Posts by robertmiles
|
1)
Message boards : Docking@Home Science : A workshop on Charm++ ( Message 7225 )Posted 1242 days ago by 
robertmiles
I thought you'd want to know about this: From: Xiang Ni <xiangni2@illinois.edu> Newsgroups: comp.parallel,news.announce.conferences Subject: Charm++ Workshop Call for Talks - April 29-30 Call for talks: 12th Workshop on Charm++ and its Applications Place: University of Illinois at Urbana Champaign Date: April 29-30, 2014 SUBMISSION DEADLINE: March 15, 2014 Authors are invited to submit abstracts describing research and development in the broad themes of parallel processing emphasized by Charm++ and AMPI, including message-driven execution, automated resource management, and compositionality. Some specific topics of interest include: - Parallel computing algorithms and applications - Tools and techniques for performance analysis and tuning - Parallel discrete event simulation techniques and applications - Parallel libraries and frameworks - Extensions and new features in Charm++ - Tools and techniques for application development and debugging - Massively parallel processing on future machines - Fault tolerance and resilience - Novel parallel programming models and abstractions - Adaptive runtime systems - Runtime management of power, energy, and heat Submissions should be in the form of extended abstracts from one to three pages. The *presentations* will be posted at the workshop website, but there will be no published proceedings. Authors are encouraged to publish them in other conferences. Please send submissions to Xiang Ni (xiangni2@illinois.edu) by the deadline below. **Important Dates Abstracts Due March 15th, 2014 Notification of Acceptance March 20th, 2014 Workshop April 29th-30th, 2014 Early submission is welcome and will expedite the reviewing process. Authors of early submissions will be notified of their acceptance as soon as possible. Please forward this invitation to any colleagues who may be interested. |
|
2)
Message boards : Wish list : Cuda support for Docking@home ( Message 7184 )Posted 1338 days ago by
robertmiles
I looked up CHARMM on the web. It uses FORTRAN77, which I've used in the past, but I'm not familiar with the current generation of compilers. The licensing terms appear to make it available only to students and academic researchers, so does UDel offer any online courses that could make me qualify? It appears to be mainly for Linux, but I could try compiling it under the Cygwin or MSYS Linux emulations for Windows. By the way, if CHARMM has too few items that can be performed in parallel, the GPU version could be as slow as one fourth the speed of the CPU version, on typical computers. |
|
3)
Message boards : Wish list : Some AIDS/HIV news ( Message 7183 )Posted 1338 days ago by
robertmiles
Could you read though the following articles and check whether they offer any new direction for your research? Several articles on a new method of treating HIV: (appears to point to the research article, but currently not reachable) http://news.rutgers.edu/news-release/drug-found-eradicate-hiv-permanently-infected-cells/20130924 (This may be the research article:) Foot Cream Kills HIV by Tricking Cells to Commit Suicide http://www.scientificamerican.com/article.cfm?id=foot-cream-kills-hiv-by-tricking-ce-2013-09 HIV in cells eradicated with antifungal drug http://www.medicalnewstoday.com/articles/266683.php Drug found to eradicate HIV permanently from infected cells http://esciencenews.com/sources/science.daily/2013/09/24/drug.found.eradicate.hiv.permanently.infected.cells Foot cream causes HIV-infected cells to 'commit suicide,' study says http://www.nydailynews.com/life-style/health/foot-cream-eradicates-hiv-cell-cultures-study-article-1.1467654#ixzz2n2e1UjVD Antifungal foot cream may help eradicate HIV http://articles.timesofindia.indiatimes.com/2013-09-27/science/42458501_1_hiv-genes-virus-researchers Foot cream kills HIV by tricking cells to commit suicide http://www.disclose.tv/news/Foot_cream_kills_HIV_by_tricking_cells_to_commit_suicide/94029#ixzz2n2eWCYLo Drug Is Found to Eradicate HIV Permanently from Infected Cells http://thinksteroids.com/forum/general-discussion/drug-found-eradicate-hiv-134344625.html Drug Found to Eradicate HIV Permanently from Infected Cells http://forums.phoenixrising.me/index.php?threads/drug-found-to-eradicate-hiv-permanently-from-infected-cells.25825/ |
|
4)
