HPC Hardware Overview
|
|
|
- Christina Hood
- 7 years ago
- Views:
Transcription
1 HPC Hardware Overview John Lockman III February 7, 2012 Texas Advanced Computing Center The University of Texas at Austin
2 Outline Some general comments Lonestar System Dell blade-based system InfiniBand ( QDR) Intel Processors Ranger System Sun blade-based system InfiniBand (SDR) AMD Processors Longhorn System Dell blade-based system InfiniBand (QDR) Intel Processors
3 About this Talk We will focus on TACC systems, but much of the information applies to HPC systems in general As an applications programmer you may not care about hardware details, but We need to think about it because of performance issues I will try to give you pointers to the most relevant architecture characteristics Do not hesitate to ask questions as we go
4 High Performance Computing In our context, it refers to hardware and software tools dedicated to computationally intensive tasks Distinction between HPC center (throughput focused) and Data center (data focused) is becoming fuzzy High bandwidth, low latency Memory Network
5 Lonestar: Intel hexa-core system
6 Lonestar: Introduction Lonestar Cluster Configuration & Diagram Server Blades Dell PowerEdge M610 Blade (Intel Hexa-Core) Server Nodes Microprocessor Architecture Features Instruction Pipeline Speeds and Feeds Block Diagram Node Interconnect Hierarchy InfiniBand Switch and Adapters Performance
7 Lonestar Cluster Overview lonestar.tacc.utexas.edu
8 Lonestar Cluster Overview Hardware Components Characteristics Peak Performance 302 TFLOPS Nodes 2 Hexa-Core Xeon nodes / cores Memory 1333 MHz DDR3 DIMMS 24 GB/node, 45 TB total Shared Disk Lustre parallel file system 1 PB Local Disk SATA 146GB/node, 276 TB total Interconnect Infiniband 4 GB/sec P-2-P
9 Blade : Rack : System 1 node : 2 x 6 cores = 12 cores 1 chassis : 16 nodes = 192 cores 1 rack : 3 x 16 nodes = 576 cores 39⅓ racks : cores 3 chassis 16 blades
10 Lonestar login nodes Dell PowerEdge M610 Intel dual socket Xeon hexa-core 3.33GHz 24 GB DDR MHz DIMMS Intel QPI 5520 Chipset Dell 1200 PowerVault 15 TB HOME disk 1 GB user quota(5x)
11 Lonestar compute nodes 16 Blades / 10U chassis Dell PowerEdge M619 Dual socket Intel hexa-core Xeon 3.33 GHz(1.25x) 13.3 GFLOPS/core(1.25x) 64 KB L1 cache (independent) 12 MB L2 cache (unified) 24 GB DDR MHz DIMMS Intel QPI 5520 Chipset 2x QPI 6.4 GT/s 146 GB 10k RPM SAS-SATA local disk (/tmp)
12 Motherboard DDR DDR Hexa-core Xeon QPI Hexa-core Xeon 12 CPU Cores IOH I/O Hub DMI PCIe ICH I/O Controller
13 Intel Xeon 5600(Westmere) 32 KB L1 cache/core 256 KB L2 cache/core Shared 12 MB L3 cache Core 1 Core 2
14 Cluster Interconnect 16 independent 4 GB/s connections/chassis
15 Lonestar Parallel File Systems: Lustre &NFS 97 TB 1GB/ user Ethernet $HOME 226 TB 200GB/ user $WORK TB InfiniBand $SCRATCH Uses IP over IB
16 Ranger: AMD Quad-core system
17 Ranger: Introduction Unique instrument for computational scientific research Housed at TACC s new machine room Over 2 ½ years of initial planning and deployment efforts Funded by the National Science Foundation as part of a unique program to reinvigorate High Performance Computing in the United States (Office of Cyberinfrastructure) ranger.tacc.utexas.edu
18 How Much Did it Cost and Who s Involved? TACC selected for very first NSF Track2 HPC system $30M system acquisition Sun Microsystems (now Oracle) was the vendor Very Large InfiniBand Installation ~4100 endpoint hosts >1350 MT47396 switches TACC, ICES, Cornell Theory Center, Arizona State HPCI are teamed to operate/support the system four 4 years ($29M)
19 Ranger: Performance Ranger debuted at #4 on the Top 500 list (ranked #25 as of November 2011)
20 Ranger Cluster Overview Hardware Components Characteristics Peak Performance 579 TFLOPS Nodes 4 Quad-Core Opteron 3,936 nodes / 62,976 cores Memory 667MHz DDR2 DIMMS 1GHz HyperTransport 32 GB/node, 123 TB total Shared Disk Lustre parallel file system 1.7 PB Local Disk NONE (flash-based) 8 Gb Interconnect Infiniband (generation 2) 1 GB/sec P-2-P 2.3 μs latency
21 Ranger Hardware Summary Compute power Teraflops 3,936 Sun four-socket blades 15,744 AMD Barcelona processors Quad-core, four flops/cycle (dual pipelines) Memory Terabytes 2 GB/core, 32 GB/node ~20 GB/sec memory B/W per node (667 MHz DDR2) Disk subsystem Petabytes 72 Sun x4500 Thumper I/O servers, 24TB each 40 GB/sec total aggregate I/O bandwidth 1 PB raw capacity in largest filesystem Interconnect - 10 Gbps / sec latency Sun InfiniBand-based switches (2), up to x ports each Full non-blocking 7-stage Clos fabric Mellanox ConnectX InfiniBand (second generation)
