A Heterogeneous Multiprocessor Architecture for Flexible Media Processing

@article{Rutten2002AHM,
  title={A Heterogeneous Multiprocessor Architecture for Flexible Media Processing},
  author={Martijn J. Rutten and Jos T. J. van Eijndhoven and Egbert G. T. Jaspers and Pieter van der Wolf and Evert-Jan D. Pol and Om Prakash Gangwal and Adwin H. Timmer},
  journal={IEEE Des. Test Comput.},
  year={2002},
  volume={19},
  pages={39-50}
}
Eclipse is a scalable architecture template for designing data-dependent stream-processing subsystems of media-processing SoCs. It combines application configuration flexibility with the efficiency of function-specific coprocessors that concurrently execute the tasks of one or more applications. 

Figures from this paper

Robust media processing in a flexible and cost-effective network of multi-tasking coprocessors
TLDR
Eclipse defines a heterogeneous multiprocessor architecture for high-performance streaming media as a subsystem of a system-on-silicon platform for the consumer electronics market as a template for multiple function-specific coprocessors that operate in parallel and independently.
Evaluating schedulers for multimedia processing on buffer-constrained SoC platforms
TLDR
An analytical framework for designing and evaluating schedulers for SoC multimedia platforms is presented and the modeling technique subsumes standard event models used in real-time scheduling and accurately captures the variability in task execution requirements.
A multicast inter-task communication protocol for embedded multiprocessor systems
TLDR
A configurable SystemC model of the ITCP protocol and its integration in a system-level design methodology is disclosed in this work and details of a multi- Task Transaction Level software shell implementation for an ARM9 with eCos RTOS are given.
Repetitive Allocation Modelling with MARTE
TLDR
This paper will highlight the expressivity of this notation and clarify its usage through examples and comparisons to other distribution notations such as in High Performance Fortran.
Dynamic reconfiguration of streaming graphs on a heterogeneous multiprocessor architecture
TLDR
Though simple and easy to use, the interface addresses the key challenge of reconfiguring individual tasks while maintaining real-time behavior and data integrity of the overall set of concurrently executing applications.
Towards a framework for system-level design of multiprocessor SoC platforms for media processing
  • S. Chakraborty
  • Computer Science
    2005 IEEE International Conference on Application-Specific Systems, Architecture Processors (ASAP'05)
  • 2005
TLDR
A high-level view of a general framework for analyzing multimedia applications running on multiprocessor system-on-chip (SoC) platforms is given, which can accurately capture the data-dependent execution time variabilities associated multimedia tasks and the burstiness of on-chip traffic resulting from multimedia processing.
Design and programming of embedded multiprocessors: an interface-centric approach
We present design technology for the structured design and programming of embedded multi-processor systems. It comprises a task-level interface that can be used both for developing parallel
Heterogeneous multiprocessor on chip compiler, architecture, place and route design space exploration
  • O. Hammami
  • Computer Science
    MELECON 2008 - The 14th IEEE Mediterranean Electrotechnical Conference
  • 2008
TLDR
The design space exploration benefits of heterogeneous multiprocessors of the combined effects of compiler, architecture and place and route are described.
Flexible hardware/software support for message passing on a distributed shared memory architecture
TLDR
This paper presents lightweight support for message passing, and has made the library as flexible as possible such that it can optimally match the application with the target architecture.
A modular simulation framework for spatial and temporal task mapping onto multi-processor SoC platforms
TLDR
A SystemC-based simulation framework, which enables the quantitative evaluation of application-to-platform mappings by means of an executable performance model, and highlights the potential for optimization of an efficient design space exploration environment.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 25 REFERENCES
Robust media processing in a flexible and cost-effective network of multi-tasking coprocessors
TLDR
Eclipse defines a heterogeneous multiprocessor architecture for high-performance streaming media as a subsystem of a system-on-silicon platform for the consumer electronics market as a template for multiple function-specific coprocessors that operate in parallel and independently.
Design of multi-tasking coprocessor control for Eclipse
  • M. Rutten, J. V. Eijndhoven, E. Pol
  • Computer Science
    Proceedings of the Tenth International Symposium on Hardware/Software Codesign. CODES 2002 (IEEE Cat. No.02TH8627)
  • 2002
TLDR
The interface facilitates the design of coprocessors that require complex control to handle data-dependent I/O, saving/restoring task state upon task switches, and pipelined processing.
Hardware-software interactions on Mpact
TLDR
The author discusses the reasons for media processors existence, the implementation of the M pact media processor, and some examples of the relationship between hardware and software on the Mpact chip.
A scalable and flexible data synchronization scheme for embedded HW-SW shared-memory systems
TLDR
This paper describes the implementation of a data-synchronization scheme that can be used in the functional description and hardware realization of algorithms for heterogeneous multiprocessor architectures, without the need for atomic semaphore instructions.
Viper: A Multiprocessor SOC for Advanced Set-Top Box and Digital TV Systems
Viper is a complete system-on-a-chip solution from Philips Semiconductors for next-generation digital television and digital video applications. It incorporates Philips' intellectual-property reuse
Compaan: deriving process networks from Matlab for embedded signal processing architectures
TLDR
The Compaan tool is presented that automatically transforms a nested loop program written in Matlab into a process network specification, which fits better with the new emerging kind of embedded architectures that use coprocessors.
Survey of architectures for media processing
TLDR
The objective of this paper is to present a detailed categorization of the various architectural alternatives for multimedia processing based on the programmability of hardware and data distribution.
TriMedia CPU64 architecture
TLDR
A new VLIW core is presented as a successor to the TriMedia TM1000, targeted for embedded use in media-processing devices like DTVs and set-top boxes and supplemented with on-chip co-processors to obtain a cost-effective system.
Processing the new world of interactive media
TLDR
This paper presents TM-1000, a multimedia system on a chip that consists of a high-performance VLIW-based CPU core, large instruction and data caches, main memory interface, and video, audio and communication related peripherals.
Media processors using a new microsystem architecture designed for the Internet era
  • D. Wyland
  • Computer Science
    Electronic Imaging
  • 1999
TLDR
The UMS is a completely programmable (including I/O) system on a chip that combines hardware performance with the fast time to market, low cost and low risk of software designs.
...
1
2
3
...