products New products
Modular InfiniteStorage SGI has announced the release of an integrated server and storage platform designed to provide cloud and data storage customers with the maximum flexibility for compute and data management applications. Dubbed Modular InfiniteStorage,
the core platform will be available as either SGI Modular InfiniteStorage Server (SGI MIS Server) or SGI Modular InfiniteStorage JBOD (SGI MIS JBOD) storage products, for wide-ranging and functional scalability in diverse data environments.
Cuda 4.1
Nvidia has released a new version of its Cuda parallel computing platform, which the company states will make it easier for computational biologists, chemists, physicists, geophysicists, other researchers and engineers to advance their simulations and computational work by using GPUs. Key enhancements include a re-designed visual profiler with automated performance analysis, providing an easier path to application acceleration, and a new compiler based on the widely- used LLVM open-source compiler infrastructure, delivering up to 10
per cent speed up in application performance.
‘The new visual profiler is amazing,’ said Joshua Anderson, lead developer of the HOOMD- blue open source molecular dynamics project. ‘With just a few clicks, it performs an automated performance analysis of your application, highlights likely problem areas, and then provides links to best-practice suggestions on improving them. It makes it quick and easy for virtually all developers to accelerate a broad range of applications,’ he added.
PGI Cuda C/C++ compiler for multi-core x86
The Portland Group is due to ship a performance-optimised PGI Cuda C/C++ compiler for multi-core x86 platforms (Cuda-x86) with its PGI 2012 release this month. Originally announced at the 2010 Nvidia GPU Technology Conference (GTC), Cuda-x86 extends Cuda beyond the GPU into a system-wide programming model. This release is a key step towards making the x86+GPU architecture an integrated parallel platform.
The PGI compiler for Cuda-x86
processes Cuda C/C++ is a native parallel-programming language for general-purpose multi-core x86 microprocessors from AMD and Intel. Cuda-x86 includes full support for Nvidia’s Cuda C/C++ language for GPUs so that programmers can recompile Cuda application source code for execution on an x86 host. Using Cuda-x86, developers can compile and optimise their Cuda applications to run on x86-based workstations, servers and clusters with or without an Nvidia GPU
24 SCIENTIFIC COMPUTING WORLD
accelerator. Cuda C/C++ applications compiled for x86 targets use multiple cores and the streaming SIMD (Single Instruction Multiple Data) capabilities of Intel and AMD CPUs for parallel execution.
In addition, PGI Cuda C/C++ for GPU devices is planned for release in mid-2012. At that time, using PGI Unified Binary technology, one binary will be able to use Nvidia GPUs when present or default to using multi-core x86 if no GPU is present.
www.pgroup.com
The size of the Nvidia
Performance Primitives (NPP) library has also been doubled with the addition of hundreds of new imaging and signal processing functions. This enables virtually any developer using image or signal processing algorithms to easily gain the benefit of GPU acceleration, with the simple addition of library calls into their application. The updated NPP library can be used for a wide variety of image and signal processing algorithms, ranging from basic filtering to advanced workflows.
www.nvidia.com/cuda
SuperWorkstations A new line-up of Supermicro’s SuperWorkstations designed specifically to meet the needs of engineers, architects, 3D and visual effects artists and graphic designers is being brought to market by Colfax International. These new systems cover a range of workloads ranging from high-end engineering and 3D modelling with real-time visualisation to video, photo, and multimedia compositing and editing.
The latest Intel Xeon 5600 series CPUs in single and dual processor configurations for high-end applications are supported, as well as Intel Xeon 3600 and a second gen Intel Core series processors for mainstream and entry-level systems. Top-end systems can accommodate up to 288GB of memory and are optimised for four Nvidia GPUs. Combining one Nvidia Quadro and three Tesla GPUs in the same system enables simultaneous editing and rendering in Autodesk 3ds Max.
www.supermicro.com/ products
www.scientific-computing.com
Suited to cloud computing and other IT storage management environments that require data and compute to be tightly coupled, the platform enables customers to pool processing and storage in the right proportions for greatest efficiency. The design features modular drive bricks, with each of the bricks capable of being loaded with either nine 3.5-inch SAS or SATA drives, or 18 2.5-inch SAS or SSD drives. As a storage server, SGI MIS Server includes eight drive bricks and two motherboards, for up to
For regular product updates, please visit
www.hpcprojects.com/products
216TB and four 1.8 to 2.9 GHz processors in a single 4U server chassis. The modularity of the system means that the same platform could be configured for extreme IOPs applications, for example, by substituting the 72 3.5-inch disk drives with 144 SSDs. For additional capacity, an SGI MIS JBOD can be added, which packs nine drive bricks for up to 243TB of disk capacity into each additional 4U enclosure.
www.sgi.com/products/ storage
Jacket v2.0
AccelerEyes has released v2.0 of Jacket, adding GPU computing capabilities for use with Matlab. The latest version delivers more speed through a host of new improvements, maximising GPU device performance and utilisation. Notable new features include a multi-GPU interface and support for OpenCL devices. With Jacket v2.0, M-code is now portable across all major GPU devices, including AMD/ATI, Intel and Nvidia chips. Jacket is the premier GPU
software plugin for Matlab, compared to alternative solutions.
www.accelereyes.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