|
本帖最后由 guichenge 于 2012-12-14 13:56 编辑
感谢 fwjmath 提供的解决方法:
将项目文件夹下面(就是放应用程序的地方,BOINC安装目录\Data\projects\einstein.phys.uwm.edu),有两个dll,分别是cudart_xp32_32_16.dll和cufft_xp32_32_16.dll。将它们复制一下,然后将副本分别重命名为cudart32_32_16.dll和cufft32_32_16.dll
--------------------------------------------------------------------------------------
先上图和Log吧
计算错误
Log:
2012/8/3 19:14:54 | | No config file found - using defaults
2012/8/3 19:14:54 | | Starting BOINC client version 7.0.28 for windows_x86_64
2012/8/3 19:14:54 | | log flags: file_xfer, sched_ops, task
2012/8/3 19:14:54 | | Libraries: libcurl/7.25.0 OpenSSL/1.0.1 zlib/1.2.6
2012/8/3 19:14:54 | | Data directory: C:\ProgramData\BOINC
2012/8/3 19:14:54 | | Running under account Administrator
2012/8/3 19:14:54 | | Processor: 8 GenuineIntel Intel(R) Core(TM) i7-3770K CPU @ 3.50GHz [Family 6 Model 58 Stepping 9]
2012/8/3 19:14:54 | | Processor: 256.00 KB cache
2012/8/3 19:14:54 | | Processor features: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss htt tm pni ssse3 cx16 sse4_1 sse4_2 syscall nx lm vmx tm2 popcnt aes pbe
2012/8/3 19:14:54 | | OS: Microsoft Windows Vista: Ultimate x64 Edition, Service Pack 1, (06.00.6001.00)
2012/8/3 19:14:54 | | Memory: 7.90 GB physical, 15.79 GB virtual
2012/8/3 19:14:54 | | Disk: 100.01 GB total, 55.92 GB free
2012/8/3 19:14:54 | | Local time is UTC +8 hours
2012/8/3 19:14:54 | | NVIDIA GPU 0: GeForce GTX 570 (driver version 301.42, CUDA version 4.20, compute capability 2.0, 1280MB, 1142MB available, 1425 GFLOPS peak)
2012/8/3 19:14:54 | | OpenCL: NVIDIA GPU 0: GeForce GTX 570 (driver version 301.42, device version OpenCL 1.1 CUDA, 1280MB, 1142MB available)
2012/8/3 19:14:54 | Rioja Science | URL http://boinc.riojascience.com/; Computer ID 1793; resource share 100
2012/8/3 19:14:54 | climateprediction.net | URL http://climateprediction.net/; Computer ID 1230131; resource share 100
2012/8/3 19:14:54 | Einstein@Home | URL http://einstein.phys.uwm.edu/; Computer ID 5628265; resource share 100
2012/8/3 19:14:54 | WUProp@Home | URL http://wuprop.boinc-af.org/; Computer ID 38258; resource share 100
2012/8/3 19:14:54 | PrimeGrid | URL http://www.primegrid.com/; Computer ID 275274; resource share 100
2012/8/3 19:14:54 | World Community Grid | URL http://www.worldcommunitygrid.org/; Computer ID 2131589; resource share 100
2012/8/3 19:14:54 | World Community Grid | General prefs: from World Community Grid (last modified 01-Jan-1970 08:00:01)
2012/8/3 19:14:54 | World Community Grid | Host location: none
2012/8/3 19:14:54 | World Community Grid | General prefs: using your defaults
2012/8/3 19:14:54 | | Reading preferences override file
2012/8/3 19:14:54 | | Preferences:
2012/8/3 19:14:54 | | max memory usage when active: 6065.67MB
2012/8/3 19:14:54 | | max memory usage when idle: 6065.67MB
2012/8/3 19:14:54 | | max disk usage: 4.00GB
2012/8/3 19:14:54 | | max CPUs used: 7
2012/8/3 19:14:54 | | (to change preferences, visit the web site of an attached project, or select Preferences in the Manager)
2012/8/3 19:14:54 | | Not using a proxy
2012/8/3 20:45:26 | Einstein@Home | work fetch resumed by user
2012/8/3 20:46:17 | Einstein@Home | Sending scheduler request: To fetch work.
2012/8/3 20:46:17 | Einstein@Home | Requesting new tasks for NVIDIA
2012/8/3 20:46:56 | Einstein@Home | Scheduler request completed: got 24 new tasks
2012/8/3 21:01:13 | Einstein@Home | Starting task p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0 using einsteinbinary_BRP4 version 125 (BRP4cuda32nv301) in slot 8
2012/8/3 21:01:19 | Einstein@Home | Computation for task p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0 finished
2012/8/3 21:01:19 | Einstein@Home | Output file p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0_0 for task p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0 absent
2012/8/3 21:01:19 | Einstein@Home | Output file p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0_1 for task p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0 absent
2012/8/3 21:01:19 | Einstein@Home | Output file p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0_2 for task p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0 absent
2012/8/3 21:01:19 | Einstein@Home | Output file p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0_3 for task p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0 absent
2012/8/3 21:01:19 | Einstein@Home | Output file p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0_4 for task p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0 absent
2012/8/3 21:01:19 | Einstein@Home | Output file p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0_5 for task p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0 absent
2012/8/3 21:01:19 | Einstein@Home | Output file p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0_6 for task p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0 absent
2012/8/3 21:01:19 | Einstein@Home | Output file p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0_7 for task p2030.20090730.G41.27+00.27.C.b6s0g0.00000_1576_0 absent
系统配置:华硕GTX570 (驱动:301.42)
Win7 sp1 64bit
NOD32+金山毒霸
CPU项目没有问题,但GPU项目总是开始计算后瞬间出错,期间重置过项目也无果。之前金山毒霸报过几次主计算程序有风险,我全部点的允许,现在更新任务没有显示报错,但之前的报错在金山的日志里也没找到当时的事件。现在怎么样才能然Eintein的nvidia GPU项目正常运行呢 |
|