June 06, 2011
June 6, 2011 -- Allinea Software (www.allinea.com) - the leading provider of parallel software development tools for high performance computing (HPC) - has released the first debugger capable of handling applications running across hundreds of thousands of cores – needed to deliver Petaflops* performance.
This latest version of Allinea DDT dramatically shortens debugging response time, improving efficiency for users at all scales. And for those working at scale on the world’s largest supercomputers, debugging on the entire system is now possible for the first time, enabled by Allinea’s new technology.
Support to handle the most complex codes
Allinea DDT 3.0 uses a new tree-based architecture that provides logarithmic performance in scalability and response time as the process count increases.
“As scale increases, using a debugger becomes even more essential, yet the challenges for debuggers in terms of performance and interface complexity become greater. We at Allinea are now providing the speed and the interface to beat this challenge. With response times measured in milliseconds at over 100,000 cores, and an interface that simplifies the presentation of many processes by merging similarities and highlighting differences we have a tool that is as easy to use on 100,000 cores as it is on 100 cores”, says Dr David Lecomber, CTO of Allinea Software.
The benefits of scalable debugging translate directly to users at all scales – with massive performance improvements for debugging small and mid-level parallel applications too. These performance improvements also enable new features that simplify the task of debugging. For example, the new Smart Highlighting capability quickly and automatically compares variables across processes, providing an indispensable visual aid for users debugging multiple processes at all scales.
Massive performance revolution for users
Mike Fish, CEO of Allinea Software, explains: “The release of Allinea DDT 3.0 marks a massive performance revolution for users, making possible tasks that are beyond the capacity of current debugging tools. As systems become ever larger, software developers at scale were running blind when trying to fix their problems. Debugging was no longer an option with conventional tool architectures and interfaces, due to unacceptably long response times and the overwhelming increase in complexity in user interfaces. Allinea DDT 3.0 has changed the game for developers and put them back in control of applications at scale.”
Chosen by the most demanding centres of excellence in parallel computing
Allinea DDT is used on 36 of the top 100 supercomputers on the respected global ‘Top 500’ list - in the US, in Europe and now in Asia. Many of the organisations that own these supercomputers have built collaboration partnerships with Allinea Software to have access to the most scalable tools in the industry. For example, Oak Ridge National Laboratory, a multi-program science and technology laboratory managed for the U.S. Department of Energy (number two in the Top 500 list) turned to Allinea to provide the tools for petascale through multi-year collaboration partnerships, as has the French Atomic Energy Authority (CEA).
Source: Allinea Software
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?