Ships Cyclone IV GX Transceiver Starter Kit
Altera Corporation has stared production shipments of its Cyclone IV FPGAs, providing roughly 20,000 gates (6K logic blocks) for as little as $3 in volume, or 50,000 gates (15K logic blocks) with built in transceivers for $6.
The Cyclone IV FPGAs are designed for cost-sensitive, small form-factor applications in the wireless, wireline, broadcast, industrial and consumer markets. These devices have a combination of low cost, 25 percent lower power compared to the previous generation of Cyclone products, and high functionality that addresses high-volume, low-cost serial protocol solution needs.
"By offering Cyclone IV GX FPGAs in production shipments up to six months earlier than competing products, our customers can realize the cost, power and unique board space benefits of these devices," said Luanne Schirrmeister, senior director of component marketing at Altera. "Also, the availability of our Starter Kit gives designers confidence knowing that Cyclone IV GX devices have proven to be interoperable with other PCI Express chip sets."
Customers can begin prototyping with the Cyclone IV GX Transceiver Starter Kit which features an EP4CGX15 FPGA with approximately 15K logic elements, 540 Kbits of RAM and two integrated 2.5Gbit/s transceivers. This lowest cost transceiver starter kit priced at $395 includes all the hardware, software, design examples and documentation necessary to easily develop an FPGA design for cost-sensitive applications. This kit also allows designers to measure the FPGA's low power consumption, test
the signal quality of the FPGA transceivers, and develop and test PCI Express 1.0 endpoint designs by using Altera's PCI Express hard intellectual property (IP). In addition, the kit can be used with the Quartus(r) II Web Edition design software where no license is required.
The smallest Cyclone IV devices, the EP4CE6 and the EP4CGX15, will start as low as $3 and $6 respectively for 250K unit quantities.
All the latest quantum computer articles
See the latest stories on quantum computing from eeNews Europe
Showing posts with label Programmable Logic. Show all posts
Showing posts with label Programmable Logic. Show all posts
Monday, March 29, 2010
Monday, March 01, 2010
Tabula Introduces Spacetime Programmable Logic Architecture
3D Architecture Enables New Category of Programmable Logic Devices
Santa Clara startup Tabula has introduced a groundbreaking programmable logic architecture that uses time as a third dimension to deliver unmatched capability and affordability. Tabula achieves this breakthrough by combining the Spacetime hardware that dynamically reconfigures logic, memory, and interconnect at multi-GHz rates with the Spacetime compiler that manages this ultra-rapid reconfiguration transparently. Tabula will use Spacetime to deliver 3-D devices that have significant density advantages and dramatically shorter interconnects when compared to FPGAs that use 2-D architectures. In addition, Tabula will deliver these benefits while preserving a traditional design methodology. As a result, Spacetime will enable a new class of programmable devices that combines the capability of an ASIC with the ease of use of an FPGA at price points suitable for volume production.
Santa Clara startup Tabula has introduced a groundbreaking programmable logic architecture that uses time as a third dimension to deliver unmatched capability and affordability. Tabula achieves this breakthrough by combining the Spacetime hardware that dynamically reconfigures logic, memory, and interconnect at multi-GHz rates with the Spacetime compiler that manages this ultra-rapid reconfiguration transparently. Tabula will use Spacetime to deliver 3-D devices that have significant density advantages and dramatically shorter interconnects when compared to FPGAs that use 2-D architectures. In addition, Tabula will deliver these benefits while preserving a traditional design methodology. As a result, Spacetime will enable a new class of programmable devices that combines the capability of an ASIC with the ease of use of an FPGA at price points suitable for volume production.
“The key to Spacetime and its many advantages is resolving the interconnect problem intrinsic to FPGAs,” said Steve Teig, Tabula’s President and CTO. “Almost 90% of the core area of FPGAs is devoted to the implementation and control of interconnect. Besides driving up die size and product cost, the long connections also limit performance and make timing closure more difficult. If you’re going to achieve a breakthrough in programmable capability and affordability, you have to make the interconnect more efficient, and that’s what Spacetime does.”
Tabula was founded by EDA pioneer Steve Teig and is led by Dennis Segers, former CEO of Matrix Semiconductor and former Senior Vice President and member of the board of directors at Xilinx. With support from premier venture capitalists including Greylock Partners, Benchmark Capital, New Enterprise Associates, Crosslink Capital, Balderton Capital, DAG Ventures, and Integral Capital, Tabula has over 80 patents granted around the Spacetime architecture with over 70 more pending. Tabula is developing a family of general-purpose 3PLD devices that are based on the Spacetime architecture. Tabula will initially target the programmable logic market but will also extend the benefits of programmability into markets that FPGAs cannot serve cost-effectively.
“The programmable logic market is one of the most profitable segments of the semiconductor industry,” said Dennis Segers, CEO of Tabula. “It was once one of the fastest growing as well, driven by rapid advancements in FPGA capability alongside Moore’s Law. Since 2000, however, there has been only incremental improvement in FPGA architectures and circuits from the market leaders, leaving programmable logic customers underserved and limiting growth for the industry segment. With the Spacetime architecture, Tabula will bring unprecedented value into the programmable logic space, restoring innovation into this formerly vibrant market and accelerating its growth.”
