a problem-oriented language requiring little knowledge of the computer on which it will be run
In the area of productivity, several projects are underway, crafting novel concepts for design of RC applications and systems, including new methods and tools for design formulation and prediction, hardware virtualization, module and core reuse, design verification and optimization, and programming with high-level languages.
an electronic device that performs an elementary logic operation
Each FPGA is a Stratix-III E260 device from Altera with 254K logic elements, 768 18x18 multipliers, and more than 4GB of DDR2 memory directly attached via three banks.
a United States Air Force defense laboratory responsible for discovering and developing and integrating fighting technologies for aerospace forces
In addition, several new collaborations have been inspired by Novo-G, with other research groups, for example, Boston University and the Air Force Research Laboratory, as well as tools vendors such as Impulse Accelerated Technologies and Mitrionics.
the procedure of calculating; determining something by mathematical or logical methods
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
the quality of being composed of relatively large particles
However, looking ahead more broadly, reconfigurable logic may be featured in future devices with a variety of structures, granularities, functionalities, etc., perhaps very similar to today's FPGAs or perhaps quite different.
a system of one or more computers and associated software with common storage
HPCwire: The new Novo-G reconfigurable computing system at the NSF Center for High-Performance Reconfigurable Computing (CHREC) has been up and running for just a few months.
an independent agency of the federal government responsible for the promotion of progress in science and engineering by supporting programs in research and education
In the U.S., the NSF Center for High-Performance Reconfigurable Computing (CHREC, pronounced "shreck"), acts as the research hub for RC, bringing together more than 30 organizations in this field.
(computer science) the part of a computer (a microprocessor chip) that does most of the data processing
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
In contrast, the structure of parallelism in reconfigurable-logic devices can be customized, that is, reconfigured, for each application or task on the fly, being versatile yet optimized specifically for each problem at hand.
Will RC be a niche solution in specific application areas or do you see this technology being used in general-purpose platforms that will be widely deployed?
In the U.S., the NSF Center for High-Performance Reconfigurable Computing (CHREC, pronounced "shreck"), acts as the research hub for RC, bringing together more than 30 organizations in this field.
It should be noted that RC, as a new paradigm of computing, is broader than FPGA acceleration for HPC. FPGA devices are the leading commercial technology available today that is capable of RC, albeit not originally designed for RC, and thus FPGAs are the focal point for virtually all experimental research and commercial deployments, with a growing list of success stories.
a person able to do a variety of different jobs acceptably well
Programmable fixed-logic devices no matter their form feature a "one size fits all" or "Jack of all trades" philosophy, with a predefined structure of parallelism, yet attempting to support all applications or some major subset.
By contrast, numerous research studies show that computing with reconfigurable-logic devices -- FPGAs, et al. -- is fundamentally superior in terms of speed and energy, due to the many advantages of adaptive, customizable hardware parallelism.
In the area of productivity, several projects are underway, crafting novel concepts for design of RC applications and systems, including new methods and tools for design formulation and prediction, hardware virtualization, module and core reuse, design verification and optimization, and programming with high-level languages.
George: On-going research projects at the four university sites of CHREC -- the University of Florida, Brigham Young University led by Dr. Brent Nelson, George Washington University led by Dr. Tarek El-Ghazawi, and Virginia Tech led by Dr. Peter Athanas -- fall into four categories: productivity, architecture, partial reconfiguration, and fault tolerance.
the practical application of science to commerce or industry
While there are a handful of commercial offerings from companies such as Convey Computer, XtremeData, GiDel, Mitrionics, and Impulse Accelerated Technologies, RC is still an area of active research.
a person whose occupation is to serve at table (as in a restaurant)
As principal challenges -- performance, productivity, and sustainability -- become more pronounced, and as R&D in RC progresses, we believe that the RC paradigm will mature and expand in its role and influence to eventually become dominant in a broad range of applications, from satellites to servers to supercomputers.
an inclination or desire; used in the plural in the phrase `left to your own devices'
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
a set whose members are members of another set; a set contained within another set
Programmable fixed-logic devices no matter their form feature a "one size fits all" or "Jack of all trades" philosophy, with a predefined structure of parallelism, yet attempting to support all applications or some major subset.
an instrumentality invented for a particular purpose
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
In the area of productivity, several projects are underway, crafting novel concepts for design of RC applications and systems, including new methods and tools for design formulation and prediction, hardware virtualization, module and core reuse, design verification and optimization, and programming with high-level languages.
Altogether, Novo-G features 96 of these FPGAs, with an upgrade underway that by January will double its RC capacity to 192 FPGAs via two coupled RC boards per server.
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
a person who makes use of a thing; someone who uses or employs something
We got the opportunity to ask Dr. George about the work going on at the Center and what he thinks RC technology can offer to high performance computing users.
the act of performing; of doing something successfully; using knowledge as distinguished from merely possessing it
In the U.S., the NSF Center for High-Performance Reconfigurable Computing (CHREC, pronounced "shreck"), acts as the research hub for RC, bringing together more than 30 organizations in this field.
However, looking ahead more broadly, reconfigurable logic may be featured in future devices with a variety of structures, granularities, functionalities, etc., perhaps very similar to today's FPGAs or perhaps quite different.
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
Each FPGA is a Stratix-III E260 device from Altera with 254K logic elements, 768 18x18 multipliers, and more than 4GB of DDR2 memory directly attached via three banks.
George: Naturally, as a relatively new paradigm of computing, RC has started with emphasis in a few targeted areas, for example, aerospace and bioinformatics, where missions and users require dramatic improvement only possible by a revolutionary approach.
electronic equipment consisting of a system of circuits
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
an independent agency of the federal government responsible for the promotion of progress in science and engineering by supporting programs in research and education
Founded in 2007, CHREC is a national research center under the auspices of the I/UCRC program of the National Science Foundation and consists of more than 30 academic, industry and government partners working collaboratively on research in this field.
CHREC is run by Dr. Alan George, who gave an address at the SC09 Workshop on High-Performance Reconfigurable Computing Technology and Applications (HPRCTA'09) on November 15.
Last but not least, as process densities increase and become more susceptible to faults, environments become harsher, and resources become more prone to soft or hard errors, research challenges arise in fault tolerance.
the atmosphere and outer space considered as a whole
George: Naturally, as a relatively new paradigm of computing, RC has started with emphasis in a few targeted areas, for example, aerospace and bioinformatics, where missions and users require dramatic improvement only possible by a revolutionary approach.
a mainframe computer that is one of the most powerful available at a given time
As principal challenges -- performance, productivity, and sustainability -- become more pronounced, and as R&D in RC progresses, we believe that the RC paradigm will mature and expand in its role and influence to eventually become dominant in a broad range of applications, from satellites to servers to supercomputers.
By contrast, numerous research studies show that computing with reconfigurable-logic devices -- FPGAs, et al. -- is fundamentally superior in terms of speed and energy, due to the many advantages of adaptive, customizable hardware parallelism.
relevance by virtue of being applicable to the matter at hand
However, we believe that inherent weaknesses of any fixed-logic device technology ... in terms of broad applicability at speed and energy efficiency, will eventually become limiting factors.
the process of becoming cooler; a falling temperature
As life-cycle costs of energy and cooling rise to approach and exceed that of software and hardware in total cost of ownership, these technologies may become unsustainable.
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
Thus, the second factor is taming this new paradigm of computing and innovations in its technologies, so that it is amenable to a broader range of users.
a workplace for the conduct of scientific research
In addition, several new collaborations have been inspired by Novo-G, with other research groups, for example, Boston University and the Air Force Research Laboratory, as well as tools vendors such as Impulse Accelerated Technologies and Mitrionics.
a point of convergence of light (or other radiation) or a point from which it diverges
It should be noted that RC, as a new paradigm of computing, is broader than FPGA acceleration for HPC. FPGA devices are the leading commercial technology available today that is capable of RC, albeit not originally designed for RC, and thus FPGAs are the focal point for virtually all experimental research and commercial deployments, with a growing list of success stories.
While there are a handful of commercial offerings from companies such as Convey Computer, XtremeData, GiDel, Mitrionics, and Impulse Accelerated Technologies, RC is still an area of active research.
a person trained in practical applications of the theory of electricity
Thus, as is natural for any new paradigm and set of technologies, design productivity is an important challenge at present for RC in general and FPGA devices in particular, so that HPC users, and others, can take full advantage without having to be trained as electrical engineers.
the distribution of forces in preparation for battle or work
It should be noted that RC, as a new paradigm of computing, is broader than FPGA acceleration for HPC. FPGA devices are the leading commercial technology available today that is capable of RC, albeit not originally designed for RC, and thus FPGAs are the focal point for virtually all experimental research and commercial deployments, with a growing list of success stories.
