Speaker: David A. Patterson,
Professor, Computer Science Division,
EECS Department, University of California, Berkeley

Title: Terabytes >> Teraflops
(Or why work on processors when I/O is where the action is?)

Abstract:
Amdahl's Law tells us with faster processors we
need faster and larger I/O. Unfortunately disks are getting smaller rather
than faster.  This talk describes the results of the RAID project
(Redundant Arrays of Inexpensive Disks), which offers much
greater performance, capacity, and reliablity from I/O systems.

I will also talk about a new project getting underway
which looks at utilizing small helical scan tapes, such as
digital-audio tapes or video tapes, to offer terabytes of
storage for the price of a fileserver. 
It promises terabytes of economical and low latency storage,
which could revolutionze libraries.

My thesis is that a factor of 1000 increase in storage capacity available
on most Ethernets will have a much greater impact than a factor of
1000 increase in processing speed for a gaggle of scientists.

--------
This talk was given as a keynote address at the ACM SIGMETRICS
Conference in Santa Clara, CA on May 13, 1993.