I see that the new (but under construction) web-site of XMOS Semiconductor, the start-up founded by the Professor of Computer Science at Bristol University, David May FRS, who invented the Inmos Transputer, is displaying a description of its products: "The low-cost, low-power alternative to FPGAs".
This is clever stuff. What do you think of when you think FPGA? You think: high power. You think: pricey. You certainly don't think low power. You don't really think low-cost. Low power, low-cost FPGA is as a new beast on the block.
The word coming out of the West Country is that the company can't quite decide whether to call it an FPGA at all, because it goes for a segment of the market which FPGAs have never addressed. That has to be the ultra-low-power, ultra-low-cost end.
And it's not an FPGA, according to the XMOS blurb, it's an 'alternative' to FPGA. So what's the best bet about the XMOS architecture?
Well seeing as May's first love was robotics, and robotics need parallel processing, and the transputer exemplified parallel processing par excellence, it's pretty much a racing certainty that it uses paralleli processing.
But parallel what? Microprocessors? DSPs? No one knows, but the word is that the chip contains an array of processing elements, rather like a PicoChip array, but whereas PicoChip aims its chips at high-end, high-performance markets, Xmos will be going for low-end consumer markets.
A statement on the company's old web-site said: 'The company's novel processor architecture emulates hardware functionality and provides solutions within the $10billion microcontroller market. Simply stated, Xmos provides a new way of implementing hardware designs. Xmos delivers customer requirements in the form of a chip that is both designed-for-purpose and customer programmable.'
It is expected that all will be revealed, as they say, later this month.
Leave a comment