While there are a handful of commercial offerings from companies such as Convey Computer, XtremeData, GiDel, Mitrionics, and Impulse Accelerated Technologies, RC is still an area of active research.
United States religious leader of the Mormon Church after the assassination of Joseph Smith; he led the Mormon exodus from Illinois to Salt Lake City, Utah (1801-1877)
George: On-going research projects at the four university sites of CHREC -- the University of Florida, Brigham Young University led by Dr. Brent Nelson, George Washington University led by Dr. Tarek El-Ghazawi, and Virginia Tech led by Dr. Peter Athanas -- fall into four categories: productivity, architecture, partial reconfiguration, and fault tolerance.
an abstract or general idea inferred or derived from specific instances
However, RC is viewed by many as lagging in effective concepts and tools for application development by domain scientists and other users to harness this potency without special skills.
It should be noted that RC, as a new paradigm of computing, is broader than FPGA acceleration for HPC. FPGA devices are the leading commercial technology available today that is capable of RC, albeit not originally designed for RC, and thus FPGAs are the focal point for virtually all experimental research and commercial deployments, with a growing list of success stories.
one of the inherent cognitive or perceptual powers of the mind
In the area of productivity, several projects are underway, crafting novel concepts for design of RC applications and systems, including new methods and tools for design formulation and prediction, hardware virtualization, module and core reuse, design verification and optimization, and programming with high-level languages.
However, we believe that inherent weaknesses of any fixed-logic device technology ... in terms of broad applicability at speed and energy efficiency, will eventually become limiting factors.
In this area, CHREC researchers are developing device- and system-level RC concepts and architectures to support scenarios that require high performance, versatility, and reliability with low power, cooling, and size, be it for outer space or the HPC computer room.
a person who designs and writes and tests computer programs
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
inventing or contriving an idea or explanation and formulating it mentally
In the area of productivity, several projects are underway, crafting novel concepts for design of RC applications and systems, including new methods and tools for design formulation and prediction, hardware virtualization, module and core reuse, design verification and optimization, and programming with high-level languages.
In this area, CHREC researchers are developing device- and system-level RC concepts and architectures to support scenarios that require high performance, versatility, and reliability with low power, cooling, and size, be it for outer space or the HPC computer room.
However, looking ahead more broadly, reconfigurable logic may be featured in future devices with a variety of structures, granularities, functionalities, etc., perhaps very similar to today's FPGAs or perhaps quite different.
Founded in 2007, CHREC is a national research center under the auspices of the I/UCRC program of the National Science Foundation and consists of more than 30 academic, industry and government partners working collaboratively on research in this field.
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
willingness to recognize and respect the beliefs or practices of others
George: On-going research projects at the four university sites of CHREC -- the University of Florida, Brigham Young University led by Dr. Brent Nelson, George Washington University led by Dr. Tarek El-Ghazawi, and Virginia Tech led by Dr. Peter Athanas -- fall into four categories: productivity, architecture, partial reconfiguration, and fault tolerance.
Altogether, Novo-G features 96 of these FPGAs, with an upgrade underway that by January will double its RC capacity to 192 FPGAs via two coupled RC boards per server.
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
In the area of productivity, several projects are underway, crafting novel concepts for design of RC applications and systems, including new methods and tools for design formulation and prediction, hardware virtualization, module and core reuse, design verification and optimization, and programming with high-level languages.
(computer science) written programs or procedures or rules and associated documentation pertaining to the operation of a computer system and that are stored in read/write memory
Thus, in theory, the hardware can be matched to the software, rather than the other way around.
Each server features a tightly-coupled set of four FPGA accelerators on a ProcStar-III PCIe board from GiDEL supported by a conventional multicore CPU, motherboard, disk, etc.
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
additional proof that something that was believed (some fact or hypothesis or theory) is correct
In the area of productivity, several projects are underway, crafting novel concepts for design of RC applications and systems, including new methods and tools for design formulation and prediction, hardware virtualization, module and core reuse, design verification and optimization, and programming with high-level languages.
Will RC be a niche solution in specific application areas or do you see this technology being used in general-purpose platforms that will be widely deployed?
the extent of a 2-dimensional surface enclosed within a boundary
While there are a handful of commercial offerings from companies such as Convey Computer, XtremeData, GiDel, Mitrionics, and Impulse Accelerated Technologies, RC is still an area of active research.
With respect to architecture, researchers are working to characterize and optimize new and emerging devices -- both fixed and reconfigurable logic -- and systems, as well as methods to promote autonomous hardware reconfiguration.
However, we believe that inherent weaknesses of any fixed-logic device technology ... in terms of broad applicability at speed and energy efficiency, will eventually become limiting factors.
It should be noted that RC, as a new paradigm of computing, is broader than FPGA acceleration for HPC. FPGA devices are the leading commercial technology available today that is capable of RC, albeit not originally designed for RC, and thus FPGAs are the focal point for virtually all experimental research and commercial deployments, with a growing list of success stories.
used to wrap around pipes or boilers or laid in attics to prevent loss of heat
However, RC is viewed by many as lagging in effective concepts and tools for application development by domain scientists and other users to harness this potency without special skills.
a person who pleads for a cause or propounds an idea
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
However, RC is viewed by many as lagging in effective concepts and tools for application development by domain scientists and other users to harness this potency without special skills.
and others ('et al.' is used as an abbreviation of `et alii' (masculine plural) or `et aliae' (feminine plural) or `et alia' (neuter plural) when referring to a number of people)
By contrast, numerous research studies show that computing with reconfigurable-logic devices -- FPGAs, et al. -- is fundamentally superior in terms of speed and energy, due to the many advantages of adaptive, customizable hardware parallelism.
King of Great Britain and Ireland from 1760 to 1820; the American colonies were lost during his reign; he became insane in 1811 and his son (later George IV) acted as regent until 1820 (1738-1820)
CHREC is run by Dr. Alan George, who gave an address at the SC09 Workshop on High-Performance Reconfigurable Computing Technology and Applications (HPRCTA'09) on November 15.
One factor is the trend for performance, productivity, and sustainability borne by growing concerns with conventional technologies about speed versus energy consumption, which increasingly favors RC. The conventional model of computing with fixed-logic multicore devices is limiting in terms of performance per unit of energy as compared to reconfigurable-logic devices.
An established technology is dominant for many years; it experiences growth over a long period of time from evolutionary advances, and one day it is partially or wholly supplanted by a new, revolutionary technology, but only after that new technology has navigated a long and winding road of research and development.
stable gear consisting of an arrangement of leather straps fitted to a draft animal so that it can be attached to and pull a cart
Productivity is often a key challenge for a new IT technology, learning how to effectively harness and exploit the inherent advantages of the new approach.
As principal challenges -- performance, productivity, and sustainability -- become more pronounced, and as R&D in RC progresses, we believe that the RC paradigm will mature and expand in its role and influence to eventually become dominant in a broad range of applications, from satellites to servers to supercomputers.
In the U.S., the NSF Center for High-Performance Reconfigurable Computing (CHREC, pronounced "shreck"), acts as the research hub for RC, bringing together more than 30 organizations in this field.
In contrast, the structure of parallelism in reconfigurable-logic devices can be customized, that is, reconfigured, for each application or task on the fly, being versatile yet optimized specifically for each problem at hand.
the central part of a car wheel (or fan or propeller etc) through which the shaft or axle passes
In the U.S., the NSF Center for High-Performance Reconfigurable Computing (CHREC, pronounced "shreck"), acts as the research hub for RC, bringing together more than 30 organizations in this field.
the physical magnitude of something (how big it is)
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
An established technology is dominant for many years; it experiences growth over a long period of time from evolutionary advances, and one day it is partially or wholly supplanted by a new, revolutionary technology, but only after that new technology has navigated a long and winding road of research and development.
NASA, DOD, and other space-related agencies worldwide are increasingly featuring RC technologies in their platforms, as is the aerospace community in general.
As life-cycle costs of energy and cooling rise to approach and exceed that of software and hardware in total cost of ownership, these technologies may become unsustainable.
the quality of having a superior or more favorable position
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
In addition, several new collaborations have been inspired by Novo-G, with other research groups, for example, Boston University and the Air Force Research Laboratory, as well as tools vendors such as Impulse Accelerated Technologies and Mitrionics.
With respect to architecture, researchers are working to characterize and optimize new and emerging devices -- both fixed and reconfigurable logic -- and systems, as well as methods to promote autonomous hardware reconfiguration.
