xcat.org Open in urlscan Pro
166.70.135.166  Public Scan

Form analysis
0 forms found in the DOM

Text Content

Welcome to xCAT xCAT is an open-source tool for automating deployment, scaling,
and management of bare metal servers and virtual machines. 
Get Started Now >
Build the future of Bare metal infrastructure

xCAT offers complete management for HPC clusters, RenderFarms, Grids, WebFarms,
Online Gaming Infrastructure, Clouds, Datacenters etc. xCAT provides an
extensible framework that is based on years of system administration best
practices and experiences. It is agile, extensible and powerful.




XCAT 2.16.5 RELEASED MARCH 8, 2023



Join us >


KEY FEATURES



OS PROVISION


HARDWARE CONTROL


INFRASTRUCTURE DISCOVERY

 * Bare metal provision method (diskful, diskless, statelite)
 * Redhat, Ubuntu, SLES, CentOS
 * ppc64le, x86_64, ppc64
 * PostgreSQL, SQLite, MariaDB, MySQL
 * PowerAI, KVM, PowerVM, zVM, VMWare
 * Cumulus Linux

 * Management protocols (IPMI, HMC, FSP, OpenBMC)
 * Remote console
 * Firmware flash
 * Power management
 * BMC configuration
 * Sensor inventory

 * BMC discovery
 * Switch based switch discovery
 * ZTP based discovery(ONIE)
 * MTMS based discovery
 * Switch based discovery
 * Sequential discovery


SCALE


CONFIGURATION MANAGEMENT


GPU / INFINIBAND

 * Hierarchical Clusters
 * Super large scale(>9000 nodes) HPC bare metal clusters
 * Large scale(>1000 nodes) clusters
 * Small-medium scale( <1000 nodes) clusters

 * Software maintenance
 * Parallel command and file dispatch
 * RESTful API
 * OS image life cycle management
 * RAID

 * NVIDIA nvidia-smi
 * Mellanox InfiniBand(IB) adapter install
 * IB network configure
 * IB switch configure
 * UFM configure


QUICK START

xCAT does provide a great deal of cluster management functionality. To set up a
xCAT cluster, practice baremetal hardware management and OS provision function,
go to xCAT Quick Start


HIGH PERFORMANCE COMPUTING (HPC)

xCAT is used to manage the servers in Summit and Sierra, two supercomputers
taking the #1 and #2 spots on the Nov 2018 Top 500.
 * Extreme scalable with hierarchy architecture
   
 * Simple and fast provisioning with diskless mode
   
 * End-2-end infrastructure discovery
   
 * Zero-touch failed server replacement
   

More...

HIGH PERFORMANCE DEEP LEARNING (AI)

Deep Learning requires lots of computational resources to process analytics on
large amounts of data, xCAT could be used to manage and deploy the Deep Learning
environment.

 * Manage Deep Learning Elements
   
 * Simple deployment of deep learning environment
   
 * Scalability
   

More...

HPC DEVELOPMENT CLOUD

Besides HPC cluster used for production, many HPC customers are still requiring
a development environment on-premise for testing and agile developing.

 * Deployment of Virtualization infrastructure
   
 * On-demand Elastic Scaling
   
 * RESTful API
   

More...


WHO'S USING XCAT

The following is an opt-in list of some xCAT users. To either add or remove your
company/organization from this list, please open an issue here.


--------------------------------------------------------------------------------



IBM

xCAT is an open-source tool for automating deployment, scaling, and management
of bare metal servers and virtual machines developed by IBM
xCAT is an official IBM high Performance Computing cluster management tool.


IBM

xCAT is an open-source tool for automating deployment, scaling, and management
of bare metal servers and virtual machines developed by IBM
xCAT is an official IBM high Performance Computing cluster management tool.


LEIBNIZ SUPERCOMPUTING CENTRE

>9000 and >3000 compute nodes are managed by xCAT in SuperMUC super computer
SuperMUC is the high-end supercomputer at the Leibniz Supercomputing Centre with
more than 241,000 cores and a combined peak performance of the two installation
phases of more than 6.8 PetaFlop/s. >6000 compute nodes are managed by xCAT in
SuperMUC-NG super computer
SuperMUC-NG has 311,040 compute cores in total with a main memory of 719 TB and
a peak performance of 26.9 PetaFlop/s.


STANFORD RESEARCH COMPUTING CENTER

The Stanford Research Computing Center (SRCC) is a joint effort of the Dean of
Research and IT Services to build and support a comprehensive program to advance
computational research at Stanford. That includes offering and supporting
traditional high-performance computing (HPC) systems, as well as systems for
high throughput and data-intensive computing. The SRCC also helps researchers
transition their analyses and models from the desktop to more capable and
plentiful resources, providing the opportunity to explore their data and answer
research questions (on-premise or in the cloud) at a scale typically not
possible on desktops or departmental servers. We use xCAT to deploy and maintain
the Sherlock cluster, Stanford's shared HPC cluster that features over 25,000
CPU cores and supports over 4,000 users.


VERSATUS HPC

100% focused on High Performance Computing, Versatus HPC is a Brazilian company
focused on delivering the best solutions for HPC scenarios in the academia,
industries and businesses. With 10 years of experience we allow the researchers
to focus exclusively on R&D pursuing its scientific objectives. We are
supporting / installing xCAT in lot of Universities and Companies in Brazil. We
always defaults to xCAT as the main provisioner and we try at best to convince
our customers to move from whatever provisioning solution, including proprietary
ones, to xCAT.


REDLINE

RedLine specializes in High Performance Computing (HPC) software and systems
engineering, development, and support, from planning, designing, and
implementation, to porting and performance tuning We have been using xCAT since
early 2011. We have deployed numerous clusters on many different hardware
platforms.


CINECA

Cineca is a not-for-profit Consortium, made up of 67 Italian universities*, 9
Italian Research Institutions, 1 Polyclinic and the Italian Ministry of
Education.


OCF

OCF supports and installs xCAT in over 95% of all our installations in the UK
and Ireland. We have vast experience and have been developing and implementing
xCAT since 2008. OCF deployed their first cluster in the UK using xCAT 2.0 soon
after it was released. We pride ourselves in being one of the leading providers
for xCAT solutions, and we would hope to tackle any problem that any individual
faces.


BSC

Barcelona Supercomputing Center. Statelite cluster of 3,456 nodes (48 racks of
72 nodes). Since this is a statelite cluster we have a large amount of service
nodes, which also serve as the NFS servers for the images (via GPFS cNFS) . one
service node per 2 racks, i.e 24 service nodes in total.


UNIVERSITY OF SAN DIEGO

University of San Diego.


COREHIVE

CoreHive use xCAT as our favorite tool to build, install, configure, secure,
optimize and deliver valuable data insights and performance for your
business-critical HPC application workloads on-premise and on the IBM Cloud or
third-party clouds like Amazon AWS , Microsoft Azure.


MEGWARE

Since its foundation in 1990, the Chemnitz (Germany) based company has been able
to draw on extensive experience in the development and installation of HPC
systems and Linux clusters. MEGWARE, as one of Europe’s leading supercomputing
specialists, has delivered and installed approximately 1,500 high-performance
computers to research institutes, universities, and industry customers
throughout Europe. MEGWARE has been using xCAT since more than 10 years. xCAT is
the favourite tool when it comes to provisioning HPC and AI clusters.

--------------------------------------------------------------------------------