Since Intel released its Tri-Gate process for 22 nm, there has been
widespread belief that planar technology is at an end. Samsung is
looking for ways to keep things going. Take a look at its paper,
"Comprehensive Extensibility of 20nm Low Power/ High Performance
Technology Platform Featuring Scalable High-k/Metal Gate Planar
Transistors with Reduced Design Corner.”
extensibility, what would IEDM be without an Intel paper on advanced
CMOS technology? Kelin Kuhn and collaborators will present the invited
talk entitled, "The Ultimate CMOS Device and Beyond." Intel will provide
its take on what remains in the CMOS roadmap and what lies beyond.
final paper among my picks is an invited talk from Infineon titled,
"The Role of Silicon, Silicon Carbide and Gallium Nitride in Power
Electronics." It's only one angle, but power electronics is attracting
increased attention with the push for solid-state lighting.
I’m very interested to hear the pro-fabless view from GlobalFoundries
in the wake of some premature announcements of the death of the
fabless/foundry business model. Ajit Manocha, CEO, GlobalFoundries,
obviously isn't buying it, given the title of his luncheon address, "Is
the Fabless/Foundry Model Dead? We Don’t Think So. Long Live Foundry
By the way, can we make that last use of "2.0" in the
semiconductor industry? Web entrepreneurs have already sucked the life
out of that meme.
David Patterson, known for his pioneering research that led to RAID, clusters and more, is part of a team at UC Berkeley that recently made its RISC-V processor architecture an open source hardware offering. We talk with Patterson and one of his colleagues behind the effort about the opportunities they see, what new kinds of designs they hope to enable and what it means for today’s commercial processor giants such as Intel, ARM and Imagination Technologies.