(biology) the basic structural and functional unit of all organisms; they may exist as independent units of life (as in monads) or may form colonies or tissues as in higher plants and animals
What are the advantages of FPGAs for high-performance computing compared to fixed-logic architectures such as CPUs, GPUs, the Cell processor?
in essence; at bottom or by one's (or its) very nature
By contrast, numerous research studies show that computing with reconfigurable-logic devices -- FPGAs, et al. -- is fundamentally superior in terms of speed and energy, due to the many advantages of adaptive, customizable hardware parallelism.
However, RC is viewed by many as lagging in effective concepts and tools for application development by domain scientists and other users to harness this potency without special skills.
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
any mechanical or electrical device that transmits or modifies energy to perform or assist in the performance of human tasks
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
the act of working out the form of something (as by making a sketch or outline or plan)
It should be noted that RC, as a new paradigm of computing, is broader than FPGA acceleration for HPC. FPGA devices are the leading commercial technology available today that is capable of RC, albeit not originally designed for RC, and thus FPGAs are the focal point for virtually all experimental research and commercial deployments, with a growing list of success stories.
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
For example, in our first application experiment working with domain scientists in computational biology, performance was sustained with 96 FPGAs that matched that of the largest machines on the NSF TeraGrid, yet provided by a machine that is hundreds of times lower in cost, power, cooling, size, etc.
(literal meaning) being at or having a relatively great or specific elevation or upward extension (sometimes used in combinations like `knee-high')
In the U.S., the NSF Center for High-Performance Reconfigurable Computing (CHREC, pronounced "shreck"), acts as the research hub for RC, bringing together more than 30 organizations in this field.
Last but not least, as process densities increase and become more susceptible to faults, environments become harsher, and resources become more prone to soft or hard errors, research challenges arise in fault tolerance.
a small fragment of something broken off from the whole
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
an outline or synopsis of a play (or, by extension, of a literary work)
In this area, CHREC researchers are developing device- and system-level RC concepts and architectures to support scenarios that require high performance, versatility, and reliability with low power, cooling, and size, be it for outer space or the HPC computer room.
after an unspecified period of time or an especially long delay
As principal challenges -- performance, productivity, and sustainability -- become more pronounced, and as R&D in RC progresses, we believe that the RC paradigm will mature and expand in its role and influence to eventually become dominant in a broad range of applications, from satellites to servers to supercomputers.
Will RC be a niche solution in specific application areas or do you see this technology being used in general-purpose platforms that will be widely deployed?
an item of information that is typical of a class or group
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
In the area of productivity, several projects are underway, crafting novel concepts for design of RC applications and systems, including new methods and tools for design formulation and prediction, hardware virtualization, module and core reuse, design verification and optimization, and programming with high-level languages.
Founded in 2007, CHREC is a national research center under the auspices of the I/UCRC program of the National Science Foundation and consists of more than 30 academic, industry and government partners working collaboratively on research in this field.
One factor is the trend for performance, productivity, and sustainability borne by growing concerns with conventional technologies about speed versus energy consumption, which increasingly favors RC. The conventional model of computing with fixed-logic multicore devices is limiting in terms of performance per unit of energy as compared to reconfigurable-logic devices.
(ancient Rome) a religious official who interpreted omens to guide public policy
Founded in 2007, CHREC is a national research center under the auspices of the I/UCRC program of the National Science Foundation and consists of more than 30 academic, industry and government partners working collaboratively on research in this field.
With respect to architecture, researchers are working to characterize and optimize new and emerging devices -- both fixed and reconfigurable logic -- and systems, as well as methods to promote autonomous hardware reconfiguration.
By contrast, numerous research studies show that computing with reconfigurable-logic devices -- FPGAs, et al. -- is fundamentally superior in terms of speed and energy, due to the many advantages of adaptive, customizable hardware parallelism.
An established technology is dominant for many years; it experiences growth over a long period of time from evolutionary advances, and one day it is partially or wholly supplanted by a new, revolutionary technology, but only after that new technology has navigated a long and winding road of research and development.
Founded in 2007, CHREC is a national research center under the auspices of the I/UCRC program of the National Science Foundation and consists of more than 30 academic, industry and government partners working collaboratively on research in this field.
neither warm nor very cold; giving relief from heat
As life-cycle costs of energy and cooling rise to approach and exceed that of software and hardware in total cost of ownership, these technologies may become unsustainable.
With fixed-logic computing, the user and application have no control over underlying hardware parallelism; they simply attempt to exploit as much as the manufacturer has deemed to provide.
a thing constructed; a complex entity constructed of many parts
Programmable fixed-logic devices no matter their form feature a "one size fits all" or "Jack of all trades" philosophy, with a predefined structure of parallelism, yet attempting to support all applications or some major subset.
As life-cycle costs of energy and cooling rise to approach and exceed that of software and hardware in total cost of ownership, these technologies may become unsustainable.
an independent agency of the United States government responsible for aviation and spaceflight
NASA, DOD, and other space-related agencies worldwide are increasingly featuring RC technologies in their platforms, as is the aerospace community in general.
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
1st President of the United States; commander-in-chief of the Continental Army during the American Revolution (1732-1799)
George: On-going research projects at the four university sites of CHREC -- the University of Florida, Brigham Young University led by Dr. Brent Nelson, George Washington University led by Dr. Tarek El-Ghazawi, and Virginia Tech led by Dr. Peter Athanas -- fall into four categories: productivity, architecture, partial reconfiguration, and fault tolerance.
small dark geese that breed in the north and migrate southward
George: On-going research projects at the four university sites of CHREC -- the University of Florida, Brigham Young University led by Dr. Brent Nelson, George Washington University led by Dr. Tarek El-Ghazawi, and Virginia Tech led by Dr. Peter Athanas -- fall into four categories: productivity, architecture, partial reconfiguration, and fault tolerance.
a large and diverse institution of higher learning created to educate for life and for a profession and to grant degrees
In addition, several new collaborations have been inspired by Novo-G, with other research groups, for example, Boston University and the Air Force Research Laboratory, as well as tools vendors such as Impulse Accelerated Technologies and Mitrionics.
However, looking ahead more broadly, reconfigurable logic may be featured in future devices with a variety of structures, granularities, functionalities, etc., perhaps very similar to today's FPGAs or perhaps quite different.
connected with or engaged in or sponsored by or used in commerce or commercial enterprises
While there are a handful of commercial offerings from companies such as Convey Computer, XtremeData, GiDel, Mitrionics, and Impulse Accelerated Technologies, RC is still an area of active research.
an area that is approximately central within some larger region
In the U.S., the NSF Center for High-Performance Reconfigurable Computing (CHREC, pronounced "shreck"), acts as the research hub for RC, bringing together more than 30 organizations in this field.
the opposition or dissimilarity of things that are compared
By contrast, numerous research studies show that computing with reconfigurable-logic devices -- FPGAs, et al. -- is fundamentally superior in terms of speed and energy, due to the many advantages of adaptive, customizable hardware parallelism.
In the U.S., the NSF Center for High-Performance Reconfigurable Computing (CHREC, pronounced "shreck"), acts as the research hub for RC, bringing together more than 30 organizations in this field.
Both of these project areas of productivity and architecture relate well to HPC.
Meanwhile, one of the unique features of some RC devices is their ability to reconfigure portions of the hardware of the chip while other portions remain unchanged and thus operational, and this powerful feature involves many research and design challenges being studied and addressed by several teams.
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
CHREC is run by Dr. Alan George, who gave an address at the SC09 Workshop on High-Performance Reconfigurable Computing Technology and Applications (HPRCTA'09) on November 15.
hang (back) or fall (behind) in movement, progress, development, etc.
However, RC is viewed by many as lagging in effective concepts and tools for application development by domain scientists and other users to harness this potency without special skills.
Will RC be a niche solution in specific application areas or do you see this technology being used in general-purpose platforms that will be widely deployed?
something with a round shape resembling a flat circular plate
Each server features a tightly-coupled set of four FPGA accelerators on a ProcStar-III PCIe board from GiDEL supported by a conventional multicore CPU, motherboard, disk, etc.
With fixed-logic computing, the user and application have no control over underlying hardware parallelism; they simply attempt to exploit as much as the manufacturer has deemed to provide.
a school teaching mechanical and industrial arts and the applied sciences
George: On-going research projects at the four university sites of CHREC -- the University of Florida, Brigham Young University led by Dr. Brent Nelson, George Washington University led by Dr. Tarek El-Ghazawi, and Virginia Tech led by Dr. Peter Athanas -- fall into four categories: productivity, architecture, partial reconfiguration, and fault tolerance.
