We need a visionary to offer glimpses into what technology can be, not just providing modifications to what already is.
As we chatted the other day, my colleague Scott Lewis said something so deceptively simple that it made us stop in our tracks.
“We need another Gene Roddenberry,” he said.
The Star Trek creator in the 1960s introduced the world to an array of futuristic technologies (the tricorder, wireless ear sets and so on) that in effect became our collective electronics product roadmap. We have many of those devices—in one form or another—today.
But what’s next? What’s our road map for another 40 years out? We don’t really have one. We don’t have a Gene Roddenberry. “The Matrix?” Hardly, the bridge here and there is a short one.
We often look to Apple, but Apple’s in the “now.” Apple this week came out with its long-awaited smart watch, which won’t be available until next year. It’s an incremental improvement — albeit a beautiful one — on existing technologies and, if you have to charge it every night, they clearly haven’t solved the battery life issue. The Apple Pay payments systems is an important addition, but not novel: Google and eBay are already there.
5G and the tactile Internet
The closest I’ve come recently to a Gene Roddenberry moment was listening to a presentation from Gerhard Fettweis, the Vodaphone Chair of Mobile Communications Systems, Dresden University of Technology, who spoke Sept. 3 to Cadence employees in San Jose.
He sketched out the template for the “tactile Internet,” a 5G world in which humans with mobile devices control real and virtual objects. But getting there will take 25 years or so.
To get there, we need to address data rates, how we design wireless communications fabrics, how we address latency, how we think about memory subsystems and how we deliver EDA tools and IP services, Fettweis cautioned.
The potential—and it won’t come for many years—is staggering. We will have astonishing—dare I say Roddenberry-like—computing power in our hands.
Fettweis said:
“We can expect 128K small Tensilica cores. We can expect 4×4 chip stacks on each side of the board. 128 chips stacked in 3d (the iPhone, he noted, contains 16 today); 4 boards in a box measuring 4x4x4 inches, exactly 1 litre in volume. We can then place 16,000 chips, which is a billion cores, which is an exascale computer in every liter.”
One challenge–inter-chip communications—is being tackled right now.
Fettweis and his colleagues at Dresden have created the Highly Adaptive Energy-Efficient Computing center, where they are working on embedded optical connectivity with embedded wave guides getting up to petabit/second bandwidth on the board and connecting boards on a backplane.
Another challenge is latency. Humans, he said, expect to see movement within a millisecond of an action. Game players get “cyber sickness” if what they’re seeing moves slower than that rate.
One way to get there is by rethinking the processor-memory relationship. Fettweis described the Tomahawk 2, a fast, energy-efficient and resilient heterogeneous multi-processor that can easily integrate very different kinds of devices.
It works by architecting “a lot of little memories with two processing engines hanging off every memory.” One of those is a vector DSP, the other a Tensilica core. “So we can switch between a single processing engine and a control processing engine as needed,” Fettweis said.
This, in addition to introducing some processing efficiency, also cuts power consumption, he said, adding:
“You get your packets decoded; they’re sitting in memory. You switch the chip into the different mode; and then DSP is turned off, the MPU turned on, hanging off the same memory and you can continue the control processing.”
Rethinking in-memory computing is promising:
“Today, we have memories with some gates hanging off. Basically we’re memory designers. We don’t have help in our current tools yet in looking at system design just from a memory optimized fashion. We’re still thinking too much of gates and not enough about memories.”
If we can tackle these problems—and Fettweis is confident that engineers will—a picture of the:
It evokes Gene Roddenberry, but without the Klingons.
I’m a first-generation Trekker and a huge fan of Roddenberry — and now I’m a fan of Gerhard Fettweis! His vision of future computing makes a whole lot of sense. Memory as a supporting fabric, with processors hanging on for the ride? I can totally see that.