Posted on 07/02/2016 12:48:39 PM PDT by Elderberry
A team from Davis University, California, has designed a processor with 1000* cores, boasting a throughput rate of 1.78 trillion instructions per second and containing 621 million transistors.
As opposed to a number of other attempts, some reaching 300 or so processors, the KiloCore chip has been fabricated and run; it was built by IBM (who else) using its 32-nm PD-SOI CMOS technology (what else).
The basic architecture used is MIMD (multiple instruction/multiple data) and each of the seven-stage-pipelined cores has a 72-instruction set, single instruction/cycle. None of the instructions is algorithm-specific setting the KiloCore apart from GPU-class devices. The terrific throughput is achieved at a clock speed of a mere 1.78 GHz, at 1.1 V. Running at 0.84 V and 1 GHz the beast consumes 13.1 W, while peak power efficiency of 5.8 pJ/Op is quoted at 0.56 V and 115 MHz.
Each core is independently powered and can shut down to leakage-only power if it has no task to perform. Rather than a cache architecture, every processor can store instructions and data in a hierarchy of locations; local memory, one or more nearby processors, on-chip independent memory modules, or off-chip memory.
The wormhole routing employed implies, among others, that messages from an adjacent or nearby core will be routed via the circuit network; those from further away in the processor matrix will travel via the packet network. If thats a veritable can of worms to programmers remains to be seen. Each core has north-south-east-west comms buffers plus a fifth channel for host-processor traffic; maximum throughput is 45.5 Gbps per router and 9.1 Gbps per port at 1.1 V.
* as a niggling detail, K in my computerized editor's dictionary is for kilo = 1024. Sure, k is also for kilo, but meaning 1000 in old money, like in kHz.
Is niggling a racist word?
Artificial intelligence will kill us all.
So, China, with your high speed record ... how does this compare???
AI will outsmart us all????
It sure kilt that Tesla passenger.
Let’s not be niggardly about it.
Eventually we will reach a point where the robots will stop serving us and we will begin serving them.
There are old single core chips with 184 million tranistors (Pentium 4), and six core i7 chips with close to 2 billion. The 621 million transistor count sounds low for a 1000 core chip. We used to worry about the overhead of managing that many cores. Has that problem been solved?
So you need two - one to parse the code, the other to crunch it.
There they go again, I thought Octet was bad.
Some people talk about the coming of a singularity, where “computer intelligence” will assume initiative.
It can’t literally do so, of course. However people have a sad propensity to WORSHIP what shouldn’t be worshiped, and the “singularity” could be a social trend. It’s up to everybody to decide how much to depend on the computer.
Sounds like a relatively simple core.
Say, you might have a movie plot there!
“Holy Computers!”
Sorta like our expderience with gov’t evolution...
Maybe some kind of omni-app that would embrace the whole web’s worth of stuff into some customized, personalized, self adjusting dashboard? Which would follow you wherever you went, on desktop, flip phone, even watch?
Not only every waking moment could be spent in contact with “The Computer,” but a way to have it interact with your dreams could be found too.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.