This page contains a Flash digital edition of a book.
high-performance computing


Allinea DDT CUDA 6 and GE Intelligent Platforms’ released


Allinea Software’s debugging tools are now available on both the CUDA 6 platform and GE Intelligent Platforms’ systems.


Allinea DDT 4.2.1 has been


tailored to offer full support for Nvidia CUDA 6, the latest release of the parallel computing platform and programming model.


Allinea DDT and Allinea MAP


are also now certified to run on GE Intelligent Platforms’ systems, allowing developers to debug and profile code precisely for this environment and to ensure that every application performs at its best.


The CUDA 6 platform features unified memory and other new features that make parallel programming easier and enable software developers to dramatically decrease the time and effort required to accelerate their scientific, engineering, enterprise and other applications. The production release of the CUDA 6 Toolkit is available today as a free download on the CUDA website. ‘We worked closely with Allinea


Software and PGI to provide world-class debugging capabilities for CUDA Fortran and OpenACC directives-based codes,’ said Duncan Poole, senior manager of Strategic Alliances at Nvidia. ‘Unified memory will be transformative for codes, as it removes the need to manually copy data between the host CPU and accelerator. The ability to debug with Allinea DDT from day one will make a huge difference to developers who need tools that can scale out to their biggest systems and most challenging bugs. With these tools available, users can quickly deploy CUDA 6 in production,’ said David Lecomber, CEO and founder of the software. As well as working with Nvidia and PGI Software, Allinea worked with other major compiler vendors to ensure that Allinea DDT also supports their GPU capabilities.


Satellite link to supercomputer sequences genome while sailing


creatures on board a ship in real-time. Because of the difficulties of storing or shipping their genetic material, it has hitherto been difficult to sequence the genomes of marine species. However, researchers at the University of Florida have got round this problem by deploying a fully-equipped genomic laboratory aboard a ship called the Copasetic and sending the initial data via a satellite link to the University’s new HiPerGator supercomputer. Aboard the Copasetic in early February and later in March-April, Professor Leonid Moroz, from the University of Florida, and his team where able to perform transcriptome sequencing of 22 organisms, among them rare comb jellies. Moroz studies fragile marine pelagic


A


organisms – comb jellies or ctenophores – for their ability to regenerate. Their wounds can heal in two to three hours and they can regenerate their elementary brains in three to five days. Another creature, sea slugs, may hold the key to the genomic basis for memory and neuronal evolution. While humans have learned to slow the progress of some diseases, Moroz said many sea creatures have already figured out how to reverse disease and injury. On board ship, samples were


University of Florida researcher has become the first scientist to sequence the genome of fragile marine


immediately processed and sequenced using the Ion Torrent Personal Genome Machine System, which was linked via satellite to the university’s new high- performance computer, HiPerGator. HiPerGator is a Dell/AMD machine, with 16,384 processing cores; a Terascala HPC storage solution with a fast open-source parallel file system; and Mellanox’s FDR 56Gbps InfiniBand interconnects. The HiPerGator was purchased and assembled for for $3.4 million. ‘The real success of these two proof- of-concept trips is that we now know we can do high-throughput sequencing


leads to ‘killing these beautiful creatures’ said Moroz. But without enough samples to repeat experiments, researchers must undertake another costly field expedition.


The potential benefits are great: about 50 per cent of drugs today are derived from natural products. The globe is 70 per cent ocean, and scientists estimate 14 million to 20 million compounds remain to be discovered at sea. However they are disappearing quickly, it has been estimated that we lose an undiscovered species every six hours. ‘We need to deploy a sequencing fleet,’ Moroz said.


SAMPLES WERE SEQUENCED USING THE ION TORRENT PERSONAL GENOME MACHINE SYSTEM


at any location,’ Moroz said. ‘This is the perfect example of collaboration and synergy between public and private institutions such as Ocean Research Corp, International SeaKeepers Society, Florida Biodiversity Institute, and Ocean Expedition (OceanX) programmes.’ Moroz said he was motivated to prove


direct sequencing and real-time genomic analysis in the middle of the ocean would work because of past frustrations with field expeditions. Creatures shipped to a lab often arrive in degraded condition. Oversampling to compensate for those errors is a problem, too, because it


‘There are potentially unique solutions


in nature for medicine, but they are disappearing.’ The first results of the sequencing at


sea were presented at the international conference, Advances in Genome Biology and Technology, held at Marco Island in Florida in February. ‘We are in the midst of a genomic


revolution,’ Moroz said. ‘We must take advantage of this great new computing facility, we are in a race to save species, in 20 years some won’t exist. Losing them would be like losing the Sistine Chapel,’ he lamented.


Bright Cluster Manager for OpenStack


Bright Computing, a provider of management solutions for clusters and clouds, has released the Bright Cluster Manager for OpenStack. This add-on for version 7 of the Bright software enables customers to deploy OpenStack private clouds on bare metal servers, providing a complete OpenStack solution with full life-cycle management. Integrating provisioning of the physical cluster with the Icehouse release of the OpenStack software stack, Bright Cluster Manager 7


20 SCIENTIFIC COMPUTING WORLD


reduces the time and effort required to get a private cloud into production. The software is designed to automate the complicated configuration and setup operations for OpenStack clouds, so system administrators don’t have to manage configuration files manually. Storage management is handled using Ceph, a unified, high-performance, distributed storage system. By decoupling the physical storage this way, systems administrators do not have to


track storage in the cloud. Bright’s integrated OpenStack monitoring and health checks let operators find and fix problems quickly, sometimes even detecting failures before they occur. ‘Bright Cluster Manager 7 for OpenStack expands our cloud management capabilities into on-premise private clouds, giving customers more options to choose from when deploying their infrastructure,’ said Dr Matthijs van Leeuwen, founder and CEO of Bright Computing.


@scwmagazine l www.scientific-computing.com


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53