BROADCOM AND ARM EXTEND RELATIONSHIP WITH STRATEGIC LICENSING AGREEMENT
By Nick Flaherty www.flaherty.co.uk
Broadcom has taken a broad license to all ARM's processor cores in a move that is fundamentally more important for the embedded market than the recent Microsoft announcement.
Broadcom now has access the entire range of ARM processors, from the smallest, lowest-power ARM CortexTM-M0 processor, through to the newly introduced, high-performance Cortex-A15 application processor and beyond. As Broadcom is pushing the system-on-chip approach strongly into the embedded market, this will see a lot more 32bit ARM cores in designs that traditionally used 16bit processors, as well as high end smartphone chips to take on Qualcomm and in highly integrated networking devices.
As part of the agreement Broadcom has access to both current and future ARM processors to use across product lines. This includes the Cortex-A15 processor for use in high performance mobile and networking applications, the specialized security hardened SC000 processor core for security applications, and the newly announced Cortex-R5 and Cortex-R7 processors for high performance real-time applications.
“ARM’s wide portfolio of cores enhances Broadcom’s strategy of designing cost- optimized high performance solutions for a wide range of applications from Bluetooth headsets to high-end application processors for tablets,” said Scott McGregor, President and CEO of Broadcom. “Broadcom and ARM have already established a successful partnership in smartphones and other exciting mobile devices. Today’s agreement will help expand that success into many new and exciting high-growth opportunities.”
“The growing partnership with Broadcom brings new opportunities” said Warren East, CEO, ARM. “Broadcom’s strength across diverse markets and their expertise in highly integrated systems brings a breadth of knowledge to the ARM Partnership. Our expanded relationship shows the universal benefits that scalable, low-power ARM IP can bring to market leading solutions across a wide range of end devices and equipment.”
All the latest quantum computer articles
See the latest stories on quantum computing from eeNews Europe
Showing posts with label multicore. Show all posts
Showing posts with label multicore. Show all posts
Tuesday, February 15, 2011
Friday, December 17, 2010
Moving multicore to embedded is key to US competitiveness
By Nick Flaherty www.flaherty.co.uk
The rapid advances in information technology that drive many sectors of the US economy could stall unless there is significant fundamental research and development of parallel computing, says a new report by the National Research Council -- which will drive the move to embedded multicore systems.
The rapid advances in information technology that drive many sectors of the US economy could stall unless there is significant fundamental research and development of parallel computing, says a new report by the National Research Council -- which will drive the move to embedded multicore systems.
Better options for managing power consumption in computers will also be essential for continued improvements in IT performance.
Advances in single-processor, sequential computer microprocessors have enabled computing performance to increase dramatically -- on the order of 10,000 times in the last 20 years but power management and other technological limitations have made it impractical to continue improving computer performance in this way much longer. Parallel computing, therefore, is the only known alternative for improving computer performance without significantly increasing costs and energy usage, the report says.
"The societal and economic impact of computer technology is undeniable, increasing productivity and efficiency and fostering innovation in medicine, defense, entertainment, and communications," said Samuel Fuller, chief technology officer and vice president of research and development for Analog Devices and chair of the committee that wrote the report. "To ensure that computing systems continue to double in performance every few years, we need to make significant changes in computer software and hardware. Investing in research and development of parallel computing offers a clear path forward."
Despite some mainstream successes in parallel computing -- such as the MapReduce programming framework used by Google to process large data sets using thousands of computers -- most parallel computing in use now is limited to comparatively narrow scientific and engineering applications. To enable parallel computing for broader use, new algorithms, programming models, operating systems, and computer architectures will be required, the report says, and research and development in these areas should be pursued.
In particular, advances are necessary to develop new parallel programming methods and supporting computing systems. Although computing hardware such as semiconductor chips that contain eight or more microprocessors have already been developed, software that can keep that many or more processors busy in parallel is not available for most computing applications.
Research and development should also focus on making computer systems more energy efficient, the report says. Power constraints now affect systems ranging from handheld devices to the largest computing data centres. Most computer chips are designed with silicon-based complementary metal oxide semiconductor (CMOS) technology. While the number of devices per CMOS chip continues to double every few years, the technology has essentially reached its limits with regard to power efficiency. Even as new parallel computing models and solutions are found, most future performance will ultimately be limited by energy constraints, the report notes.
It cautions that while parallel computing is the best alternative for improving future performance, there is no guarantee that it will bring rapid advances like those experienced in recent decades, and a number of uncertainties still need to be addressed. Therefore, research and development should also explore fundamentally different alternatives to today's CMOS technology.
The report also recommends developing open interface standards for parallel programming to promote cooperation and innovation in the industry, designing tools and methods for transferring today's sequential computing to parallel applications, and emphasizing parallel computing as part of computer science education.
