Skip to content

Data Central Banner

SDSC > Data Central > About Data Central

Data Resources

SDSC Data Central provides and supports a wide range of data resources, as well as computing resources dedicated to data analysis and mining. Resources are available through a peer-reviewed process to academic researchers in the U.S.

A summary of available resources and links for more detailed information can be found below. For more information on how to apply for available data resources visit the Data Cental "Applying for Data Resources" page.

Overview

Data Central's storage resources consist of these components:

  • Hardware:
    • disk
    • tape
    • login nodes
    • database servers
    • web servers
  • Software:
    • database software
    • data management tool, Storage Resource Broker (SRB)
    • data mining and analysis software
    • visualization software
    • data transfer software

See diagram of Storage and Compute Resources

Data Resources

With a capacity of more than 27 petabytes of tape and disk storage, Data Central storage resources are especially designed for high-performance users. Data Central's work with commercial vendors, to prototype and deploy cutting-edge storage resources driven by the needs of users, has led to new records for data transfer. It has also led to innovative storage configurations enabling new capabilities and usage models in local and remote grid computing environments.

SAM-QFS

SAM-QFS

A high-performance archival storage system at Data Central. It allows users to directly access data using a disk cache file system, then automatically migrates the data to tape. SAM-QFS User Guide >

SRB

Storage Resource Broker (SRB)

A client-server middleware connecting to heterogeneous data resources over a network and accessing replicated data sets. SRB User Guide >

HPSS

High Performance Storage System (HPSS)

A centralized, long-term data storage system. HPSS has the capacity to store 25 PB of data, and data is added at a rate exceeding 100 TB a month. HPSS User Guide >

Global Parallel File System - Wide Area Network (GPFS-WAN)

A centralized file system for long- or short-term data storage of high-volume multi-site runs, as well as large TeraGrid-based data collections. GPFS-WAN is a 700-TB storage system mounted on several TeraGrid platforms. GPFS-WAN User Guide.

Databases

A variety of databases are available on several different architectures in order to accommodate and serve the different DataBase needs. More about Database Resources >

Associated Services and Software

Data Central provides a variety of software that is designed for the available resources to aid researchers in data manipulation, etc.

Software

Data Central provides a wide range of software applications to analyize your data. More about Software tools >

Off-site Back-up

Data Central also offers off-site back-up at reasonable cost. Please contact us if interested: datacentral-allocations@sdsc.edu.

Compute Resources

IA-64

IA-64 Linux Cluster

SDSC's IA-64 cluster currently consists of 262 IBM cluster nodes, each with dual 1.5 GHz Intel® Itanium® 2 processors, for a peak performance of 3.1 teraflops. IA-64 Cluster User Guide >

 

BlueGene

IBM BlueGene/L

With 3,072 compute nodes and rated at 17.2 teraflops, BlueGene provides a glimpse into the future of cost-effective compute power in a small package. BlueGene User Guide>

OnDemand

OnDemand Cluster

A Rocks cluster with Intel dual-socket, dual-core compute nodes. The 2.0 GHz, 32-way nodes have 8 GB of memory. OnDemand has a nominal theoretical peak performance of 2.4 TFlops. OnDemand User Guide >

Sun X64 (Bebop)

A Solaris machine that is exclusively reserved for data analysis and data mining with SAS software. Bebop User Guide >

Did You Get
What You
Wanted?
Yes No
Comments