(often followed by `of' or `to') yielding readily to or capable of
Last but not least, as process densities increase and become more susceptible to faults, environments become harsher, and resources become more prone to soft or hard errors, research challenges arise in fault tolerance.
small workplace where handcrafts or manufacturing are done
CHREC is run by Dr. Alan George, who gave an address at the SC09 Workshop on High-Performance Reconfigurable Computing Technology and Applications (HPRCTA'09) on November 15.
a machine for performing calculations automatically
While there are a handful of commercial offerings from companies such as Convey Computer, XtremeData, GiDel, Mitrionics, and Impulse Accelerated Technologies, RC is still an area of active research.
an operation that is assigned by a higher headquarters
George: Naturally, as a relatively new paradigm of computing, RC has started with emphasis in a few targeted areas, for example, aerospace and bioinformatics, where missions and users require dramatic improvement only possible by a revolutionary approach.
In the U.S., the NSF Center for High-Performance Reconfigurable Computing (CHREC, pronounced "shreck"), acts as the research hub for RC, bringing together more than 30 organizations in this field.
George: On-going research projects at the four university sites of CHREC -- the University of Florida, Brigham Young University led by Dr. Brent Nelson, George Washington University led by Dr. Tarek El-Ghazawi, and Virginia Tech led by Dr. Peter Athanas -- fall into four categories: productivity, architecture, partial reconfiguration, and fault tolerance.
NASA, DOD, and other space-related agencies worldwide are increasingly featuring RC technologies in their platforms, as is the aerospace community in general.
In contrast, the structure of parallelism in reconfigurable-logic devices can be customized, that is, reconfigured, for each application or task on the fly, being versatile yet optimized specifically for each problem at hand.
It should be noted that RC, as a new paradigm of computing, is broader than FPGA acceleration for HPC. FPGA devices are the leading commercial technology available today that is capable of RC, albeit not originally designed for RC, and thus FPGAs are the focal point for virtually all experimental research and commercial deployments, with a growing list of success stories.
a person with advanced knowledge of one or more sciences
However, RC is viewed by many as lagging in effective concepts and tools for application development by domain scientists and other users to harness this potency without special skills.
With respect to architecture, researchers are working to characterize and optimize new and emerging devices -- both fixed and reconfigurable logic -- and systems, as well as methods to promote autonomous hardware reconfiguration.
Last but not least, as process densities increase and become more susceptible to faults, environments become harsher, and resources become more prone to soft or hard errors, research challenges arise in fault tolerance.
The driving issues in this community -- again performance, productivity, and especially sustainability -- are becoming increasingly important in HPC.
HPCwire: In the past couple of years, non-RC accelerators like the Cell processor and now, especially, general-purpose GPUs have been making big news in the HPC world, with major deployments planned.
As life-cycle costs of energy and cooling rise to approach and exceed that of software and hardware in total cost of ownership, these technologies may become unsustainable.
With fixed-logic computing, the user and application have no control over underlying hardware parallelism; they simply attempt to exploit as much as the manufacturer has deemed to provide.
the act of starting something for the first time; introducing something new
Thus, the second factor is taming this new paradigm of computing and innovations in its technologies, so that it is amenable to a broader range of users.
Programmable fixed-logic devices no matter their form feature a "one size fits all" or "Jack of all trades" philosophy, with a predefined structure of parallelism, yet attempting to support all applications or some major subset.
Will RC be a niche solution in specific application areas or do you see this technology being used in general-purpose platforms that will be widely deployed?
In the area of productivity, several projects are underway, crafting novel concepts for design of RC applications and systems, including new methods and tools for design formulation and prediction, hardware virtualization, module and core reuse, design verification and optimization, and programming with high-level languages.
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
Thus, as is natural for any new paradigm and set of technologies, design productivity is an important challenge at present for RC in general and FPGA devices in particular, so that HPC users, and others, can take full advantage without having to be trained as electrical engineers.
Productivity is often a key challenge for a new IT technology, learning how to effectively harness and exploit the inherent advantages of the new approach.
being connected either logically or causally or by shared characteristics
NASA, DOD, and other space-related agencies worldwide are increasingly featuring RC technologies in their platforms, as is the aerospace community in general.
As principal challenges -- performance, productivity, and sustainability -- become more pronounced, and as R&D in RC progresses, we believe that the RC paradigm will mature and expand in its role and influence to eventually become dominant in a broad range of applications, from satellites to servers to supercomputers.
While there are a handful of commercial offerings from companies such as Convey Computer, XtremeData, GiDel, Mitrionics, and Impulse Accelerated Technologies, RC is still an area of active research.
a general concept that marks divisions or coordinations in a conceptual scheme
George: On-going research projects at the four university sites of CHREC -- the University of Florida, Brigham Young University led by Dr. Brent Nelson, George Washington University led by Dr. Tarek El-Ghazawi, and Virginia Tech led by Dr. Peter Athanas -- fall into four categories: productivity, architecture, partial reconfiguration, and fault tolerance.
the quality of being reproducible in amount or performance
With reconfigurable-logic computing, the user and application define the hardware parallelism, featuring wide and deep parallelism as appropriate, with selectable precision, optimized data paths, etc., up to the limits of total device capacity.
It should be noted that RC, as a new paradigm of computing, is broader than FPGA acceleration for HPC. FPGA devices are the leading commercial technology available today that is capable of RC, albeit not originally designed for RC, and thus FPGAs are the focal point for virtually all experimental research and commercial deployments, with a growing list of success stories.
With respect to architecture, researchers are working to characterize and optimize new and emerging devices -- both fixed and reconfigurable logic -- and systems, as well as methods to promote autonomous hardware reconfiguration.
Founded in 2007, CHREC is a national research center under the auspices of the I/UCRC program of the National Science Foundation and consists of more than 30 academic, industry and government partners working collaboratively on research in this field.
With reconfigurable-logic computing, the user and application define the hardware parallelism, featuring wide and deep parallelism as appropriate, with selectable precision, optimized data paths, etc., up to the limits of total device capacity.
With reconfigurable-logic computing, the user and application define the hardware parallelism, featuring wide and deep parallelism as appropriate, with selectable precision, optimized data paths, etc., up to the limits of total device capacity.
In the U.S., the NSF Center for High-Performance Reconfigurable Computing (CHREC, pronounced "shreck"), acts as the research hub for RC, bringing together more than 30 organizations in this field.
Programmable fixed-logic devices no matter their form feature a "one size fits all" or "Jack of all trades" philosophy, with a predefined structure of parallelism, yet attempting to support all applications or some major subset.
a group of independent but interrelated elements comprising a unified whole
HPCwire: The new Novo-G reconfigurable computing system at the NSF Center for High-Performance Reconfigurable Computing (CHREC) has been up and running for just a few months.
(comparative of `much' used with mass nouns) a quantifier meaning greater in size or amount or extent or degree
In the U.S., the NSF Center for High-Performance Reconfigurable Computing (CHREC, pronounced "shreck"), acts as the research hub for RC, bringing together more than 30 organizations in this field.
An established technology is dominant for many years; it experiences growth over a long period of time from evolutionary advances, and one day it is partially or wholly supplanted by a new, revolutionary technology, but only after that new technology has navigated a long and winding road of research and development.
For example, in our first application experiment working with domain scientists in computational biology, performance was sustained with 96 FPGAs that matched that of the largest machines on the NSF TeraGrid, yet provided by a machine that is hundreds of times lower in cost, power, cooling, size, etc.
In addition, several new collaborations have been inspired by Novo-G, with other research groups, for example, Boston University and the Air Force Research Laboratory, as well as tools vendors such as Impulse Accelerated Technologies and Mitrionics.
any celestial body orbiting around a planet or star
As principal challenges -- performance, productivity, and sustainability -- become more pronounced, and as R&D in RC progresses, we believe that the RC paradigm will mature and expand in its role and influence to eventually become dominant in a broad range of applications, from satellites to servers to supercomputers.
However, we believe that inherent weaknesses of any fixed-logic device technology ... in terms of broad applicability at speed and energy efficiency, will eventually become limiting factors.
Thus, the second factor is taming this new paradigm of computing and innovations in its technologies, so that it is amenable to a broader range of users.
George: On-going research projects at the four university sites of CHREC -- the University of Florida, Brigham Young University led by Dr. Brent Nelson, George Washington University led by Dr. Tarek El-Ghazawi, and Virginia Tech led by Dr. Peter Athanas -- fall into four categories: productivity, architecture, partial reconfiguration, and fault tolerance.
Each server features a tightly-coupled set of four FPGA accelerators on a ProcStar-III PCIe board from GiDEL supported by a conventional multicore CPU, motherboard, disk, etc.
HPCwire: The new Novo-G reconfigurable computing system at the NSF Center for High-Performance Reconfigurable Computing (CHREC) has been up and running for just a few months.
a category of things distinguished by some common characteristic or quality
However, looking ahead more broadly, reconfigurable logic may be featured in future devices with a variety of structures, granularities, functionalities, etc., perhaps very similar to today's FPGAs or perhaps quite different.