22 Ranger Hardware Summary (cont.) 25 Management servers - Sun 4-socket x4600s 4 Login servers, quad-core processors 1 Rocks master, contains software stack for nodes 2 SGE servers, primary batch server and backup 2 Sun Connection Management servers, monitors hardware 2 InfiniBand Subnet Managers, primary and backup 6 Lustre Meta-Data Servers, enabled with failover 4 Archive data-movers, move data to tape library 4 GridFTP servers, external multi-stream transfer Ethernet Networking - 10Gbps Connectivity Two external 10GigE networks: TeraGrid, NLR 10GigE fabric for login, data-mover and GridFTP nodes, integrated into existing TACC network infrastructure Force10 S2410P and E1200 switches
23 Infiniband Cabling in Ranger Sun switch design with reduced cable count, manageable, but still a challenge to cable 1312 InfiniBand 12x to 12x cables 78 InfiniBand 12x to three 4x splitter cables Cable lengths range from 7-16m, average 11m 9.3 miles of InfiniBand cable total (15.4 km)
24 Space, Power and Cooling System Power: 3.0 MW total System: 2.4 MW ~90 racks, in 6 row arrangement ~100 in-row cooling units ~4000 ft 2 total footprint Cooling: ~0.6 MW In-row units fed by three 400-ton chillers Enclosed hot-aisles Supplemental 280-tons of cooling from CRAC units Observations: Space less an issue than power Cooling > 25kW per rack difficult Power distribution a challenge, more than 1200 circuits
25 External Power and Cooling Infrastructure
26 Switches in Place
27 InfiniBand Cabling in Progress
28 Ranger Features AMD Processors: HPC Features 4 FLOPS/CP 4 Sockets on a board 4 Cores per socket HyperTransport (Direct Connect between sockets) 2.3 GHz core Any idea what the peak floating-point performance of a node is? 2.3 GHz * 4 Flops/CP * 16 cores = GFlops Peak Performance Any idea how much an application can sustain? Can sustain over 80% of peak with DGEMM (matrix-matrix multiply) NUMA Node Architecture (16 cores per node, think hybrid) 2-tier InfiniBand (NEM Magnum ) Switch System Multiple Lustre (Parallel) File Systems
29 Ranger Architecture internet Login Nodes X4600 X4600 I/O Nodes WORK File System 1 82 C48 Blades Compute Nodes 4 sockets X 4 cores 3,456 IB ports, each 12x Line splits into 3 4x lines. Bisection BW = 110Tbps. Magnum InfiniBand Switches Thumper X Metadata Server X per File Sys. 24 TB each 72 GigE InfiniBand
30 Ranger Infiniband Topology NEM NEM Magnum Switch NEM NEM NEM NEM NEM NEM 78 NEM NEM NEM NEM NEM NEM NEM NEM 12x InfiniBand 3 cables combined
31 Bandwidth (MB/sec) MPI Tests: P2P Bandwidth Point-to-Point MPI Measured Performance Ranger - OFED MVAPICH Lonestar - OFED 1.1 MVAPICH Shelf Latencies: ~1.6 µs Rack Latencies: ~2.0 µs Peak BW: ~965 MB/s Effictive Bandwith is improved at smaller message size Message Size (Bytes) 1E+08
32 Bisection BW (GB/sec). Full Bisection BW Efficiency. Ranger: Bisection BW Across 2 Magnums % Ideal Measured 100.0% % % % # of Ranger Compute Racks 20.0% 0.0% # of Ranger Compute Racks Able to sustain ~73% bisection bandwidth efficiency with all 3936 nodes communicating simultaneously (82 racks)
33 Sun Motherboard for AMD Barcelona Chips Compute Blade 4 Sockets 4 Cores 8 Memory Slots/Socket HyperTransport 1 GHz
34 8.3 GB/s 8.3 GB/s Passive Midplane 8.3 GB/s 8.3 GB/s Sun Motherboard for AMD Barcelona Chips A maximum neighbor NUMA Configuration for 3-port HyperTransport. Two PCIe x8 32Gbps One PCIe x4 16Gbps NEM Switch HyperTransport Bidirectional is 6.4GB/s, Unidirectional is 3.2GB/s. Dual Channel, 533MHz Registered, ECC Memory
35 Intel/AMD Dual- to Quad-core Evolution AMD Opteron Dual-Core AMD Barcelona/Phenom Quad-Core MCH MCH Intel Woodcrest Intel Clovertown
36 Caches in Quad Core CPUs Intel Quad-Core L2 caches are not independent AMD Quad-Core L2 caches are independent Memory Controller Memory Controller L2 L2 L3 L2 L2 L2 L2 L1 L1 L1 L1 L1 L1 L1 L1 Core 1 Core 2 Core 3 Core 4 Core 1 Core 2 Core 3 Core 4
37 Cache sizes in AMD Barcelona HT 0 HT 1 HT 2 Crossbar Switch System Request Interface L3 2 MB Mem Ctrl HT link bandwidth is 24 GB/s (8 GB/s per link) Memory controller bandwidth up to 10.7 GB/s (667 MHz) L2 512 KB L2 512 KB L2 512 KB L2 512 KB L1 64 KB L1 64 KB L1 64 KB L1 64 KB Core 1 Core 2 Core 3 Core 4
38 Other Important Features AMD Quad-core (K10, code name Barcelona) Instruction fetch bandwidth now 32 bytes/cycle 2MB L3 cache on-die; 4 x 512KB L2 caches; 64KB L1 Instruction & Data caches. SSE units are now 128-bit wide -> single-cycle throughput; improved ALU and FPU throughput Larger branch prediction tables, higher accuracies Dedicated stack engine to pull stack-related ESP updates out of the instruction stream
39 AMD 10h Processor
40 Speeds and Feeds Load Speed Store Speed 4 W/CP 2 W/CP 2 W/CP 1 W/CP 0.5 W/CP 0.5 W/CP 533MHz DDR2 DIMMS On Die External Registers L1 Data L2 64 KB 512 KB L3 2 MB Memory Latency Cache States: 3 CP ~15 CP ~25 CP ~300 CP MOESI (Modified, Owner, Exclusive, Shared, Invalid) MOESI is beneficial when latency/bandwidth between cpus is significantly better than main memory W : FP Word (64 bit) CP : Clock Period Cache line size (L1/L2) is 8W 4 FLOPS / CP
