ACM Home Page
Please provide us with feedback. Feedback
MIMD implementation with PicoBlaze microprocessor using MPI functions
Full text PdfPdf (282 KB)
Source ACM International Conference Proceeding Series; Vol. 285 archive
Proceedings of the 2007 international conference on Computer systems and technologies table of contents
Bulgaria
SESSION: Computer systems table of contents
Article No. 4  
Year of Publication: 2007
ISBN:978-954-9641-50-9
Author
Pavel Zaykov  Technical University of Sofia, Bulgaria
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 3,   Downloads (12 Months): 34,   Citation Count: 0
Additional Information:

abstract   references   index terms  

Tools and Actions: Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/1330598.1330604
What is a DOI?

ABSTRACT

The article represents an approach of designing multiprocessor parallel architecture based on message passing paradigm in one of the Xilinx Spartan 3 family chips. Compared to the Flynn's taxonomy it falls in MIMD architectures with SPMD program model. Each node consist PicoBlaze -- 8-bits RISC microcontroller, local memory and communication assistant. Nodes are connected using custom-made network switch. Software abstraction model of the system is hierarchically designed in three layers. The lowest one is responsible for communication protocols and State Machines. The second one consists implementations of MPI_Send and MPI_Receive functions, which deliver abstraction for layer three -- program realization. Evaluation of the system is made -- system acceleration is measured using scalability of data and hardware resources.