This is the April 2003 Digest of SIGARCH Messages (sigarch-apr03): * ISCA 2003 Call for Participation http://isca03.cs.princeton.edu Submitted by Allan Gottlieb <gottlieb@nyu.edu> * SIGARCH travel grants for companion care-provider for ISCA 2003 http://isca03.cs.princeton.edu/grants.htm Submitted by Sarita Adve <sadve@cs.uiuc.edu> * SIGARCH student travel grants for ISCA 2003 http://isca03.cs.princeton.edu/grants.htm Submitted by Sarita Adve <sadve@cs.uiuc.edu> * 2003 International Conference on Parallel Processing (ICPP-03) Call for Papers http://www.cis.ohio-state.edu/~icpp2003/ Submitted by Sudhanva Gurumurthi <gurumurt@cse.psu.edu> * 2003 Workshop on Duplicating, Deconstructing, and Debunking Call for Papers http://www.ece.wisc.edu/~wddd Submitted by Bryan Black <bryan.black@intel.com> * First Value-Prediction Workshop http://www.csl.cornell.edu/VPW1/ Submitted by Martin Burtscher <burtscher@csl.cornell.edu> * SNIA Worldwide Repository for I/O Traces, Tools and Analysis http://www.snia.org/apps/IOTTA_Survey/register.php Submitted by Arnold Jones <td@snia.org> * IEEE Computer Special Issue on Power- and Temperature-Aware Computing http://www.computer.org Submitted by Kevin Skadron <skadron@cs.virginia.edu> * Computer Architecture Letters http://www.comp-arch-letters.org Submitted by Kevin Skadron <skadron@cs.virginia.edu> --Doug Burger SIGARCH Information Director infodir_SIGARCH@acm.org * Archive: http://www.cs.wisc.edu/~lists/archive/sigarch-members/maillist.html * Web pages: http://www.cs.wisc.edu/~arch/www/, http://www.acm.org/sigarch/ * To remove yourself from the SIGARCH mailing list: mail listserv@acm.org with message body: unsubscribe SIGARCH-MEMBERS ----------------------------------------------------------------- Doug Burger Office: 3.432 ACES Assistant Professor Phone: 512-471-9795 Department of Computer Sciences Assistant: 512-471-9442 University of Texas at Austin Fax: 512-232-1413 Taylor Hall 2.124 E-mail: dburger@cs.utexas.edu Austin, TX 78712-1188 USA www.cs.utexas.edu/users/dburger ----------------------------------------------------------------- * ISCA 2003 Call for Participation The thirtieth International Symposium on Computer Architecture (ISCA) will be held at the Town and Country Hotel in San Diego 9-11 June, 2003. ISCA 2003 is a constitutent conference in the ACM Federated Computing Research Conference (FCRC). Information about ISCA, including its tutorial/workshop program can be found at <http://isca03.cs.princeton.edu>. Information about FCRC, including registration and hotel information can be found at <"http:acm.org/sigs/conferences/fcrc>. ---------------------------------------------------------------------- ---------------------------------------------------------------------- * SIGARCH travel grants for companion care-provider for ISCA 2003 http://isca03.cs.princeton.edu/grants.htm SIGARCH is providing funds for a limited number of travel grants to attend ISCA 2003 for a companion care-provider for a SIGARCH member who is: (1) a person with a physical disability necessitating a companion, or (2) a parent of an infant less than one year old who cannot travel without the infant and a care-provider for the infant. The only costs covered are those incurred solely for the transportation of the companion. Shared transportation expenses, such as taxis, and non-transportation costs, such as room and board, are not covered. The application deadline is 9 May 2003 and recipients will be notified approximately one week later. The size of grants may be limited due to budgetary constraints. In particular, there may be upper bounds on specific items, and we may set different upper bounds based upon the level of involvement (symposium speaker, vs. workshop speaker, vs. coauthor for example). Grants will be paid on submission of original travel receipts and a brief trip report. Grant application forms are available here. To apply for a grant, email or snail mail a completed application form to: Allan Gottlieb <gottlieb@nyu.edu> NEC Research Institute 4 Independence Way Princeton NJ 08540 ---------------------------------------------------------------------- ---------------------------------------------------------------------- * SIGARCH student travel grants for ISCA 2003 http://isca03.cs.princeton.edu/grants.htm SIGARCH is providing funds for a limited number of travel grants for student members of SIGARCH to attend ISCA 2003. Grants can cover transportation, symposium registration, and lodging (limited to the night before and the nights of the symposium itself, not workshops or tutorials). Meals are not covered. The application deadline is 9 May 2003 and recipients will be notified approximately one week later. The size of grants may be limited due to budgetary constraints. In particular there may be upper bounds on specific items, and we may set different upper bounds based upon the level of involvement (symposium speaker, vs. workshop speaker, vs. coauthor for example). Grants will be paid on submission of original travel receipts and a brief trip report. Grant application forms are available here. To apply for a grant, email or snail mail a completed application form to: Allan Gottlieb <gottlieb@nyu.edu> NEC Laboratories America 4 Independence Way Princeton NJ 08540 ---------------------------------------------------------------------- ---------------------------------------------------------------------- * 2003 International Conference on Parallel Processing (ICPP-03) Call for Papers http://www.cis.ohio-state.edu/~icpp2003/ ---------------------------------------------------------------------- ---------------------------------------------------------------------- * 2003 Workshop on Duplicating, Deconstructing, and Debunking Call for Papers ************************************************************* CALL FOR PAPERS: WDDD 2003 ************************************************************* Workshop on Duplicating, Deconstructing, and Debunking http://www.ece.wisc.edu/~wddd Held in conjunction with