"The societal and economic impact of computer technology is undeniable, increasing productivity and efficiency and fostering innovation in medicine, defense, entertainment, and communications," said Samuel Fuller, chief technology officer and vice president of research and development for Analog Devices and chair of the committee that wrote the report. "To ensure that computing systems continue to double in performance every few years, we need to make significant changes in computer software and hardware. Investing in research and development of parallel computing offers a clear path forward."
Despite some mainstream successes in parallel computing -- such as the MapReduce programming framework used by Google to process large data sets using thousands of computers -- most parallel computing in use now is limited to comparatively narrow scientific and engineering applications. To enable parallel computing for broader use, new algorithms, programming models, operating systems, and computer architectures will be required, the report says, and research and development in these areas should be pursued.
In particular, advances are necessary to develop new parallel programming methods and supporting computing systems. Although computing hardware such as semiconductor chips that contain eight or more microprocessors have already been developed, software that can keep that many or more processors busy in parallel is not available for most computing applications.
Research and development should also focus on making computer systems more energy efficient, the report says. Power constraints now affect systems ranging from handheld devices to the largest computing data centres. Most computer chips are designed with silicon-based complementary metal oxide semiconductor (CMOS) technology. While the number of devices per CMOS chip continues to double every few years, the technology has essentially reached its limits with regard to power efficiency. Even as new parallel computing models and solutions are found, most future performance will ultimately be limited by energy constraints, the report notes.
It cautions that while parallel computing is the best alternative for improving future performance, there is no guarantee that it will bring rapid advances like those experienced in recent decades, and a number of uncertainties still need to be addressed. Therefore, research and development should also explore fundamentally different alternatives to today's CMOS technology.
The report also recommends developing open interface standards for parallel programming to promote cooperation and innovation in the industry, designing tools and methods for transferring today's sequential computing to parallel applications, and emphasizing parallel computing as part of computer science education.
Related articles
- Future computing boosts will need a revolution (newscientist.com)
- CUDA by Example: An Introduction to General-Purpose GPU Programming, Published By Addison-Wesley Professional (eon.businesswire.com)
- Nvidia looks to the future of GPU computing (zdnet.co.uk)
- Who Wants Parallel Computers? (rjlipton.wordpress.com)
Monday, November 08, 2010
Marvell takes ARM into the enterprise cloud with quad core chip
By Nick Flaherty www.flaherty.co.uk
While attention has been focussed on startup SmoothStone for enterprise computing on the ARM chip platform, Marvell has done its usual job of working away quietly and then coming up with a key device.
It has launched a quad-core processing, enterprise-class cloud computing platform based on its own spin of the the ARM architecture. At 1.6GHz the ARMADA XP is the fastest ARM processor available on the market today for enterprise class applications and integrates four Marvell designed ARM compliant 1.6GHz CPU cores along with a range of I/O peripherals and is aiming at delivering the best performance per watt to empower emerging cloud computing applications ranging from high performance networking and web servers to high volume home server products like Network Attached Storage (NAS) and media servers.
Using ARM for the cloud is a smart move as the low power tackles on e of the key problems of the datacentre - heat dissipation. But it also avoids the problem of operating system - the cloud doesn't really care as long as it can run the application, and many of these are Linux-based.
"Marvell's introduction of a powerful solution for enterprise-class cloud computing applications is a very important milestone in the mobile Internet revolution—cloud computing mobile servers like those powered by the ARMADA XP are the key link in what I envision to be a seamless, unified ecosystem of mobile connected devices, information appliances and smart 'furnishings,'" said Weili Dai, Co-Founder of Marvell. "Marvell's leadership in mobility, consumer, storage, enterprise networking and Wi-Fi products completes the circuit, delivering a powerful end-to-end total solution to anyone connected to the new global mesh, from consumers to small business and the enterprise."
The ARMADA XP supplements the Marvell Plug Computer initiative by enabling a new class of mobile servers to serve the growing performance demands of connected consumer devices like smartphones and tablets.
The ARMADA XP is based on Marvell-designed ARM v7 MP compatible CPU offering 1.6GHz processing per core performance, delivering 16,600 DMIPS to make high performance computing affordable for mainstream applications. It integrates 2 MB of L2 cache and supports 64-bit DDR3 memory interface with ECC at 800MHz clock rate to enable a high throughput memory sub-system design. The ARMADA XP is a highly integrated System-on-a-Chip (SoC) that combines quad x4 PCI-express (PCI-e) interfaces, multiple USB ports, Gigabit Ethernet ports, SATA ports, security engine and other I/O peripherals to make system designs simple and economical. With ARMADA XP's advanced power management architecture, it offers the industry's best performance per watt to alleviate the challenges of energy and cooling costs faced by enterprise and server class systems.