Message boards : Wish list : Cuda support for Docking@home ( Message 7182 )Posted 1338 days ago by
robertmiles
I've taken an online course in CUDA, and am looking for an online course in OpenCL. I've found that the minimum compiler that can handle the C or C++ portion of CUDA workunits costs about $400, for the Windows version only. I'm not sure if there is a suitable C or C++ compiler for using CUDA under Linux, but if there is, it is likely to be free. I'd be interested in looking at the source code of CHARMM to see if I might be able to convert it to a CUDA version. Also, are there any license restrictions on distributing the source code, and does it use pthreads or any other threading library? Does it have many sections where a list of things can be done in any order, or even all at once, since the things in the list do not write to the same variables as any other things in the lists? How much would you need to upgrade the servers to handle the additional volume of workunits a GPU version would allow? |
|
5)
Message boards : Number crunching : Win7 64bit problem with Docking ( Message 7169 )Posted 1364 days ago by
robertmiles
11/13/2013 10:48:18 PM | Docking | task 1ebz1ohr_mod0014crossdockinghiv1_35109_223951_0 aborted by user Quite likely, because you are now the only one with this problem and you aren't sending enough information back to the server to identify what the problem is. Some items that might help us provide information: What is the update status of Windows 7 on that computer? Is SP1 installed? How up-to-date are you on installing the other Windows 7 updates? What version number of BOINC are you using? What is your setting on how much of the memory BOINC can use? Is BOINC allowed to keep workunits in memory while they are suspended, but BOINC is still running? What number driver are you using for that GT 630? Could you post some excerpts from the BOINC log file? For example, the first part gives some of the information I mentioned above, and a few recent lines giving the events related to a few Docking workunits may contain other useful information. |
|
6)
Message boards : Number crunching : Win7 64bit problem with Docking ( Message 7150 )Posted 1434 days ago by
robertmiles
Like so many others here, I am having difficulty with zero-progress workunits under Win7. As I see that the issue seems unresolved, I have disconnected Docking in my account manager. I've been running Docking workunits on my 64bit Win7 computer for months now without such a problem. Your computer must be different from mine in some important way to have such a problem. Also, note that your post is the first post in this thread for about a year. You may need to check whether the date on your computer is set to the correct month and the correct year. |
|
7)
Message boards : Number crunching : Docking at home and CUDA GPU ? ( Message 7137 )Posted 1479 days ago by
robertmiles
A GPU version of CHARMM already exists, but does not appear to be in use at Docking@Home. http://www.charmm.org/ Could we have an explanation of why it's not used yet? |
|
8)
Message boards : Number crunching : Docking at home and CUDA GPU ? ( Message 7132 )Posted 1479 days ago by
robertmiles
I've now finished one online CUDA course and started another. I'm looking for an online OpenCL course, but haven't found one yet. Two questions that may determine whether I can work on a GPU version: 1. Are there any restrictions on distribution of the source code to those for which working on campus is impractical? 2. Does the source code use pthreads, or any other threading library? Another question that may determine whether a GPU version is useful at all: Do large parts of the program have sections that can be done in any order since they never write to each other's variables? |
|
9)
Message boards : Number crunching : Incorrect Function 1 ( Message 6938 )Posted 1749 days ago by
robertmiles
A large fraction, but not all, of my 1hvi1htf workunits are now giving this compute error: Incorrect function. (0x1) - exit code 1 (0x1) Could you investigate why, and what should be done about this? |
|
10)
Message boards : Application Info : Application suggestions ( Message 6919 )Posted 1759 days ago by
robertmiles
In the next round of applications, could you add an early step that checks if the input files are complete, in order to avoid wasting CPU time like the last batch of workunits with incomplete input files? |
Next 10 posts