务的CPU个数没有限制。多余四个的任务将进入最大任务队列中等待。
用户可以用 qstat -f 来查看目前各个用户使用CPU的情况
用qsub来提交并行和串行任务
用qdel来删除不在需要的任务
如果发现qdel不能删除任务,请通知系统管理员来处理.
如果并行计算过程中有大量数据输出，可以考虑在/scratch目录中进行运算。由于/scratch属于
本地硬盘,数据不通过网络转移到nfs的/home目录，从而减少了对网络带宽的占用。
9. Benchmarks
THE DL_POLY BENCHMARK
The benchmark summarized below is designed to reflect the typical range of simulations undertaken by the molecular dynamicist. It includes 6 calculations carried out using the DL_POLY molecular dynamics code, and includes the following functionality
Benchmark 1: Simulation of a sodium-potassium disilicate glass (1080 atoms, 300 time steps);
Benchmark 2: Simulation of metallic aluminium with Sutton-Chen potential at 300K (256 atoms, 8000 time steps);
Benchmark 3: Simulation of valinomycin in 1223 water molecules (3837 atoms, 100 time steps);
Benchmark 4: Dynamic Shell model water structure (768 atoms, 1024 sites, 1000 time steps);
Benchmark 5: Dynamic Shell model MgCl2 structure (768 atoms, 1280 sites, 1000 time steps);
Benchmark 8: Simulation of a model membrane with 2 membrane chains, 202 solute molecules and 2746 solvent molecules (3148 atoms, 1000 time steps).
******** SYSTEM 1 *********************************** Hardware
Machine Name -- baobab.isis.unc.edu
3 Master Nodes and 39 Compute Nodes Beowulf Cluster with a total of 84 Processors
Tyan Thunder MP Motherboard
Dual AMD Athlon 1600+ 1.4GHz MP Processor 2GB DDR RAM on each node
20GB EIDE Hard Drive for Operating System Myrinet Fiber PCI Adapter with 2MB
Master nodes installed with RAID 5 SCSI Controller connected to 3 76GB Hard Drives
Myrinet Switch with 64 port enclosure Operating System
RedHat Linux 7.2 with XFS File System 2.4.9-13SGI_XFS_1.0.2smp Kernel absoft ProFortran Compilers
FORTRAN 77 (f77): Absoft FORTRAN 77 compiler version 5.0 FORTRAN 90 (f90/f95): Absoft Fortran 90/95 compiler version 3.0
Number of Processors 1 2 4 8 16 ------------------------------------------------------ Benchmark 1(seconds) 112.5 56.5 31.6 22.5 17.7 Benchmark 2(seconds) 111.9 59.8 37.0 30.5 33.8 Benchmark 3(seconds) 111.2 56.5 32.6 18.8 13.9 Benchmark 4(seconds) 100.3 49.6 32.8 26.6 30.4 Benchmark 5(seconds) 179.9 62.2 39.8 33.6 37.5 Benchmark 8(seconds) 112.5 56.5 31.6 22.5 17.7 ------------------------------------------------------
******** SYSTEM 2 *********************************** Hardware
Machine Name -- gandalf.chem.unc.edu
1 Master Nodes and 32 Compute Nodes Beowulf Cluster with a total of 33 Processors
Intel(R) Pentium(R) 4 CPU 1700MHz 1GB DDR RAM on each node
20GB EIDE Hard Drive for Operating System 100 M ether PCI Adapter Operating System
RedHat Linux 7.1 Fortran Compilers
FORTRAN 77 (f77): GNU Fortran 0.5.26 20000731 (Red Hat Linux 7.1 2.96-81) (g77)
FORTRAN 90 (f90): VAST/f90 compiler (works with g77)
Number of Processors 1 2 4 8 16 ---------------------------------------------------- Benchmark 1(seconds) 142.0 85.4 61.5 71.4 87.0 Benchmark 2(seconds) 168.0 122.0 122.1 -- -- Benchmark 3(seconds) 160.0 87.8 61.5 -- -- Benchmark 4(seconds) 131.0 123.7 128.0 -- -- Benchmark 5(seconds) 212.0 131.7 158.2 -- -- Benchmark 8(seconds) 121.0 98.9 115.7 -- -- ---------------------------------------------------
******** SYSTEM 3 *********************************** Hardware
Machine Name -- ding.simugroup
1 Master Nodes and 6 Compute Nodes Beowulf Cluster with a total of 8 Processors