Key Features
Marvell offers complete development platforms for the ARMADA XP enabling customers to start system development without waiting for hardware. Development platforms are available including software drivers and board support package.
While attention has been focussed on startup SmoothStone for enterprise computing on the ARM chip platform, Marvell has done its usual job of working away quietly and then coming up with a key device.
It has launched a quad-core processing, enterprise-class cloud computing platform based on its own spin of the the ARM architecture. At 1.6GHz the ARMADA XP is the fastest ARM processor available on the market today for enterprise class applications and integrates four Marvell designed ARM compliant 1.6GHz CPU cores along with a range of I/O peripherals and is aiming at delivering the best performance per watt to empower emerging cloud computing applications ranging from high performance networking and web servers to high volume home server products like Network Attached Storage (NAS) and media servers.
Using ARM for the cloud is a smart move as the low power tackles on e of the key problems of the datacentre - heat dissipation. But it also avoids the problem of operating system - the cloud doesn't really care as long as it can run the application, and many of these are Linux-based.
"Marvell's introduction of a powerful solution for enterprise-class cloud computing applications is a very important milestone in the mobile Internet revolution—cloud computing mobile servers like those powered by the ARMADA XP are the key link in what I envision to be a seamless, unified ecosystem of mobile connected devices, information appliances and smart 'furnishings,'" said Weili Dai, Co-Founder of Marvell. "Marvell's leadership in mobility, consumer, storage, enterprise networking and Wi-Fi products completes the circuit, delivering a powerful end-to-end total solution to anyone connected to the new global mesh, from consumers to small business and the enterprise."
The ARMADA XP supplements the Marvell Plug Computer initiative by enabling a new class of mobile servers to serve the growing performance demands of connected consumer devices like smartphones and tablets.
The ARMADA XP is based on Marvell-designed ARM v7 MP compatible CPU offering 1.6GHz processing per core performance, delivering 16,600 DMIPS to make high performance computing affordable for mainstream applications. It integrates 2 MB of L2 cache and supports 64-bit DDR3 memory interface with ECC at 800MHz clock rate to enable a high throughput memory sub-system design. The ARMADA XP is a highly integrated System-on-a-Chip (SoC) that combines quad x4 PCI-express (PCI-e) interfaces, multiple USB ports, Gigabit Ethernet ports, SATA ports, security engine and other I/O peripherals to make system designs simple and economical. With ARMADA XP's advanced power management architecture, it offers the industry's best performance per watt to alleviate the challenges of energy and cooling costs faced by enterprise and server class systems.
Key Features
- Industry's first quad-core ARM processor for enterprise applications
- Up to 1.6GHz processing performance for each ARM v7 compliant core
- 16,600 DMIPS performance at less than 10 watts
- "Heterogeneous multiprocessing" (SMP/AMP/Mixed) with "hardware-based Cache Coherence"
- Up to 2MB system level two cache
- Supplements the ARMADA family of single, dual-core and tri-core processors for easy software porting
- 64-bit DDR2/DDR3/DDR3L memory interface with ECC support at up to 800MHz clock rates
- 4 PCI-e Gen 2.0 units
- 4 enterprise class Gigabit networking ports
- Up to 16 high speed Marvell SERDES lanes with multi functionality (PCI-e, SATA, SGMII, QSGMII)
- Multiple USB ports
- Ultra low power consumption with advanced power management capabilities
Marvell offers complete development platforms for the ARMADA XP enabling customers to start system development without waiting for hardware. Development platforms are available including software drivers and board support package.
Related articles
- Marvell unveils 1.6GHz quad-core Armada XP processor for cloud computing (slashgear.com)
- Marvell's 1.5GHz, Triple Core ARM Processor Can Handle 140 Hours of Music on One Charge [Guts] (gizmodo.com)
- Tri-core, 1.5GHz ARM SoC touted for 1080p 3D video (linuxfordevices.com)
Monday, August 16, 2010
Sundance ships 12 core development system
Customer shipment three months after launch
By Nick Flaherty www.flaherty.co.uk
Sundance Multiprocessor Technology in Chesham, outside London, has started shipping its flagship multiprocessor development system to a customer three months after adding the system to its website.
The EVP6472-941 (left) is directly targeted at the new breed of high intensity processing applications where performance and energy efficiency are critical. Early adopter applications include digital recording, software defined radio (SDR), software reconfigurable applications in signals intelligence (SIGINT) and military communications (MILCOM) platforms.