With fixed-logic computing, the user and application have no control over underlying hardware parallelism; they simply attempt to exploit as much as the manufacturer has deemed to provide.
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
the place where a person or organization can be found or communicated with
CHREC is run by Dr. Alan George, who gave an address at the SC09 Workshop on High-Performance Reconfigurable Computing Technology and Applications (HPRCTA'09) on November 15.
a workplace for the conduct of scientific research
In addition, several new collaborations have been inspired by Novo-G, with other research groups, for example, Boston University and the Air Force Research Laboratory, as well as tools vendors such as Impulse Accelerated Technologies and Mitrionics.
give a promotion to or assign to a higher position
With respect to architecture, researchers are working to characterize and optimize new and emerging devices -- both fixed and reconfigurable logic -- and systems, as well as methods to promote autonomous hardware reconfiguration.
In the future, RC will become more important for a growing set of missions, applications, and users and, concomitantly, it will become more amenable to them, so that productivity is maximized alongside performance and sustainability.
a collection of facts from which conclusions may be drawn
With reconfigurable-logic computing, the user and application define the hardware parallelism, featuring wide and deep parallelism as appropriate, with selectable precision, optimized data paths, etc., up to the limits of total device capacity.
George: Naturally, as a relatively new paradigm of computing, RC has started with emphasis in a few targeted areas, for example, aerospace and bioinformatics, where missions and users require dramatic improvement only possible by a revolutionary approach.
to a distinctly greater extent or degree than is common
The driving issues in this community -- again performance, productivity, and especially sustainability -- are becoming increasingly important in HPC.
HPCwire: In the past couple of years, non-RC accelerators like the Cell processor and now, especially, general-purpose GPUs have been making big news in the HPC world, with major deployments planned.
an item of factual information derived from measurement or research
With reconfigurable-logic computing, the user and application define the hardware parallelism, featuring wide and deep parallelism as appropriate, with selectable precision, optimized data paths, etc., up to the limits of total device capacity.
the airforce of the United States of America; the agency that defends the United States through control and exploitation of air and space
In addition, several new collaborations have been inspired by Novo-G, with other research groups, for example, Boston University and the Air Force Research Laboratory, as well as tools vendors such as Impulse Accelerated Technologies and Mitrionics.
While there are a handful of commercial offerings from companies such as Convey Computer, XtremeData, GiDel, Mitrionics, and Impulse Accelerated Technologies, RC is still an area of active research.
the cardinal number that is the sum of one and one and one
Each server features a tightly-coupled set of four FPGA accelerators on a ProcStar-III PCIe board from GiDEL supported by a conventional multicore CPU, motherboard, disk, etc.
An established technology is dominant for many years; it experiences growth over a long period of time from evolutionary advances, and one day it is partially or wholly supplanted by a new, revolutionary technology, but only after that new technology has navigated a long and winding road of research and development.
Both of these project areas of productivity and architecture relate well to HPC.
Meanwhile, one of the unique features of some RC devices is their ability to reconfigure portions of the hardware of the chip while other portions remain unchanged and thus operational, and this powerful feature involves many research and design challenges being studied and addressed by several teams.
Altogether, Novo-G features 96 of these FPGAs, with an upgrade underway that by January will double its RC capacity to 192 FPGAs via two coupled RC boards per server.
George: Naturally, as a relatively new paradigm of computing, RC has started with emphasis in a few targeted areas, for example, aerospace and bioinformatics, where missions and users require dramatic improvement only possible by a revolutionary approach.
Both of these project areas of productivity and architecture relate well to HPC.
Meanwhile, one of the unique features of some RC devices is their ability to reconfigure portions of the hardware of the chip while other portions remain unchanged and thus operational, and this powerful feature involves many research and design challenges being studied and addressed by several teams.
specifically or especially distinguished from others
Thus, as is natural for any new paradigm and set of technologies, design productivity is an important challenge at present for RC in general and FPGA devices in particular, so that HPC users, and others, can take full advantage without having to be trained as electrical engineers.
As principal challenges -- performance, productivity, and sustainability -- become more pronounced, and as R&D in RC progresses, we believe that the RC paradigm will mature and expand in its role and influence to eventually become dominant in a broad range of applications, from satellites to servers to supercomputers.
While there are a handful of commercial offerings from companies such as Convey Computer, XtremeData, GiDel, Mitrionics, and Impulse Accelerated Technologies, RC is still an area of active research.
It should be noted that RC, as a new paradigm of computing, is broader than FPGA acceleration for HPC. FPGA devices are the leading commercial technology available today that is capable of RC, albeit not originally designed for RC, and thus FPGAs are the focal point for virtually all experimental research and commercial deployments, with a growing list of success stories.
maintained at length without interruption or weakening
For example, in our first application experiment working with domain scientists in computational biology, performance was sustained with 96 FPGAs that matched that of the largest machines on the NSF TeraGrid, yet provided by a machine that is hundreds of times lower in cost, power, cooling, size, etc.
a database containing an ordered array of items (names or topics)
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
on this day as distinct from yesterday or tomorrow
It should be noted that RC, as a new paradigm of computing, is broader than FPGA acceleration for HPC. FPGA devices are the leading commercial technology available today that is capable of RC, albeit not originally designed for RC, and thus FPGAs are the focal point for virtually all experimental research and commercial deployments, with a growing list of success stories.
As life-cycle costs of energy and cooling rise to approach and exceed that of software and hardware in total cost of ownership, these technologies may become unsustainable.
Last but not least, as process densities increase and become more susceptible to faults, environments become harsher, and resources become more prone to soft or hard errors, research challenges arise in fault tolerance.
suitable for a particular person or place or condition etc
With reconfigurable-logic computing, the user and application define the hardware parallelism, featuring wide and deep parallelism as appropriate, with selectable precision, optimized data paths, etc., up to the limits of total device capacity.
As principal challenges -- performance, productivity, and sustainability -- become more pronounced, and as R&D in RC progresses, we believe that the RC paradigm will mature and expand in its role and influence to eventually become dominant in a broad range of applications, from satellites to servers to supercomputers.
something determined in relation to something that includes it
Both of these project areas of productivity and architecture relate well to HPC.
Meanwhile, one of the unique features of some RC devices is their ability to reconfigure portions of the hardware of the chip while other portions remain unchanged and thus operational, and this powerful feature involves many research and design challenges being studied and addressed by several teams.
consisting of great mass; containing a great quantity of matter
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
having great (or a certain) extent from one side to the other
As principal challenges -- performance, productivity, and sustainability -- become more pronounced, and as R&D in RC progresses, we believe that the RC paradigm will mature and expand in its role and influence to eventually become dominant in a broad range of applications, from satellites to servers to supercomputers.
a series of steps to be carried out or goals to be accomplished
Founded in 2007, CHREC is a national research center under the auspices of the I/UCRC program of the National Science Foundation and consists of more than 30 academic, industry and government partners working collaboratively on research in this field.
English admiral who defeated the French fleets of Napoleon but was mortally wounded at Trafalgar (1758-1805)
George: On-going research projects at the four university sites of CHREC -- the University of Florida, Brigham Young University led by Dr. Brent Nelson, George Washington University led by Dr. Tarek El-Ghazawi, and Virginia Tech led by Dr. Peter Athanas -- fall into four categories: productivity, architecture, partial reconfiguration, and fault tolerance.
Will RC be a niche solution in specific application areas or do you see this technology being used in general-purpose platforms that will be widely deployed?
With fixed-logic computing, the user and application have no control over underlying hardware parallelism; they simply attempt to exploit as much as the manufacturer has deemed to provide.
Will RC be a niche solution in specific application areas or do you see this technology being used in general-purpose platforms that will be widely deployed?
a relative position or degree of value in a graded group
In the area of productivity, several projects are underway, crafting novel concepts for design of RC applications and systems, including new methods and tools for design formulation and prediction, hardware virtualization, module and core reuse, design verification and optimization, and programming with high-level languages.
In contrast, the structure of parallelism in reconfigurable-logic devices can be customized, that is, reconfigured, for each application or task on the fly, being versatile yet optimized specifically for each problem at hand.