ISCA-30 San Diego, CA June 8, 2003 ------------------------------------------------------------- IMPORTANT DATES --------------- Abstracts due: April 25, 2003 Submissions due: May 2, 2003 Acceptance: May 18, 2003 Final version: June 1, 2003 WORKSHOP OVERVIEW ----------------- WDDD provides the computer architecture and microarchitecture research community a forum for work that validates or duplicates earlier results; deconstructs prior findings by providing greater, in-depth insight into causal relationships or correlations; or debunks earlier findings by describing precisely how and why proposed techniques fail where earlier successes were claimed, or succeed where failure was reported. Traditionally, computer architecture conferences and workshops focus almost exclusively on novelty and performance, neglecting an abundance of interesting work that lacks one or both of these attributes. A significant part of research--in fact, the backbone of the scientific method--involves independent validation of existing work and the exploration of strange ideas that never pan out. This workshop provides a venue for disseminating such work in our community. Published validation experiments strengthen existing work, while thorough comparisons provide new dimensions and perspectives. Studies that refute or correct existing work also strengthen the research community, by ensuring that published material is technically correct and has sound assumptions. Publishing negative or strange or unexpected results will allow future researchers to learn the hard lessons of others, without repeating their effort. This workshop will set a high scientific standard for such experiments, and will require insightful analysis to justify all conclusions. The workshop will favor submissions that provide meaningful insights and point to underlying root causes for the failure or success of the technique under investigation. Acceptable work must thoroughly investigate and clearly communicate why the proposed technique performs as the results indicate. Rebuttals may be invited for debunking submissions. SUBMISSION TOPICS ----------------- * Independent validation of earlier results with meaningful analysis * In-depth analysis and sensitivity studies that provide further insight into earlier findings, or identify key parameters or assumptions that affect the results * Studies that refute earlier findings, with clear justification and explanation * Negative results for ideas that intuitively make sense and should work, along with explanations for why they do not SUBMISSION GUIDELINES --------------------- * Submit a 200-word abstract plus title and list of authors in plain text email by April 25, 2003, on the workshop website www.ece.wisc.edu/~wddd * Submit a 5000-word double-spaced manuscript by May 2, 2003, as a PS or PDF file on the workshop website www.ece.wisc.edu/~wddd Inappropriate submissions, as described in the submitted abstract, will be rejected outright. Similarly, inflammatory, abusive, or overtly combative and negative submissions will not be considered. Accepted papers will be published in the ISCA-30 workshop proceedings. WORKSHOP ORGANIZERS ------------------- Bryan Black, Intel Labs, bryan.black@intel.com Mikko Lipasti, University of Wisconsin, mikko@engr.wisc.edu PROGRAM COMMITTEE ----------------- Brad Calder, UCSD Bob Colwell, R & E Colwell Alvy Lebeck, Duke Vijay Pai, Rice Guri Sohi, Wisconsin ---------------------------------------------------------------------- ---------------------------------------------------------------------- * First Value-Prediction Workshop http://www.csl.cornell.edu/VPW1/ to be held in conjunction with the 30th International Symposium on Computer Architecture San Diego, California Saturday, June 7, 2003 Theme The first Value-Prediction Workshop (VPW1) encompasses all hardware and software speculation mechanisms that require multi-bit predictions as well as value profiling and other value-based optimization techniques. Topics include but are not limited to · value predictors (instruction source operands and/or results) · confidence estimators · latency predictors · pre-execution block predictors · way predictors for set-associative caches · line eviction/flush predictors · dependency predictors · address predictors (prefetchers) · branch target predictors · multi-branch predictors (for trace caches) · value profiling · value-based optimizations Important Dates Submission: April 25 (5pm EDT) Notification: May 16 Final paper: May 29 Submission Guidelines Submissions must use at least 10-point fonts, one-inch margins, and are not to exceed six US letter size pages (including figures and tables). Submissions must be in PDF. Please email submissions and questions to vpw1@csl.cornell.edu. Organizers Martin Burtscher (Cornell University) Amer Diwan (University of Colorado at Boulder) Program Committee Brad Calder (University of California, San Diego) Tom Conte (North Carolina State University) Rajiv Gupta (The University of Arizona) Mikko H. Lipasti (University of Wisconsin - Madison) Avi Mendelson (Intel Corporation) Yiannakis Sazeides (University of Cyprus) ---------------------------------------------------------------------- ---------------------------------------------------------------------- * SNIA Worldwide Repository for I/O Traces, Tools and Analysis Storage Network Industry Association (SNIA) Worldwide Repository for I/O Traces, Tools and Analysis I/O trace data is a valuable resource that allows the Storage Industry to provide solutions that better aligns with actual customer use. In addition trace data allows Academic researchers the ability to test their research with real world data. Unfortunately, I/O trace data availability has been rare, so historically the Storage Industry has been forced to use archaic trace data (sometimes 20 years old in the Academic Community) to project customer workload requirements with new products. In an effort to better serve the marketplace that is demanding improved storage