Fabrication and integration of photonic devices for phase-change memory and neuromorphic computing

Изготовление и интеграция фотонных устройств для памяти с фазовым переходом и нейроморфных вычислений
Wei Zhang, Wen You Zhou, Xueyang Shen, Xiaolong Yang, Jiangjing Wang
2023-12-13

chalcogenide phase-change materialsneuromorphic computingplasmonic microheaterssilicon photonic integrated circuitswaveguide-integrated PCM memory
Abstract In the past decade, there has been tremendous progress in integrating chalcogenide phase-change materials (PCMs) on the silicon photonic platform for non-volatile memory to neuromorphic in-memory computing applications. In particular, these non von Neumann computational elements and systems benefit from mass manufacturing of silicon photonic integrated circuits (PICs) on 8-inch wafers using a 130 nm complementary metal-oxide semiconductor line. Chip manufacturing based on deep-ultraviolet lithography and electron-beam lithography enables rapid prototyping of PICs, which can be integrated with high-quality PCMs based on the wafer-scale sputtering technique as a back-end-of-line process. In this article, we present an overview of recent advances in waveguide integrated PCM memory cells, functional devices, and neuromorphic systems, with an emphasis on fabrication and integration processes to attain state-of-the-art device performance. After a short overview of PCM based photonic devices, we discuss the materials properties of the functional layer as well as the progress on the light guiding layer, namely, the silicon and germanium waveguide platforms. Next, we discuss the cleanroom fabrication flow of waveguide devices integrated with thin films and nanowires, silicon waveguides and plasmonic microheaters for the electrothermal switching of PCMs and mixed-mode operation. Finally, the fabrication of photonic and photonic–electronic neuromorphic computing systems is reviewed. These systems consist of arrays of PCM memory elements for associative learning, matrix-vector multiplication, and pattern recognition. With large-scale integration, the neuromorphicphotonic computing paradigm holds the promise to outperform digital electronic accelerators by taking the advantages of ultra-high bandwidth, high speed, and energy-efficient operation in running machine learning algorithms.
1
Chalcogenide phase-change materials have been integrated with silicon photonics for non-volatile memory and neuromorphic in-memory computing.
2
Deep-ultraviolet and electron-beam lithography enable rapid prototyping of photonic circuits, while back-end-of-line PCM integration supports high-quality devices.
3
Fabrication advances include PCM-integrated waveguides, silicon and germanium platforms, nanowires, and plasmonic microheaters enabling electrothermal switching and mixed-mode operation.
4
Mass-manufactured silicon photonic integrated circuits can be fabricated on 8-inch wafers using a 130 nm CMOS process and integrated with wafer-scale-sputtered PCMs.
5
Photonic and photonic-electronic systems use PCM arrays for associative learning, matrix-vector multiplication, and pattern recognition, with large-scale integration offering potential advantages in bandwidth, speed, and energy efficiency over digital accelerators.

waveguide-integrated chalcogenide phase-change material photonic memory cells, devices, and neuromorphic computing systems on silicon photonic platforms

fabrication and integration processes governing the device performance and functionality of PCM-based photonic memory and neuromorphic systems

Publication Details
Publication Date
2023-12-13
Journal
Publisher
ISSN
Cited by
66
Access Type
Author Information
Authors
Wei Zhang
Wen You Zhou
Xueyang Shen
Xiaolong Yang
Jiangjing Wang
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%