Scope and Motivation

MEDEA-2005 aims to continue the high level of interest of the previous editions held with PACT Conference since 2000.

Due to the ever-increasing gap between CPU and memory speed, there is a great interest in evaluating and proposing processor, multiprocessor and system architectures dealing with the "memory wall" and the wire-delay problems. One of the most interesting approaches is based on decoupling resources, both on-chip and off-chip. In addition, a modular high-level design is becoming more and more important in order to reduce design costs.

In this scenario, system design issues, with particular emphasis on memory subsystem, should be addressed taking into account the combined effect of the system architecture and the particular application domain. In fact, the interaction between the behavior of the application and the system on which it executes stresses the memory subsystem and pushes towards specific solutions.

Typical architectural choices include single processor vs. multiprocessor/multicore solutions, traditional vs. clustered architectures, superscalar, multithreaded or VLIW architectures with emphasis on single chip design. Application domains encompass commercial (Web, DB, and multimedia), embedded (personal, mobile, automotive, automation and medical), networking applications, etc.

MEDEA-2005 Workshop wants to be a forum for academic and industrial people to meet, discuss and exchange their ideas, experience and solutions in the design and evaluation of architectures for embedded, commercial and general purpose systems aimed to address memory performance issues.

As in the previous editions, accepted papers, in an extended form if needed, will appear on the March 2006 special issue of ACM SigArch Computer Architecture News ). The format of the workshop includes presentations of selected papers and discussion after each presentation. Selected papers may be considered for pubblication on the Journal of Embedded Computing (ISSN 1740-4460).


Topics of Interest
-Memory Hierarchy Design for Embedded/General Purpose Systems
-Processor and System Architectures and their impact on memory performances
-Bus/Interconnection Architectures and their impact on memory performances
-Network On Chip
-Low-Power/Wire Delay design of memory hierarchies

-On-chip Multiprocessors and System On Chip

oarchitectures, development tools and applications

o Memory Hierarchy Issues for Heterogeneous Systems

o solutions for embedded, DSP, commercial, scientific and technical workloads

o Inter-Chip and Intra-Chip memory latency tolerant and reduction techniques

o Code optimization techniques

-Academic/industrial experience in high performance, embedded systems and memory design


Organizing and Steering Committee

Sandro Bartolini, bartolini@dii.unisi.it

University of Siena, Italy 

Pierfrancesco Foglia, foglia@iet.unipi.it

University of Pisa, Italy 

Roberto Giorgi, giorgi@dii.unisi.it

University of SienaItaly

Cosimo Antonio Prete, prete@iet.unipi.it
University of Pisa, Italy



Program Committee 
Erik Altman, erik@watson.ibm.com
     IBM T.J. Watson Research Center, NY, USA
Fumio Arakawa, arakawa@crl.hitachi.co.jp
     Central Research Lab., Hitachi Ltd. , Japan

Alessio Bechini, mailto:a.bechini@iet.unipi.it

     University of Pisa, Italy 

Mats Brorsson, Mats.Brorsson@imit.kth.se

     Royal Inst. of Techn. Stockholm, Sweden 

Ali Hurson, hurson@cse.psu.edu

     Penn. State University, PA, USA

David Kaeli, kaeli@ece.neu.edu

     Northeastern University, MA, USA

Krishna Kavi, kavi@cs.unt.edu

     University of North Texas, TX, USA

Stephen Keckler, skeckler@cs.utexas.edu

     University of Texas at Austin, TX, USA

Hiroaki Kobayashi, koba@isc.tohoku.ac.jp

     Tohoku University, Sendai, Japan

David M. Koppelman, koppel@ece.lsu.edu

     Louisiana State Univ., Baton Rouge, LA, USA

Sally McKee, sam@csl.cornell.edu

     Cornell University, NY, USA

Enrico Martinelli, enrico@dii.unisi.it

     University of Siena, Italy

Alexander Milencovich, milenka@eng.uah.edu

     University of Alabama, Huntsville, AL

Veljko Milutinovic, vm@ubbg.etf.ac.yu

     University of Belgrade, Serbia, YU 

Sanjay Patel, sjp@crhc.uiuc.edu

     University of Illinois, Il, USA

Toshinori Sato, toshinori.sato@computer.org

     Kyushu Institute of Technology, Iizuka, Japan

Naohiko Shimizu, pshimizu@fa2.so-net.ne.jp

     Tokai University, Hiratsuka-city, Japan

Alan J. Smith, smith@cs.berkeley.edu

     Univ. of California, Berkeley, CA

Mateo Valero, mateo@ac.upc.es

     Universidad Politecnica de Catalunya, Spain

Theo Ungerer, ungerer@informatik.uni-augsburg.de,

     University of Augsburg, DE, EU

Stamatis Vassiliadis, mailto:S.Vassiliadis@et.tudelft.nl

     T.U. Delft, The Netherlands.

Wei Zhang, zhang@engr.siu.edu.