The US$5,995 system uses two Texas Instruments (TI) TMS320C6472 multicore DSPs with twelve TMS320C64x+ processor cores clocked at 500MHz for real time processing tasks. A Xilinx Virtex-5 FX30T FPGA provides the co-processor, with an embedded PowerPC440 processor core and a quad channel 14-bit ADC sampling at up to 250 MSPS. The EVP6472-941 offers two DDR2 SDRAM memory banks of 256MB assessable by each C6472 processor.
The EVP6472-941 is supplied with a complete board support package including the USB drivers, software functions and API for Windows. Essential tools are TIs Code Composer Studio 4.x that is supplied free of charge with the XDS100 USB JTAG Emulator for the C6472 DSP processor. Xilinx ISE development software can be downloaded from xilinx.com to target the Virtex-5 FX30T FPGA.
A range of third party design tools for TI DSP and Xilinxs FPGA also support the EVP6472-941; including 3Ls Diamond Multiprocessor Tool-Suite, RTW-EC and HDLCoder from The MathWorks, comprehensive VHDL and Verilog support from EDA vendors, and Co-Developer and a growing range of IP-Cores from Impulse.
Extensive general purpose input/output (GPIO) connectors are available with the EVP6472-941. Sundance Local Bus (SLB) interface to customize input/output (I/O) signals, four RS-232 ports, Gigabit Ethernet connection, LVTTL lines for synchronization, MicroSD Flash socket as an extension of the on-board Flash memories and JTAG headers to enable DSP and FPGA debugging.
"As we continue to see an uptick in business confidence and design starts, the launch of the EVP6472-941 signals a new generation of high intensity platform solutions architected around the C6472," said Flemming Christensen, Managing Director of Sundance Multiprocessor Technology Ltd. "Development of the EVP6472-941 reflects the strength of our collaboration with TI. As we roll out the new family of Multicore Developer Platforms (MDPs), customers will have even greater flexibility to configure a platform solution that fits their power, performance and cost budgets."
By Nick Flaherty www.flaherty.co.uk
Sundance Multiprocessor Technology in Chesham, outside London, has started shipping its flagship multiprocessor development system to a customer three months after adding the system to its website.
The EVP6472-941 (left) is directly targeted at the new breed of high intensity processing applications where performance and energy efficiency are critical. Early adopter applications include digital recording, software defined radio (SDR), software reconfigurable applications in signals intelligence (SIGINT) and military communications (MILCOM) platforms.
The US$5,995 system uses two Texas Instruments (TI) TMS320C6472 multicore DSPs with twelve TMS320C64x+ processor cores clocked at 500MHz for real time processing tasks. A Xilinx Virtex-5 FX30T FPGA provides the co-processor, with an embedded PowerPC440 processor core and a quad channel 14-bit ADC sampling at up to 250 MSPS. The EVP6472-941 offers two DDR2 SDRAM memory banks of 256MB assessable by each C6472 processor.
The EVP6472-941 is supplied with a complete board support package including the USB drivers, software functions and API for Windows. Essential tools are TIs Code Composer Studio 4.x that is supplied free of charge with the XDS100 USB JTAG Emulator for the C6472 DSP processor. Xilinx ISE development software can be downloaded from xilinx.com to target the Virtex-5 FX30T FPGA.
A range of third party design tools for TI DSP and Xilinxs FPGA also support the EVP6472-941; including 3Ls Diamond Multiprocessor Tool-Suite, RTW-EC and HDLCoder from The MathWorks, comprehensive VHDL and Verilog support from EDA vendors, and Co-Developer and a growing range of IP-Cores from Impulse.
Extensive general purpose input/output (GPIO) connectors are available with the EVP6472-941. Sundance Local Bus (SLB) interface to customize input/output (I/O) signals, four RS-232 ports, Gigabit Ethernet connection, LVTTL lines for synchronization, MicroSD Flash socket as an extension of the on-board Flash memories and JTAG headers to enable DSP and FPGA debugging.
"As we continue to see an uptick in business confidence and design starts, the launch of the EVP6472-941 signals a new generation of high intensity platform solutions architected around the C6472," said Flemming Christensen, Managing Director of Sundance Multiprocessor Technology Ltd. "Development of the EVP6472-941 reflects the strength of our collaboration with TI. As we roll out the new family of Multicore Developer Platforms (MDPs), customers will have even greater flexibility to configure a platform solution that fits their power, performance and cost budgets."
