Information Technology Reference
In-Depth Information
Fig. 7.15. Moore's law. (a) Gordon
Moore's original prediction. (b)
Moore's law still working after
nearly fifty years.
(a)
(b)
16
10
10
4G
16
14
13
12
11
10
9
8
7
6
5
4
3
2
512M
1G
2G
10
9
10
8
10
7
10
6
10
5
10
4
10
3
10
2
10
1
10
0
1960
1965 Actual data
MOS Arrays
6
4
128
256M
MOS Logic 1975 Actual data
Itanium
®
Pentium
®
4
Pentium
®
III
Pentium
®
II
Pentium
®
1975 Projection
Memory
Microprocessor
16M
4M
1M
256k
i486
®
64k
i386
®
80286
4k
1
6
k
1k
8086
8080
4004
1
0
1965
19701975
1980
1985
1990
1995
2000
2005
2010
YEAR
In 1968, I was invited to give a talk at a workshop on semiconductor devices
at Lake of the Ozarks. In those days you could get everyone who was doing
cutting-edge work in one room, so that the workshops were where all
the action was. I had been thinking about Gordon Moore's question, and
decided to make it the subject of my talk. As I prepared for this event, I
began to have serious doubts about my sanity. My calculations were telling
me that, contrary to all the current lore in the field, we could
scale
down
the technology such that
everything got better
: the circuits got more
complex, they ran faster, and they took less power - WOW! That's a violation
of Murphy's law that won't quit! But the more I looked at the problem, the
more I became convinced that the result was correct, so I went ahead and
gave the talk, to hell with Murphy! That talk provoked considerable debate,
and at the time most people didn't believe the result. But by the time the
next workshop rolled around, a number of other groups had worked through
the problem for themselves, and we were pretty much in agreement. The
consequences of this result for modern information technology have, of
course, been staggering.
12
The basic scaling principles underlying Moore's law were first described in
papers in 1972 by Carver Mead and Bruce Hoeneisen of Caltech and by Robert
Dennard and colleagues at IBM. But it was a paper from Dennard in 1974 that
laid out the astonishing result - now called
Dennard scaling
- most clearly for
the industry. This showed that shrinking the geometry and reducing the sup-
ply voltage led to both power reduction and performance improvement. In
summary, Dennard scaling said that reducing the length, width, and gate oxide
thickness of transistor features by a constant
k
results in transistors that are
k
2
B.7.11. The citation for the 2002 award of the U.S. National Medal of Technology to Caltech
professor Carver Mead, reads as follows: “For his pioneering contributions to microelectronics
that include spearheading the development of tools and techniques for modern integrated circuit
design, laying the foundation for fabless semiconductor companies, catalyzing the electronic
design automation field, training generations of engineers that have made the United States the
world leader in microelectronics technology, and founding more than twenty companies.”
B2
Search WWH ::
Custom Search