The Multicore World 2017 conference to be held in Wellington from February 20 to 22 promises some pretty heady presentations on cutting edge technologies. How about posits, approximate computing, quantum information, exascale computing?
The conference is organised by Open Parallel Ltd (New Zealand) and sponsored by MBIE, Catalyst IT, NZRise and Oracle Labs.
Conference organiser and Open Parallel CEO, Nicolas Erdody, says: “The assemblage of big brains around multicore computing and parallel programming will pose questions and answers as the world moves towards exascale computing in the next decade.”
He says being part of such discussions can position New Zealand technologists, entrepreneurs and scientists at the intersection of two massive global markets that will benefit the country’s future growth: decision-making (estimated in $2 trillion) and food and agriculture (estimated in $5 trillion).
Among the presentations will be one from Prof Michelle Simmons, an Australian Research Council Laureate Fellow and director at the Centre for Quantum Computation & Communication Technology, at the University of New South Wales.
She will describe “the emerging field of quantum information, a response to the fact that device miniaturisation will soon reach the atomic limit, set by the discreteness of matter, leading to intensified research in alternative approaches for creating logic devices of the future.”
As for posits and approximate computing, all will be revealed by Dr John Gustafson, former director of Intel Labs and now visiting professor at the National University of Singapore. He will "reveal a new data type called posit that provide a better solution for approximate computing.”
If you can’t make Multicore World and are curious to know more. Check out this presentation given at the Stanford EE Computer Systems Colloquium on 1 February, Beyond Floating Point: Next-Generation Computer Arithmetic.
The abstract explains: “A new data type called a ‘posit’ is designed for direct drop-in replacement for IEEE Standard 754 floats. Unlike unum arithmetic, posits do not require interval-type mathematics or variable size operands, and they round if an answer is inexact, much the way floats do. However, they provide compelling advantages over floats, including simpler hardware implementation that scales from as few as two-bit operands to thousands of bits.”
If you are intrigued rather than bamboozled by that, a video of the talk is available.
The conference is organised by Open Parallel Ltd (New Zealand) and sponsored by MBIE, Catalyst IT, NZRise and Oracle Labs