Spacetime Architecture Overview
A Spacetime device reconfigures on the fly at multi-GHz rates, executing each portion of a design in an automatically defined sequence of steps. Although manufactured using a standard CMOS process, Spacetime uses this ultra-rapid reconfiguration to make Time a third dimension, resulting in a 3-D device with multiple layers or folds in which computation and signal transmission can occur. Each fold performs a portion of the desired function and stores the result in place. When some or all of a fold is reconfigured, it uses the locally stored data to perform the next portion of the function. By rapidly reconfiguring to execute different portions of each function, a 3-D Spacetime device can implement a complex design using only a small fraction of the resources that would be required by an inherently 2-D FPGA. A designer can realize all of the benefits of 3-D within a familiar methodology using the Spacetime compiler that automatically maps standard RTL into Spacetime.
Related articles
Silicon Basis heads for FPGA test chip (ElectronicsWeekly)
- Xilinx Reports a Solid Quarter - Analyst Blog (benzinga.com)
- Altera Announces Fourth Quarter Results Sales Up Strongly (eon.businesswire.com)
Wednesday, July 29, 2009
Reconfigurable computing sees giant launch
With 96 high end FPGAs and 26 quad-core Nehalem Xeon processors, the world's largest and most powerful reconfigurable computer has been launched at the University of Florida.
Novo-G uses 96 Altera Stratix-III E260 devices, each with 768 18x18 multipliers, 254K logic elements and 204K registers, with 4.25GB of memory attached. These are housed in 24 GiDEL ProcStar-III quad-FPGA boards and supported by the 26 quad-core processors, 20Gb/s non-blocking DDR InfiniBand, GigE, and 576GB total RAM.
Novo-G will support a variety of tools, including vendor tools as well as various CHREC tools for formulation, design, translation, and execution. At the device level, Novo-G of course supports applications design with VHDL and Verilog, but also several high level ESL programming languages.
CHREC research equipment features a broad assortment of high-end FPGAs, accelerator boards, servers, clusters, and scalable systems. RC resources include those from AlphaData (boards), Altera (devices, boards, tools), Celoxica (boards), Cray (machines), DRC (machine, module), GiDEL (boards, tools), Nallatech (boards, cluster, tools), Pico Computing (boards), SGI (machines), SRC (machines), Tilera (GFE board), Xilinx (devices, boards, tools), and XtremeData (machines, modules).
Novo-G uses 96 Altera Stratix-III E260 devices, each with 768 18x18 multipliers, 254K logic elements and 204K registers, with 4.25GB of memory attached. These are housed in 24 GiDEL ProcStar-III quad-FPGA boards and supported by the 26 quad-core processors, 20Gb/s non-blocking DDR InfiniBand, GigE, and 576GB total RAM.
“Construction has been completed on the new Novo-G machine and it is now ready to support a variety of research experiments in CHREC for various projects and participants,” said Dr. Alan D. George, Professor of ECE and Director of the NSF Centre for High-performance Reconfigurable Computing (CHREC) at the University of Florida. “Novo-G is believed to be the most powerful reconfigurable computer in the known world, certainly at least the academic/research community and the FPGAs featured in Novo-G are among the most powerful available today.”
“Although Novo-G may at first sound like it only serves as a research machine in the HPC realm of reconfigurable computing (RC), in reality it supports equally well the HPEC (embedded) realm of RC,” he said. “The boards featured in Novo-G (GiDEL ProcStar-III) are themselves originally marketed and intended as embedded processing boards, each with four big FPGAs with many attached memory banks plus various other supporting devices. We happen to be putting and using more of them in a single machine than anyone has attempted before and researchers can focus on issues with a single FPGA, a set of two, three, or four FPGAs on a single board with fast streaming pipes between, or many FPGAs (up to 96) spanning multiple boards, as their needs require. Thus, Novo-G will be supporting RC research projects that span the HPC and HPEC sides.
Novo-G will support a variety of tools, including vendor tools as well as various CHREC tools for formulation, design, translation, and execution. At the device level, Novo-G of course supports applications design with VHDL and Verilog, but also several high level ESL programming languages.
“We have successfully ported the Impulse-C tool to this platform, the Altera FP Compiler is already in use in our work, and efforts are in progress to do the same for Mitrion-C, all with help from the board and associated tool vendors,” said Dr George “Efforts are in the works to port our CHREC performance tool (ReCAP) and its debug/verification sidekick to Novo-G, and our folks on RCML, Intermediate Fabrics, etc. also have plans for Novo-G.”
CHREC research equipment features a broad assortment of high-end FPGAs, accelerator boards, servers, clusters, and scalable systems. RC resources include those from AlphaData (boards), Altera (devices, boards, tools), Celoxica (boards), Cray (machines), DRC (machine, module), GiDEL (boards, tools), Nallatech (boards, cluster, tools), Pico Computing (boards), SGI (machines), SRC (machines), Tilera (GFE board), Xilinx (devices, boards, tools), and XtremeData (machines, modules).
Subscribe to:
Posts (Atom)