Related articles
- Xilinx Showcases End Market Solutions Based on LabVIEW FPGA at NIWeek 2010 (prnewswire.com)
- Software Defined Radio, Signals Intelligence, Tactical Communications And Radar Applications To Benefit From New GE FPGA Boards (eon.businesswire.com)
- Analog Devices Simplifies Wireless Infrastructure System Design with Mixed-Signal, Digital Pre-Distortion Development Platform Using Xilinx FPGAs (eon.businesswire.com)
Friday, May 28, 2010
Infineon Bristol wins two major European projects
By Nick Flaherty www.flaherty.co.uk
Infineon's design centre in Bristol is part of two of the largest R&D projects in Europe for the multicore development for automotive and safety critical systems alongside embedded software house Wittenstein High Integrity Systems (HIS). The involvement in the two multimillion euro ARTEMIS projects is covered in the current issue of SiliconSouthWest. With over 50 silicon designers, Infineon's Bristol centre will be working on new multicore versions of its TriCore microcontroller for a European electric car design based on real time embedded technology and for safety critical systems. For the safety elements, the design of the controller has to be fully documented and verified with new safety critical design techniques developed.
The €26m RECOMP project is looking at the isolation of safety-critical parts of systems using multicore technology, allowing software updates without the need for re-certification. There are 41 participants from 8 countries, with Wittenstein HIS in Bristol and the UK arm of Thales alongside Delphi, TUV SUD, EADS and Intel.
Infineon is working on a dual core version of its TriCore microcontroller for several of the demonstrators being developed in the three year project. These will cover automotive, aerospace, industrial control systems, lifts and transportation systems. The project aims to provide reference designs and platform architectures, together with the required design methods and tools, for achieving cost-effective certification and re-certification of mixed-criticality, component based, multicore systems for a European standard reference technology.
The €36m POLLUX project aims to develop the architecture, component design and prototyping of a electric/hybrid vehicle embedded systems architecture. The project - Process Oriented Electrical Control Units for Electrical Vehicles Developed on a multi-system real-time embedded platform - has 35 participants from 12 countries and is led by Fiat alongside ST Microelectronics, NXP, ON Semi, Continental, PSA Peugeot Citroen and Thales. Other UK organisations involved are QinetiQ and the University of Sheffield.
The Bristol Design Centre will be working on the specifications, design and development of another multicore microcontroller architecture, again based on TriCore, producing chips for the subsystems and demonstrators in the next two years.
Infineon's design centre in Bristol is part of two of the largest R&D projects in Europe for the multicore development for automotive and safety critical systems alongside embedded software house Wittenstein High Integrity Systems (HIS). The involvement in the two multimillion euro ARTEMIS projects is covered in the current issue of SiliconSouthWest. With over 50 silicon designers, Infineon's Bristol centre will be working on new multicore versions of its TriCore microcontroller for a European electric car design based on real time embedded technology and for safety critical systems. For the safety elements, the design of the controller has to be fully documented and verified with new safety critical design techniques developed.
The €26m RECOMP project is looking at the isolation of safety-critical parts of systems using multicore technology, allowing software updates without the need for re-certification. There are 41 participants from 8 countries, with Wittenstein HIS in Bristol and the UK arm of Thales alongside Delphi, TUV SUD, EADS and Intel.
Infineon is working on a dual core version of its TriCore microcontroller for several of the demonstrators being developed in the three year project. These will cover automotive, aerospace, industrial control systems, lifts and transportation systems. The project aims to provide reference designs and platform architectures, together with the required design methods and tools, for achieving cost-effective certification and re-certification of mixed-criticality, component based, multicore systems for a European standard reference technology.
The €36m POLLUX project aims to develop the architecture, component design and prototyping of a electric/hybrid vehicle embedded systems architecture. The project - Process Oriented Electrical Control Units for Electrical Vehicles Developed on a multi-system real-time embedded platform - has 35 participants from 12 countries and is led by Fiat alongside ST Microelectronics, NXP, ON Semi, Continental, PSA Peugeot Citroen and Thales. Other UK organisations involved are QinetiQ and the University of Sheffield.
The Bristol Design Centre will be working on the specifications, design and development of another multicore microcontroller architecture, again based on TriCore, producing chips for the subsystems and demonstrators in the next two years.
Thursday, May 27, 2010
STMicro brings SMP ARM multicore to embedded
Symmetrical ARM Cortex multiprocessor architecture with DDR3 delivers cost efficiency, computing power and customizability for multiple embedded applications
By Nick Flaherty www.flaherty.co.uk
Leveraging its experience of the production-proven SPEAr300 and SPEAr600 lines, the new SPEAr1300 product line couples dual ARM Cortex-A9 processors with a DDR3 memory interface and is manufactured in ST’s low-power 55nm HCMOS (high-speed CMOS) process technology.
The dual ARM Cortex-A9 processors support fully symmetrical operation, at speeds up to 600MHz/core for 3000 DMIPS equivalent.
The SPEAr1300 makes use of ST’s innovative Network-on-Chip technology for internal peripheral interconnect, assuring support for multiple different traffic profiles, while maximizing data throughput in the most cost-effective and power-efficient way. Initial sampling has already started to early adopters.