41 Ranger Disk Subsystem - Lustre Disk system (OSS) is based on Sun x4500 Thumper Each server has 48 SATA II 500 GB drives (24TB total) - running internal software RAID Dual Socket/Dual-Core 2.6 GHz 72 Servers Total: 1.7 PB raw storage (that s 288 cores just to drive the file systems) Metadata Servers (MDS) based on SunFire x4600s MDS is Fibre-channel connected to 9TB Flexline Storage Target Performance Aggregate bandwidth: 40 GB/sec
42 Ranger Parallel File Systems: Lustre 36 OSTs 72 OSTs 96TB 6GB/ user $HOME 193TB 200GB/ user $WORK 6 Thumpers 12 Thumpers InfiniBand Switch 12 blades/chassis blade OSTs 773TB 50 Thumpers $SCRATCH Uses IP over IB
43 Write Speed (GB/sec). Write Speed (GB/sec). I/O with Lustre over Native InfiniBand $SCRATCH File System Throughput $SCRATCH Single Application Performance Stripecount=1 Stripecount= Stripecount=1 Stripecount= # of Writing Clients # of Writing Clients Max. total aggregate performance of 38 or 46 GB/sec depending on stripecount (Design Target = 32GB/sec) External users have reported performance of ~35 GB/sec with a 4K application run
44 Longhorn: Intel Quad-core system
45 Longhorn: Introduction First NSF extreme Digital Visualization grant (XD Vis) Designed for scientific visualization and data analysis Very large memory per computational core Two NVIDIA Graphics cards per node Rendering performance 154 billion triangles/second
46 Longhorn Cluster Overview Hardware Components Characteristics Peak Performance (CPUs) 512 Intel Xeon E TFLOPS Peak Performance (GPUs, SP) System Memory 128 NVIDIA Quadroplex 2200 S4 DDR3-DIMMS 500 TFLOPS 48 GB/node (240 nodes) 144 GB/node (16 nodes) 13.5 TB total Graphics Memory 512 FX5800 x 4GB 2 TB Disk Lustre parallel file system 210 TB Interconnect QDR Infiniband 4 GB/sec P-2-P
47 Longhorn fat nodes Dell R710 Intel dual socket quad-core Xeon 2.53GHz 144 GB DDR3 ( 18 GB/core ) Intel 5520 chipset NVIDIA Quadroplex 2200 S4 4 NVIDIA Quadro FX CUDA cores 4 GB Memory 102 GB/s Memory bandwidth
48 Longhorn standard nodes Dell R610 Dual socket Intel quad-core Xeon 2.53 GHz 48 GB DDR3 ( 6 GB/core ) Intel 5520 chipset NVIDIA Quadroplex 2200 S4 4 NVIDIA Quadro FX CUDA cores 4 GB Memory 102 GB/s Memory bandwidth
49 DDR3 DDR3 DDR3 DDR3 DDR3 DDR3 DDR3 DDR3 DDR3 Motherboard (R610/R710) Quad Core Intel Xeon 5500 Quad Core Intel Xeon 5500 DDR3 DDR3 DDR3 DDR3 DDR3 DDR3 DDR3 DDR3 DDR3 12 DIMM slots (R610) 18 DIMM slots (R710) Intel lanes PCI Express or 36 lines PCI Express 2.0
50 QPI 0 QPI 1 Cache Sizes in Intel Nehalem QPI 0 QPI 1 Memory Controller Memory Controller Core 1 Core 2 Core 3 Core 4 L3 8 MB Shared L3 Cache L2 256 KB L1 32 KB Core 1 L2 256 KB L1 32 KB Core 2 L2 256 KB L1 32 KB Core 3 L2 256 KB L1 32 KB Core 4 Total QPI bandwidth up to 25.6 GB/s (@ 3.2 GHz) 2 20-lane QPI links 4 quadrants (10 lanes each)
51 Nehalem μarchitecture
52 Storage Ranch Long term tape storage Corral 1 PB of spinning disk
53 Ranch Archival System Sun StorageTek Silo 10,000 - T1000B tapes 6,000 - T1000C tapes ~40 PB total capacity Used for long-term storage
54 6PB DataDirect Networks online disk storage 8 Dell 1950 servers 8 Dell 2950 servers 12 Dell R710 servers High Performance Parallel File System Multiple databases irods data management Replication to tape archive Multiple levels of access control Web and other data access available globally Corral
55 Coming Soon (2013) Stampede 10 PFLOP peak performance 272 TB total memory 14 PB of disk storage Intel Xeon Processor E5 Family (Sandy Bridge) Also includes a special pre-release shipment of the Intel Many Integrated Core (MIC) co-processor
56 References
57 Lonestar Related References User Guide services.tacc.utexas.edu/index.php/lonestar-user-guide Developers
58 Ranger Related References User Guide services.tacc.utexas.edu/index.php/ranger-user-guide Forums forums.amd.com/devforum Developers developer.amd.com/home.jsp developer.amd.com/rec_reading.jsp
59 Longhorn Related References User Guide services.tacc.utexas.edu/index.php/longhorn-user-guide General Information Developers developer.intel.com/design/pentium4/manuals/index2.htm developer.nvidia.com/forums/index.php
HPC Update: Engagement Model
HPC Update: Engagement Model MIKE VILDIBILL Director, Strategic Engagements Sun Microsystems mikev@sun.com Our Strategy Building a Comprehensive HPC Portfolio that Delivers Differentiated Customer Value
Sun Constellation System: The Open Petascale Computing Architecture
CAS2K7 13 September, 2007 Sun Constellation System: The Open Petascale Computing Architecture John Fragalla Senior HPC Technical Specialist Global Systems Practice Sun Microsystems, Inc. 25 Years of Technical
