Peter Athanas
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Peter Athanas has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Jorge Alberto Surís
Virginia Polytechnic Institute and State University
3 shared publications - Stephen Craven
Bradley Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University, Blacksburg, VA 24061, USA
2 shared publications - Adolfo Recio
Virginia Polytechnic Institute and State University
1 shared publication Brad Hutchings
1 shared publication- Brent Nelson
Dept. of Electrical and Computer Engineering, NSF Center for High-Performance Reconfigurable Computing (CHREC), Brigham Young University, Provo, UT, USA
1 shared publication - Cameron D. Patterson
Virginia Tech
1 shared publication
Latest Publications
- 14 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 10 (11) , 4879-4897
On the Evaluation of Different High-Performance Computing Platforms for Hyperspectral Imaging: An OpenCL-Based Approach
Hyperspectral imaging systems are a powerful tool for obtaining surface information in many different spectral channels that can be used in many different applications. Nevertheless, the huge amount of information provided by hyperspectral images also has a downside, since it has to be processed and analyzed. For such purpose, parallel hardware devices, such as field-programmable gate arrays (FPGAs) and graphic processing units (GPUs), are typically used, especially for hyperspectral imaging applications under real-time constraints. However, developing hardware applications typically requires expertise in the specific targeted device, as well as in the tools and methodologies that can be used to perform the implementation of the desired algorithms in that device. In this scenario, the Open Computing Language (OpenCL) emerges as a very interesting solution in which a single high-level language can be used to efficiently develop applications in multiple and different hardware devices. In this work, the parallel Fast Algorithm for Linearly Unmixing Hyperspectral Images (pFUN) has been implemented in two different NVIDIA GPUs, the GeForce GTX 980 and the Tesla K40c, using OpenCL. The obtained results are compared with the results provided by the previously developed NVIDIA CUDA implementation of the pFUN algorithm for the same GPU devices for comparing the efficiency of OpenCL against a more specific synthesis design language for the targeted hardware devices, such as CUDA is for NVIDIA GPUs. Moreover, the FUN algorithm has also been implemented into a Bitware Stratix V Altera FPGA, using OpenCL, for comparing the results that can be obtained using OpenCL when targeting different devices and architectures. The obtained results demonstrate the suitability of the followed methodology in the sense that it allows the achievement of efficient FPGA and GPU implementations able to cope with the stringent requirements imposed by hyperspectral imaging systems.
- 14 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 10 (11) , 4879-4897
On the Evaluation of Different High-Performance Computing Platforms for Hyperspectral Imaging: An OpenCL-Based Approach
Hyperspectral imaging systems are a powerful tool for obtaining surface information in many different spectral channels that can be used in many different applications. Nevertheless, the huge amount of information provided by hyperspectral images also has a downside, since it has to be processed and analyzed. For such purpose, parallel hardware devices, such as field-programmable gate arrays (FPGAs) and graphic processing units (GPUs), are typically used, especially for hyperspectral imaging applications under real-time constraints. However, developing hardware applications typically requires expertise in the specific targeted device, as well as in the tools and methodologies that can be used to perform the implementation of the desired algorithms in that device. In this scenario, the Open Computing Language (OpenCL) emerges as a very interesting solution in which a single high-level language can be used to efficiently develop applications in multiple and different hardware devices. In this work, the parallel Fast Algorithm for Linearly Unmixing Hyperspectral Images (pFUN) has been implemented in two different NVIDIA GPUs, the GeForce GTX 980 and the Tesla K40c, using OpenCL. The obtained results are compared with the results provided by the previously developed NVIDIA CUDA implementation of the pFUN algorithm for the same GPU devices for comparing the efficiency of OpenCL against a more specific synthesis design language for the targeted hardware devices, such as CUDA is for NVIDIA GPUs. Moreover, the FUN algorithm has also been implemented into a Bitware Stratix V Altera FPGA, using OpenCL, for comparing the results that can be obtained using OpenCL when targeting different devices and architectures. The obtained results demonstrate the suitability of the followed methodology in the sense that it allows the achievement of efficient FPGA and GPU implementations able to cope with the stringent requirements imposed by hyperspectral imaging systems.