The new architecture offers industry-leading performance in terms of DMIPS/MHz and power consumption/DMIPS ratios, in addition to cost efficiency and customizability advantages. The availability of integrated DDR3 memory controller and a full set of connectivity peripherals like PCIe, SATA, USB and Ethernet, among other features, make the SPEAr1300 the ideal choice for high-performance applications including networking, thin client, videoconferencing, NAS (Network-Attached Storage), computer peripherals, and factory automation.
“This new architecture for the SPEAr family builds upon the unrivalled low power and multiprocessing capabilities of the ARM Cortex-A9 processor core” said Loris Valenti, General Manager of ST’s Computer Systems SoC Division. “Upcoming SPEAr embedded microprocessors will deliver an unprecedented combination of processing performance, memory throughput, flexibility and low power for next-generation connectivity appliances.”
Key features:
- Dual ARM Cortex-A9 cores, running at 600MHz for 3000 DMIPS equivalent
- 64-bit AXI (AMBA3) bus Network-on-Chip technology
- DRAM and L2 cache with Error Correction Code (ECC)
- 533MHz 32-bit DDR3 memory controllers with ECC; 16-bit DDR2 also supported
- Accelerator coherence port
- Gigabit Ethernet
- PCIe 2.0 supporting 5 GT/s (Gigatransfers/second)
- SATA II 3 Gbit/s
- USB 2.0
- 256-bit key hardware encryption/decryption
- 1.3 million gates of configurable logic
Embedded microprocessors from the new SPEAr1300 product line will be announced over the next few months, expanding ST’s SPEAr family and providing an extensive choice for leading customers.
Related articles
- Dust Networks Announces ARM Cortex-M3 Processor Based IEEE 802.15.4 SoC (eon.businesswire.com)
- Intel's NAS-specific Atom platform hastens PCification (arstechnica.com)
- COM Express module sports 32nm processors (linuxfordevices.com)
Friday, April 30, 2010
NetLogic Microsystems and TSMC Collaborate on 28nm Process Technology
Includes analogue capability for high speed interfaces
As an early development partner, NetLogic is using TSMC’s 28nm node to raise networking infrastructure performance and significantly differentiating its product line from the competition.In June 2009 Netlogic bought RMI (Raza Microsystems) to add a range of high performance multicore network processors to its range.
NetLogic has launched advanced product development for multiple industry-leading product lines on the TSMC 28nm node. The 28HP process offers significant speed, and power efficiency advantages over previous process nodes. In addition, NetLogic Microsystems is developing a suite of custom high-performance circuits optimized around TSMC’s 28nm node, including high-speed serial interface technology, analogue and clocking circuitry, core processing elements and other standard cells, as well as refining the design and tape-out flow for this advanced node.
“By being a consistent early adopter across four generations of process technology, NetLogic Microsystems has consistently provided very high performance and low power products for mission-critical network infrastructure systems,” said Rick Cassidy, president of TSMC North America. “We welcome the extension of our close relationship to include NetLogic Microsystems’ role as an 28nm early technology adopter.”
“We are proud to have been one of the early partners for TSMC in 80nm, 55nm, 40nm and now 28nm for our best-in-class knowledge-based processors, multi-core processors and 10/40/100 Gigabit PHY product families,” said Ron Jankov, president and CEO at NetLogic Microsystems. “By combining the superior design and architecture of our products with TSMC’s proven leadership and track record in advanced manufacturing technologies, we are able to deliver highly innovative products with unprecedented performance, scalability and energy efficiency to our customers.”
NetLogic Microsystems offers high-performance multi-core, multi-threaded processors, knowledge-based processors, content processors, and high-speed 10/40/100 Gigabit Ethernet PHY solutions. These market-leading products are designed into high-performance systems such as switches, routers, wireless base stations, security appliances, networked storage appliances and service gateways to significantly enhance the performance and functionality of next-generation 3G/4G mobile wireless infrastructure, data center, enterprise, metro Ethernet, edge and core infrastructure networks.
Related articles by Zemanta
- NetLogic Microsystems Showcases High-Performance Networking Silicon Leadership at Embedded Systems Conference/MultiCore Expo and Interop 2010 (eon.businesswire.com)
- NetLogic Microsystems Achieves 400th Issued U.S. Patent (eon.businesswire.com)
- NetLogic Microsystems' Industry-Leading Product Portfolio Powers LTE Trials Worldwide (eon.businesswire.com)
- ZTESec Selects NetLogic Microsystems for Intelligent Layer 7 Network Interface Cards (NICs) for Server and Storage Cloud-Computing Applications (eon.businesswire.com)
- NetLogic Microsystems Enables Significantly Richer LTE and IPTV Network Services with the World's First Knowledge-based Processor with High-Speed Serial Interface (eon.businesswire.com)
Tuesday, April 27, 2010
CriticalBlue and Freescale collaborate to streamline and simplify multicore software development
CriticalBlue’s Prism development environment now available for QorIQ multicore processors
CriticalBlue is working with Freescale Semiconductor to make its Prism development environment available to support Freescale’s QorIQ multicore processor families. Software developers will be able to migrate, optimise and verify their existing software applications on Freescale’s multicore platforms based on Power Architecture technology.
