The Leading Source for Global News and Information Covering the Ecosystem of High Productivity Computing
November 06, 2008
HyperCore architecture overcomes historical challenges to widespread adoption of manycore technology
TOKYO, Nov. 6 -- Plurality Ltd., a developer of advanced manycore processor solutions, today announced at the Multicore Expo Japan 2008 the beta release of an extensive set of development tools for its HyperCore Architecture Line (HAL) of manycore processors. The tools will facilitate the evaluation and widespread adoption of Plurality's technology. Manycore architecture -- from tens to thousands of cores per processor -- is widely acknowledged as the natural evolution of multicore processing. HAL processors will offer the highest performance at the lowest price per watt per square millimeter of any chip-level shared memory machine currently on the market.
"With multicore already mainstream, the future of computing inevitably will require massive parallelism performed on manycore processors," said Plurality CEO, Igor Pe'er. "Because HyperCore is a comprehensive hardware and software manycore solution, it meets the need for a viable, standard platform for low-cost, massively-parallel processing."
Positioned as a general-purpose accelerator for applications with a high degree of inherent parallelism, HyperCore acts as an extension of the most popular processor architectures (x86, PowerPC, and ARM). The HyperCore architecture includes 16-256 cores and multi-ported L1 shared memory in which each core is equidistant from the memory. A key component of the architecture is a hardware-based, low-latency, high-throughput synchronizer/scheduler that manages the cores according to a task map and balances the load among the cores. The synchronizer/scheduler ensures scalable performance that enables nearly linear speedup, regardless of the number of cores in the processor. Among the many applications ideal for the HyperCore processor are image and video processing, video surveillance, gaming, network processing, security, and software-defined radio.
"Plurality's HyperCore will give us tremendous value -- at least 10 times the performance of our current computing solution," says Dekel Tzidon, head of research and IP development at BVR Systems Ltd., where Plurality's manycore emulator is under evaluation for parallel processing in military simulation systems. "With Plurality's programming model we will be able to quickly recompile over one million lines of application code to run on a manycore processor without major changes. We also can significantly reduce the hardware, software and operating costs of our simulation systems with Plurality's acceleration boards."
The HAL toolset includes a cycle-accurate simulator that runs on an x86 platform (Linux and Windows OS); a GCC cross-compiler (v. 4.0.1); GNU Binutils v. 2.18; a cross-debugger that works within the Eclipse development environment; and an emulator supporting Linux and Windows native environments. The tools enable a gradual approach from exploring parallel decomposition with the emulator to precise evaluation of the performance of a 256-core system with the simulator. Plurality's serial-like task-oriented programming model enables developers to easily write code for computations that are offloaded from the main processor. It simplifies the recompilation of serial code to parallel code and enables intuitive parallel programming of new applications.
Plurality's manycore development tools are currently being evaluated at the University of Otago in Dunedin, New Zealand. Stuart Barson, business manager in the university's Research and Enterprise Office, says, "We are excited to work with Plurality's emulator and look forward to receiving the simulator, so that we can learn how to readjust our algorithms."
Several labs in the Electrical Engineering department at the Technion – Israel Institute of Technology in Haifa, Israel also are checking the tools. According to Peleg Aviely, Plurality's vice president of engineering, "The Technion is very interested in our implementation of shared L1 cache memory, whose traits are reminiscent of a Parallel Random Access Machine (PRAM), and in our hardware synchronizer/scheduler, which lets the programmer focus on concurrency instead of synchronization and communication issues."
Plurality is developing acceleration boards that interface to a main CPU via a PCI Express connection and AMD's HyperTransport link. Plurality is a partner in AMD's Torrenza initiative, which enables hardware manufacturers other than AMD to connect a co-processor to an open CPU slot on the AMD Opteron 64 via its HyperTransport link. Daniel Daniel, country manager of AMD Israel, says "AMD is pleased that Plurality supports the Torrenza initiative. We believe Plurality offers an excellent solution for customers who need to accelerate applications requiring massively-parallel processing."
Pricing and Product Availability
The beta version of Plurality's development tools is available immediately at no charge and can be downloaded from http://www.plurality.com/download_form.html. Plurality will release an FPGA-based 32-core evaluation board during Q2, 2009. A 64-core chip (HAL-64) will be introduced during the second half of 2009, along with an acceleration board that includes the HAL-64 processor. For further information, email the company at info@plurality.com or visit www.plurality.com.
Page: 1 of 2(Digg, Technorati, more)
PGI Accelerator™ Fortran 95/03 and C99 compilers for x64+NVIDIA
Accelerate applications on x64+GPU platforms by adding OpenMP-like compiler directives to existing Fortran and C programs. Available now for Linux, MacOS and Windows. Download a free 15 day trial.
Platform HPC Workgroup Manager
Platform HPC Workgroup Manager integrates all the cluster productivity tools you need to deploy, run and manage your HPC environment.
C-DAC announces plans for a petaflop system; IBM researchers are working on vertical integration techniques to extend Moore's Law another 15 years. We recap those stories and more in our weekly wrapup.
Read More...
The Moscow State University supercomputer, Lomonosov, has been selected for a high-performance makeover, with the goal of tripling its processing power to achieve petaflop-level performance in 2010. T-Platforms, who developed and manufactured the supercomputer, is the odds-on favorite to lead the project.
Read More...
Right on schedule, Intel has launched its Xeon 5600 processors, codenamed "Westmere EP." The 5600 represents the 32nm sequel to the Xeon 5500 (Nehalem EP) for dual-socket servers. Intel is touting better performance and energy efficiency, along with new security features, as the big selling points of the new Xeons.
Read More...
Mar 19 | OfficialWire | New super to support intelligence work Down Under. Read more...
Mar 18 | ChannelWeb | Westmere parts already showing up in HPC machines. Read more...
Mar 17 | The Register | But what about the tier ones? Read more...
Mar 17 | Cadalyst Magazine | A new generation of workstations is changing the nature of technical computing. Read more...
Mar 17 | Linux Magazine | Latest iteration of Sun Grid Engine able to tap into Cloud. Read more...
Jan 12 | | In-depth look at vSMP Foundation server virtualization technology, technical implementation, use cases and capabilities. The technical whitepaper provides an architectural overview and details on the three vSMP Foundation products: vSMP Foundation for SMP, vSMP Foundation for Cluster and vSMP Foundation for Cloud.
Jan 18 | | This white paper discusses Gore’s copper cable assemblies, and how they continue to exceed the standards for providing reliable, cost-effective solutions for high-performance computer applications.
Join this online panel discussion for live Q&A with leading industry experts, analysts, and end-users to discuss the latest innovations, best practices, barriers to implementation, and measurable benefits of server virtualization with a particular focus on today's real world solutions.
Learn about scalable fault-tolerant architectures and examples of energy efficient and scalable supercomputing clusters using dual QDR InfiniBand to combine capacity computing with network failover capabilities with the help of programming languages such as MPI and a robust Linux cluster management package.
LIVE@SCO9: The IBM team discusses new innovations in hardware, software and services that help clients better understand their workloads and get insight from their R&D efforts. Technology demonstrations include the soon-to-be-released Power7 HPC processor, the DCS990 system with 2.4 petabytes of storage, the xCAT management tool, secure HPC cloud computing and more. Winners of two HPCwire Readers' and Editors’ Choice Awards! Take the IBM virtual tour at SC09 or more information go online to: http://www-03.ibm.com/systems/deepcomputing/sc09.html