hpc infrastructure
play

HPC Infrastructure HPC Day October 15 th 2014 Information - PowerPoint PPT Presentation

Information Technology Services (ITS) HPC Infrastructure HPC Day October 15 th 2014 Information Technology Services | www.odu.edu/its | itshelp@odu.edu HPC@ODU Introduction High Performance Computing Resources. Storage


  1. Information Technology Services (ITS) HPC Infrastructure  HPC Day October 15 th 2014  Information Technology Services | www.odu.edu/its | itshelp@odu.edu

  2. HPC@ODU Introduction High Performance Computing Resources.  Storage  Software  Support staff  Education and Outreach  2 Information Technology Services | www.odu.edu/its | itshelp@odu.edu

  3. HPC@ODU Introduction  Supporting research computing with parallel compute environments using MPI and OpenMP protocols.  Pre 2013, ZORKA & NIKOLA were providing computation resources to the campus researchers.  Some examples of resources in these clusters:  40 Dell PE 1950 nodes, 4 cores each & 8GB RAM.  4 Dell PE R900 nodes, 16 cores each & 32GB RAM.  7 Sun Fire X46000 M2 Nodes, 32 cores each & 64 GB RAM.  17 APPRO nodes , Tesla M2090 GPU’s, 12 cores & 48GB RAM .  NFS based scratch space mounted on all compute nodes (about 2TB). Research Mass storage, accessible from Head Node (approximately 60TB of data plus tape storage). 3 Information Technology Services | www.odu.edu/its | itshelp@odu.edu

  4. HPC Turing Cluster Base Configuration  New HPC cluster , primarily deployed to support GROMACS.  Funding support from Dr. Vernier, Bio-Electric research center & ITS.  Initial specification for Turing Cluster is as follows:  FDR based infiniband switches.  Dell C8000 chassis with eight (8) SLEDS  Each SLED has 16 cores (E5-2660) & 32GB RAM.  (1) Head Nodes , Dell R720 server with 128GB memory  1Gbps switching hardware with 10Gbps uplinks  Base for expansion of research computing infrastructure at ODU.  Available to Researchers for computation since Fall 2013. 4 Information Technology Services | www.odu.edu/its | itshelp@odu.edu 4

  5. HPC Turing Cluster Expansion  Integration of 8 computes nodes purchased by Dr. Gangfeng Ma (Civil & Environmental Engineering Department)  Thirty Six (36) compute SLED’s added by ITS  720 compute cores (E5-2660v2, ivy-bridge)  128GB per node, total 24TB.  2x500GB local disk per compute node.  Additional Head Node for redundancy ( Dell R720 server with 128GB memory)  Separate Login Node for optimal compute environment. 5 Information Technology Services | www.odu.edu/its | itshelp@odu.edu

  6. Turing Cluster Summer 2014 upgrade  Seventy Six(76) CRAY CS-GB-512X compute nodes  1520 compute cores (E5-26670v2, ivy-bridge)  128GB per node.  2x250GB local disk per compute node.  Four (4) High Memory Nodes  32 compute cores (E5-4610v2, ivy-bridge) per node  768 GB per node.  Ten(10) Xeon Phi Nodes  Each node has 2 Xeon Phi (60 core) co processors.  Each node has 20 cores (E5-2670v2, ivy-bridge) , 128 GB memory  Infiniband (FDR based) compute backbone upgraded  324 level 1 FDR interfaces.  144 level 2 backbone interfaces. 6 Information Technology Services | www.odu.edu/its | itshelp@odu.edu

