Research Cyberinfrastructure Collaboration Resources

Similar documents
University at Buffalo Center for Computational Research

Isilon Scale Out NAS. Morten Petersen, Senior Systems Engineer, Isilon Division

Emerging Technologies for HPC Storage

IBM Scale Out Network Attached Storage (SONAS) using the Acuo Universal Clinical Platform

Advanced Research Compu2ng Informa2on Technology Virginia Tech

Users and utilization of CERIT-SC infrastructure

The Why and How of HPC-Cloud Hybrids with OpenStack

Delivers cost savings, high definition display, and supercharged sharing

Dell EMC Ready Bundle for HPC Digital Manufacturing Dassault Systѐmes Simulia Abaqus Performance

ARCHER/RDF Overview. How do they fit together? Andy Turner, EPCC

LBRN - HPC systems : CCT, LSU

Xcellis Technical Overview: A deep dive into the latest hardware designed for StorNext 5

THE SUMMARY. CLUSTER SERIES - pg. 3. ULTRA SERIES - pg. 5. EXTREME SERIES - pg. 9

The BioHPC Nucleus Cluster & Future Developments

Design a Remote-Office or Branch-Office Data Center with Cisco UCS Mini

Sherlock for IBIIS. William Law Stanford Research Computing

Secure, scalable storage made simple. OEM Storage Portfolio

DVS, GPFS and External Lustre at NERSC How It s Working on Hopper. Tina Butler, Rei Chi Lee, Gregory Butler 05/25/11 CUG 2011

Sun Lustre Storage System Simplifying and Accelerating Lustre Deployments

Cisco HyperFlex HX220c M4 and HX220c M4 All Flash Nodes

TECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 11th CALL (T ier-0)

Mellanox InfiniBand Solutions Accelerate Oracle s Data Center and Cloud Solutions

Storage for HPC, HPDA and Machine Learning (ML)

Design a Remote-Office or Branch-Office Data Center with Cisco UCS Mini

Organizational Update: December 2015

Introduction to High-Performance Computing (HPC)

How to Use a Supercomputer - A Boot Camp

An Introduction to GPFS

Cisco HyperFlex Hyperconverged Infrastructure Solution for SAP HANA

Mr. D. Vinod IT Architect

Tiered IOPS Storage for Service Providers Dell Platform and Fibre Channel protocol. CloudByte Reference Architecture

IT Certification Exams Provider! Weofferfreeupdateserviceforoneyear! h ps://

SGI Overview. HPC User Forum Dearborn, Michigan September 17 th, 2012

GPFS for Life Sciences at NERSC

Isilon Performance. Name

RHRK-Seminar. High Performance Computing with the Cluster Elwetritsch - II. Course instructor : Dr. Josef Schüle, RHRK

Before We Start. Sign in hpcxx account slips Windows Users: Download PuTTY. Google PuTTY First result Save putty.exe to Desktop

Genomics on Cisco Metacloud + SwiftStack

Surveillance Dell EMC Storage with Synectics Digital Recording System

VxRail: Level Up with New Capabilities and Powers GLOBAL SPONSORS

Modernize Your IT with Dell EMC Storage and Data Protection Solutions

SuperMike-II Launch Workshop. System Overview and Allocations

SLIDE 1 - COPYRIGHT 2015 ELEPHANT FLOWS IN THE ROOM: SCIENCEDMZ NATIONALLY DISTRIBUTED

VMware vcloud Air Key Concepts

Cisco HyperFlex HX220c M4 and HX220c M4 All Flash Nodes

Data Protection for Cisco HyperFlex with Veeam Availability Suite. Solution Overview Cisco Public

TECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 6 th CALL (Tier-0)

Illinois Proposal Considerations Greg Bauer

WVU RESEARCH COMPUTING INTRODUCTION. Introduction to WVU s Research Computing Services

Cisco HyperFlex HX220c M4 Node

Decentralized Distributed Storage System for Big Data

SECURE, FLEXIBLE ON-PREMISE STORAGE WITH EMC SYNCPLICITY AND EMC ISILON

Minnesota Supercomputing Institute Regents of the University of Minnesota. All rights reserved.