     Southern Illinois University, Carbondale, IL.
 
 


Information for Authors

The papers should be at most 8 pages in length. The abstracts and papers should be submitted in PDF format by email toPierfrancesco Foglia and SandroBartolini
Paper should be written in standard IEEE format for conference proceedings. Hard copy (postal) submissions will not be accepted. 
Please email submissions by August 1, 2005. You receive an acknowledgment of your submission by the following week. Authors will be notified of acceptance or rejection byAugust 31, 2005 and the final papers are due by September 5, 2005
To speed-up the reviewing process, we encourage also submission of abstract by July 24, 2005
All submissions will be refereed, and informal proceedings will be printed and distributed at the workshop. Accepted papers appear in the March 2006 special issue of ACM SigArch Computer Architecture News. The workshop committee may invite authors to extend their papers for inclusion in the special issue.

Important Dates


 


July 24, 2005
Abstract Submission (not mandatory) 
August 1, 2005
Paper Submission Deadline
August 31, 2005
Acceptance Notification
September 5, 2005
Final Papers Due
September 17, 2005
Workshop will start in Saint Louis


Registration and accommodation

Attendees are requested to go to the hosting PACT'05 conference to perform the registration to Medea-2005 and make room reservations in the conference hotels. We suggest that you make your room reservation in advance and register before the advance registration deadline to benefit from combined PACT'05/Medea'05 registration fees.



Final Program
 
Dusty Caches for Reference Counting Garbage Collection
A. Friedman, P. Krishnamurthy, R. Chamberlain, R. K. Cytron, J. E. Fritts
Data Trace cache: an application specific cache architecture
S. Ramaswamy, J. Sreeram, S. Yalamanchili, K. V. Palem
Making a case for split data caches for embedded applications
A. Naz, K. Kavi, M. Rezaei, W. Li
Exploiting the Replication Cache to Improve Cache Read Bandwidth Cost-Effectively 
B. Allu, W. Zhang, M. Kandala
An Efficient Synchronization Technique for Multiprocessor Systems
M. Monchiero, G. Palermo, C. Silvano, O. Villa
Hiding message delivery and reducing memory access latency by providing
 direct-to-cache transfer during receive operations in a message passing environment
F. Khunjush, N. J. Dimopoulos
NPCryptBench: A Cryptographic Benchmark Suite for Network Processors
Y. Yue, C. Lin, Z. Tan
Memory Bandwidth Optimization through Stream Descriptors
A. Lopez-Lagunas, S. M. Chai
Energy-efficient instruction scheduling exploiting memory access slack
A. Chiyonobu, T. Sato
Analysis of Embedded Video Coder Systems: a System Level Approach
A. Bardine, A. Bechini, P. Foglia, C.A. Prete

 
 
 
 


Schedule

13:30 - Workshop begins: Welcome Message
13:40 - 15:00 Session I: Caching in general purpose and embedded systems

Dusty Caches for Reference Counting Garbage Collection
A. Friedman, P. Krishnamurthy, R. Chamberlain, R. K. Cytron, J. E. Fritts, Washington University, St. Louis, Missouri.
Data Trace cache: an application specific cache architecture
S. Ramaswamy, J. Sreeram, S. Yalamanchili, K. V. Palem, Georgia Institute of Technology, Atlanta, Georgia.
Making a case for split data caches for embedded applications 
A. Naz, K. Kavi, M. Rezaei, W. Li, The University of North Texas, Denton, Texas.
Exploiting the Replication Cache to Improve Cache Read Bandwidth Cost-Effectively 
B. Allu, W. Zhang, M. Kandala, Southern Illinois University, Carbondale, Illinois.
15:00 - 15:30 Break
15:30 - 16:30 Session II: Multiprocessors and network processors
An Efficient Synchronization Technique for Multiprocessor Systems
M. Monchiero, G. Palermo, C. Silvano, O. Villa, Politecnico di Milano, Italy.
Hiding message delivery and reducing memory access latency by providing direct-to-cache transfer during receive operations in a message passing environment
F. Khunjush, N. J. Dimopoulos, University of Victoria, Victoria, Canada.
NPCryptBench: A Cryptographic Benchmark Suite for Network Processors 
Y. Yue, C. Lin, Tsinghua University, China, Z. Tan, University of California, Berkeley, California
16:30 - 17:30 Session III: Energy, memory bandwidth and system optimizations
Memory Bandwidth Optimization through Stream Descriptors
A. Lopez-Lagunas, ITESM Campus Toluca, Tocula, Mexico, S. M. Chai, ESPS-COE, Motorola Labs.
Energy-efficient instruction scheduling exploiting memory access slack
A. Chiyonobu, T. Sato, Kyushu Institute of Technology, Japan
Analysis of Embedded Video Coder Systems: a System Level Approach
A. Bardine, A. Bechini, P. Foglia, C.A. Prete, University of Pisa, Pisa, Italy