[FIRM] Invitation to Parallel Computing Colloquium
Sabri Pllana
pllana at par.univie.ac.at
Di Jun 1 14:09:43 CEST 2010
Department of Scientific Computing of the University of Vienna Invites
to the Parallel Computing Colloquium
On WEDNESDAY, 2. June, 2010, 10:00 (s.t.), Hörsaal 1, UZA II
- Areal Althanstraße
http://www.wegweiser.ac.at/ww5/static/plaene/pdf/A_UP-uza.pdf
- UZA II
http://www.wegweiser.ac.at/static/plaene/pdf/A_UZA-II.pdf
Speaker:
Prof. Uzi Vishkin
University of Maryland
USA
Title:
Using Simple Abstraction to Guide the Reinvention of Computing for
Parallelism
Abstract:
The sudden shift from single-processor computer systems to
many-processor parallel ones requires reinventing much of Computer
Science (CS): how to actually build and program the new parallel
systems. CS urgently requires convergence to a robust parallel
general-purpose platform that provides good performance and is easy
enough to program by at least all CS majors. Unfortunately, lesser
ease-of- programming objectives have eluded decades of parallel
computing research. The idea of starting with an established easy
parallel programming model and build an architecture for it has been
treated as radical by vendors. This talk advocates a more radical idea.
Start with a minimalist stepping-stone: a simple abstraction that
encapsulates the desired interface between programmers and system
builders. An Immediate Concurrent Execution (ICE) abstraction proposal
is followed by two specic contributions: (i) A general-purpose many-core
Explicit Multi-Threaded (XMT) computer architecture. XMT was designed
from the ground up to capitalize on the huge on-chip resources becoming
available in order to support the formidable body of knowledge, known as
PRAM (for parallel random-access machine, or model) algorithmics, and
the latent, though not widespread, familiarity with it. (ii) A
programmer?s workow that links: ICE, PRAM algorithmics and XMT
programming. The synchronous PRAM provides ease of algorithm design, and
ease of reasoning about correctness and complexity. Multi-threaded
programming relaxes this synchrony for implementation. Directly
reasoning about soundness and performance of multi-threaded code is
generally known to be error prone. To circumvent that, the work
incorporates multiple levels of abstraction: the programmer must only
establish that the multi-threaded program behavior matches the PRAM-like
algorithm it implements, a much simpler task. Current XMT hardware and
software prototypes, and demonstrated ease-of-programming and strong
speedups suggest that we may be much better prepared for the challenges
ahead than many realize. In fact, by the Goldstine, von-Neumann 1947
formative paper on the serial paradigm our approach is not radical at
all. Tenets such as not compromising the ease and speed of the human
process and the harnessing of mathematical induction may be as old as
computing itself. However, to meet the then extreme scarcity of
hardware, the 1947 paper constrained induction with what the prevailing
CS doctrine has come to consider "natural" and/or "simple". Helped by
XMT hardware patents, ICE augments induction with a rudimentary
abstraction that sidesteps this von-Neumann mental and hardware bottleneck.
Bio:
Prof. Uzi Vishkin started his work on parallel computing in 1979 as a
PhD student at the Technion, Israel. His initial focus was on parallel
algorithms and parallel algorithmic thinking. The 1982 Shiloach-Vishkin
work-depth methodology for presenting parallel algorithms provided the
presentation framework in several parallel algorithm (known as PRAM
algorithms) texts that also include a considerable number of parallel
algorithms he co-authored. In 1996, he was elected ACM Fellow for, among
other things, having "played a leading role in forming and shaping what
thinking in parallel has come to mean in the fundamental theory of
Computer Science". He is also an ISI-Thompson Highly Cited Researcher.
This parallel algorithms theory provided the basis for Prof. Vishkin's
invention of the PRAM-On-Chip desktop supercomputer framework that
scales beyond 1000 processors on chip. He later led its extensive
hardware and software prototyping, including a 64-processor computer
that has already been programmed by over 100 middle-school and
high-school students. He was named a Maryland Innovator of the Year for
his PRAM-On-Chip venture, whose main patent has been widely cited in
patents of the major vendors. A follow-up proposal, entitled Center for
Reinvention of Computing for Parallelism, ranked first among 49
proposals in a recent University System of Maryland (USM) wide
competition for Maryland Research Centers of Excellence. He has been
Professor of Electrical and Computer Engineering at the University of
Maryland Institute for Advanced Computer Studies (UMIACS) since 1988. He
was affiliated with Tel Aviv University between and 1984 and 1997, and
was Chair of CS there in 1987-8, and also worked for IBM T.J. Watson and
New York University.