Thursday, July 8, 2004
Noon - 1 pm
Hamerschlag Hall D-210
In this talk I explore the strengths and weaknesses of Spatial
Computation (SC), a method of translating programs into hardware by
assigning to each program instruction a dedicated hardware
implementation. SC synthesizes circuits with ample parallelism, using
only local communication. SC addresses many of the limitations of
contemporary high-performance processor architectures: limited ability
to exploit parallelism, reliance on slow global communication signals,
design complexity, inflexibility of the instruction-set architecture,
low energy efficiency, high power consumption.
This talk will describe a specific instance of SC, called
Application-Specific Hardware (ASH). Program transformations
developed for ASH have broad applicability in the realms of
traditional compilation, high-level synthesis and asynchronous
circuits. This talk will focus on CASH: a compiler for ASH, which
translates ANSI C programs into asynchronous hardware circuits.
Circuits generated by CASH from dusty-deck C multimedia kernels
compare favorably in performance with high-end superscalar
microprocessors, while being up to three orders of magnitude more
efficient in terms of energy and energy-delay.
Mihai Budiu is currently a postdoc in the Computer Science Department of Carnegie Mellon University. He has received his Ph.D. from CMU in December 2003 with a dissertation on "Spatial Computation". His
research is at the intersection of optimizing compilers, computer architecture, reconfigurable hardware and high-level synthesis. His research explores the implications of deep sub-micron and self-assembled electronic nanotechnology for building future computer architectures. Mihai was previously a member of the CMU PipeRench virtualizable reconfigurable hardware project: Mihai wrote the PipeRench compiler tools, which subsumed a complete CAD tool-chain.
Seminar Info Contact:
or visit http://www.pdl.cmu.edu/SDI/