Performance

Performance

X10 won the HPC Challenge "Best Performance" Award in the Class II competition at SC'12. The X10 submission (paper, presentation,…

Productivity

Productivity

X10 provides Java-like productivity with Java or C++ interoperability

Scale

Scale

From GPUs to clusters to Blue Gene, utilize the single source X10 advantage across them all!

Frontpage Slideshow | Copyright © 2006-2011 JoomlaWorks Ltd.

The latest news about the X10 programming language.

X10 2.5.1 Released

We are happy to announce the release of X10 and X10DT 2.5.1. The primary features in this release are enhancements to Resilient and Elastic X10.  The release is available for download at http://x10-lang.org/releases/x10-release-251.

4 December 2014

X10'14 Workshop program available

The  X10'14 workshop program is now available, including links to papers and slides presented at the workshop.

ScaleGraph 2.2 Released

The ScaleGraph group has announced the release of ScaleGraph 2.2.  ScaleGraph is a graph library for large-scale graph processing built using X10. Features at a glance:

  • XPregel ­– a framework for Pregel computational model
  • Betweenness Centrality
  • Degree Distribution
  • HyperANF (beta)
  • Maximum Flow (beta)
  • Minimum Spanning Tree (beta)
  • PageRank
  • Strongly Connected Component
  • Explicitly Managed Memory

For more information, please refer to scalegraph.org.

IIT Madras Benchmark Suite Released

A new kernel benchmark suite -- IMSuite: IIT Madras benchmark suite for simulating distributed algorithms has been released. IMSuite implements twelve classical distributed algorithms in two task parallel languages - X10 (x10-2.3.0) and HJ.  IMSuite is an open source benchmark suite, which can be freely downloaded at: http://www.cse.iitm.ac.in/~suyash/imsuite/

The slides and sample programs from the first X10 2.4 tutorial APGAS Programming in X10 given at the Hartree Centre Summer School are now available. 

X10 won the HPC Challenge "Best Performance" Award in the Class II competition at SC'12.

The X10 submission (paper, presentation, code) was based on X10 code for Global HPL, Global Random Access and Global FFT and Unbalanced Tree Search (UTS) benchmarks and performance runs on the PERCS machine. All benchmarks were run at 32K cores, some also at 55K cores. We showed good scaling and good to outstanding absolute performance on all benchmarks. More details are available at the HPC Challenge 2012 Awards page.

All papers and presentations from the X10 2012 Workshop are now available from the workshop program page.  Videos of the X10 tutorial and the Main Memory Map Reduce presentations are also available.

 

A new release (version 2.1.0) of the IBM Parallel Debugger for X10 Programming, is available from IBM developerWorks. This release includes a number of bug fixes and user interface improvements including an activity view and enhancements to the variable view to display the contents of DistArrays.

Version 2.1.0 of the IBM Parallel Debugger for X10 Programming requires version 2.2.2.2 of X10 and X10DT.

 

David Hudak has updated his X10 tutorial to X10 version 2.2.1.  The tutorial is available at http://www.osc.edu/~dhudak
All example code was tested with X10 v2.2.1 built with gcc v4.4.5 and mvapich2 v1.6 on Glenn, the OSC production cluster. 

Page 1 of 2