Dell Technologies IoT Solution Surveillance with Genetec Security Center

Dell EMC Ready Bundle for HPC Digital Manufacturing ANSYS Performance

Installation and Cluster Deployment Guide

Shared File System Requirements for SAS Grid Manager. Table Talk #1546 Ben Smith / Brian Porter

Exadata Database Machine: 12c Administration Workshop Ed 2

A GPFS Primer October 2005

Leveraging Software-Defined Storage to Meet Today and Tomorrow s Infrastructure Demands

Architecting Storage for Semiconductor Design: Manufacturing Preparation

Exadata Database Machine: 12c Administration Workshop Ed 2 Duration: 5 Days

High Performance Computing Resources at MSU

Virtualizing SQL Server 2008 Using EMC VNX Series and VMware vsphere 4.1. Reference Architecture

Introduction to BioHPC New User Training

Veritas NetBackup on Cisco UCS S3260 Storage Server

DDN About Us Solving Large Enterprise and Web Scale Challenges

Performance Boost for Seismic Processing with right IT infrastructure. Vsevolod Shabad CEO and founder +7 (985)

Computer Science Section. Computational and Information Systems Laboratory National Center for Atmospheric Research

Enterprise power with everyday simplicity

TECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 13 th CALL (T ier-0)

Chelsio Communications. Meeting Today s Datacenter Challenges. Produced by Tabor Custom Publishing in conjunction with: CUSTOM PUBLISHING

NetApp Clustered Data ONTAP 8.2 Storage QoS Date: June 2013 Author: Tony Palmer, Senior Lab Analyst

Building a government cloud Concepts and Solutions

Feedback on BeeGFS. A Parallel File System for High Performance Computing

MyCloud Computing Business computing in the cloud, ready to go in minutes

TELSTRA CLOUD SERVICES CLOUD INFRASTRUCTURE PRICING GUIDE UNITED KINGDOM

GPFS Experiences from the Argonne Leadership Computing Facility (ALCF) William (Bill) E. Allcock ALCF Director of Operations

Enterprise power with everyday simplicity

DDN. DDN Updates. Data DirectNeworks Japan, Inc Shuichi Ihara. DDN Storage 2017 DDN Storage

Application Performance on IME

Exam : Title : Storage Sales V2. Version : Demo

VMware vsphere Data Protection 5.8 TECHNICAL OVERVIEW REVISED AUGUST 2014

Exadata Database Machine: 12c Administration Workshop Ed 2

Exdata Database Machine: 12c Administration Workshop Ed 2

Microsoft Office SharePoint Server 2007

IBM Spectrum Scale vs EMC Isilon for IBM Spectrum Protect Workloads

Supercomputer and grid infrastructure! in Poland!

Modernize Your IT with FlexPod. NetApp & Schneider Electric

NetApp FAS8000 Series

Surveillance Dell EMC Storage with Cisco Video Surveillance Manager

PracticeTorrent. Latest study torrent with verified answers will facilitate your actual test

Parallel File Systems for HPC

VxRack FLEX Technical Deep Dive: Building Hyper-converged Solutions at Rackscale. Kiewiet Kritzinger DELL EMC CPSD Snr varchitect

GPU Technology Conference 2018, San Jose S8199: GPU Enabled VDI Made the Grade at USC Viterbi School of Engineering

[MS10992]: Integrating On-Premises Core Infrastructure with Microsoft Azure

WHITE PAPER QUANTUM S XCELLIS SCALE-OUT NAS. Industry-leading IP Performance for 4K, 8K and Beyond

IBM Spectrum NAS, IBM Spectrum Scale and IBM Cloud Object Storage

THESUMMARY. ARKSERIES - pg. 3. ULTRASERIES - pg. 5. EXTREMESERIES - pg. 9

How To Design a Cluster

Transcription:

Research Cyberinfrastructure Collaboration Resources Computational resources are an important part of research endeavors, and that research varies with respect to its data and processing demands, and also with respect to the need to compute, modify theories/codes, recompute, etc.. Computational resources are essential to help build research programs, to extend the value of extramural contracts/grants/awards, and to help sustain programs. Some projects may take weeks to realize, some may take decades to realize; scalable, predictable, and sustainable resources are required. Research problems are not one-sized; therefore, computational demands are not one-sized. I. Consultation and Engagement Research computing depends on an Engagement Team of experienced scientists who are also adept with various computational, information-processing, and data management techniques. An Engagement Team is loosely organized by disciplinary families, for example: Physical, Information, Mathematical, Computer Science Life and Environmental Science Health Outcomes and Clinical Research Economics, Social and Behavioral Science, Business Humanities If a project does not fit one of the above families easily, we assign an engagement member as appropriate. Engagement team members perform three general functions: (i) user/group onboarding, (ii) disciplinary/project outreach, (iii) advanced consultations. Contributions by engagement team members range from co-investigation and article co-authorship to assisting lab teams with job submission scripts, to collaborating on scientific workshops. II. Research CyberInfrastructure A. Cluster-scale Computation and Information-Processing High Performance Computation The Killdevil cluster at UNC-Chapel Hill is a 772 node (9152 core) Dell Linux cluster with QDR Infiniband interconnect and a minimum of 4-GB memory per core, and two 32-core hosts with one terabyte of memory each to accommodate codes that require extremely large amounts of RAM. Killdevil also includes 64 NVidia Tesla GPUs (M2070). A 125-TB Lustre parallel filesystem is presented to Killdevil over Infiniband. Killdevil uses the IBM LSF batch scheduling system. A high performance NFS scratch filesystem of 225-TB is presented to Killdevil over Ethernet. Also, a permanent 4-PB high performance scale-out NFS storage cluster on Dell/EMC Isilon X-series was recently installed in 2016 as a lifecycle replacement of a prior system; Killdevil nodes may access to this space by request if required.

