The demo at the booth showed that the Intel Xeon E5 along with the Altera Arria 10 FPGA. We asked how this was being accomplished and were told that the demo was not just an Intel Xeon E5 with an Arria 10 FPGA PCIe card. We were told that this is a sample setup sent to some customers that combined the Intel Xeon E5 with Arria 10 FPGA on-package. We confirmed that this was a Broadwell not a Skylake generation part and were told that it was indeed Broadwell. The expectation is that these Intel Xeon E5 + FPGA chips are being used by developers and early access customers prior to Skylake-EP’s early access shipments start en masse.
Furthermore, Intel also presented details about its Deep Learning Inference Accelerator, a PCIe based card with the Altera Arria 10 FPGA. This product will come out in 2017.
Some more in-depth information about the chip giant's AI plans can be read at EE Times. The site points out Intel bought two neural networking startups, Nervana and Movidius, and provides a picture of how the marketplace looks right now. Deep learning is probably one of the hottest growth markets right now, market watcher Tractica believes sales of deep learning hardware could skyrocket from $436 million in 2015 to a massive $41.5 billion by 2024.
On a related note, Intel also said it's going to invest over $250 million in autonomous driving projects over the next two years and called data "the new oil" of automated driving:
When it comes to the car of the future and automated driving experiences, however, data is literally the new oil. Data has the potential to radically change the way we think about the driving experience: as consumers, as automakers, as technologists and as citizens of our communities.
In fact, as a technologist, one of the trends I see as most disruptive to almost every industry is the enormous flood of data driven by the proliferation of smart, connected devices.