I checked the abstract again and all the numbers are correct. Here it is: "The Intel 32nm Poulson processor contains 3.1 billion transistors integrated onto a single 544mm2 silicon die size. Eight processor cores and a total of 54MB of on-chip cache are linked by an on-chip ring-like interconnect bus."
I calculated 2.7B instead of ~2.6B because I used 1MBit=1024*1024=1.049 million cells. Either way it does not make too much difference. For comparison, the 45nm Xeon 7500 (aka Nahalem-EX) had 2.3B transistors and a total of 26.5 MB of cache which leaves about 1B for other things, much more reasonable.
It is interesting that a simple CPU captures our imagination at the same time that an extremely complex one is rolling out. I suspect that it is because small numbers are easier to grasp than large ones - and because we can appreciate that a device built with simple materials and a simple architecture has the potential to be incorporated in unexpected ways in existing products.
@pixies, Polymer is a solid state material, although it is not semicondcutor so everything is good with the ISSCCC name! BTW, everything can be a solid state (if the temperature is right ;-) so they selected pretty general name...Kris
Intel uses 8T SRAM for lower level cache. Assuming all 6T, 54MB of cache would have a SRAM cell transistor count of 2.7B already. That leaves only 0.4B for redundancy, cache peripheral, and the 8 cores. Do the numbers add up right?
What are the engineering and design challenges in creating successful IoT devices? These devices are usually small, resource-constrained electronics designed to sense, collect, send, and/or interpret data. Some of the devices need to be smart enough to act upon data in real time, 24/7. Specifically the guests will discuss sensors, security, and lessons from IoT deployments.