ICL Project News

PAPI 3.6 Released

Fri, 02 May 2008 20:25:32 GMT

After much delay and anticipation, PAPI 3.6 has finally been released.

In addition to support for newer dual and quad core processors from Intel and AMD, this version has added support for POWER6 with Linux, new offerings from Cray, Itanium multicore chips, and FreeBSD.

GridSolve version 0.18.0 released

Fri, 25 Apr 2008 22:14:48 GMT

This release resolves some problems with building and running on 64-bit platforms. The version of SQLite used been upgraded to 3.5.3. As well as a few performance enhancements.
Download from the Software section.

Hatem Ltaief joins the multicore team at ICL

Wed, 30 Jan 2008 15:12:01 GMT

HPC Challenge Awards at SC07

Wed, 29 Aug 2007 15:36:47 GMT

On Tuesday (November 13th) 12:15 – 1:15 BOF session (1 hour).

The DARPA High Productivity Computing Systems (HPCS) Program and IDC are pleased to announce the annual HPC Challenge Award Competition (www.hpcchallenge.org). The goal of the competition is to focus the HPC community’s attention on developing a broad set of HPC hardware and HPC software capabilities that are necessary to productively use HPC systems. The awards session will be held during the SC07 conference on Tuesday Number 13th during the 12:15 – 1:15 BOF session in rooms C1 / C2 / C3.

SCALASCA 0.9 released

Tue, 21 Aug 2007 17:28:15 GMT

New features include runtime summarization and new patterns

GridSolve version 0.17.0 released

Wed, 18 Jul 2007 19:57:20 GMT

This is a bugfix release. There was a problem with the proxy not�allowing servers to register and there were some problems with�the "make install" process. Download from the Software section.

HPCC 1.2 Released

Mon, 25 Jun 2007 17:17:56 GMT

We are pleased to announce the long awaited version 1.2 of HPCC. It contains many bug fixes, major features, and minor enhancements many of which were contributed by users. The major focus of this release was to improve accuracy of the reported results and ensure scalability of the code on the largest supercomputer installations with hundreds of thousands of computational cores.

MIT Lincoln Laboratory Activates LLGrid

Fri, 15 Jun 2007 13:34:15 GMT

MIT Lincoln Laboratory (http://www.ll.mit.edu/.) has enabled its next generation LLGrid interactive/on-demand parallel computing system. This system was provided to Lincoln Laboratory via a DoD High Performance Computing Modernization Program (HPCMP) Distributed High Performance Investment in collaboration with Dell Computer, Inc.
The DoD HPCMP-mandated acceptance test was conducted using the HPC Challenge benchmark suite (http://icl.cs.utk.edu/hpcc/). This benchmark suite is designed to stress a wide variety of parallel components: processor, memory, network bandwidth, and network latency. As part of the acceptance test, Lincoln Laboratory ran 170 variations using different processors and memory sizes.
This baseline performance data is available here, MIT LLGrid data.
Read more...

GridSolve version 0.16.0 released

Sun, 03 Jun 2007 16:04:56 GMT

Both GridSolve and the GridSolve Windows Client Library have a new release to version 0.16.0.

PAPI-C Technology Pre-Release

Thu, 05 Apr 2007 17:20:15 GMT

A pre-release of the new PAPI-C Component technology, PAPI-C version 3.9.0, is now available for select platforms.

Epilog Tracing Library for Windows Compute Cluster Server

Wed, 28 Mar 2007 19:51:54 GMT

The Epilog tracing library (part of the KOJAK toolset [1,2]) has been ported to the Microsoft Compute Cluster platform. The library can capture traces from MPI applications written in either FORTRAN or C/C++. The traces can be used to visualize and analyze the message passing behavior in Vampir (Intel Trace Analyzer) after converting traces to VTF format and to automatically search for patterns of inefficient execution with KOJAK/Scalasca [3].

New Headline test

Tue, 06 Feb 2007 17:59:40 GMT

Test Text test

SC06 PAPI BOF Presentation

Mon, 20 Nov 2006 14:15:01 GMT

If you missed the PAPI BOF at this year's Supercomputing, you can catch up on what's happening with Phil Mucci's BOF presentation slides, found here: [papi-bof-sc06.pdf]

HPC Challenge Benchmark at SC06

Tue, 14 Nov 2006 15:10:55 GMT

The HPC Challenge (HPCC) benchmark suite has been funded by the DARPA High Productivity Computing Systems (HPCS) program to help define the performance boundaries of future Petascale computing systems. HPCC is a suite of tests that examine the performance of high-end architectures using kernels with memory access patterns more challenging than those of the High Performance LINPACK (HPL) benchmark used in the Top500 list.
Read more...

HPC Challenge Benchmark at SC06

Mon, 13 Nov 2006 15:04:26 GMT