Prior to July 1, 2017, UNC-Chapel Hill will implement a new cluster explicitly designed for MPI and/or OpenMP+MPI hybrid (or relevantly similar) workloads typical of disciplines and programs that have significant calculation and/or simulation workloads. In subsequent additions, the new cluster is to have high-end GPU and Xeon Phi compute capability as well. Research groups, programmes, investigators, and users in general, whose typical workloads are MPI and/or OpenMP+MPI hybrid (or relevantly similar) workloads will be provided access to and resource allocations on the new cluster at UNC-Chapel Hill, Dogwood, post-implementation. High-throughput, data-intensive, regulated-data, and big-data computation Longleaf is a new cluster at UNC-Chapel Hill explicitly designed to address the computational, data-intensive, memory-intensive, and big data needs of researchers and research programmes that require scalable information-processing capabilities that are not of the MPI and/or OpenMP+MPI hybrid variety. Longleaf includes 117 General-Purpose nodes (24-cores each; 256-GB RAM; 2x10Gbps NIC) and 24 Big-Data nodes (12-cores each; 256-GB RAM; 2x10Gbps; 2x40Gbps), 5 large memory nodes (3-TB RAM each), 5 GPU nodes each with GeForce GTX1080 cards (102,400 CUDA cores in total), zero-hop connections to a high-performance and high-throughput parallel filesystem (GPFS; a.k.a., IBM SpectrumScale ) and storage subsystem with 14- controllers, over 225-TB of high-performance SSD disk storage, and approximately 2-PB of high-performance SAS disk. The nodes include local SSD disks for a GPFS Local Read-Only Cache ( LRoC ) that optimizes the most frequent metadata data/file requests to the node itself, thus eliminating traversals of the network fabric and disk subsystem. Both General-Purpose and Big-Data nodes have 68-GigaBytes/second of memory bandwidth. General-Purpose nodes have 10.67GB of memory per core and 53.34-Megabytes/second of network bandwidth per core. Big-Data nodes have 21.34GB of memory per core and 213.34-Megabytes/second of network bandwidth per core. Longleaf uses the SLURM resource management and batch scheduling system. Longleaf s total conventional compute core count is 6,496 cores (note: this count reflects that hyperthreading enabled). Also, a permanent 4PB high performance scale-out NFS storage cluster on Dell/EMC Isilon X-series was recently installed in 2016 as a lifecycle replacement of a prior system; this storage is presented to all Longleaf nodes. Research groups, programmes, investigators, and users in general, whose typical workloads are best satisfied by Longleaf are provided access to and resource allocations there. Killdevil will be retired or repurposed once all researchers, research programs, etc., have been provided appropriate access to and allocations on Longleaf and/or the new cluster system, Dogwood. B. Permanent storage systems and data management RC-Isilon For comparatively large capacity permanent storage, UNC-Chapel Hill presents a 4PB high performance scale-out NFS storage cluster on Dell/EMC Isilon X-series (recently installed in 2016 as a lifecycle replacement of a prior system). Researchers whose research requires it may receive a 5-TB allocation upon request. On a project-by-