As communication equipment vendors migrate from single-core to multicore designs, they face the complex and time consuming task of rewriting their code to work with multiple cores. The addition of Prism support to Freescale’s QorIQ multicore ecosystem will help customers preserve the value of their legacy code while designing with new multicore platforms. The Prism tool helps eliminate guesswork by profiling the code base and suggesting which routines are best to leave in serial sequence and which ones are candidates for parallel sequencing across multiple cores. With this capability, Freescale customers are able to optimise their software code to achieve maximum hardware performance.
Related articles by Zemanta
- Freescale Unleashes Industry's Highest Performing DSP Core for Medical, Aerospace and Test (The Embedded Blog)
- New Strategic Alliances Strengthen and Expand Software Solutions for Freescale Processors (eon.businesswire.com)
- Wind River Tackles Increasing Network Congestion by Enabling Wire-Speed Application Throughput (eon.businesswire.com)
- Wind River Delivers Suite of Multi-architecture Embedded Software Development Tools (eon.businesswire.com)
Texas Instruments embraces Linux for C64x DSP processors
Reflects embedded industry move to open source
TI has announced Linux kernel support for its TMS320C64x digital signal processors (DSPs) and multicore system-on-chips (SoCs) targeted for applications such as communications and mission critical infrastructure, medical diagnostics, and high-performance test and measurement. As customers move towards open source initiatives as a key element of their products, application developers can benefit from the availability of Linux on TI’s DSPs by having less software to develop, and focusing more on differentiating features and software in their applications.
Availability
TI has announced Linux kernel support for its TMS320C64x digital signal processors (DSPs) and multicore system-on-chips (SoCs) targeted for applications such as communications and mission critical infrastructure, medical diagnostics, and high-performance test and measurement. As customers move towards open source initiatives as a key element of their products, application developers can benefit from the availability of Linux on TI’s DSPs by having less software to develop, and focusing more on differentiating features and software in their applications.
“TI’s C64x processors have an enviable footprint in signal processing oriented high-performance multicore applications,” said Olaf Soentgen of Nash Technologies. “The introduction of Linux support expands the utility of the C64x DSP processors into portions of these applications that traditionally have been reserved for RISC cores. We are taking advantage of Linux availability on TI’s SoC to lower the cost and simplify the development of femtocell base stations.”
TI’s C64x Linux effort is a community collaboration with considerable support already in place. As part of the effort to port the Linux kernel to the C64x ISA, Code Sourcery is developing a complete tool chain including support for the GNU Compiler Collection (GCC) and the GNU Project Debugger (GDB). The project’s goal is that both the C64x Linux kernel and the GCC / GDB tools will be accepted by kernel.org and the Free Software Foundation, making both fully supported as open source community projects. In addition, TI will sponsor a Linux-C64x portal and a community-oriented distribution program to facilitate communication and development around this technology. ENEA is making its open source, scalable multicore communications stack available to the C64x Linux community, as well as offering advanced multicore platform software and debugging tools. Nash Technologies is implementing features ranging from advanced chip level functions, such as multicore interprocessor communications, to complete LTE protocols. PolyCore Software, also an early community participant, is implementing the MCAPI multicore communications framework.
TI’s C64x Linux effort is a community collaboration with considerable support already in place. As part of the effort to port the Linux kernel to the C64x ISA, Code Sourcery is developing a complete tool chain including support for the GNU Compiler Collection (GCC) and the GNU Project Debugger (GDB). The project’s goal is that both the C64x Linux kernel and the GCC / GDB tools will be accepted by kernel.org and the Free Software Foundation, making both fully supported as open source community projects. In addition, TI will sponsor a Linux-C64x portal and a community-oriented distribution program to facilitate communication and development around this technology. ENEA is making its open source, scalable multicore communications stack available to the C64x Linux community, as well as offering advanced multicore platform software and debugging tools. Nash Technologies is implementing features ranging from advanced chip level functions, such as multicore interprocessor communications, to complete LTE protocols. PolyCore Software, also an early community participant, is implementing the MCAPI multicore communications framework.
