Reconfigurable Work Farms on a Massively Parallel Processor Array

Butts, Mike; Budlong, Brad; Wasson, P.; White, Elizabeth L.

doi:10.1109/fccm.2008.6

Cited by 4 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A heterogeneous work farm introduces the next level of system dynamics by having a variety of worker objects available, executing a variety of functions on input data [12]. Each work packet contains input data with an opcode in the header indicating the function to apply.…”

Section: Heterogeneous Load Balancingmentioning

confidence: 99%

Multi-mode sensor processing on a dynamically reconfigurable massively parallel processor array

Chen¹,

Butts²,

Budlong³

et al. 2008

Signal Processing, Sensor Fusion, and Target Recognition XVII

Self Cite

View full text Add to dashboard Cite

This paper introduces a novel computing architecture that can be reconfigured in real time to adapt on demand to multimode sensor platforms' dynamic computational and functional requirements. This 1 teraOPS reconfigurable Massively Parallel Processor Array (MPPA) has 336 32-bit processors. The programmable 32-bit communication fabric provides streamlined inter-processor connections with deterministically high performance. Software programmability, scalability, ease of use, and fast reconfiguration time (ranging from microseconds to milliseconds) are the most significant advantages over FPGAs and DSPs. This paper introduces the MPPA architecture, its programming model, and methods of reconfigurability. An MPPA platform for reconfigurable computing is based on a structural object programming model. Objects are software programs running concurrently on hundreds of 32-bit RISC processors and memories. They exchange data and control through a network of self-synchronizing channels. A common application design pattern on this platform, called a work farm, is a parallel set of worker objects, with one input and one output stream. Statically configured work farms with homogeneous and heterogeneous sets of workers have been used in video compression and decompression, network processing, and graphics applications. INTRODUCTIONMany advanced SIR (Surveillance, Intelligence and Reconnaissance) sensors support multi-mode operation to respond to unique situational demands. For example, the Lockheed Martin AN/SPY-2 is a long-range, 3D, and multi-function radar that is designed for theater ballistic-missile defense and full-area anti-air warfare in addition to short-to medium-range searching and multi-target tracking. The BAE SAMPSON multi-function radar provides weapon-control functions in addition to search and precision tracking of multiple targets. Most advanced E-O (Electro-Optic) systems integrate multiple types of E-O/IR detectors in one sensor package. The Thales SIRIUS long-range IR search and track system provides bispectral panoramic surveillance with simultaneous MWIR-and LWIR-band operation for automatic detection, track initiation, target priority ranking, and tracking. In moving-platform E-O sensor packages, while versatility is as important as it is in the larger systems, the stringent physical constrains of airborne gimbals and reconnaissance pods pose additional weight and size challenges.Historically, each mode of sensor operation required dedicated hardware and software modules. From the system architecture point of view, such worst-case design approaches waste system resources. A large portion of the processing resources sit idle and redundant at any given time. Demands for increases in functional and operational requirements, and decreases in cost, footprint, and power, suggest the need for a hardware processing platform that can be reconfigured on demand to support multi-mode sensor processing. The DoD's JTRS initiative even made reconfigurability a requirement for Software Defined Radio (SDR). SDR...

show abstract

Section: Heterogeneous Load Balancingmentioning

confidence: 99%

Multi-mode sensor processing on a dynamically reconfigurable massively parallel processor array

Chen¹,

Butts²,

Budlong³

et al. 2008

Signal Processing, Sensor Fusion, and Target Recognition XVII

Self Cite

View full text Add to dashboard Cite

show abstract

“…The reconfiguration process based on its specification in the occam-pi language can be performed by taking into account a work farm design approach [21,22]. A worker is a particular function mapped onto a specific processor or group of processors.…”

Section: Implementing the Reconfiguration Frameworkmentioning

confidence: 99%

Occam-pi for Programming of Massively Parallel Reconfigurable Architectures

Ul-Abdin

Svensson

2012

International Journal of Reconfigurable Computing

View full text Add to dashboard Cite

Massively parallel reconfigurable architectures, which offer massive parallelism coupled with the capability of undergoing run-time reconfiguration, are gaining attention in order to meet the increased computational demands of high-performance embedded systems. We propose that the occam-pi language is used for programming of the category of massively parallel reconfigurable architectures. The salient properties of the occam-pi language are explicit concurrency with built-in mechanisms for interprocessor communication, provision for expressing dynamic parallelism, support for the expression of dynamic reconfigurations, and placement attributes. To evaluate the programming approach, a compiler framework was extended to support the language extensions in the occam-pi language and a backend was developed to target the Ambric array of processors. We present two case-studies; DCT implementation exploiting the reconfigurability feature of occam-pi and a significantly large autofocus criterion calculation based on the dynamic parallelism capability of the occam-pi language. The results of the implemented case studies suggest that the occam-pi-language-based approach simplifies the development of applications employing run-time reconfigurable devices without compromising the performance benefits.

show abstract