In the U.S., the NSF Center for High-Performance Reconfigurable Computing (CHREC, pronounced "shreck"), acts as the research hub for RC, bringing together more than 30 organizations in this field.
a way of doing something, especially a systematic way; implies an orderly logical arrangement (usually in steps)
In the area of productivity, several projects are underway, crafting novel concepts for design of RC applications and systems, including new methods and tools for design formulation and prediction, hardware virtualization, module and core reuse, design verification and optimization, and programming with high-level languages.
a state in southeastern United States between the Atlantic and the Gulf of Mexico; one of the Confederate states during the American Civil War
George: On-going research projects at the four university sites of CHREC -- the University of Florida, Brigham Young University led by Dr. Brent Nelson, George Washington University led by Dr. Tarek El-Ghazawi, and Virginia Tech led by Dr. Peter Athanas -- fall into four categories: productivity, architecture, partial reconfiguration, and fault tolerance.
Will RC be a niche solution in specific application areas or do you see this technology being used in general-purpose platforms that will be widely deployed?
By contrast, numerous research studies show that computing with reconfigurable-logic devices -- FPGAs, et al. -- is fundamentally superior in terms of speed and energy, due to the many advantages of adaptive, customizable hardware parallelism.
George: Naturally, as a relatively new paradigm of computing, RC has started with emphasis in a few targeted areas, for example, aerospace and bioinformatics, where missions and users require dramatic improvement only possible by a revolutionary approach.
As principal challenges -- performance, productivity, and sustainability -- become more pronounced, and as R&D in RC progresses, we believe that the RC paradigm will mature and expand in its role and influence to eventually become dominant in a broad range of applications, from satellites to servers to supercomputers.
It should be noted that RC, as a new paradigm of computing, is broader than FPGA acceleration for HPC. FPGA devices are the leading commercial technology available today that is capable of RC, albeit not originally designed for RC, and thus FPGAs are the focal point for virtually all experimental research and commercial deployments, with a growing list of success stories.
The driving issues in this community -- again performance, productivity, and especially sustainability -- are becoming increasingly important in HPC.
HPCwire: In the past couple of years, non-RC accelerators like the Cell processor and now, especially, general-purpose GPUs have been making big news in the HPC world, with major deployments planned.
In the U.S., the NSF Center for High-Performance Reconfigurable Computing (CHREC, pronounced "shreck"), acts as the research hub for RC, bringing together more than 30 organizations in this field.
pecuniary reimbursement to the winning party for the expenses of litigation
As life-cycle costs of energy and cooling rise to approach and exceed that of software and hardware in total cost of ownership, these technologies may become unsustainable.
In this area, CHREC researchers are developing device- and system-level RC concepts and architectures to support scenarios that require high performance, versatility, and reliability with low power, cooling, and size, be it for outer space or the HPC computer room.
George: Naturally, as a relatively new paradigm of computing, RC has started with emphasis in a few targeted areas, for example, aerospace and bioinformatics, where missions and users require dramatic improvement only possible by a revolutionary approach.
in spite of everything; without regard to drawbacks
Programmable fixed-logic devices no matter their form feature a "one size fits all" or "Jack of all trades" philosophy, with a predefined structure of parallelism, yet attempting to support all applications or some major subset.
As life-cycle costs of energy and cooling rise to approach and exceed that of software and hardware in total cost of ownership, these technologies may become unsustainable.
One factor is the trend for performance, productivity, and sustainability borne by growing concerns with conventional technologies about speed versus energy consumption, which increasingly favors RC. The conventional model of computing with fixed-logic multicore devices is limiting in terms of performance per unit of energy as compared to reconfigurable-logic devices.
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
applying to all or most members of a category or group
Will RC be a niche solution in specific application areas or do you see this technology being used in general-purpose platforms that will be widely deployed?
being of such surpassing excellence as to suggest inspiration by the gods
In addition, several new collaborations have been inspired by Novo-G, with other research groups, for example, Boston University and the Air Force Research Laboratory, as well as tools vendors such as Impulse Accelerated Technologies and Mitrionics.
With fixed-logic computing, the user and application have no control over underlying hardware parallelism; they simply attempt to exploit as much as the manufacturer has deemed to provide.
shaped or conditioned or disciplined by training; often used as a combining form
Thus, as is natural for any new paradigm and set of technologies, design productivity is an important challenge at present for RC in general and FPGA devices in particular, so that HPC users, and others, can take full advantage without having to be trained as electrical engineers.
In the area of productivity, several projects are underway, crafting novel concepts for design of RC applications and systems, including new methods and tools for design formulation and prediction, hardware virtualization, module and core reuse, design verification and optimization, and programming with high-level languages.
(used of count nouns) every one considered individually
In contrast, the structure of parallelism in reconfigurable-logic devices can be customized, that is, reconfigured, for each application or task on the fly, being versatile yet optimized specifically for each problem at hand.
George: Naturally, as a relatively new paradigm of computing, RC has started with emphasis in a few targeted areas, for example, aerospace and bioinformatics, where missions and users require dramatic improvement only possible by a revolutionary approach.
producing or capable of producing an intended result or having a striking effect
However, RC is viewed by many as lagging in effective concepts and tools for application development by domain scientists and other users to harness this potency without special skills.
produced or marked by conscious design or premeditation
Both of these project areas of productivity and architecture relate well to HPC.
Meanwhile, one of the unique features of some RC devices is their ability to reconfigure portions of the hardware of the chip while other portions remain unchanged and thus operational, and this powerful feature involves many research and design challenges being studied and addressed by several teams.
the piece of land on which something is located (or is to be located)
George: On-going research projects at the four university sites of CHREC -- the University of Florida, Brigham Young University led by Dr. Brent Nelson, George Washington University led by Dr. Tarek El-Ghazawi, and Virginia Tech led by Dr. Peter Athanas -- fall into four categories: productivity, architecture, partial reconfiguration, and fault tolerance.
a person who uses scientific knowledge to solve practical problems
Thus, as is natural for any new paradigm and set of technologies, design productivity is an important challenge at present for RC in general and FPGA devices in particular, so that HPC users, and others, can take full advantage without having to be trained as electrical engineers.
obtainable or accessible and ready for use or service
It should be noted that RC, as a new paradigm of computing, is broader than FPGA acceleration for HPC. FPGA devices are the leading commercial technology available today that is capable of RC, albeit not originally designed for RC, and thus FPGAs are the focal point for virtually all experimental research and commercial deployments, with a growing list of success stories.
For example, in our first application experiment working with domain scientists in computational biology, performance was sustained with 96 FPGAs that matched that of the largest machines on the NSF TeraGrid, yet provided by a machine that is hundreds of times lower in cost, power, cooling, size, etc.
It should be noted that RC, as a new paradigm of computing, is broader than FPGA acceleration for HPC. FPGA devices are the leading commercial technology available today that is capable of RC, albeit not originally designed for RC, and thus FPGAs are the focal point for virtually all experimental research and commercial deployments, with a growing list of success stories.
a quantifier that can be used with count nouns and is often preceded by `as' or `too' or `so' or `that'; amounting to a large but indefinite number
By contrast, numerous research studies show that computing with reconfigurable-logic devices -- FPGAs, et al. -- is fundamentally superior in terms of speed and energy, due to the many advantages of adaptive, customizable hardware parallelism.
a homogeneous mixture of two or more substances; frequently (but not necessarily) a liquid solution
Will RC be a niche solution in specific application areas or do you see this technology being used in general-purpose platforms that will be widely deployed?
However, looking ahead more broadly, reconfigurable logic may be featured in future devices with a variety of structures, granularities, functionalities, etc., perhaps very similar to today's FPGAs or perhaps quite different.
the capability of conscious choice and decision and intention
Will RC be a niche solution in specific application areas or do you see this technology being used in general-purpose platforms that will be widely deployed?
violent or severe weather (viewed as caused by the action of the four elements)
Each FPGA is a Stratix-III E260 device from Altera with 254K logic elements, 768 18x18 multipliers, and more than 4GB of DDR2 memory directly attached via three banks.
the act of controlling and steering the movement of a vehicle or animal
The driving issues in this community -- again performance, productivity, and especially sustainability -- are becoming increasingly important in HPC.
HPCwire: In the past couple of years, non-RC accelerators like the Cell processor and now, especially, general-purpose GPUs have been making big news in the HPC world, with major deployments planned.
held up or having the weight borne especially from below
Each server features a tightly-coupled set of four FPGA accelerators on a ProcStar-III PCIe board from GiDEL supported by a conventional multicore CPU, motherboard, disk, etc.
However, looking ahead more broadly, reconfigurable logic may be featured in future devices with a variety of structures, granularities, functionalities, etc., perhaps very similar to today's FPGAs or perhaps quite different.
a source of aid or support that may be drawn upon when needed
Last but not least, as process densities increase and become more susceptible to faults, environments become harsher, and resources become more prone to soft or hard errors, research challenges arise in fault tolerance.
While there are a handful of commercial offerings from companies such as Convey Computer, XtremeData, GiDel, Mitrionics, and Impulse Accelerated Technologies, RC is still an area of active research.
