This isn't something I thought I'd be writing in 2016, but a team at the University of California, Davis, Department of Electrical and Computer Engineering have hit a world's first. The team have designed the first "KiloCore" processor, which has 1000 independent programmable processors, with a maximum computation rate of 1.78 trillion instructions per second.
The new 1000-core processor has 621 million transistors and was shown off during the recent 2016 Symposium on VLSI Technology and Circuits in Honolulu on June 16. Professor of Electrical and Computer Engineering, Bevan Baas, who led the team that designed KiloCore, said: "To the best of our knowledge, it is the world's first 1,000-processor chip and it is the highest clock-rate processor ever designed in a university".
Up until now, there has been no other chips made with over 300 processors, with most of them being made for research purposes and only a handful are sold commercially. The new 1000-processor KiloCore was fabricated by IBM on their 32nm CMOS technology, so we're not even talking anything radically advanced like the 14nm and 10nm nodes that are being used and played with now.
Each of the 1000 cores can run its own small program independently of others, which is a much more flexible approach than the usual Single Instruction Multiple Data (SIMD) way of doing things, which is the way GPUs work with computational data. The thought process behind this is to break an application into many smaller pieces, with each of them running in parallel on different processors, allowing for high throughput, and lowered energy consumption.
The processor cores are independently clocked, so many of them can completely shut themselves down when they're not needed. Each of the 1000 cores run at an average maximum clock frequency of 1.78GHz, as the cores transfer data directly to each other, instead of a pooled memory area that can be a very large botteleck to data.
The impressive new KiloCore processor is the most energy-efficient "many-core" processor ever reported, according to Baas. The 1000 processors can execute 115 billion instruction per second, while only dissipating 0.7W, which is low enough to be powered from a single AA battery - yeah, my jaw is on the floor, too. The KiloCore processor executes instructions 100x more efficiently than modern laptop CPUs, which is another impressive feat.
Where will the KiloCore processor be used? Well, applications are already in development for wireless encoding/decoding, video processing, encyption, and others that require large amounts of parallel data - with the scientific community and datacenter record processing industries surely getting nerded out by the KiloCore.
All I want to know, is will it run Crysis?