  7. Turing Cluster Total Total Total Compute GPU/MIC Cores/ GPU Co- GPU/MIC Storage Total Storage Quantity Cores Cores Item Description Sockets Socket Processors cores/Socket Mem(GB) (TB) Mem(GB) (TB) PowerEdge C8220, 2 x E5- Dell C8000 chassis 2660(2.2GHz), Mellanox single port 8 128 0 Sandy-Bridge nodes FDR 2 8 0 0 128 1 1024 8 PowerEdge C8220, 2 x E5- Dell C8000 chassis 2660v2(2.2GHz), Mellanox single port 36 720 0 Ivy-Bridge nodes FDR 2 10 0 0 128 1 4608 36 PowerEdge C6220, 2 x E5- Dell C6000 chassis 2660(2.2GHz), Mellanox single port 8 128 0 Sandy-Bridge nodes FDR 2 8 0 0 128 1 1024 8 PowerEdge C6220, 2 x E5- Dell C6000 chassis 2660(2.2GHz), Mellanox single port 12 192 0 Sandy-Bridge nodes FDR 2 8 0 0 128 1 1536 12 CRAY SR5110 CRAY CS-GB-512X, 2 x E5- chassis Ivy-Bridge 2670v2(2.5GHz), Mellanox single port 76 1520 0 nodes FDR 2 10 0 0 128 0.5 9728 38 CRAY SR5110 CRAY CS-GB-512X, 2 x E5- chassis Ivy-Bridge 2670v2(2.5GHz), 2 x Xeon Phi 5110P, 10 200 1200 nodes Mellanox single port FDR 2 10 2 60 128 1 1280 10 Intel R2304LH2HKC, 4 x E5-4610v2, 4 128 0 High Memory Nodes Mellanox single port FDR 4 8 0 0 768 4 3072 16 APPRO 1426G4, 2 x Intel Xeon X5650 CRAY Appro GPU (2.67Ghz), 4 x NVidia M2090 GPU 17 204 34816 Nodes processor, Mellanox single port QD 2 6 4 512 48 1 816 17 7 Information Technology Services | www.odu.edu/its | itshelp@odu.edu

  8. HPC Turing 8 Information Technology Services | www.odu.edu/its | itshelp@odu.edu

  9. STORAGE HPC  Legacy Clusters had NFS based scratch space mounted on all compute nodes.  Research Mass storage, accessible from Head Node (approximately 60TB of disk plus tape storage).  Complete redesign of the computational storage infrastructure.  EMC Isilon based scale out NAS storage .  Integration of additional 430TB for computational research.  Integration of 36TB of LUSTRE based scratch space. 9 Information Technology Services | www.odu.edu/its | itshelp@odu.edu

  10. Turing Cluster Queuing Strategy  Current Job Scheduler is SGE.  Four separate job queues  Traditional computational resources  High memory nodes  APPRO GPU nodes  Nodes with dual Intel Xeon Phi  Fair Queuing Strategy  Shared computational resources  Compensates user over time 10 Information Technology Services | www.odu.edu/its | itshelp@odu.edu

  11. HPC Software Packages Some Software Packages on HPC Turing Cluster:  COMSOL (finite element analysis & simulation software for physics and engineering)  MATLAB  (Numerical computational software, plotting of functions, implementation of algorithms) CHARMM (Molecular dynamics simulation & analysis software)  METIS (Software package for graph partitioning)  GAUSSIAN (Software package for computational biology)  GROMACS (Molecular dynamics simulation & analysis software for proteins, lipids and nucleic acids)  R (Software programming language & software environment for statistical computing and graphs)  CLC Bio (Software package for analysis of biological data)  MOLPRO (Software package used for quantum chemistry calculations)  DDSCAT (Software package for calculating scattering and absorption of irregular particles)  11 Information Technology Services | www.odu.edu/its | itshelp@odu.edu

  12. Globus Globus (SaaS)  12 Information Technology Services | www.odu.edu/its | itshelp@odu.edu

  13. HPC@ODU Support Structure  Early 2013 , HPC support staff challenges  Two engineers moved on to other opportunities  One systems administrator position realigned for HPC support.  Started recruitment process to add two position focused on HPC  Addition to two (2) dedicated HPC systems engineers.  Jeaime Powell  Terry Stilwell  A computational scientist position is ready to to be recruited shortly. 13 Information Technology Services | www.odu.edu/its | itshelp@odu.edu

  14. Education & Outreach  Effective means of communicating with researchers and students on campus regarding available resources and services  Quarterly HPC newsletter  HPC day.  New faculty outreach .  HPC Advisory Committee. 14 Information Technology Services | www.odu.edu/its | itshelp@odu.edu

  15. HPC DAY THANK YOU 15 Information Technology Services | www.odu.edu/its | itshelp@odu.edu

Recommend


More recommend