Thomas M. Stricker - Professor at ETH Zürich

this is my old personal home page as professor hosted by an independent ISP!
As I am working in secretive industry now - there is little material for a new page.

assistant professor of
computer science


postal address:
   Institut für Computersysteme
   ETH Zentrum / RZ H21
   CH-8092 Zürich
   Switzerland
street address (add for FedEx, DHL, UPS):
   Clausiusstrasse 59
voice: 41 1 632 7316 fax: ...1307

e-mail
tomstr at inf.ethz.ch
tomstr at acm.org
tomstr at computer.org

whereabouts:
finger tomstr, home address,
videostream (if on)

directions to my office
visitors page


   ....here is a collection of links to all my group-, laboratory-, department-, university and other
       home pages: CoPs [my current umbrella project], PDS [the group in Parallel and Distributed
       Systems, I am running], ICS [the Laboratory for Computersystems, I was chairing for a while],
       DINFK [Dept. of Computer Science, I am affilated with], ETHZ [Swiss Institute of Technology,
       the University, I work at]. My who-is-who entry in the faculty directory (german, english), and
       a completely out of date entry in the official university register of ongoing research...(note [1])


about my research:

My research interests are in distributed systems and in high speed communication technologies. My current plans include research in computer architecture (memory systems modeling) and in system software (infrastructures for scalable and distributed applications). I am currently building systems based on commodity PC hardware connected by a Gigabit networking technology with good scalability for several applications in scientific computing, distributed databases and everyday computing. An important priority in my research are proper scientific methods in performance modelling and in performance prediction of systems. My most recent work of (computer) architecture is the 128 x 1GHz node multiboot cluster XIBALBA, which is used for a variety of research within the departement of computer science (see project description, XIBALBA maintainers page).

about my vision on the future of computing and communication:

While the computer hardware itself is getting faster and faster, steadily and according to a well predictable technology curve, the overall performance of a system remains dominated by system software overheads. Solving the problem of software overheads of a large system is more complex and challenging, than increasing clock speed, the capacity of memory or the instruction issue rates of the microprocessors. Commodity hardware components found in high performance desktop computers (currently based 1-4 Intel 80686 CPUs, aka Pentium Pro/II) and new standard network technologies (currently 1000BaseT, 10k Ethernet, multi GB SCI/Myrinet and Infiniband) are becoming commodities and are available at an excellent price/performance ratios. Such systems will give us an cost effective hardware test bed for our investigation of overall system performance. Optimizing a parallel or distribute system as a whole still requires many research contributions of better architectural models, better software structures and more efficient programming at the system software level.

about my lectures:

99-002 Practical Computer Science II, Advanced Programming and Software Design (University of Constance), SS02, course homepage.
37-836 Informatik II, Algorithms, Data structures and Problem solving for the EE students (Abt IIIb), SS99, course homepage.
37-235 Computer Systems Performance Analysis and Benchmarking, WS02 course homepage.
37-023 Systemprogrammierung (low level programming),WS02, course homepage.

about the projects I contribute / contributed to:

about the software we released

about some past activities:

On April 22, 1997 I held a public inauguration lecture as a professor of computer science in the Auditorium Maximum, HG F30 at ETH Zürich. The transparencies for this lecture are available for download: (stricker-antritt.pdf, [1.5 MB]).

helpful pages in the area of clusters, high performance computing and computer architecture

List of seven selected publications

For a complete list of my publication, see the publications page of the CoPs project.

OS Support for a Commodity Database on PC Clusters — Distributed Devices vs. Distributed File Systems in proceedings of Sixteenth Australasian Database Conference (ADC), Feb 1-3, 2005, Newcastle, Australia, with Felix Rauch. Reprints: abstract, fulltext in pdf. Slides of the presentation by Felix: pdf.

Zero-Copy for CORBA — Efficient Communication for Distributed Object Middleware
in proceedings of the 12th International Symposium on High Performance Distributed Computing HPDC, Seattle, Washington, June 22-24, 2003, with Christian Kurmann.
Reprints: abstract, acrobat, compressed postscript.
Slides of my presentation: acrobat, compressed postscript

Cost/Performance Tradeoffs in Network Interconnects for Clusters of Commodity PCs
. Proc. Workshop on Communication Architecture for Clusters in conjunction with International Parallel and Distributed Processing Symposium (IPDPS '03), April 22, 2003, Nice, France, with Christian Kurmann, Felix Rauch. Reprint:  abstract, acrobat, postscript, compressed postscript.
Slides of the presentation by Felix: acrobat, postscript, compressed postscript.

