announced an R&D breakthrough today in chip development that could lead to the
creation of field programmable gate arrays (FPGAs)
eight times denser than those currently being produced.
The increased density would greatly reduce the amount of energy needed to power the chips.
The company said the new chips could be built
using the same sized transistors used in current FPGA design, so they could
be built in current fabrication plants with minor modification.
“As conventional chip electronics continue to shrink, Moore’s Law
physics,” said Stan Williams, an HP senior fellow and director of Quantum
Science Research at HP Labs. “Excessive heating and defective device operation
arise at the nanoscale.
“What we’ve been able to do is combine conventional
CMOS technology with nanoscale switching devices in a hybrid circuit to
increase effective transistor density, reduce power dissipation, and
dramatically improve tolerance to defective devices.”
The research was led by Williams, along with fellow researcher Greg
Snider who is a senior architect with Quantum Science Research for HP Labs.
The technology calls for a nanoscale crossbar switch structure to be
layered on top of conventional CMOS
HP Labs researchers have named “field programmable nanowire interconnect
(FPNI)” — a variation of FPGA technology.
In the FPNI approach, all logic operations are performed in the CMOS,
whereas most of the signal routing in the circuit is handled by a crossbar
that sits above the transistor layer.
Since conventional FPGAs use 80 percent to 90 percent of their CMOS for signal routing, the FPNI circuit is much more
efficient; the density of transistors actually used for performing logic is
much higher, and the amount of electrical power required for signal routing
But none of this is coming soon. The researchers presented what they said
is a “conservative” chip model using 15-nanometer-wide crossbar wires
combined with 45-nm half-pitch CMOS, which they said they believe could be
technologically viable by 2010. It could well be worth the wait.
Williams said if implemented, the FPNI chips would be equivalent to leaping
ahead three generations on the international technology roadmap for silicon
without having to shrink the transistors.
“The expense of fabricating chips is increasing dramatically with the
demands of increasing manufacturing tolerances,” said Snider. “We believe this approach
could increase the usable device density of FPGAs by a factor of eight,
using tolerances that are no greater than those required of today’s
Insight64 analyst Nathan Brookwood said HP’s announcement looks promising. But he
also noted new technologies and approaches don’t always have as big an
impact in advancing chip technology as initially believed.
“This looks like one of the many alternatives clever scientists have come up with over the years,” Brookwood told internetnews.com. “What’s not
clear to me is how fixed logic devices like microprocessors and DSPs
that focus on FPGA technology, would find it potentially very beneficial.”