project basis, researchers may request additional storage space (usually not to exceed 25-TBs of added space) for the duration of a time-delimited project (usually not to exceed 3-years), pending available capacity. Network Attached Storage (NAS) Researchers have access to Netapp filer storage providing predominantly NFS (and also CIFS for specific use cases). High-performance storage to is delivered via SATA disks; extreme-performance storage is delivered via SAS disks. All storage is configured with large controller caches and redundant hardware components to protect against single points of failure. This storage space is snapshotted in order to support file recovery in the event of accidental deletions. Cluster users receive an institutional allocation of 10-GB per person. Active archive Quantum StorNext is an active archive with 600-TB disk cache, and in excess of 4-PB tape storage. Data protected against media failure via two copies, and encrypted on tape. Faculty receive an institutional allocation of 2-TB per person; laboratories and project teams receive an institutional allocation of 10-TB per person. Additional capacity is available for incremental cost. SecureFTP To facilitate the deposition of files/data from external organizations into relevant computational resources offers a secure file-transfer-protocol service that allows files/data to be uploaded but prohibits downloading. This file transfer service meets additional IT-Security requirements for sensitive data. Globus Globus (http://www.globus.org) is available for secure data/file transfer amongst participating institutions. C. Secure Research Workspace Redesigned and re-architected in 2013 by UNC-Chapel Hill, the Secure Research Workspace (SRW) contains computational and storage resources specifically designed for management and interaction with high-risk data. The SRW is used for storage and access to Electronic Health Records (EHR) and other highly sensitive or regulated data; it includes technical and administrative controls that satisfy applicable institutional policies. SRW is specifically designed to be an enclave that minimizes the risk of storing and computing on regulated or sensitive data. Technically, the SRW is an advanced implementation of a Virtual Desktop Infrastructure (VDI) system based on VMWare Horizon View, Cisco Unified Computing System, Netapp Clustered Data ONTAP comprised of standard disk and flash arrays, with network segmentation and protection guaranteed by design, by adaptive Palo Alto enterprise firewalls, and enterprise TippingPoint Intrusion Prevention System appliances. Access controls and permissions are managed via centrally administered systems and technologies appropriate to ensure security

practices and procedures are correctly and consistently applied. ITS-Research Computing consults with the investigator or research group to arrive at a reasonable initial configuration suitable for their respective project(s). The default software installed is: ActivePerl Adobe Reader ArcGIS Workflow Manager ERD Concepts 6 Google Chrome Internet Explorer Java Runtime Java Development Kit Microsoft Accessories Bundle Microsoft Sharepoint Workspace Microsoft Silverlight Microsoft-SQL Server 2008 Notepad++ NSClient++ Oracle Client R Rstudio Rsyslog SAS Stata 13 In addition, Data Leakage Prevention software is available for install on systems that enable data ingress and egress but require detailed access and transfer logging, or that require additional server-level controls. Twostep (or two-factor ) authentication is also available as required or requested. D. Virtual Computing Lab Virtual Computing Lab (http://vcl.unc.edu) is a self-service private cloud virtualization service. Originally developed by NC State University in collaboration with IBM, VCL (see http://vcl.apache.org) provides researchers with anytime, anywhere access to custom application environments created specifically for their use. With only a web-browser, users can make a reservation for an application, either in advance or immediately, and the VCL will provision that application on a centrally maintained server, and provide the user with remote access to that server. VCL provides users remote access to hardware and software that they would otherwise have to install themselves on their own systems, or visit a computer lab to use. It also reduces the burden on computer labs to maintain large numbers of applications on individual lab computers, where in many cases it s difficult for some applications to coexist on the same machine. In the VCL, operating system images with the desired applications and custom configurations are stored in an image library, and deployed to a server on-demand when a user requests it.

E. Select Commercial Scientific Software The research cyberinfrastructure environment licenses commercial software to support the research community. Notable software includes: Amber Atlas.ti Biovia (DiscoveryStudio, MaterialsStudio); formerly Accelrys COMSOL Cambridge Crystallographic ESRI Gaussian Globus Connect Harris Geospatial Solutions (ENVI+IDL); formerly Excelis Intel Compilers KEGG Database MapleSoft Mathworks Mplus nquery (Statistical Solutions) Portland Group (Fortran/C/C++) PyMOL RogueWave (TotalView and IMSL) SAS Schrödinger Scientific Computing Modeling (ADF and BAND Modeling Suite) StataCorp (Stata/SE) Certara (SYBYL) Wolfram (Mathematica) X-win32 The above list is not exhaustive. III. Training Currently delivered face to face at UNC-Chapel Hill, there are short courses during the Summer, Fall and Spring terms. Courses are: Linux: Intermediate Linux: Introduction Matlab: Intermediate Matlab: Introduction Python for Scientific Computing

Python Workshop QIIME Scientific Computing: Gaussian and GaussView Scientific Computing: Introduction to Computational Chemistry Shell Scripting TarHeel Linux Using Research Computing Clusters Web Scraping See http://its.unc.edu/rc-services/research-computing-training/. Delivering training workshops effectively in a manner that does not require face-to-face presence is a goal. Contact: J. Michael Barker, Ph.D. Assistant Vice Chancellor for Research Computing and Learning Technologies UNC-Chapel Hill michael_barker@unc.edu