Combining Task- and Data Parallelism to Speed up Protein Folding on a Desktop Grid Platform - Is efficient protein folding possible with CHARMM on the United Devices MetaProcessor? in proceedings of CCGRID 2003, Mar 2-7, Berlin, Germany also in technical report #386, Department of CS, ETH Zürich with Bennet Uk, Michela Taufer, Giovanni Settanni, Andrea Cavalli, Amedeo Caflisch.
Reprints: abstract, acrobat.

Speculative Defragmentation - A Technique to Improve the Communication Software Efficiency for Gigabit Ethernetin proceedings of the 9th International Symposium on High Performance Distributed Computing HPDC, Pittsburgh, Pennsylvania, August 1-4, 2000, with Chris Kurmann, Michel Müller, Felix Rauch. Reprint: abstract, acrobat, compressed postscript. Slides: acrobat Journal version appears in The Journal of Networks, Software Tools and Applications. Volume 4, Issue 1, page 7-18, March 2001, (c) Kluwer Academic Publishers.

Optimizing Memory System Performance for Communication in Parallel Computers in proceedings of the International Symposium on Computer Architecture, ACM/IEEE ISCA'95, June 1995, with Thomas Gross, abstract. acrobat, compressed postscript

Communication Styles for Parallel Systems
.
IEEE Computer, vol.27, no. 12, December, 1994, pp. 34-44, with Thomas Gross, Atsushi Hasegawa, Susan Hinrichs, David O'Hallaron. Reprint as acrobat (5MB), Extended version appears as CMU technical report CMU-CS-92-215. abstract. acrobat, compressed-postscript.


about a slander by the newspaper NZZ and my university...

  Upon request of my department head and the official faculty representation at our university, myself, some ETH staff and students drafted a rebuttal to an ill conceived proposal for an acceptable use policy of the WWW proposed by the university administrators. In particular the proposed policy of 1997 proposed that Internet links be treated as if they were content and that links
that could lead to illegal content must be removed immediately from ETH home-pages. A slightly revised version focuses properly on acceptable content on ETH servers and did no longer prohibit links per se. It is effective since March 1st, 1999.

During the discussion of this ill conceived university internal legislation I created, discussed and blogged a schoolbook example pointing out that the World Wide Web is a new worldwide medium involving links and that they are spanning across different community standards of a more or lesser free speech in the US and in Switzerland. To illustrate my point I included some references (links) to two web-sites demonstrating the extent of racism (www.stop-the-hate.org) and the extent of pornography (www.persiankitty.com) on the Internet. Neither racist propaganda nor pornographic pictures were ever reproduced on my pages and no direct reference to such content was given, but both links referred to sites that did deal with the corresponding topics by giving leads or citing numerous examples. Stop-the-hate.org is actually an old, well respected web-site of a civil rights activist who is sharply condemning racism. There is no lack of disclaimers on the web sites I referenced.

After nearly four years of working under criminal charges the superior court of the state of Zürich finally confirmed all the acquittals by the lower courts and established a final ruling on the case as of Sept. 30, 2003. It upheld an earlier ruling of the district court that a link to a link to a link to a racist page can not be considered as willingful support for the act of racist propaganda under the Swiss anti racism laws. It admitted in its ruling that even if it were, the freedom of research and teaching in the swiss constitution would have to be considered and would be likely to prevail over the fact that hate speech is spread by the mere discussion of its existence and the scholarly references to it. The court had to further admit to a violation of my human rights as expressed in the European Human Rights Charter by the excessive length of a criminal trial, that an attorney general was trying to uphold without sufficient grounds. It looks like the criminal system is liable for damages and remuneration that occurred due to the destruction my academic career and my reputation. However the local justice system and the ETH seem to have in common that they refuse to admit of any wrongdoing and mishandling the case, so I had to appeal to the Zürich supreme court of appeals to fight for remuneration until that court granted my appeal and ordered the lower courts to retry the ruling on my damage claims.

I have to admit that six years after the slander I lost all faith in a legal system that sides in such a way with a slanderer to ruin a persons life based on a false accusation. This system is functioning just like in Kafkas "The Trial". I thought these criminal prosecutions based on alleged "wrong thinking" and "politically incorrect expression" are only possible in totalitarian dictatorships and not in one of the oldest and most stable democracies. Also I am deeply disappointed of a university president and a majority of my faculty colleagues who behaved in a most unjust and sleazy way, mobbing me out of office as a scholar and refusing to take the slightest effort to defend the academic integrity nor the constitutional freedom of research or teaching.

Last updates:
tomstr@acm.org
December 21, 1997, Sept 2000, July 2001, Dec 2003, Dec 2005