“Our customers are rapidly moving towards open source as a critical element of their solutions,” said Brian Glinsman, general manager of TI’s communications infrastructure business. “Because of the C64x-basedDSP processors’ low power consumption and cost effectiveness, customers are interested in running traditional DSP MAC/PHY and codec algorithms as well as classic RISC control code and protocols on our DSPs. TI’s embracing of Linux and an open tool chain for the industry workhorse C64x DSP processor makes this kind of integration practical.”
Availability
Product support for the C64x Linux kernel will be available for TI’s TMS320C6472, TMS320C6474, TMS320C6455 and TMS320C6457 DSP processors in 3Q10.
Related articles
- Why Linux Is Not Attracting Young Developers (linux.slashdot.org)
- Low-Impact Operating System Tracing (google-opensource.blogspot.com)
- Android and Linux Discuss Code Reunion (readwriteweb.com)
- Anatomy of Linux Kernel Shared Memory (linux.slashdot.org)
- Linux Kernel is Worth $1.4 Billion (teabreak.pk)
- Google in talks to re-admit Android to Linux kernel (go.theregister.com)
Monday, December 21, 2009
Step forward for multicore Linux
CriticalBlue and MontaVista Partner to Expand Multicore Software Development
CriticalBlue, the Edinburgh-based pioneer of embedded multicore software analysis, exploration and verification tools, has joined the MontaVista partner program and will make their Prism product available on MontaVista Linux 6 and Montavista Linux Carrier Grade Edition products.
This announcement continues the broadening of Prism integrations with key players in the multicore software development eco-system by adding support for an industrial strength, commercial quality Linux. Prism is an award-winning embedded multicore programming system which allows software engineers to easily asses and realize the full potential of multicore processors without significant change to their development flow. It analyzes the behavior of code running on either hardware development boards or simulators. It allows engineers to take their existing sequential code, and without making any changes, explore and analyze opportunities for concurrency. Having identified the optimal parallelization strategy in this way, the developer will implement parallel structures, and use Prism again to verify efficient and thread-safe operations.
MontaVista Linux is the first commercial Linux provider to be supported by Prism. The Prism Eclipse plug-in will be integrated into the MontaVista DevRocket integrated development environment (IDE), providing the most advanced embedded Linux development environment for multicore software on the market. MontaVista customers will now be able to quickly analyze the potential benefit of new, high-performance, multicore software platforms for their existing application code and develop new code and quickly tune it for operation on multicore processors, all within a single MontaVista DevRocket environment, and all in the familiar Eclipse framework.
Prism is available today for ARM and MIPS cores with several other leading multicore processor architectures coming in Q1 2010.
CriticalBlue, the Edinburgh-based pioneer of embedded multicore software analysis, exploration and verification tools, has joined the MontaVista partner program and will make their Prism product available on MontaVista Linux 6 and Montavista Linux Carrier Grade Edition products.
This announcement continues the broadening of Prism integrations with key players in the multicore software development eco-system by adding support for an industrial strength, commercial quality Linux. Prism is an award-winning embedded multicore programming system which allows software engineers to easily asses and realize the full potential of multicore processors without significant change to their development flow. It analyzes the behavior of code running on either hardware development boards or simulators. It allows engineers to take their existing sequential code, and without making any changes, explore and analyze opportunities for concurrency. Having identified the optimal parallelization strategy in this way, the developer will implement parallel structures, and use Prism again to verify efficient and thread-safe operations.
MontaVista Linux is the first commercial Linux provider to be supported by Prism. The Prism Eclipse plug-in will be integrated into the MontaVista DevRocket integrated development environment (IDE), providing the most advanced embedded Linux development environment for multicore software on the market. MontaVista customers will now be able to quickly analyze the potential benefit of new, high-performance, multicore software platforms for their existing application code and develop new code and quickly tune it for operation on multicore processors, all within a single MontaVista DevRocket environment, and all in the familiar Eclipse framework.
Prism is available today for ARM and MIPS cores with several other leading multicore processor architectures coming in Q1 2010.
“Developers need to analyze their real world applications running on commercial Linux platforms like MontaVista Linux using common frameworks like Eclipse,” said David Stewart, CEO, CriticalBlue. “By partnering with MontaVista, and integrating with the MontaVista DevRocket IDE, Prism will support the broadest range of platforms on a commercial quality Linux, allowing our joint customers a way to rapidly ensure safe and timely migration of their software onto multicore platforms and efficient exploitation of the parallelism inherent within.”
“By combining CriticalBlue’s Prism solution, MontaVista Linux and MontaVista DevRocket, our customers will benefit from the most advanced multicore integrated development environment available for embedded Linux,” said Dan Cauchy, vice president, marketing at MontaVista Software. “This integrated environment will allow developers to quickly analyze, convert and tune sequential code into parallel code and harness the full capabilities of MontaVista Linux running on modern multicore processors.”
Subscribe to:
Posts (Atom)