RDMA over Ethernet - A Preliminary Study
RDMA over Ethernet - A Preliminary Study Hari Subramoni, Miao Luo, Ping Lai and Dhabaleswar. K. Panda Computer Science & Engineering Department The Ohio State University Outline Introduction Problem Statement
Building Clusters for Gromacs and other HPC applications
Building Clusters for Gromacs and other HPC applications Erik Lindahl lindahl@cbr.su.se CBR Outline: Clusters Clusters vs. small networks of machines Why do YOU need a cluster? Computer hardware Network
Parallel Programming Survey
Christian Terboven 02.09.2014 / Aachen, Germany Stand: 26.08.2014 Version 2.3 IT Center der RWTH Aachen University Agenda Overview: Processor Microarchitecture Shared-Memory
Lecture 1: the anatomy of a supercomputer
Where a calculator on the ENIAC is equipped with 18,000 vacuum tubes and weighs 30 tons, computers of the future may have only 1,000 vacuum tubes and perhaps weigh 1½ tons. Popular Mechanics, March 1949
ECLIPSE Performance Benchmarks and Profiling. January 2009
ECLIPSE Performance Benchmarks and Profiling January 2009 Note The following research was performed under the HPC Advisory Council activities AMD, Dell, Mellanox, Schlumberger HPC Advisory Council Cluster
LS DYNA Performance Benchmarks and Profiling. January 2009
LS DYNA Performance Benchmarks and Profiling January 2009 Note The following research was performed under the HPC Advisory Council activities AMD, Dell, Mellanox HPC Advisory Council Cluster Center The
THE SUN STORAGE AND ARCHIVE SOLUTION FOR HPC
THE SUN STORAGE AND ARCHIVE SOLUTION FOR HPC The Right Data, in the Right Place, at the Right Time José Martins Storage Practice Sun Microsystems 1 Agenda Sun s strategy and commitment to the HPC or technical
Intel Cluster Ready Appro Xtreme-X Computers with Mellanox QDR Infiniband
Intel Cluster Ready Appro Xtreme-X Computers with Mellanox QDR Infiniband A P P R O I N T E R N A T I O N A L I N C Steve Lyness Vice President, HPC Solutions Engineering slyness@appro.com Company Overview
FLOW-3D Performance Benchmark and Profiling. September 2012
FLOW-3D Performance Benchmark and Profiling September 2012 Note The following research was performed under the HPC Advisory Council activities Participating vendors: FLOW-3D, Dell, Intel, Mellanox Compute
How To Build A Supermicro Computer With A 32 Core Power Core (Powerpc) And A 32-Core (Powerpc) (Powerpowerpter) (I386) (Amd) (Microcore) (Supermicro) (
TECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 7 th CALL (Tier-0) Contributing sites and the corresponding computer systems for this call are: GCS@Jülich, Germany IBM Blue Gene/Q GENCI@CEA, France Bull Bullx
Hadoop on the Gordon Data Intensive Cluster
Hadoop on the Gordon Data Intensive Cluster Amit Majumdar, Scientific Computing Applications Mahidhar Tatineni, HPC User Services San Diego Supercomputer Center University of California San Diego Dec 18,
PCIe Over Cable Provides Greater Performance for Less Cost for High Performance Computing (HPC) Clusters. from One Stop Systems (OSS)
PCIe Over Cable Provides Greater Performance for Less Cost for High Performance Computing (HPC) Clusters from One Stop Systems (OSS) PCIe Over Cable PCIe provides greater performance 8 7 6 5 GBytes/s 4
Oracle Database Reliability, Performance and scalability on Intel Xeon platforms Mitch Shults, Intel Corporation October 2011
Oracle Database Reliability, Performance and scalability on Intel platforms Mitch Shults, Intel Corporation October 2011 1 Intel Processor E7-8800/4800/2800 Product Families Up to 10 s and 20 Threads 30MB
ALPS Supercomputing System A Scalable Supercomputer with Flexible Services
ALPS Supercomputing System A Scalable Supercomputer with Flexible Services 1 Abstract Supercomputing is moving from the realm of abstract to mainstream with more and more applications and research being
Appro Supercomputer Solutions Best Practices Appro 2012 Deployment Successes. Anthony Kenisky, VP of North America Sales
Appro Supercomputer Solutions Best Practices Appro 2012 Deployment Successes Anthony Kenisky, VP of North America Sales About Appro Over 20 Years of Experience 1991 2000 OEM Server Manufacturer 2001-2007
EDUCATION. PCI Express, InfiniBand and Storage Ron Emerick, Sun Microsystems Paul Millard, Xyratex Corporation
PCI Express, InfiniBand and Storage Ron Emerick, Sun Microsystems Paul Millard, Xyratex Corporation SNIA Legal Notice The material contained in this tutorial is copyrighted by the SNIA. Member companies
Building a Top500-class Supercomputing Cluster at LNS-BUAP
Building a Top500-class Supercomputing Cluster at LNS-BUAP Dr. José Luis Ricardo Chávez Dr. Humberto Salazar Ibargüen Dr. Enrique Varela Carlos Laboratorio Nacional de Supercómputo Benemérita Universidad
Can High-Performance Interconnects Benefit Memcached and Hadoop?
