Customization of application specific heterogeneous multi-pipeline processors

Radhakrishnan, S.; Guo, Hui; Parameswaran, Sri

doi:10.1109/date.2006.244094

Cited by 8 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An explorer with performance estimator is shown in Figure 2. Examples of such approaches are [4][5][6][7][8][9][10][11][12][13][14][15].…”

Section: Fig 1: Asip Design Methodologymentioning

confidence: 99%

ADA: Applications Define ASIP

Jain¹

2014

IJCA

View full text Add to dashboard Cite

Interest in Application Specific Instruction set Processors or ASIPs has increased significantly. Sincere efforts have been put in improving ASIP design methodologies in industry as well as in academia. By the close observation and analysis of these approaches, it was found that though the existing approaches are focusing on making the process automatic and providing better GUI to help the designers, core technique used in deciding the suitable architecture (processor and memory) is based on design space exploration. This exploration is done with the help of estimators. Such estimators are either simulator based or scheduler based. This study identifies that both types of techniques are very far from the ideal dream technique in which applications should have defined the suitable architecture configuration and these techniques are becoming unsuitable in current scenario. Each problem has a solution hidden in it. This scenario motivated us to propose a novel and revolutionary ASIP design technique making the dream true. The Proposed technique does not focuses on design space exploration, it focuses on directly defining processors for given applications rather than searching for suitable configuration in a jungle of configurations can be suggested by the architecture design space. General TermsComputer Architecture, Processor Design, Processor Design Technology.

show abstract

“…An explorer with performance estimator is shown in Figure 2. Examples of such approaches are [4][5][6][7][8][9][10][11][12][13][14][15].…”

Section: Fig 1: Asip Design Methodologymentioning

confidence: 99%

ADA: Applications Define ASIP

Jain¹

2014

IJCA

View full text Add to dashboard Cite

show abstract

“…For example, multi-pipelines were used to support application specific processors [13], discrete Fourier transformations in real-time [12] and medical imaging [11]. Our approach differs from these approaches because the pipeline is interweaved with a complex memory organisation supporting the GCA model ( Figure 4).…”

Section: Introductionmentioning

confidence: 99%

A scalable configurable architecture for the massively parallel GCA model

Jendrsczok

Ediger

Hoffmann

2009

International Journal of Parallel, Emergent and Distributed Sys

View full text Add to dashboard Cite

The global cellular automata model (GCA) is a massively parallel computation model which extends the classical cellular automata (CA) model with dynamic global neighbours. We present for that model a data parallel architecture which is scalable in the number of parallel pipelines and which uses application specific operators (adapted operators). The instruction set consists of control and RULE instructions. A RULE computes the next cell contents for each cell in the destination object. The machine consists of P pipelines. Each pipeline has an associated primary memory bank and has access to the global memory (real or emulated multiport memory). Therefore each pipeline can execute one cell operation in every clock cycle. The diffusion of particles was used as an example in order to demonstrate the adaptive operators, the machine programming and its performance. Particles which point to each other within a defined neighbourhood search space are interchanged. The pointers are modified in each generation by a pseudo random function. For that application, an application-specific data parallel machine with up to 32 pipelines was synthesised for an Altera field-programmable gate array. In addition, this application was described in the high-level language GCAL. The RULE instruction can also automatically be extracted from the GCAL program leading to the same generated application specific DPA machine.

show abstract

“…For example multi-pipelines were used to support application specific processors [11], discrete fourier transformations in real-time [10] and medical imaging [9]. Our approach differs from these approaches because the pipeline is interweaved with a complex memory organization supporting the GCA model (Fig.…”

Section: Introductionmentioning

confidence: 99%

A scalable configurable architecture for the massively parallel GCA model

Jendrsczok

Ediger

Hoffmann

2008

2008 IEEE International Symposium on Parallel and Distributed Processing

View full text Add to dashboard Cite

The Global Cellular Automata model (GCA) is a massively parallel computation model which extends the classical Cellular Automata model (CA) with dynamic global neighbors. We present for that model a data parallel architecture which is scalable in the number of parallel pipelines and which uses application specific operators (adapted operators). The instruction set consists of control and RULE instructions. A RULE computes the next cell contents for each cell in the destination object. The machine consists of P pipelines. Each pipeline has an associated primary memory bank and has access to the global memory (real or emulated multi port memory).The diffusion of particles was used as an example in order to demonstrate the adaptive operators, the machine programming and its performance. Particles which point to each other within a defined neighborhood search space are interchanged. The pointers are modified in each generation by a pseudo random function. The machine with up to 32 pipelines was synthesized for an Altera FPGA for that application.

show abstract

Customization of application specific heterogeneous multi-pipeline processors

Abstract: ABSTRACT

Cited by 8 publications

References 23 publications

ADA: Applications Define ASIP

ADA: Applications Define ASIP

A scalable configurable architecture for the massively parallel GCA model

A scalable configurable architecture for the massively parallel GCA model

Contact Info

Product

Resources

About