- 1 November 2014
- Published by Elsevier in Microprocessors and Microsystems
- Vol. 38 (8) , 843-844
Introduction to Special issue on FPGA Devices and Applications
- 1 November 2014
- Published by Elsevier in Microprocessors and Microsystems
- Vol. 38 (8) , 843-844
Introduction to Special issue on FPGA Devices and Applications
- 31 July 2010
- Published by Springer Nature in Journal of Signal Processing Systems
- Vol. 64 (3) , 469-481
On the Implementation of a Quasi-Generic Synchronization Architecture for Linear Digital Modulations
- 31 July 2010
- Published by Springer Nature in Journal of Signal Processing Systems
- Vol. 64 (3) , 469-481
On the Implementation of a Quasi-Generic Synchronization Architecture for Linear Digital Modulations
- 1 July 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 239-245
How Threats Drive the Development of Secure Reconfigurable Devices
SRAM-based FPGAs are becoming an attractive target technology for the deployment of secure and cryptographic operations. Because of this, much work has been done in exposing the security vulnerabilities of reconfigurable computing devices. Direct probing, side channel, fault injection, and replay attacks are among the many that can be variously applied to steal secret configurations, keys, data, and access. Here we review the threats faced by FPGAs and propose and analyze security solutions implementable by both FPGA application designers and FPGA vendors. We also look at the particular case of configuration security and use game theory to model the attacker/defender relationship as a 2-person strategic game.
- 1 July 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 239-245
How Threats Drive the Development of Secure Reconfigurable Devices
SRAM-based FPGAs are becoming an attractive target technology for the deployment of secure and cryptographic operations. Because of this, much work has been done in exposing the security vulnerabilities of reconfigurable computing devices. Direct probing, side channel, fault injection, and replay attacks are among the many that can be variously applied to steal secret configurations, keys, data, and access. Here we review the threats faced by FPGAs and propose and analyze security solutions implementable by both FPGA application designers and FPGA vendors. We also look at the particular case of configuration security and use game theory to model the attacker/defender relationship as a 2-person strategic game.
- 1 July 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 198-202
Dynamically Reconfigurable Radios from a High-Level Specification
The dynamic reconfigurability of field programmable gate arrays offers great benefits to software defined radio applications. Leveraging these benefits is difficult, owing to a lack of tool support and the detailed architectural knowledge required. To fully exploit the potential of dynamic hardware, a high-level development environment has been created. This development environment has been validated by implementing a reconfigurable AM radio on a software defined radio platform.
- 1 July 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 198-202
Dynamically Reconfigurable Radios from a High-Level Specification
The dynamic reconfigurability of field programmable gate arrays offers great benefits to software defined radio applications. Leveraging these benefits is difficult, owing to a lack of tool support and the detailed architectural knowledge required. To fully exploit the potential of dynamic hardware, a high-level development environment has been created. This development environment has been validated by implementing a reconfigurable AM radio on a software defined radio platform.
- 1 July 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 05473578,p. 229-233
Untethered On-The-Fly Radio Assembly With Wires-On-Demand
In systems typified by software defined radio, existing flows for run-time FPGA reconfiguration limit resource efficiency when constructing datapaths. We present the wires-on-demand framework that allocates a sandbox region in which modules from a library are flexibly placed and interconnected rapidly and autonomously in an embedded platform without vendor tools.
- 1 July 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 05473578,p. 229-233
Untethered On-The-Fly Radio Assembly With Wires-On-Demand
In systems typified by software defined radio, existing flows for run-time FPGA reconfiguration limit resource efficiency when constructing datapaths. We present the wires-on-demand framework that allocates a sandbox region in which modules from a library are flexibly placed and interconnected rapidly and autonomously in an embedded platform without vendor tools.
