Faster, More Secure Photonic Chip Boosts AI Training

Good news!

"A microchip that uses light instead of electricity can potentially be faster and more energy efficient at the complex computations essential to training AI than conventional electronics. In addition, researchers say the new chips may be significantly more secure against hacking. ...
“It might be around 1,000 to 10,000 times faster,” ...

In the new study, researchers created a silicon wafer that varied in height from 150 to 220 nanometers. The height variations were organized so that the chip could scatter light in specific patterns. When input in the form of light flows into the chip, the output light encodes data from complex tasks.

The scientists designed the microchip to perform vector matrix multiplication operations. These calculations, which involve multiplying grids of numbers known as matrices, are key to many computational tasks, including operating neural networks. ..."

From the abstract:

"Inverse-designed silicon photonic metastructures offer an efficient platform to perform analogue computations with electromagnetic waves. However, due to computational difficulties, scaling up these metastructures to handle a large number of data channels is not trivial. Furthermore, a typical inverse-design procedure is limited to a small computational domain and therefore tends to employ resonant features to achieve its objectives. This results in structures that are narrow-bandwidth and highly sensitive to fabrication errors. Here we employ a two-dimensional (2D) inverse-design method based on the effective index approximation with a low-index contrast constraint. This results in compact amorphous lens systems that are generally feed-forward and low-resonance. We designed and experimentally demonstrated a vector–matrix product for a 2 × 2 matrix and a 3 × 3 matrix. We also designed a 10 × 10 matrix using the proposed 2D computational method. These examples demonstrate that these techniques have the potential to enable larger-scale wave-based analogue computing platforms."

Faster, More Secure Photonic Chip Boosts AI Training - IEEE Spectrum Optical computing can perform matrix computations at the speed of light

Inverse-designed low-index-contrast structures on a silicon photonics platform for vector–matrix multiplication (no public access)

The area highlighted in red on this silicon photonic chip can perform 3-by-3-matrix operations, relevant for AI-related computations.