Founded in 2007, CHREC is a national research center under the auspices of the I/UCRC program of the National Science Foundation and consists of more than 30 academic, industry and government partners working collaboratively on research in this field.
NASA, DOD, and other space-related agencies worldwide are increasingly featuring RC technologies in their platforms, as is the aerospace community in general.
George: On-going research projects at the four university sites of CHREC -- the University of Florida, Brigham Young University led by Dr. Brent Nelson, George Washington University led by Dr. Tarek El-Ghazawi, and Virginia Tech led by Dr. Peter Athanas -- fall into four categories: productivity, architecture, partial reconfiguration, and fault tolerance.
George: Naturally, as a relatively new paradigm of computing, RC has started with emphasis in a few targeted areas, for example, aerospace and bioinformatics, where missions and users require dramatic improvement only possible by a revolutionary approach.
Each FPGA is a Stratix-III E260 device from Altera with 254K logic elements, 768 18x18 multipliers, and more than 4GB of DDR2 memory directly attached via three banks.
(comparative of `much' used with mass nouns) a quantifier meaning greater in size or amount or extent or degree
In the U.S., the NSF Center for High-Performance Reconfigurable Computing (CHREC, pronounced "shreck"), acts as the research hub for RC, bringing together more than 30 organizations in this field.
the cardinal number that is the sum of three and one
Each server features a tightly-coupled set of four FPGA accelerators on a ProcStar-III PCIe board from GiDEL supported by a conventional multicore CPU, motherboard, disk, etc.
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
the act of conducting a controlled test or investigation
For example, in our first application experiment working with domain scientists in computational biology, performance was sustained with 96 FPGAs that matched that of the largest machines on the NSF TeraGrid, yet provided by a machine that is hundreds of times lower in cost, power, cooling, size, etc.
applying the mind to learning and understanding a subject (especially by reading)
By contrast, numerous research studies show that computing with reconfigurable-logic devices -- FPGAs, et al. -- is fundamentally superior in terms of speed and energy, due to the many advantages of adaptive, customizable hardware parallelism.
a stout length of sawn timber; made in a wide variety of sizes and used for many purposes
Each server features a tightly-coupled set of four FPGA accelerators on a ProcStar-III PCIe board from GiDEL supported by a conventional multicore CPU, motherboard, disk, etc.
Programmable fixed-logic devices no matter their form feature a "one size fits all" or "Jack of all trades" philosophy, with a predefined structure of parallelism, yet attempting to support all applications or some major subset.
George: On-going research projects at the four university sites of CHREC -- the University of Florida, Brigham Young University led by Dr. Brent Nelson, George Washington University led by Dr. Tarek El-Ghazawi, and Virginia Tech led by Dr. Peter Athanas -- fall into four categories: productivity, architecture, partial reconfiguration, and fault tolerance.
a wrong action attributable to bad judgment or ignorance or inattention
Last but not least, as process densities increase and become more susceptible to faults, environments become harsher, and resources become more prone to soft or hard errors, research challenges arise in fault tolerance.
one of the British colonies that formed the United States
George: On-going research projects at the four university sites of CHREC -- the University of Florida, Brigham Young University led by Dr. Brent Nelson, George Washington University led by Dr. Tarek El-Ghazawi, and Virginia Tech led by Dr. Peter Athanas -- fall into four categories: productivity, architecture, partial reconfiguration, and fault tolerance.
be a delegate or spokesperson for; represent somebody's interest or be a proxy or substitute for, as of politicians and office holders representing their constituents, or of a tenant representing other tenants in a housing dispute
Moreover, in terms of fundamental computing principles, they are an evolutionary development in device architecture, and as such represent less risk.
In the area of productivity, several projects are underway, crafting novel concepts for design of RC applications and systems, including new methods and tools for design formulation and prediction, hardware virtualization, module and core reuse, design verification and optimization, and programming with high-level languages.
Both of these project areas of productivity and architecture relate well to HPC.
Meanwhile, one of the unique features of some RC devices is their ability to reconfigure portions of the hardware of the chip while other portions remain unchanged and thus operational, and this powerful feature involves many research and design challenges being studied and addressed by several teams.
However, looking ahead more broadly, reconfigurable logic may be featured in future devices with a variety of structures, granularities, functionalities, etc., perhaps very similar to today's FPGAs or perhaps quite different.
the rational investigation of questions about existence and knowledge and ethics
Programmable fixed-logic devices no matter their form feature a "one size fits all" or "Jack of all trades" philosophy, with a predefined structure of parallelism, yet attempting to support all applications or some major subset.
to a complete degree or to the full or entire extent (`whole' is often used informally for `wholly')
An established technology is dominant for many years; it experiences growth over a long period of time from evolutionary advances, and one day it is partially or wholly supplanted by a new, revolutionary technology, but only after that new technology has navigated a long and winding road of research and development.
However, RC is viewed by many as lagging in effective concepts and tools for application development by domain scientists and other users to harness this potency without special skills.
of or relating to or belonging to a nation or country
Founded in 2007, CHREC is a national research center under the auspices of the I/UCRC program of the National Science Foundation and consists of more than 30 academic, industry and government partners working collaboratively on research in this field.
the month following October and preceding December
CHREC is run by Dr. Alan George, who gave an address at the SC09 Workshop on High-Performance Reconfigurable Computing Technology and Applications (HPRCTA'09) on November 15.
Founded in 2007, CHREC is a national research center under the auspices of the I/UCRC program of the National Science Foundation and consists of more than 30 academic, industry and government partners working collaboratively on research in this field.
the quality of being able to perform; a quality that permits or facilitates achievement or accomplishment
Both of these project areas of productivity and architecture relate well to HPC.
Meanwhile, one of the unique features of some RC devices is their ability to reconfigure portions of the hardware of the chip while other portions remain unchanged and thus operational, and this powerful feature involves many research and design challenges being studied and addressed by several teams.
(usually followed by `of') having capacity or ability
It should be noted that RC, as a new paradigm of computing, is broader than FPGA acceleration for HPC. FPGA devices are the leading commercial technology available today that is capable of RC, albeit not originally designed for RC, and thus FPGAs are the focal point for virtually all experimental research and commercial deployments, with a growing list of success stories.
the cognitive process of acquiring skill or knowledge
Productivity is often a key challenge for a new IT technology, learning how to effectively harness and exploit the inherent advantages of the new approach.
the act of delivering or distributing something (as goods or mail)
In the U.S., the NSF Center for High-Performance Reconfigurable Computing (CHREC, pronounced "shreck"), acts as the research hub for RC, bringing together more than 30 organizations in this field.
Thus, as is natural for any new paradigm and set of technologies, design productivity is an important challenge at present for RC in general and FPGA devices in particular, so that HPC users, and others, can take full advantage without having to be trained as electrical engineers.
Reconfigurable Computing Research Pushes Forward Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
the arithmetic operation of summing; calculating the sum of two or more numbers
In addition, several new collaborations have been inspired by Novo-G, with other research groups, for example, Boston University and the Air Force Research Laboratory, as well as tools vendors such as Impulse Accelerated Technologies and Mitrionics.
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
Each FPGA is a Stratix-III E260 device from Altera with 254K logic elements, 768 18x18 multipliers, and more than 4GB of DDR2 memory directly attached via three banks.
The driving issues in this community -- again performance, productivity, and especially sustainability -- are becoming increasingly important in HPC.
HPCwire: In the past couple of years, non-RC accelerators like the Cell processor and now, especially, general-purpose GPUs have been making big news in the HPC world, with major deployments planned.
The driving issues in this community -- again performance, productivity, and especially sustainability -- are becoming increasingly important in HPC.
HPCwire: In the past couple of years, non-RC accelerators like the Cell processor and now, especially, general-purpose GPUs have been making big news in the HPC world, with major deployments planned.
state capital and largest city of Massachusetts; a major center for banking and financial services
In addition, several new collaborations have been inspired by Novo-G, with other research groups, for example, Boston University and the Air Force Research Laboratory, as well as tools vendors such as Impulse Accelerated Technologies and Mitrionics.
the first month of the year; begins 10 days after the winter solstice
Altogether, Novo-G features 96 of these FPGAs, with an upgrade underway that by January will double its RC capacity to 192 FPGAs via two coupled RC boards per server.
representation of something (sometimes on a smaller scale)
One factor is the trend for performance, productivity, and sustainability borne by growing concerns with conventional technologies about speed versus energy consumption, which increasingly favors RC. The conventional model of computing with fixed-logic multicore devices is limiting in terms of performance per unit of energy as compared to reconfigurable-logic devices.