- Open Access
- 1 July 2008
- Published by Defense Technical Information Center (DTIC)
Future Field Programmable Gate Array (FPGA) Design Methodologies and Tool Flows
Interest is growing in the use of FPGA devices for high-performance, efficient parallel computation. The large amount of programmable logic, internal routing, and memory can be used to perform a wide variety of high-performance computation more efficiently than traditional microprocessor-based computing architectures. The productivity of FPGA design, however, is very low. FPGA design is very time consuming and requires low-level hardware design skills. This study investigated this FPGA design productivity problem and identified potential solutions that will provide revolutionary improvements in design productivity. Three research areas that must be addressed to achieve such improvements are significant improvement in reuse of FPGA circuits, identification and deployment of higher level design abstractions, and increasing the number of turns per day to significantly increase the number of design iterations. The results of this study suggest that with adequate advancement in each of these areas, FPGA design productivity can be increased by 25X over current practice.
- 1 July 2008
- Published by Defense Technical Information Center (DTIC)
Open AccessFuture Field Programmable Gate Array (FPGA) Design Methodologies and Tool Flows
Interest is growing in the use of FPGA devices for high-performance, efficient parallel computation. The large amount of programmable logic, internal routing, and memory can be used to perform a wide variety of high-performance computation more efficiently than traditional microprocessor-based computing architectures. The productivity of FPGA design, however, is very low. FPGA design is very time consuming and requires low-level hardware design skills. This study investigated this FPGA design productivity problem and identified potential solutions that will provide revolutionary improvements in design productivity. Three research areas that must be addressed to achieve such improvements are significant improvement in reuse of FPGA circuits, identification and deployment of higher level design abstractions, and increasing the number of turns per day to significantly increase the number of design iterations. The results of this study suggest that with adequate advancement in each of these areas, FPGA design productivity can be increased by 25X over current practice.
- Open Access
- 1 January 2007
- Published by Springer Nature in EURASIP Journal on Embedded Systems
- Vol. 2007 (1)
Examining the Viability of FPGA Supercomputing
- 1 January 2007
- Published by Springer Nature in EURASIP Journal on Embedded Systems
- Vol. 2007 (1)
Open AccessExamining the Viability of FPGA Supercomputing
- Open Access
- 1 January 2007
- Published by Springer Nature in EURASIP Journal on Embedded Systems
- Vol. 2007 (1) , 1-8
Examining the Viability of FPGA Supercomputing
- 1 January 2007
- Published by Springer Nature in EURASIP Journal on Embedded Systems
- Vol. 2007 (1) , 1-8
Open AccessExamining the Viability of FPGA Supercomputing
- 1 September 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Exploring Non-Traditional Hardware-Software Interaction
The joint test action group (JTAG) has created what has become a world-wide standard/debug interface for a variety of hardware devices. The emergence of devices such as the Xilinx Virtex-II Pro FPGA, which closely couple advanced microprocessors with reconfigurable logic, presents an opportunity to expand JTAG's capabilities beyond debugging. We present the design and implementation of a platform that combines JTAG, reconfigurable logic, and advanced processor debug features to create a rich environment for exploring non-traditional interaction between hardware and software. More specifically, we outline several possible configurations, discuss performance, and present possible applications
- 1 September 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Exploring Non-Traditional Hardware-Software Interaction
The joint test action group (JTAG) has created what has become a world-wide standard/debug interface for a variety of hardware devices. The emergence of devices such as the Xilinx Virtex-II Pro FPGA, which closely couple advanced microprocessors with reconfigurable logic, presents an opportunity to expand JTAG's capabilities beyond debugging. We present the design and implementation of a platform that combines JTAG, reconfigurable logic, and advanced processor debug features to create a rich environment for exploring non-traditional interaction between hardware and software. More specifically, we outline several possible configurations, discuss performance, and present possible applications