Can High-Performance Interconnects Benefit Memcached and Hadoop? D. K. Panda and Sayantan Sur Network-Based Computing Laboratory Department of Computer Science and Engineering The Ohio State University,
CORRIGENDUM TO TENDER FOR HIGH PERFORMANCE SERVER
CORRIGENDUM TO TENDER FOR HIGH PERFORMANCE SERVER Tender Notice No. 3/2014-15 dated 29.12.2014 (IIT/CE/ENQ/COM/HPC/2014-15/569) Tender Submission Deadline Last date for submission of sealed bids is extended
ECLIPSE Best Practices Performance, Productivity, Efficiency. March 2009
ECLIPSE Best Practices Performance, Productivity, Efficiency March 29 ECLIPSE Performance, Productivity, Efficiency The following research was performed under the HPC Advisory Council activities HPC Advisory
High Performance. CAEA elearning Series. Jonathan G. Dudley, Ph.D. 06/09/2015. 2015 CAE Associates
High Performance Computing (HPC) CAEA elearning Series Jonathan G. Dudley, Ph.D. 06/09/2015 2015 CAE Associates Agenda Introduction HPC Background Why HPC SMP vs. DMP Licensing HPC Terminology Types of
Parallel Large-Scale Visualization
Parallel Large-Scale Visualization Aaron Birkland Cornell Center for Advanced Computing Data Analysis on Ranger January 2012 Parallel Visualization Why? Performance Processing may be too slow on one CPU
PCI Express Impact on Storage Architectures. Ron Emerick, Sun Microsystems
PCI Express Impact on Storage Architectures Ron Emerick, Sun Microsystems SNIA Legal Notice The material contained in this tutorial is copyrighted by the SNIA. Member companies and individual members may
An Alternative Storage Solution for MapReduce. Eric Lomascolo Director, Solutions Marketing
An Alternative Storage Solution for MapReduce Eric Lomascolo Director, Solutions Marketing MapReduce Breaks the Problem Down Data Analysis Distributes processing work (Map) across compute nodes and accumulates
An Introduction to the Gordon Architecture
An Introduction to the Gordon Architecture Gordon Summer Institute & Cyberinfrastructure Summer Institute for Geoscientists August 8-11, 2011 Shawn Strande Gordon Project Manager San Diego Supercomputer
TREND MICRO SOFTWARE APPLIANCE SUPPORT
TREND MICRO SOFTWARE APPLIANCE SUPPORT What Trend Micro solutions support Software Appliance deployments? The following solutions support the software appliance form factor, and the subsequent hardware
PCI Express and Storage. Ron Emerick, Sun Microsystems
Ron Emerick, Sun Microsystems SNIA Legal Notice The material contained in this tutorial is copyrighted by the SNIA. Member companies and individuals may use this material in presentations and literature
HPC Growing Pains. Lessons learned from building a Top500 supercomputer
HPC Growing Pains Lessons learned from building a Top500 supercomputer John L. Wofford Center for Computational Biology & Bioinformatics Columbia University I. What is C2B2? Outline Lessons learned from
Using the Intel Xeon Phi (with the Stampede Supercomputer) ISC 13 Tutorial
Using the Intel Xeon Phi (with the Stampede Supercomputer) ISC 13 Tutorial Bill Barth, Kent Milfeld, Dan Stanzione Tommy Minyard Texas Advanced Computing Center Jim Jeffers, Intel June 2013, Leipzig, Germany
BIG DATA The Petabyte Age: More Isn't Just More More Is Different wired magazine Issue 16/.07
BIG DATA The Petabyte Age: More Isn't Just More More Is Different wired magazine Issue 16/.07 Martien Ouwens Datacenter Solutions Architect Sun Microsystems 1 Big Data, The Petabyte Age: Relational Next
PCI Express Impact on Storage Architectures and Future Data Centers. Ron Emerick, Oracle Corporation
PCI Express Impact on Storage Architectures and Future Data Centers Ron Emerick, Oracle Corporation SNIA Legal Notice The material contained in this tutorial is copyrighted by the SNIA. Member companies
GPU System Architecture. Alan Gray EPCC The University of Edinburgh
GPU System Architecture EPCC The University of Edinburgh Outline Why do we want/need accelerators such as GPUs? GPU-CPU comparison Architectural reasons for GPU performance advantages GPU accelerated systems
Headline in Arial Bold 30pt. The Need For Speed. Rick Reid Principal Engineer SGI
Headline in Arial Bold 30pt The Need For Speed Rick Reid Principal Engineer SGI Commodity Systems Linux Red Hat SUSE SE-Linux X86-64 Intel Xeon AMD Scalable Programming Model MPI Global Data Access NFS
Using PCI Express Technology in High-Performance Computing Clusters
Using Technology in High-Performance Computing Clusters Peripheral Component Interconnect (PCI) Express is a scalable, standards-based, high-bandwidth I/O interconnect technology. Dell HPC clusters use
New Storage System Solutions
New Storage System Solutions Craig Prescott Research Computing May 2, 2013 Outline } Existing storage systems } Requirements and Solutions } Lustre } /scratch/lfs } Questions? Existing Storage Systems
Overview of HPC systems and software available within
Overview of HPC systems and software available within Overview Available HPC Systems Ba Cy-Tera Available Visualization Facilities Software Environments HPC System at Bibliotheca Alexandrina SUN cluster
Cluster Implementation and Management; Scheduling
Cluster Implementation and Management; Scheduling CPS343 Parallel and High Performance Computing Spring 2013 CPS343 (Parallel and HPC) Cluster Implementation and Management; Scheduling Spring 2013 1 /
SUN HARDWARE FROM ORACLE: PRICING FOR EDUCATION
SUN HARDWARE FROM ORACLE: PRICING FOR EDUCATION AFFORDABLE, RELIABLE, AND GREAT PRICES FOR EDUCATION Optimized Sun systems run Oracle and other leading operating and virtualization platforms with greater
PCI Express Impact on Storage Architectures and Future Data Centers. Ron Emerick, Oracle Corporation
PCI Express Impact on Storage Architectures and Future Data Centers Ron Emerick, Oracle Corporation SNIA Legal Notice The material contained in this tutorial is copyrighted by the SNIA. Member companies
1 DCSC/AU: HUGE. DeIC Sekretariat 2013-03-12/RB. Bilag 1. DeIC (DCSC) Scientific Computing Installations
Bilag 1 2013-03-12/RB DeIC (DCSC) Scientific Computing Installations DeIC, previously DCSC, currently has a number of scientific computing installations, distributed at five regional operating centres.
