Posts by Dotsch
|
11)
Message boards : Number crunching : Test WUs ( Message 4043 )Posted 3348 days ago by Dotsch Crosscompiling on MacOS is very easy. You have got two different compilers installed with the Apple XCode installation. One is called i686-apple-darwin8-gcc-4.0.1 the other one powerpc-apple-darwin8-gcc-4.0.1. There are two different methods to get it crosscompiled : 1. via the configure script - set CC="powerpc-apple-darwin8-gcc-4.0.1" and CXX="powerpc-apple-darwin8-g++-4.0.1" - issue the configure script with the option "--target=powerpc-apple-darwin" or "--target=powerpc-apple-darwin8". - gmake 2. Via the Makefile - Change all the gcc/g++... statements in the Makefile to powerpc-apple-darwin8-gcc... - gmake 3. via XCode - If you have a xcode project made, you can select the target platforms (Intel/PPC/Universal) by a switch The BOINC Client , LIB and API crosscompiles very well on MacOS. Also the most science applications. For the testing of the powerpc application on the Intel Mac you should nothing pay attention. Via Rosetta, the binary emulation of the PPC CPU, it is posible to let PPC binaries running on the Intel Mac with a los of performance. If you have some further questions, feel free to contact me. |
|
12)
Message boards : Number crunching : Test WUs ( Message 4001 )Posted 3352 days ago by Dotsch My Intel Mac got one successfull validated WU. Good work ! |
|
13)
Message boards : Wish list : PS3 ( Message 3669 )Posted 3512 days ago by Dotsch SETI, PS3Grid and yoyo has a PS3 SPE appication. SIMAP and Einstein and PPE only application. |
|
14)
Message boards : Number crunching : Invalid results reported thread [Use Here] ( Message 3355 )Posted 3734 days ago by Dotsch I have some invalid results from my Mac (Intel) : http://docking.utep.edu/result.php?resultid=191636 http://docking.utep.edu/result.php?resultid=187665 http://docking.utep.edu/result.php?resultid=182663 |
|
15)
Message boards : Number crunching : Valid result = No Credit Granted ( Message 3277 )Posted 3742 days ago by Dotsch I have simliar problems. 1 invalid which computed OK till the end : http://docking.utep.edu/result.php?resultid=182663 and two with no consensus yet : http://docking.utep.edu/result.php?resultid=187665, http://docking.utep.edu/result.php?resultid=181876. |
|
16)
Message boards : Macintosh : Checked, but no consensus yet ( Message 3273 )Posted 3743 days ago by Dotsch I have two results, where reported as "Checked, but no consensus yet" : http://docking.utep.edu/workunit.php?wuid=48836 http://docking.utep.edu/workunit.php?wuid=54973 Not shure if this is a validation problem by different results. |
|
17)
Message boards : Macintosh : Application suspends sometimes ( Message 3102 )Posted 3762 days ago by Dotsch Today, the charm application suspends. It was showing as running in the BOINC manager, but did not use any CPU. This happened on other BOINC projects, too. I had reported the problem to David, and he has written a fix, which was included in the BOINC API 5.8.x. The problem could also occur sometime on previos BOINC API releases, but mostly when CPU throtteling would be used. Which BOINC API have you used for the charm 5.05 ? |
|
18)
Message boards : Number crunching : Credits on Intel Mac with app 5.05 ( Message 3043 )Posted 3770 days ago by Dotsch I have noticed a slowdown on MacOS Intel, too. The old application was about 2.5 hours, the new one was about 5.5 hours. |
|
19)
Message boards : Application Info : 64-Bit / 32 bit, SSE3 and other extensions? ( Message 3002 )Posted 3772 days ago by Dotsch I hear that in some cases the processing time can be halved or more. The speed up from 64 bits and the compiler flags differ heavly on the application and on the architecture. Some applications could also run slower with 64 bit compared with 32 bits. My expiriance is about -5 to 10 % faster with heavy optimized flags. Also about -15 to +15 % with 64 bits and good optimisation. If you get more, you have luck... |
|
20)
Message boards : Macintosh : WU 20240 ( Message 2925 )Posted 3781 days ago by Dotsch It's possible that this setting helps alleviate the problem, but I don't know whether it would be a good solution since we would have to ask everybody to switch it on specially for D@H. There are some projects, where the "leave application in memory" switch should be enabled by default, CPDN for example.. Remember that this is a randomly occuring problem: it only happens when the boinc client switches projects in the middle of the checkpoint routine. As multi project cruncher, I have a heavy switching beteen the apps, so I had about 75 % invalid docking results. |
Next 10 posts