PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
Photonics information processing strategies offer the unique ability to perform analog computation with ultra-low latency and high efficiency. However, designing compact and reconfigurable photonic architectures which scale well is a challenge. The combination of nonvolatile optical materials (such as Ge2Sb2Te5) and integrated photonics is a promising approach which enables non-volatile optical memory on-chip with low drift, compact footprint, and high-speed readout. The first part of the talk will focus on using this photonic memory—together with wavelength division multiplexing and “in-memory” computing techniques—to enable high-speed matrix-vector operations for machine learning applications. The second half of this talk will cover methods for configuring these optical phase-change materials using electrical programming schemes, such as mixed-mode plasmonic memory and electro-thermal switching with on-chip microheaters.
Nathan Youngblood
"Reconfigurable phase-change photonic platforms for fast and efficient in-memory computing", Proc. SPIE PC12647, Active Photonic Platforms (APP) 2023, PC126470W (4 October 2023); https://doi.org/10.1117/12.2676236
ACCESS THE FULL ARTICLE
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Nathan Youngblood, "Reconfigurable phase-change photonic platforms for fast and efficient in-memory computing," Proc. SPIE PC12647, Active Photonic Platforms (APP) 2023, PC126470W (4 October 2023); https://doi.org/10.1117/12.2676236