NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER Early Experiences with Datastar: A 10TF Power4 + Federation.

Slides:



Advertisements
Similar presentations
IBM 1350 Cluster Expansion Doug Johnson Senior Systems Developer.
Advertisements

SAN DIEGO SUPERCOMPUTER CENTER Blue Gene for Protein Structure Prediction (Predicting CASP Targets in Record Time) Ross C. Walker.
SAN DIEGO SUPERCOMPUTER CENTER HDF5/SRB Integration July 10, 2006 Mike Wan SRB, SDSC Peter Cao
Supercomputing Challenges at the National Center for Atmospheric Research Dr. Richard Loft Computational Science Section Scientific Computing Division.
Beowulf Supercomputer System Lee, Jung won CS843.
Performance Analysis of Virtualization for High Performance Computing A Practical Evaluation of Hypervisor Overheads Matthew Cawood University of Cape.
SAN DIEGO SUPERCOMPUTER CENTER at the UNIVERSITY OF CALIFORNIA, SAN DIEGO Performance of Applications Using Dual-Rail InfiniBand 3D Torus Network on the.
Scheduling of parallel jobs in a heterogeneous grid environment Scheduling of parallel jobs in a heterogeneous grid environment Each site has a homogeneous.
IBM RS6000/SP Overview Advanced IBM Unix computers series Multiple different configurations Available from entry level to high-end machines. POWER (1,2,3,4)
NPACI Panel on Clusters David E. Culler Computer Science Division University of California, Berkeley
NPACI: National Partnership for Advanced Computational Infrastructure Supercomputing ‘98 Mannheim CRAY T90 vs. Tera MTA: The Old Champ Faces a New Challenger.
SUMS Storage Requirement 250 TB fixed disk cache 130 TB annual increment for permanently on- line data 100 TB work area (not controlled by SUMS) 2 PB near-line.
An Introduction to Princeton’s New Computing Resources: IBM Blue Gene, SGI Altix, and Dell Beowulf Cluster PICASso Mini-Course October 18, 2006 Curt Hillegas.
Massive High-Performance Global File Systems for Grid Computing -By Phil Andrews, Patricia Kovatch, Christopher Jordan -Presented by Han S Kim.
Hitachi SR8000 Supercomputer LAPPEENRANTA UNIVERSITY OF TECHNOLOGY Department of Information Technology Introduction to Parallel Computing Group.
IPPS 981 Berkeley FY98 Resource Working Group David E. Culler Computer Science Division U.C. Berkeley
PARALLEL PROCESSING The NAS Parallel Benchmarks Daniel Gross Chen Haiout.
IBM RS/6000 SP POWER3 SMP Jari Jokinen Pekka Laurila.
NPACI: National Partnership for Advanced Computational Infrastructure August 17-21, 1998 NPACI Parallel Computing Institute 1 Cluster Archtectures and.
Real Parallel Computers. Modular data centers Background Information Recent trends in the marketplace of high performance computing Strohmaier, Dongarra,
Mass RHIC Computing Facility Razvan Popescu - Brookhaven National Laboratory.
UNIVERSITY of MARYLAND GLOBAL LAND COVER FACILITY High Performance Computing in Support of Geospatial Information Discovery and Mining Joseph JaJa Institute.
File System Benchmarking
SDSC RP Update TeraGrid Roundtable Reviewing Dash Unique characteristics: –A pre-production/evaluation “data-intensive” supercomputer based.
Principles of Scalable HPC System Design March 6, 2012 Sue Kelly Sandia National Laboratories Abstract: Sandia National.
QCD Project Overview Ying Zhang September 26, 2005.
9/16/2000Ian Bird/JLAB1 Planning for JLAB Computational Resources Ian Bird.
Seaborg Cerise Wuthrich CMPS Seaborg  Manufactured by IBM  Distributed Memory Parallel Supercomputer  Based on IBM’s SP RS/6000 Architecture.
UTA Site Report Jae Yu UTA Site Report 4 th DOSAR Workshop Iowa State University Apr. 5 – 6, 2007 Jae Yu Univ. of Texas, Arlington.
National Center for Supercomputing Applications University of Illinois at Urbana-Champaign Cell processor implementation of a MILC lattice QCD application.
Physics Steven Gottlieb, NCSA/Indiana University Lattice QCD: focus on one area I understand well. A central aim of calculations using lattice QCD is to.
A Framework for Elastic Execution of Existing MPI Programs Aarthi Raveendran Tekin Bicer Gagan Agrawal 1.
The Red Storm High Performance Computer March 19, 2008 Sue Kelly Sandia National Laboratories Abstract: Sandia National.
Rensselaer Why not change the world? Rensselaer Why not change the world? 1.
S AN D IEGO S UPERCOMPUTER C ENTER N ATIONAL P ARTNERSHIP FOR A DVANCED C OMPUTATIONAL I NFRASTRUCTURE On pearls and perils of hybrid OpenMP/MPI programming.
