November 18, 2009
WARWICK, England, Nov. 17 -- Allinea Software today announced that it has made available a pre-release version of the Distributed Debugging Tool (DDT) for the CUDA architecture to selected end-user customers. This software will be demonstrated live at SC09.
Following a successful collaboration with NVIDIA and the Commissariat Energie Atomique (CEA), Allinea Software has developed a version of DDT that offers native support for NVIDIA Tesla GPUs based on the massively parallel CUDA architecture. This Linux-specific version of DDT complements and extends the capabilities of NVIDIA's CUDA Toolkit by providing the ability to debug HPC applications across clusters of multicore x86-64 servers, each of which may contain multiple Telsa GPUs. The intuitive GUI interface offers a seamless debugging experience on these hybrid architectures by combining features for MPI, OpenMP and CUDA within a single, easy-to-use development platform.
"Over recent months, our technical team has been working closely with NVIDIA to ensure that we can provide native debugging capabilities on CUDA-enabled hardware. At the same time, we have collaborated with key end-users, and in particular the CEA, to define product features that are specific to this particular programming paradigm," said Michael Rudgyard, CEO of Allinea Software. "By providing developers with a consistent framework for debugging multi-process, multi-threaded code that runs on native x86-64 hardware as well as on Tesla co-processors, we believe that we can help PetaFlop computing on hybrid architectures to become a mainstream technology."
"GPUs are delivering transformative performance increases in scientific computing applications, speeding up discovery anywhere from 20 to 200 times," said Andy Keane, general manger of Tesla business at NVIDIA. "Tools like Allinea DDT play a crucial role in the development of scalable GPU computing applications by reducing the time and effort it takes to develop large scale applications." A full version of DDT for the CUDA architecture is expected in Q1 2010, although potential customers are invited to contact Allinea if they are interested in early access to this technology. Allinea Software and NVIDIA will be exhibiting at the Supercomputing Conference (SC09) in Portland, Ore., from Nov. 16-20, 2009. Demonstrations of DDT for the CUDA architecture will take place on the Allinea stand, booth #1808.
About Allinea Software Ltd.
Based in Warwick, England, with subsidiaries in the US and Germany, Allinea Software Ltd. is a leading supplier of tools for parallel programming and high performance computing (HPC). Allinea's products are used by leading commercial and research institutions across the world, and have consistently set the standard for affordability, functionality and ease-of-use -- whether applied to applications at modest scale or petascale applications on the world's largest supercomputers. With new product features aimed at multi-threaded applications and novel computing architectures, Allinea is now bringing its wealth of experience in parallel tools to the rapidly-expanding arena of multicore processing. For more information, visit www.allinea.com.
Source: Allinea Software Ltd.
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?