The PHI solution. Fujitsu Industry Ready Intel XEON-PHI based solution. SC2013 - Denver
1 The PHI solution Fujitsu Industry Ready Intel XEON-PHI based solution SC2013 - Denver Industrial Application Challenges Most of existing scientific and technical applications Are written for legacy execution
Sun Microsystems Special Promotions for Education and Research January 9, 2007
Sun Microsystems Special Promotions for Education and Research Solve big problems on a small budget with Sun-Education s trusted partner for cutting-edge technology solutions. Sun solutions help your campus
JUROPA Linux Cluster An Overview. 19 May 2014 Ulrich Detert
Mitglied der Helmholtz-Gemeinschaft JUROPA Linux Cluster An Overview 19 May 2014 Ulrich Detert JuRoPA JuRoPA Jülich Research on Petaflop Architectures Bull, Sun, ParTec, Intel, Mellanox, Novell, FZJ JUROPA
PCI Express Impact on Storage Architectures and Future Data Centers
PCI Express Impact on Storage Architectures and Future Data Centers Ron Emerick, Oracle Corporation Author: Ron Emerick, Oracle Corporation SNIA Legal Notice The material contained in this tutorial is
LS-DYNA Best-Practices: Networking, MPI and Parallel File System Effect on LS-DYNA Performance
11 th International LS-DYNA Users Conference Session # LS-DYNA Best-Practices: Networking, MPI and Parallel File System Effect on LS-DYNA Performance Gilad Shainer 1, Tong Liu 2, Jeff Layton 3, Onur Celebioglu
Oracle Exadata: The World s Fastest Database Machine Exadata Database Machine Architecture
Oracle Exadata: The World s Fastest Database Machine Exadata Database Machine Architecture Ron Weiss, Exadata Product Management Exadata Database Machine Best Platform to Run the
7 Real Benefits of a Virtual Infrastructure
7 Real Benefits of a Virtual Infrastructure Dell September 2007 Even the best run IT shops face challenges. Many IT organizations find themselves with under-utilized servers and storage, yet they need
Toward a practical HPC Cloud : Performance tuning of a virtualized HPC cluster
Toward a practical HPC Cloud : Performance tuning of a virtualized HPC cluster Ryousei Takano Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology
SUN ORACLE DATABASE MACHINE
SUN ORACLE DATABASE MACHINE FEATURES AND FACTS FEATURES From 2 to 8 database servers From 3 to 14 Sun Oracle Exadata Storage Servers Up to 5.3 TB of Exadata QDR (40 Gb/second) InfiniBand Switches Uncompressed
Deploying Microsoft SQL Server 2005 Business Intelligence and Data Warehousing Solutions on Dell PowerEdge Servers and Dell PowerVault Storage
White Paper Dell Microsoft - Reference Configurations Deploying Microsoft SQL Server 2005 Business Intelligence and Data Warehousing Solutions on Dell PowerEdge Servers and Dell PowerVault Storage Abstract
Sockets vs. RDMA Interface over 10-Gigabit Networks: An In-depth Analysis of the Memory Traffic Bottleneck
Sockets vs. RDMA Interface over 1-Gigabit Networks: An In-depth Analysis of the Memory Traffic Bottleneck Pavan Balaji Hemal V. Shah D. K. Panda Network Based Computing Lab Computer Science and Engineering
Build GPU Cluster Hardware for Efficiently Accelerating CNN Training. YIN Jianxiong Nanyang Technological University jxyin@ntu.edu.
Build Cluster Hardware for Efficiently Accelerating CNN Training YIN Jianxiong Nanyang Technological University jxyin@ntu.edu.sg Visual Object Search Private Large-scale Visual Object Database Domain Specifi
Stovepipes to Clouds. Rick Reid Principal Engineer SGI Federal. 2013 by SGI Federal. Published by The Aerospace Corporation with permission.
Stovepipes to Clouds Rick Reid Principal Engineer SGI Federal 2013 by SGI Federal. Published by The Aerospace Corporation with permission. Agenda Stovepipe Characteristics Why we Built Stovepipes Cluster
DDR3 memory technology
DDR3 memory technology Technology brief, 3 rd edition Introduction... 2 DDR3 architecture... 2 Types of DDR3 DIMMs... 2 Unbuffered and Registered DIMMs... 2 Load Reduced DIMMs... 3 LRDIMMs and rank multiplication...
