64__ati14.exe
12/10/2011 7:19:48 PM | Milkyway@home | Finished download of plum_slice_model_good.hist
12/10/2011 7:19:48 PM | Milkyway@home | Started download of parameters-82-2s.txt
12/10/2011 7:19:48 PM | Milkyway@home | Started download of single_t82_1_2.txt
12/10/2011 7:19:49 PM | Milkyway@home | Finished download of parameters-82-2s.txt
12/10/2011 7:19:49 PM | Milkyway@home | Started download of stars-82-coadd.txt
12/10/2011 7:19:54 PM | Milkyway@home | Finished download of single_t82_1_2.txt
12/10/2011 7:19:54 PM | Milkyway@home | Starting task ps_separation_82_2s_mix1_2_1749222_0 using milkyway version 82
12/10/2011 7:19:58 PM | Milkyway@home | Finished download of stars-82-coadd.txt
12/10/2011 7:20:47 PM | Milkyway@home | Sending scheduler request: To fetch work.
12/10/2011 7:20:47 PM | Milkyway@home | Requesting new tasks for CPU and ATI GPU
12/10/2011 7:20:48 PM | Milkyway@home | Scheduler request completed: got 1 new tasks
12/10/2011 7:20:48 PM | Milkyway@home | [error] State file error: missing application file milkyway_nbody_0.80_windows_x86_64__mt
12/10/2011 7:20:48 PM | Milkyway@home | [error] No app version found for app milkyway_nbody platform windows_x86_64 ver 80 classmt; discarding nbody-Plum_Embedded_102259_0
12/10/2011 7:21:07 PM | Milkyway@home | Computation for task ps_separation_82_2s_mix1_2_1749222_0 finished
12/10/2011 7:21:07 PM | Milkyway@home | Starting task ps_separation_82_2s_mix1_2_1749221_0 using milkyway version 82
26) Message boards : News : milkyway back up (Message 51560)
Posted 31 Oct 2011 by Jesse Viviano
Post:
Unfortunately, the server just went down again.
27) Message boards : News : more maximum time limit elapsed bug stuff (Message 48882)
Posted 20 May 2011 by Jesse Viviano
Post:
Could it be possible that your settings are not accounting for the possibility that when BOINC responds that there are 12 processors to use that it is failing to account for the hyperthreading my 6-core hyperthreaded processor is presenting? BOINC might be expecting twice the processing power it is actually getting. I noticed that some of the work units that fail on a Core i7 with hyperthreading work well on a Core 2 without hyperthreading.
28) Message boards : News : more maximum time limit elapsed bug stuff (Message 48872)
Posted 19 May 2011 by Jesse Viviano
Post:
I recently upgraded my BOINC client, and I am still getting some n-body work units that fail due to maximum time limits exceeded. Some n-body work units also pass. Few if any of the regular work units are giving me problems, and the last problem regular work unit I had was with the ATI client failing to record the results to stderr, and that was a week or two ago and has nothing to do with this problem.

