Yi Zhang
Department of Computing
Science
Chalmers University of
Technology
Location
The Thirteenth Annual ACM Symposium on
Parallel Algorithms and Architectures (SPAA '01) was held at Hersonissos, Crete
Island, Greece, July 4-6, 2001. Crete is the largest Greek Island and is notable
for its geographical location, climate and diverse natural beauty as well as its
unique cultural and historical heritage. Flying to Crete is very easy, there are
several charter flights that connect Sweden and Crete.
The
Conference
SPAA is supported by the ACM Special Interest
Groups on Algorithms and Computation Theory (SIGACT) and Computer Architecture (SIGARCH). This year SPAA was co-located with the 33rd
Annual ACM Symposium on Theory of Computing (STOC) and the 28th International
Colloquium on Automata, Languages and Programming (ICALP). The whole event
lasted one week. SPAA 2001 covered all traditional research on parallel and
distributed algorithms and architectures, plus new aspects including satellite
networks, the web, quantum and DNA computing.
I attended the conference in order to present
the regular paper titled: “A Simple, Fast and Scalable Non-Blocking Concurrent
FIFO Queue for Shared Memory Multiprocessor Systems”, authored by Philippas
Tsigas and me. Our paper was presented the second day of the conference during
the morning session.
This year, SPAA had a single track with 34
papers and 14 revue papers presented during the three days of the conference.
For my own research, I found the following
papers very interesting:
1.
“Room Synchronizations” by G. Blelloch, P. Cheng, P.
Gibbons
This paper proposes a new synchronization technology to allow parallel access to data structures. The technology considers the asynchronous system with bounded delay, which is more realistic model compared with the fully asynchronous system.
2.
“Scheduling Best-Effort and Real-Time Pipelined
Applications on Time-Shared Clusters”, Y. Zhang, A.
Sivasubramaniam
This paper addresses scheduling the CPU
resources of a cluster system. They consider scheduling both best-effort and
real-time applications that have processes communication with each other on such
a cluster parallel system.
3.
“Pursuit and Evasion on a Ring: An Infinite
Hierarchy for Parallel Real-Time System”, S. Bruda, S. Akl
Several complexity classes based on timed
w-language are presented in this
paper for parallel real-time systems.
The arrangements of the conference were very
good. The only disappointment for me was that there was no keynote talk for
SPAA.