By contrast, numerous research studies show that computing with reconfigurable-logic devices -- FPGAs, et al. -- is fundamentally superior in terms of speed and energy, due to the many advantages of adaptive, customizable hardware parallelism.
While there are a handful of commercial offerings from companies such as Convey Computer, XtremeData, GiDel, Mitrionics, and Impulse Accelerated Technologies, RC is still an area of active research.
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
become different in some particular way, without permanently losing one's or its former characteristics or essence
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
By contrast, numerous research studies show that computing with reconfigurable-logic devices -- FPGAs, et al. -- is fundamentally superior in terms of speed and energy, due to the many advantages of adaptive, customizable hardware parallelism.
an extended fictional work in prose; usually in the form of a story
In the area of productivity, several projects are underway, crafting novel concepts for design of RC applications and systems, including new methods and tools for design formulation and prediction, hardware virtualization, module and core reuse, design verification and optimization, and programming with high-level languages.
In addition, several new collaborations have been inspired by Novo-G, with other research groups, for example, Boston University and the Air Force Research Laboratory, as well as tools vendors such as Impulse Accelerated Technologies and Mitrionics.
an ordered manner; orderliness by virtue of being methodical and well organized
In the U.S., the NSF Center for High-Performance Reconfigurable Computing (CHREC, pronounced "shreck"), acts as the research hub for RC, bringing together more than 30 organizations in this field.
activity directed toward making or doing something
We got the opportunity to ask Dr. George about the work going on at the Center and what he thinks RC technology can offer to high performance computing users.
a quantifier that can be used with count nouns and is often preceded by `a'; a small but indefinite number
George: Naturally, as a relatively new paradigm of computing, RC has started with emphasis in a few targeted areas, for example, aerospace and bioinformatics, where missions and users require dramatic improvement only possible by a revolutionary approach.
It should be noted that RC, as a new paradigm of computing, is broader than FPGA acceleration for HPC. FPGA devices are the leading commercial technology available today that is capable of RC, albeit not originally designed for RC, and thus FPGAs are the focal point for virtually all experimental research and commercial deployments, with a growing list of success stories.
(biology) the process of an individual organism growing organically; a purely biological unfolding of events involved in an organism changing gradually from a simple to a more complex level
An established technology is dominant for many years; it experiences growth over a long period of time from evolutionary advances, and one day it is partially or wholly supplanted by a new, revolutionary technology, but only after that new technology has navigated a long and winding road of research and development.
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
(of quantities) imprecise but fairly close to correct
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
of the immediate past or just previous to the present time
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
George: Naturally, as a relatively new paradigm of computing, RC has started with emphasis in a few targeted areas, for example, aerospace and bioinformatics, where missions and users require dramatic improvement only possible by a revolutionary approach.
metal device shaped in such a way that when it is inserted into the appropriate lock the lock's mechanism can be rotated
Productivity is often a key challenge for a new IT technology, learning how to effectively harness and exploit the inherent advantages of the new approach.
Each FPGA is a Stratix-III E260 device from Altera with 254K logic elements, 768 18x18 multipliers, and more than 4GB of DDR2 memory directly attached via three banks.
to a complete degree or to the full or entire extent (`whole' is often used informally for `wholly')
Altogether, Novo-G features 96 of these FPGAs, with an upgrade underway that by January will double its RC capacity to 192 FPGAs via two coupled RC boards per server.
However, looking ahead more broadly, reconfigurable logic may be featured in future devices with a variety of structures, granularities, functionalities, etc., perhaps very similar to today's FPGAs or perhaps quite different.
any of the more than 100 known substances (of which 92 occur naturally) that cannot be separated into simpler substances and that singly or in combination constitute all matter
Each FPGA is a Stratix-III E260 device from Altera with 254K logic elements, 768 18x18 multipliers, and more than 4GB of DDR2 memory directly attached via three banks.
consisting of or involving two parts or components usually in pairs
Altogether, Novo-G features 96 of these FPGAs, with an upgrade underway that by January will double its RC capacity to 192 FPGAs via two coupled RC boards per server.
While there are a handful of commercial offerings from companies such as Convey Computer, XtremeData, GiDel, Mitrionics, and Impulse Accelerated Technologies, RC is still an area of active research.
In contrast, the structure of parallelism in reconfigurable-logic devices can be customized, that is, reconfigured, for each application or task on the fly, being versatile yet optimized specifically for each problem at hand.
to a complete degree or to the full or entire extent (`whole' is often used informally for `wholly')
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
brought about or set up or accepted; especially long established
An established technology is dominant for many years; it experiences growth over a long period of time from evolutionary advances, and one day it is partially or wholly supplanted by a new, revolutionary technology, but only after that new technology has navigated a long and winding road of research and development.
Both of these project areas of productivity and architecture relate well to HPC.
Meanwhile, one of the unique features of some RC devices is their ability to reconfigure portions of the hardware of the chip while other portions remain unchanged and thus operational, and this powerful feature involves many research and design challenges being studied and addressed by several teams.
One factor is the trend for performance, productivity, and sustainability borne by growing concerns with conventional technologies about speed versus energy consumption, which increasingly favors RC. The conventional model of computing with fixed-logic multicore devices is limiting in terms of performance per unit of energy as compared to reconfigurable-logic devices.
With fixed-logic computing, the user and application have no control over underlying hardware parallelism; they simply attempt to exploit as much as the manufacturer has deemed to provide.
Last but not least, as process densities increase and become more susceptible to faults, environments become harsher, and resources become more prone to soft or hard errors, research challenges arise in fault tolerance.
a process of becoming larger or longer or more numerous or more important
Last but not least, as process densities increase and become more susceptible to faults, environments become harsher, and resources become more prone to soft or hard errors, research challenges arise in fault tolerance.
going or proceeding or going in advance; showing the way
It should be noted that RC, as a new paradigm of computing, is broader than FPGA acceleration for HPC. FPGA devices are the leading commercial technology available today that is capable of RC, albeit not originally designed for RC, and thus FPGAs are the focal point for virtually all experimental research and commercial deployments, with a growing list of success stories.
a particular course of action intended to achieve a result
Last but not least, as process densities increase and become more susceptible to faults, environments become harsher, and resources become more prone to soft or hard errors, research challenges arise in fault tolerance.
keep or maintain in unaltered condition; cause to remain or last
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
However, looking ahead more broadly, reconfigurable logic may be featured in future devices with a variety of structures, granularities, functionalities, etc., perhaps very similar to today's FPGAs or perhaps quite different.
As principal challenges -- performance, productivity, and sustainability -- become more pronounced, and as R&D in RC progresses, we believe that the RC paradigm will mature and expand in its role and influence to eventually become dominant in a broad range of applications, from satellites to servers to supercomputers.
disciple of Jesus and leader of the Apostles; regarded by Catholics as the vicar of Christ on earth and first Pope
George: On-going research projects at the four university sites of CHREC -- the University of Florida, Brigham Young University led by Dr. Brent Nelson, George Washington University led by Dr. Tarek El-Ghazawi, and Virginia Tech led by Dr. Peter Athanas -- fall into four categories: productivity, architecture, partial reconfiguration, and fault tolerance.
a form of energy that is transferred by a difference in temperature
For example, HPC machines lauded in the upper tier of the TOP500 list as most powerful in the world are remarkably high in performance yet also remarkably massive in size, energy, heat, and cost, all featuring programmable, fixed-logic devices, for example, CPU, GPU, Cell.
move with force, "He pushed the table into a corner"
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
Last but not least, as process densities increase and become more susceptible to faults, environments become harsher, and resources become more prone to soft or hard errors, research challenges arise in fault tolerance.
ability to produce solutions in some problem domain
Founded in 2007, CHREC is a national research center under the auspices of the I/UCRC program of the National Science Foundation and consists of more than 30 academic, industry and government partners working collaboratively on research in this field.
Reconfigurable Computing Research Pushes Forward
Despite all the all the recent hoopla about GPGPUs and eight-core CPUs, proponents of reconfigurable computing continue to sing the praises of FPGA-based HPC. The main advantage of reconfigurable computing, or RC for short, is that programmers are able to change the circuitry of the chip on the fly.
Programmable fixed-logic devices no matter their form feature a "one size fits all" or "Jack of all trades" philosophy, with a predefined structure of parallelism, yet attempting to support all applications or some major subset.
In contrast, the structure of parallelism in reconfigurable-logic devices can be customized, that is, reconfigured, for each application or task on the fly, being versatile yet optimized specifically for each problem at hand.
the organized action of making of goods and services for sale
Founded in 2007, CHREC is a national research center under the auspices of the I/UCRC program of the National Science Foundation and consists of more than 30 academic, industry and government partners working collaboratively on research in this field.
computing