PCI Express IO Virtualization Overview
Ron Emerick, Oracle Corporation Author: Ron Emerick, Oracle Corporation SNIA Legal Notice The material contained in this tutorial is copyrighted by the SNIA unless otherwise noted. Member companies and
Cray XT3 Supercomputer Scalable by Design CRAY XT3 DATASHEET
CRAY XT3 DATASHEET Cray XT3 Supercomputer Scalable by Design The Cray XT3 system offers a new level of scalable computing where: a single powerful computing system handles the most complex problems every
Xserve Transition Guide. November 2010
Transition Guide November 2010 2 Introduction Key points Apple will not be developing a future version of Orders for will be accepted through January 31, 2011 Apple will honor all warranties and extended
SR-IOV In High Performance Computing
SR-IOV In High Performance Computing Hoot Thompson & Dan Duffy NASA Goddard Space Flight Center Greenbelt, MD 20771 hoot@ptpnow.com daniel.q.duffy@nasa.gov www.nccs.nasa.gov Focus on the research side
Kriterien für ein PetaFlop System
Kriterien für ein PetaFlop System Rainer Keller, HLRS :: :: :: Context: Organizational HLRS is one of the three national supercomputing centers in Germany. The national supercomputing centers are working
Intel Xeon Processor E5-2600
Intel Xeon Processor E5-2600 Best combination of performance, power efficiency, and cost. Platform Microarchitecture Processor Socket Chipset Intel Xeon E5 Series Processors and the Intel C600 Chipset
Brainlab Node TM Technical Specifications
Brainlab Node TM Technical Specifications BRAINLAB NODE TM HP ProLiant DL360p Gen 8 CPU: Chipset: RAM: HDD: RAID: Graphics: LAN: HW Monitoring: Height: Width: Length: Weight: Operating System: 2x Intel
Optimizing GPU-based application performance for the HP for the HP ProLiant SL390s G7 server
Optimizing GPU-based application performance for the HP for the HP ProLiant SL390s G7 server Technology brief Introduction... 2 GPU-based computing... 2 ProLiant SL390s GPU-enabled architecture... 2 Optimizing
Scale up: Building a State-of-the Art Enterprise Supercomputer. Sponsored By: Participants
Scale up: Building a State-of-the Art Enterprise Supercomputer Sponsored By: Participants 2006 Appro International, Inc. All rights reserved. Reproduction, adaptation, or translation without prior written
PADS GPFS Filesystem: Crash Root Cause Analysis. Computation Institute
PADS GPFS Filesystem: Crash Root Cause Analysis Computation Institute Argonne National Laboratory Table of Contents Purpose 1 Terminology 2 Infrastructure 4 Timeline of Events 5 Background 5 Corruption
IBM System x family brochure
IBM Systems and Technology System x IBM System x family brochure IBM System x rack and tower servers 2 IBM System x family brochure IBM System x servers Highlights IBM System x and BladeCenter servers
Michael Kagan. michael@mellanox.com
Virtualization in Data Center The Network Perspective Michael Kagan CTO, Mellanox Technologies michael@mellanox.com Outline Data Center Transition Servers S as a Service Network as a Service IO as a Service
Comparing the performance of the Landmark Nexus reservoir simulator on HP servers
WHITE PAPER Comparing the performance of the Landmark Nexus reservoir simulator on HP servers Landmark Software & Services SOFTWARE AND ASSET SOLUTIONS Comparing the performance of the Landmark Nexus
INDIAN INSTITUTE OF TECHNOLOGY KANPUR Department of Mechanical Engineering
INDIAN INSTITUTE OF TECHNOLOGY KANPUR Department of Mechanical Engineering Enquiry No: Enq/IITK/ME/JB/02 Enquiry Date: 14/12/15 Last Date of Submission: 21/12/15 Formal quotations are invited for HPC cluster.
HP ProLiant BL660c Gen9 and Microsoft SQL Server 2014 technical brief
Technical white paper HP ProLiant BL660c Gen9 and Microsoft SQL Server 2014 technical brief Scale-up your Microsoft SQL Server environment to new heights Table of contents Executive summary... 2 Introduction...
SUN HARDWARE FROM ORACLE: PRICING FOR EDUCATION
SUN HARDWARE FROM ORACLE: PRICING FOR EDUCATION AFFORDABLE, RELIABLE, AND GREAT PRICES FOR EDUCATION Optimized Sun systems run Oracle and other leading operating and virtualization platforms with greater
Multi-Threading Performance on Commodity Multi-Core Processors
Multi-Threading Performance on Commodity Multi-Core Processors Jie Chen and William Watson III Scientific Computing Group Jefferson Lab 12000 Jefferson Ave. Newport News, VA 23606 Organization Introduction
Trends in High-Performance Computing for Power Grid Applications
Trends in High-Performance Computing for Power Grid Applications Franz Franchetti ECE, Carnegie Mellon University www.spiral.net Co-Founder, SpiralGen www.spiralgen.com This talk presents my personal views
A Smart Investment for Flexible, Modular and Scalable Blade Architecture Designed for High-Performance Computing.