BlueGene/L Facts Platform Characteristics 512-node prototype 64 rack BlueGene/L Machine Peak Performance 1.0 / 2.0 TFlops/s 180 / 360 TFlops/s Total Memory.
SciDAC All Hands Meeting, March 2-3, 2005 Northwestern University PIs:Alok Choudhary, Wei-keng Liao Graduate Students:Avery Ching, Kenin Coloma, Jianwei.
1 A New Approach to File System Cache Writeback of Application Data Sorin Faibish – EMC Distinguished Engineer P. Bixby, J. Forecast, P. Armangau and S.
IPDPS 2005, slide 1 Automatic Construction and Evaluation of “Performance Skeletons” ( Predicting Performance in an Unpredictable World ) Sukhdeep Sodhi.
SoCal Infrastructure OptIPuter Southern California Network Infrastructure Philip Papadopoulos OptIPuter Co-PI University of California, San Diego Program.
National Computational Science National Center for Supercomputing Applications National Computational Science NCSA Terascale Clusters Dan Reed Director,
1/30/2003 BARC1 Profile-Guided I/O Partitioning Yijian Wang David Kaeli Electrical and Computer Engineering Department Northeastern University {yiwang,
10/22/2002Bernd Panzer-Steindel, CERN/IT1 Data Challenges and Fabric Architecture.
- Rohan Dhamnaskar. Overview  What is a Supercomputer  Some Concepts  Couple of examples.
ARGONNE NATIONAL LABORATORY Climate Modeling on the Jazz Linux Cluster at ANL John Taylor Mathematics and Computer Science & Environmental Research Divisions.
SAN DIEGO SUPERCOMPUTER CENTER SDSC's Data Oasis Balanced performance and cost-effective Lustre file systems. Lustre User Group 2013 (LUG13) Rick Wagner.
HPSS for Archival Storage Tom Sherwin Storage Group Leader, SDSC
HPCMP Benchmarking Update Cray Henry April 2008 Department of Defense High Performance Computing Modernization Program.
O AK R IDGE N ATIONAL L ABORATORY U.S. D EPARTMENT OF E NERGY Probe Plans and Status SciDAC Kickoff July, 2001 Dan Million Randy Burris ORNL, Center for.
NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE Capability Computing – High-End Resources Wayne Pfeiffer Deputy Director NPACI & SDSC NPACI.
NEES Cyberinfrastructure Center at the San Diego Supercomputer Center, UCSD George E. Brown, Jr. Network for Earthquake Engineering Simulation Analyzing.
PC clusters in KEK A.Manabe KEK(Japan). 22 May '01LSCC WS '012 PC clusters in KEK s Belle (in KEKB) PC clusters s Neutron Shielding Simulation cluster.
CASPUR Site Report Andrei Maslennikov Lead - Systems Rome, April 2006.
National Energy Research Scientific Computing Center (NERSC) HPC In a Production Environment Nicholas P. Cardo NERSC Center Division, LBNL November 19,
GreenCloud: A Packet-level Simulator of Energy-aware Cloud Computing Data Centers Dzmitry Kliazovich ERCIM Fellow University of Luxembourg Apr 16, 2010.
Comprehensive Scientific Support Of Large Scale Parallel Computation David Skinner, NERSC.
ISG We build general capability Introduction to Olympus Shawn T. Brown, PhD ISG MISSION 2.0 Lead Director of Public Health Applications Pittsburgh Supercomputing.
Randy MelenApril 14, Stanford Linear Accelerator Center Site Report April 1999 Randy Melen SLAC Computing Services/Systems HPC Team Leader.
SAN DIEGO SUPERCOMPUTER CENTER at the UNIVERSITY OF CALIFORNIA, SAN DIEGO Advanced User Support for MPCUGLES code at University of Minnesota October 09,
Building and managing production bioclusters Chris Dagdigian BIOSILICO Vol2, No. 5 September 2004 Ankur Dhanik.
The 2001 Tier-1 prototype for LHCb-Italy Vincenzo Vagnoni Genève, November 2000.
Computing Issues for the ATLAS SWT2. What is SWT2? SWT2 is the U.S. ATLAS Southwestern Tier 2 Consortium UTA is lead institution, along with University.
A Scalable Distributed Datastore for BioImaging R. Cai, J. Curnutt, E. Gomez, G. Kaymaz, T. Kleffel, K. Schubert, J. Tafas {jcurnutt, egomez, keith,
Pathway to Petaflops A vendor contribution Philippe Trautmann Business Development Manager HPC & Grid Global Education, Government & Healthcare.
PADME Kick-Off Meeting – LNF, April 20-21, DAQ Data Rate - Preliminary estimate Tentative setup: all channels read with Fast ADC 1024 samples, 12.
A Practical Evaluation of Hypervisor Overheads Matthew Cawood Supervised by: Dr. Simon Winberg University of Cape Town Performance Analysis of Virtualization.
INTRODUCTION TO XSEDE. INTRODUCTION  Extreme Science and Engineering Discovery Environment (XSEDE)  “most advanced, powerful, and robust collection.
Is System X for Me? Cal Ribbens Computer Science Department
BlueGene/L Supercomputer
Computational issues Issues Solutions Large time scale
Presentation transcript:

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER Early Experiences with Datastar: A 10TF Power4 + Federation system Giri Chukkapalli SDSC

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER Outline Datastar specs and setup Porting issues from BH to DS Initial setup difficulties and current DS status Initial science highlights Benchmark codes Results Conclusions

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER SDSC National NSF center with compute and data resources allocated freely through peer review process Transitioning from NPACI to CyberInfrastructure through Teragrid SDSC’s emphasis and contribution to the national CI initiative is Data intensive computing Acquired Datastar at the beginning of the year to replace Bluehorizon as the main compute engine

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER DataStar 10.1 TF, 1760 processors total way 1.7 GHz IBM p690s 2 nodes 64 GB memory for login and interactive use 6 nodes 128 GB memory for scientific computation 2 nodes 128 GB memory for database, DiscoveryLink 1 node 256 GB memory for batch scientific computation All p690s connected to Gigabit Ethernet with 10 GE coming soon way 1.5 GHz IBM p GB memory Batch scientific computation All nodes Federation switch attached All nodes SAN attached

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER SDSC DataStar 187 Total Nodes 11 p p (5) (171) (7)

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER SANergy Data Movement Orion Teragrid Network SAM-QFS DISK 2Gb 1Gb x 4 p690 Federation Switch SAN Switch Infrastructure 2Gb x 4 SANergy MDC Metadata operations, NFS Data operations SANergy client

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER ~400 Sun FC Disk Arrays (~4100 disks, 540 TB total) 32 FC Tape Drives Sun Fire 15K DataStar 176 P655s SAM-QFSETF DBSAN-GPFS 5 x Brocade (1408 2Gb ports) DataStar 11 P690s SANergy Client SANergy Server Force HPSS

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER Porting issues We moved from default 32bit to default 64bit Fairly easy to port from BH to DS Mixed Fortran + C/C++ codes give some trouble

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER Initial Setup and difficulties Substantial jump in weight, power and cooling load from BH to DS Memory and performance leak Fixed through NFS automounts Removing unnecessary daemons Problems related to GPFS over SAN IBM FC adapters, Brocade switches and SUN disks Loss of processors, memory, cache HMC issues Federation issues

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER Large scale preproduction computing 100k to 200k hours per project Onuchic, UCSD: Study the folding kinetics of a beta hairpin at room temperature in explicit water Yeung **3 turbulence run Goodrich, BU - 3D calculation of the shearing and eruption of solar active regions on 201 x 251 x 251 mesh Richard Klein, UCB: dynamical evolution, gravitational collapse and fragmentation of large turbulent molecular cloud in the galaxy NREL, Cornell: Cellulose project, 1 million atom CHARMM simulation of protein interactions

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER Performance analysis All codes are 64bit compiled Still some problems, so the results may not be the best All the runs are done on 1.5GHz P655s Communication performance NAS benchmarks CG, FT, LU and MG Applications ENZO and CHARMM

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER Latency and Bandwidth comparison MPI Latencies (usec) Bandwidth (MB/s) BH DS BH DS Intra-node Inter-node

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER Bisection bandwidth

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER Barrier performance (Federation)

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER MPI broadcast performance

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER Unusual Bcast behavior

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER MPI_Alltoall

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER Understanding the raw MPI call performance (message size, No. of PEs) is useful to interpret real application MPI traces

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER GPFS performance Metadata performance File read, write performance MPI_tile_io, IOR, Pallas MPI I/O, MDTEST Each processor writes one rectangular tile 16 bytes per element each tile is 1000 x 1000 elements 1024PE run writes 32X32 tiles: 16GB file

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER GPFS Performance (MPI I/O)

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER NAS Benchmarks: Strong scaling

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER NAS benchmarks: strong scaling

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER NAS benchmarks: strong scaling DS %peak is more flatter than BH owing to the better bandwidth Initially %peak increases due to cache effects and then drops due to communication over heads Sparse matrix codes give the worst %peak and dense matrix codes gives the best %peak

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER Application benchmarks ENZO: Astrophysics code Consumes 1 Million hours on Datastar CHARMM: MD chemistry code Both are Community codes

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER Original Enzo performance on DS,BG/L

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER Improved Enzo performance on BH and DS

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER CHARMM performance 64bit compilation Rarely been run beyond a single node Previously it didn’t scale beyond 32 PEs Short hand written FFTs need to be optimized further Initiated a tuning project with the developers targeting large scale simulations

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER summary Datastar is rapidly becoming stable with good performance. Switch routing issues remaining

NATIONAL PARTNERSHIP FOR ADVANCED COMPUTATIONAL INFRASTRUCTURE SAN DIEGO SUPERCOMPUTER CENTER