|
Eckert-Mauchly Award
CONTACT: Virginia Gold
212-626-0505
v_gold@acm.org
IMMEDIATE
ACM and IEEE CS HONOR DESIGNER OF CUSTOMIZED COMPUTER CHIPS
HP Scientist Developed Automated Design Tool to Speed Chip Production
New York May, 20, 2002 -- The Association for Computing Machinery (ACM) and the IEEE Computer Society
(IEEE CS) will jointly present the prestigious Eckert-Mauchly Award to Dr. B. Ramakrishna (Bob) Rau of HP Labs,
HP's central research facility, for his pioneering contributions to instruction-level parallel processors and
compilers that use a style of architecture called VLIW (Very Long Instruction Word). Rau, who manages HP Labs'
Compiler and Architecture Research (CAR) Program, developed a prototype of an automated design tool for custom
processors that produces customized chips more quickly and less expensively than those designed manually. The
Eckert-Mauchly Award, which carries a $5000 prize, will be presented at the International Symposium on Computer
Architecture (ISCA), May 25-29, 2002.
"Bob Rau has been instrumental in developing the core architectural concept known as EPIC (Explicitly Parallel
Instruction Computing), which is the basis of today's most commonly-used processors," said John R. White,
executive director and CEO of ACM. "He has made a significant contribution to maintaining the spectacular rate of
increase in microprocessor performance without unacceptable hardware complexity."
Rau and his group have leveraged their VLIW/EPIC technology to develop PICO (Program In, Chip Out), a prototype of
an automated design tool for custom processors and accelerators. The EPIC architectural concept is the basis of
the Intel IA-64 architecture, jointly developed by Intel and HP. Custom chips are expected to increase in demand
as "smart products" such as multimedia devices and navigation systems in automobiles enter wider use. "Such tools
will encourage a huge smart-product industry to flourish," said Rau.
His group's mission at HP's CAR Program is to develop high-performance computing solutions for embedded
applications, which often require extreme cost and performance goals that cannot be met by conventional
off-the-shelf equipment. "To achieve these goals, we focus on exploiting very high levels of customization and
parallelism to get high performance at a reduced cost," Rau said.
Rau is a Member of ACM and a Fellow of IEEE (Institute of Electrical and Electronics Engineers). He has taught at
the University of Illinois, Urbana-Champaign, where he is currently an adjunct professor, and has been a consulting
professor at Stanford University. Prior to joining HP Labs, Rau co-founded Cydrome Inc. and was chief architect of
the Cydra 5 mini-supercomputer, one of the first commercial VLIW products. He received a bachelor of technology
degree from the Indian Institute of Technology in Madras, India, and earned his MS and PhD degrees at Stanford
University in California.
ACM and IEEE CS will jointly present the Eckert-Mauchly Award, described as the most prestigious award in the
computer architecture community, at the ISCA in Anchorage, Alaska later this month. The award, initiated in 1989,
is given for contributions to computer and digital systems architecture. It was named for John Presper Eckert and
John William Mauchly, who collaborated on the design and construction of the first large scale electronic computing
machine, known as ENIAC - the Electronic Numerical Integrator and Computer, in 1947.
About ACM
The Association for Computing Machinery (ACM) is a major force in advancing the skills of information technology
professionals and students. ACM serves its global membership by delivering cutting edge technical information and
transferring ideas from theory to practice. ACM hosts the computing industry's leading Portal to Computing
Literature. With its world-class journals and magazines, dynamic special interest groups, numerous conferences,
workshops and electronic forums, ACM is a primary resource for the information technology field. For additional
information about ACM, visit our web site at www.acm.org.
# # #
|