Appro HyperBlade A Smart Investment for Flexible, Modular and Scalable Blade Architecture Designed for High-Performance Computing. Appro HyperBlade clusters are flexible, modular scalable offering a high-density
A Quantum Leap in Enterprise Computing
A Quantum Leap in Enterprise Computing Unprecedented Reliability and Scalability in a Multi-Processor Server Product Brief Intel Xeon Processor 7500 Series Whether you ve got data-demanding applications,
A Study on the Scalability of Hybrid LS-DYNA on Multicore Architectures
11 th International LS-DYNA Users Conference Computing Technology A Study on the Scalability of Hybrid LS-DYNA on Multicore Architectures Yih-Yih Lin Hewlett-Packard Company Abstract In this paper, the
High Performance Data-Transfers in Grid Environment using GridFTP over InfiniBand
High Performance Data-Transfers in Grid Environment using GridFTP over InfiniBand Hari Subramoni *, Ping Lai *, Raj Kettimuthu **, Dhabaleswar. K. (DK) Panda * * Computer Science and Engineering Department
Discovering Computers 2011. Living in a Digital World
Discovering Computers 2011 Living in a Digital World Objectives Overview Differentiate among various styles of system units on desktop computers, notebook computers, and mobile devices Identify chips,
Extreme Computing: The Bull Way
Architect of an Open World Extreme Computing: The Bull Way Dr.-Ing. Joachim Redmer, Director HPC ( j.redmer@bull.de ) Bull today Bull is an Information Technology company, focusing on open and secure systems
PCI Technology Overview
PCI Technology Overview February 2003 February 2003 Page 1 Agenda History and Industry Involvement Technology Information Conventional PCI PCI-X 1.0 2.0 PCI Express Other Digi Products in PCI/PCI-X environments
How To Compare Amazon Ec2 To A Supercomputer For Scientific Applications
Amazon Cloud Performance Compared David Adams Amazon EC2 performance comparison How does EC2 compare to traditional supercomputer for scientific applications? "Performance Analysis of High Performance
Achieving a High Performance OLTP Database using SQL Server and Dell PowerEdge R720 with Internal PCIe SSD Storage
Achieving a High Performance OLTP Database using SQL Server and Dell PowerEdge R720 with This Dell Technical White Paper discusses the OLTP performance benefit achieved on a SQL Server database using a
Cisco Unified Computing System Hardware
Cisco Unified Computing System Hardware C22 M3 C24 M3 C220 M3 C220 M4 Form Factor 1RU 2RU 1RU 1RU Number of Sockets 2 2 2 2 Intel Xeon Processor Family E5-2400 and E5-2400 v2 E5-2600 E5-2600 v3 Processor
Purchase of High Performance Computing (HPC) Central Compute Resources by Northwestern Researchers
Information Technology Purchase of High Performance Computing (HPC) Central Compute Resources by Northwestern Researchers Effective for FY2016 Purpose This document summarizes High Performance Computing
Accelerating Data Compression with Intel Multi-Core Processors
Case Study Predictive Enterprise Intel Xeon processors Intel Server Board Embedded technology Accelerating Data Compression with Intel Multi-Core Processors Data Domain incorporates Multi-Core Intel Xeon
Dell Microsoft Business Intelligence and Data Warehousing Reference Configuration Performance Results Phase III
White Paper Dell Microsoft Business Intelligence and Data Warehousing Reference Configuration Performance Results Phase III Performance of Microsoft SQL Server 2008 BI and D/W Solutions on Dell PowerEdge
Mellanox Cloud and Database Acceleration Solution over Windows Server 2012 SMB Direct
Mellanox Cloud and Database Acceleration Solution over Windows Server 2012 Direct Increased Performance, Scaling and Resiliency July 2012 Motti Beck, Director, Enterprise Market Development Motti@mellanox.com
Introduction History Design Blue Gene/Q Job Scheduler Filesystem Power usage Performance Summary Sequoia is a petascale Blue Gene/Q supercomputer Being constructed by IBM for the National Nuclear Security
www.bsc.es MareNostrum 3 Javier Bartolomé BSC System Head Barcelona, April 2015
www.bsc.es MareNostrum 3 Javier Bartolomé BSC System Head Barcelona, April 2015 Index MareNostrum 3 Overview Compute Racks Infiniband Racks Management Racks GPFS Network Racks HPC GPFS Storage Hardware
The Bus (PCI and PCI-Express)
4 Jan, 2008 The Bus (PCI and PCI-Express) The CPU, memory, disks, and all the other devices in a computer have to be able to communicate and exchange data. The technology that connects them is called the
Flash Performance in Storage Systems. Bill Moore Chief Engineer, Storage Systems Sun Microsystems
Flash Performance in Storage Systems Bill Moore Chief Engineer, Storage Systems Sun Microsystems 1 Disk to CPU Discontinuity Moore s Law is out-stripping disk drive performance (rotational speed) As a
Transforming your IT Infrastructure for Improved ROI. October 2013
1 Transforming your IT Infrastructure for Improved ROI October 2013 Legal Notices This presentation is for informational purposes only. INTEL MAKES NO WARRANTIES, EXPRESS OR IMPLIED, IN THIS SUMMARY. Software
Agenda. HPC Software Stack. HPC Post-Processing Visualization. Case Study National Scientific Center. European HPC Benchmark Center Montpellier PSSC
HPC Architecture End to End Alexandre Chauvin Agenda HPC Software Stack Visualization National Scientific Center 2 Agenda HPC Software Stack Alexandre Chauvin Typical HPC Software Stack Externes LAN Typical
SUN FIRE X4170, X4270, AND X4275 SERVER ARCHITECTURE Optimizing Performance, Density, and Expandability to Maximize Datacenter Value
SUN FIRE X4170, X4270, AND X4275 SERVER ARCHITECTURE Optimizing Performance, Density, and Expandability to Maximize Datacenter Value White Paper April 2009 Abstract In compact 1U and 2U form factors, the
JuRoPA. Jülich Research on Petaflop Architecture. One Year on. Hugo R. Falter, COO Lee J Porter, Engineering
JuRoPA Jülich Research on Petaflop Architecture One Year on Hugo R. Falter, COO Lee J Porter, Engineering HPC Advisoy Counsil, Workshop 2010, Lugano 1 Outline The work of ParTec on JuRoPA (HF) Overview
Lecture 2 Parallel Programming Platforms
Lecture 2 Parallel Programming Platforms Flynn s Taxonomy In 1966, Michael Flynn classified systems according to numbers of instruction streams and the number of data stream. Data stream Single Multiple
The Hardware Dilemma. Stephanie Best, SGI Director Big Data Marketing Ray Morcos, SGI Big Data Engineering
The Hardware Dilemma Stephanie Best, SGI Director Big Data Marketing Ray Morcos, SGI Big Data Engineering April 9, 2013 The Blurring of the Lines Business Applications and High Performance Computing Are
Primergy Blade Server
Primergy Blade Server (Konsolidace a virtualizace) Petr Matěna Prague, 15.8.2006 Řešení FSC Primergy, VMware, BladeFrame Serverová platforma pro DDC (Dynamic Data Center) Industry Standard servery Mission
Current Status of FEFS for the K computer
Current Status of FEFS for the K computer Shinji Sumimoto Fujitsu Limited Apr.24 2012 LUG2012@Austin Outline RIKEN and Fujitsu are jointly developing the K computer * Development continues with system