The first 64-bit ARM server SoC, a new benchmark for mobile graphics chips and APIs and an in-depth paper from someone at Apple about an ultra-mobile ARM SoCs inside an iWatch.
These are a few of the papers I’d really like to see this fall’s ARM Tech Con in Silicon Valley. Friday, May 31, is the deadline to submit papers, but I suspect if one of these blockbusters came in a little late organizers would find a way to squeeze it in.
First, it’s time for a full disclosure of a 64-bit ARM server SoC. I’d most like to see the one being developed in Austin by Samsung because it’s one of the most secretive of the many designs in the works. Qualcomm is a close second.
Both these companies have said zip about their plans. Only job postings gave them away.
But competition in this space is super heated. Applied Micro will have been talking about its X-Gene chip for two years come this fall, so they are probably due for a full disclosure of the technical details—and they had better be showing a working ASIC by the event or they will lose credibility.
Also in the hunt are Calxeda and Marvell (which are actually shipping 32-bitters today), as well as AMD, Nvidia and maybe even Huawei which have yet to show silicon. Come to think of it, there ought to be three or four papers on this topic.
MIPS have been shipping 64-bit for years (multi-core etc), but why will ARM be successful when no silicon on the horizon for 2 years? AMCC is about a year later than initially promised. With a 64-bit SoC, power is important, but why would you need it for mobile? So much other stuff eating power, that the core might be less than 10%, so why choose ARM? Freescale has PowerPC 64-bit multi-core SoC, looking at ARM for A50. Too many architectural differences within ARM (and MIPS) camps. Architectural details still not readily available either.
I'm interested in Steve Furbers SpiNNaker neural simulation project. I guess there at the hardware ramp-up stage so havent yet done massive neural-net experimentation.
Its all blue-sky "who know where it might lead" stuff, but could be the first steps to "your AI buddy in your pocket".
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.