performance, the SNIA I/O Traces, Tools and Analysis Technical Work Group is constructing the "World Wide Repository for I/O Traces, Tools and Analysis" - a valuable resource that will contain traces, tools, and analysis supporting a current robust population of trace data. To ensure this repository will be a relevant and efficient resource for you, we ask your assistance in completing the following survey (see URL below). The information you provide will be greatly appreciated. http://www.snia.org/apps/IOTTA_Survey/register.php ---------------------------------------------------------------------- ---------------------------------------------------------------------- * IEEE Computer Special Issue on Power- and Temperature-Aware Computing Guest Editors: Mircea R. Stan, ECE Department, University of Virginia Kevin Skadron, CS Department, University of Virginia Call for Papers: deadline June 1, 2003 Despite the continuous scaling of processes and supply voltages, and the increased awareness of low-power issues in the computer design and design automation communities, power consumption by state-of-the-art ICs has continually increased in recent years. This apparent paradox results from the increased density enabled by process scaling and a multilayer interconnect, coupled with increases in area and especially in clock frequency driven by an insatiable market for high performance systems. Temperature is also on the verge of becoming a first-class design constraint along with the more traditional constraints of cost, performance, and power. The increasing importance of thermal effects stems from an exponential increase in on-chip power densities, with today's processors having power densities greater than a hot plate and within an order of magnitude of a rocket nozzle. An integrated and coordinated set of design techniques is required in order to successfully manage growing power and thermal demands while still meeting performance, reliability, and cost targets. Research, characterization, and survery papers are requested for the December 2003 issue of IEEE Computer. This issue will be devoted to the subjects of Power-Aware and Temperature-Aware Computing, including run-time and compile-time techniques at the circuit, architecture, and system levels for improving battery life, current delivery, and operating temperature; and integrated concerns of reliability and quality of service. An integrated and coordinated set of design techniques is required in order to successfully manage growing power and thermal demands while still meeting performance, reliability, and cost targets. Example topics of interest include circuit, architecture, and system techniques for regulating static and dynamic power; improved models for power, current-delivery, and thermal aspects; compiler-hardware and OS-hardware cooperation, methods for optimizing energy efficiency subject to real-time or quality-of-service requirements, and active-cooling techniques. Send inquiries to Guest Editors Mircea R. Stan, University of Virginia (mircea@virginia.edu) and Kevin Skadron, University of Virginia (skadron@virginia.edu). Submit pdf documents by June 1 to computer-ma@computer.org and specify the special issue of Power-Aware and Temperature-Aware Computing. ---------------------------------------------------------------------- ---------------------------------------------------------------------- * Computer Architecture Letters Computer Architecture Letters is pleased to announce the publication of another paper online at our website, <http://www.comp-arch-letters.org>; the abstract appears below. The papers will appear in print in our next paper issue. The print issues are distributed to the entire IEEE Computer Society TCCA membership, and e-mail notifications of newly accepted papers are sent on a regular basis to the TCCA and ACM SIGARCH memberships. The objective of Letters is to publish short (4-page), timely articles of high-quality work. We are very much aware of the long delays in our field between submissions of manuscripts and their eventual appearance in print. We are doing something about that with this journal. After a little more than one year of operation, we have maintained an average turnaround time from submission to author notification of just one month, with an acceptance rate of 20%. We encourage the community to continue submitting papers to Letters. Submissions are welcomed on any topic in computer architecture, especially but not limited to: - Microprocessor and multiprocessor systems - Microarchitecture and ILP processors - Workload characterization - Performance evaluation and simulation techniques - Compiler-hardware and operating system-hardware interactions - Interconnect architectures - Memory and cache systems - Power and thermal issues at the architecture level - I/O architectures and techniques - Independent validation of previously published results - Analysis of unsuccessful techniques - Network and embedded-systems processors - Real-time and high-availability architectures - Reconfigurable systems The call for papers and instructions for submission can be found at <http://www.comp-arch-letters.org> Abstracts --------- K.-H. Sihn, J. Lee, J.-W. Cho. "A Speculative Coherence Scheme using Decoupling Synchronization for Multiprocessor Systems." Volume 2, Mar. 2003. Abstract: This paper proposes a new speculative coherence scheme, SCDS, for hardware distributed shared memory systems to reduce the overhead of coherence action in directory-based cache-coherence protocol. SCDS has two main features, predicting accurate timing of speculative coherence with synchronization information and detecting write pattern (migratory and non-migratory) for exclusive blocks' speculative coherence action. In our simulation, SCDS outperforms existing schemes (DSI and LTP) for well-synchronized applications. ---------------------------------------------------------------------- ----------------------------------------------------------------------