I wonder if you might get some help if you visit http://boinc.berkeley.edu/dev/ and use the message boards there or the BOINC projects email lists at http://lists.ssl.berkeley.edu/mailman/listinfo/boinc_projects for help. There might be a setting that you might be overlooking that could be obvious to another person. The same problem happens to the best of us (e.g. someone failing to declare a variable as volatile in C when using it to spin-wait on an I/O transaction and therefore the compiler optimizes the variable by moving it to a register).
29) Message boards : News : more maximum time limit elapsed bug stuff (Message 48862)
Posted 19 May 2011 by Jesse Viviano
Post:
I am still getting maximum time exceeded errors on the n-body work units, though one or a few are now completing successfully. My computer is now going into high priority mode as well. One failed at 82%. Another failed at 85%. It looks like I am getting a mix of successes and failures. These failures were under BOINC x64 version 6.10.60. Since BOINC released a new version, 6.12.26, I have upgraded since then.
30) Message boards : News : another change for the maximum time limit elapsed bug (Message 48661)
Posted 9 May 2011 by Jesse Viviano
Post:
You might need to double the deadline. I just got a computation error on an N-body work unit after getting around 63% of the work unit done. I am using a Core i7 980X with hyper-threading enabled. Nothing is overclocked.
31) Message boards : News : maximum time limit elapsed bug (Message 48621)
Posted 9 May 2011 by Jesse Viviano
Post:
The n-body WUs are failing due to maximum time limit elapsed. Everything else is fine. I have Win7 64-bit, an Intel Core i7 980X, and a Sapphire Radeon HD 6970. I am using BOINC 6.10.60. My Catalyst drivers are the 11.4 production drivers. I am using stock everything, no app_info.xml, and no overclocking whatsoever.
32) Message boards : News : fix to the invalid workunit problem (Message 48529)
Posted 7 May 2011 by Jesse Viviano
Post:
I noticed that many of the work units now only allow a maximum of one error before the work unit is rejected. That seems to be a bad idea due to the number of people with outdated graphics drivers (causing some ATI/AMD work units to fail) and those with optimized applications that will generate validate errors because they still upload results with file uploads, where the validator no longer looks.
33) Message boards : News : n-body workunits with maximum time elapsed (Message 48522)
Posted 7 May 2011 by Jesse Viviano
Post:
It seems that all the results I am turning in are now being marked invalid for the main MilkyWay@home application.
34) Message boards : News : N-body updated to 0.40 (Message 48510)
Posted 6 May 2011 by Jesse Viviano
Post:
I am getting a maximum time exceeded error on my N-body work units after running for 3 seconds. I will try resetting the project to see if that will help. Some have suggested that using an app_info.xml is causing this, but I have not ever worked with any app_info.xml file.

Oops! I accidentally forgot to do the reset when I allowed more tasks in.
35) Message boards : News : N-body updated to 0.40 (Message 48500)
Posted 6 May 2011 by Jesse Viviano
Post:
I am getting a maximum time exceeded error on my N-body work units after running for 3 seconds. I will try resetting the project to see if that will help. Some have suggested that using an app_info.xml is causing this, but I have not ever worked with any app_info.xml file.
36) Message boards : Number crunching : No milkyway files in Trasfers tab why? (Message 48299)
Posted 28 Apr 2011 by Jesse Viviano
Post:
I believe that the stderr is sent when the task is reported.
37) Message boards : Number crunching : Questions about my AMD Athlon processor and SSE3 (Message 48059)
Posted 20 Apr 2011 by Jesse Viviano
Post:
No SSE3 capable stock client has been released. The best you will get is SSE2.
38) Message boards : News : ATI application updated to 0.60 (Message 47873)
Posted 15 Apr 2011 by Jesse Viviano
Post:
Actually, the plan class should be "ati14". The reason CAL 1.3 had plan classes "ati13", "ati13amd", and "ati13ati" is that AMD changed its libraries' names from AMD names to ATI names. AMD did not do any such thing for CAL 1.4. The "ati13ati" class refers to the ATI named libraries, and the others refer to the AMD named libraries.
39) Message boards : News : ATI application updated to 0.60 (Message 47817)
Posted 14 Apr 2011 by Jesse Viviano
Post:
I am getting this message:
4/13/2011 11:26:17 PM	Milkyway@home	Message from server: ATI GPU: Upgrade to the latest driver to process tasks using your computer's GPU

I do not know why I am getting this message because I am using AMD's latest stable driver package, Catalyst 11.3. The driver itself is version 8.831.2.0 for Windows 7 64-bit. Did the administrator set this to accept Catalyst 11.4 and later only? That package is still a beta package.
40) Message boards : Number crunching : Wrong application served to my computer (Message 47754)
Posted 13 Apr 2011 by Jesse Viviano
Post:
One valid reason for keeping the 32-bit version is to take advantage of the x87 FPU's native 80-bit precision. However, using SSE2 throws that advantage out the window because SSE2 does things either in 32-bit or 64-bit precision and cannot handle 80-bit precision.

The x87 FPU is deprecated in 64-bit mode by both AMD's ABI (used everywhere except in Windows) and by the Microsoft 64-bit ABI (used only in Windows), so it should not be used in 64-bit mode because neither ABI are required to save the contents of the x87 FPU registers when they need to swap tasks. They are required to save the contents of the x87 FPU registers for a program running in compatibility mode (e.g. a 16-bit or 32-bit protected mode program that makes absolutely no use of real or virtual 8086 mode running on an OS running in long mode).


Previous 20 · Next 20

©2022 Astroinformatics Group