What's New

Feature Article

Feature Article

Stochastic Magnetic Circuits Rival Quantum Computing

Circuits based on the stochastic evolution of nanoscale magnets have been used to split large numbers into prime-number factors — a problem that only quantum computers were previously expected to solve efficiently.

One of the driving forces behind the development of quantum computers has been an algorithm that can factor large integers, thus undermining encryption protocols. Current quantum computers cannot achieve this due to noise, and classical digital computers are far too slow. In contrast, Dr. Dmitri Nikonov of Intel presented an overview of some new research from Purdue and Tohoku Universities that promises practical factorization of large integers in the near future, without quantum computing.

This work is based on neither classical bits nor quantum bits (known as qubits), but on a distinct third foundation known as probabilistic bits or p-bits. Each p-bit fluctuates rapidly in real time between two configurations with a known probability, thus enabling probabilistic or stochastic computing.

The specific implementation is an integrated circuit of 8 nanomagnets, each fluctuating between an up and down state. Operating at room temperature, these are magnetic tunnel junctions similar to devices already being used for MRAM. The authors demonstrate an experimental circuit that can factor integers up to 945, and suggest that scaling to larger circuits that can factor much larger numbers is possible in the near term.

This may provide an example of “quantum-inspired” computing, whereby unconventional classical computer architectures may be used to address problems that were previously thought to require true quantum computing methods.

Read the news article by Dr. Nikonov, available without charge.

Access the research article, “Integer factorization using stochastic magnetic tunnel junctions”.

Technology Spotlight

Technology Spotlight

Low-Power Image Recognition Challenge (LPIRC)

LPIRC has been held annually since 2015, with the aim of improving the energy efficiency of computer vision technology. This year a record number of 22 teams participated and they submitted 234 solutions. Most solutions are significantly better than the solutions in 2018. This challenge had two different tracks: object detection and image classification.

The 2019 LPIRC Workshop was held in Long Beach, California, as part of the Computer Vision and Pattern Recognition Conference (CVPR 2019). View the program for this LPIRC Workshop.

This included presentations by previous winners, plus invited speakers from Google, Xilinx, UC Berkeley, MIT, Qualcomm, and Arizona State University.

Videos of the presentations are available via IEEE.tv. Watch the conference overview.

The other presentations are linked via the program.

Another LPIRC Workshop is being held as part of the International Conference on Computer Vision (ICCV) in Seoul, Korea, 28 October 2019. View the program.