Tag Archives: multicore

MIT Research Team Speeds Chips with Internet Technology

Li-Shiuan Peh, an associate professor of electrical engineering and computer science at MIT, will present a paper at the 2012 Design Automation Conference in June. Peh and her colleagues will present a paper that summarizes ten years of research on networks on chip. In the paper, the researcher team established theoretical limits on the efficiency of packet-switched on-chip communication networks. In addition, they also presented measurements performed on a test chip in which they came very close to reaching several of those limits.

Continue reading

Freescale, CriticalBlue Team on Multicore Software Development

Freescale Semiconductor and CriticalBlue Limited have expanded their relationship with an alliance focused on streamlining embedded multicore software development for Freescale platforms. CriticalBlue’s Prism development environment will support a broader range of Freescale’s QorIQ and Power Architecture-based multicore products. In addition, the companies will co-develop tools, extensions and methods to help customers more easily migrate software developed for single core targets to multicore platforms, and to optimize parallel compute performance once the software has been migrated.

Continue reading

Applied Micro Circuits Unveils PacketPro Multicore Processor Family

Applied Micro Circuits Corporation (NASDAQ:AMCC), or AppliedMicro, announced its next-generation PacketPro[tm] multicore processor System-on-a-Chip (SoC) family, designed with advanced subsystem and offload acceleration hardware to enable new levels of security, high availability, low latency, and power management for embedded applications. PacketPro is AppliedMicro’s second-generation embedded processor SoC family and the first to feature offload of critical features for multiple PowerPC® processors with frequency capabilities ranging in performance from 600 MHz to 2.0 GHz and beyond.

Continue reading

Elektrobit, Infineon Team on Multicore Reference Implementation

EB (Elektrobit), a leading developer of cutting-edge embedded technology solutions for automotive and wireless industries, has developed a multicore reference implementation in collaboration with Infineon Technologies AG. The implementation is based on Infineon’s TriCore technology. The partners have also integrated an AUTOSAR 3.1-compliant Microcontroller Abstraction Layer (MCAL) for Infineon’s microcontrollers in the TriCore and XC2000 series into the EB tresos AutoCore basic software core. This means that a basic software core is now available that enables scalable software solutions according to the recommendations of the German manufacturer software initiative (Hersteller Initiative Software, HIS) and can thus reduce hardware costs.

Continue reading

Power Architecture Development Community Welcomes Enea

Power.org, the open collaborative organization that enables, develops and promotes standards for Power Architecture® technology, announced that Enea, a leader in multicore technology for communication-driven products, has joined the Power Architecture development community. Enea will add its knowledge to the collaborative effort advancing Power Architecture standards that enable high performance next generation solutions at lower costs and with faster development times. Enea is a world leader in the development of realtime operating systems (RTOS), hypervisors, development tools and interprocess communications technology (IPC) that simplify the transition to multicore processing platforms.

Continue reading

Wind River, Cavium Networks Team on Multicore Solutions for OCTEON

Wind River, a world leader in embedded and mobile software, and Cavium Networks (NASDAQ:CAVM), an industry-leading provider of highly integrated semiconductor products, announced a multi-year strategic partnership to co-market optimized VxWorks and Linux multicore solutions to networking and telecommunications customers worldwide. The companies will align long-term product roadmaps and Wind River will commercially support Cavium’s OCTEON® family of multicore processors through OCTEON II and a subsequent processor family with board support packages for Wind River’s diverse software portfolio.

Continue reading

Marvell Develops Quadruple Core Processor for ARM Instruction Set

Marvell (Nasdaq: MRVL), a worldwide leader in integrated silicon solutions, announced another breakthrough in advanced chip design: the world’s first “quadruple” core processor for applications utilizing the ARM instruction set. Building on a long and successful history of CPU core development and previous multicore implementations, Marvell’s achievement represents a milestone breakthrough for the ARM ecosystem with many positive implications for consumers. Based on the same CPU architecture as the Marvell® ARMADA(TM) 500 and 600 processor series, Marvell’s quadcore implementation can deliver gigahertz-plus processing per core and is designed for customer-specific products such as mass consumer market and high volume gaming applications.

Continue reading

Loongson Designs CPU with Synopsys CustomSim Circuit Simulator

Synopsys, Inc. (Nasdaq: SNPS), a world leader in software and IP for semiconductor design, verification and manufacturing, announced that Loongson Technology Co., Ltd. (Loongson) (funded by the Institute of Computing Technologies of the Chinese Academy of Sciences) achieved first-pass silicon success on its 65-nanometer, multicore, high-performance Loongson-3 CPU design using Synopsys’ CustomSim(TM) circuit simulator. The CustomSim solution was successfully deployed for timing and dynamic power simulation of advanced full-custom blocks, PLL, HyperTransport, register file, and content-addressable memory (CAM). The CustomSim solution’s SPICE-level precision and higher performance versus other FastSPICE tools enabled Loongson to achieve first-pass silicon success with 3x faster verification turnaround time.

Continue reading

MathWorks Upgrades Parallel Computing Toolbox

The MathWorks announced a new version of Parallel Computing Toolbox that now provides an improved distributed array construct to enable MATLAB users to directly access from a MATLAB session data that is stored on multicore computers or computer clusters. In addition, key algorithms in Statistics Toolbox and Communications Toolbox now execute faster when run in conjunction with Parallel Computing Toolbox.

Continue reading