A large-scale integrated vector–matrix multiplication processor based on monolayer molybdenum disulfide memories

Abstract

Data-driven algorithms—such as signal processing and artificial neural networks—are required to process and extract meaningful information from the massive amounts of data currently being produced in the world. This processing is, however, limited by the traditional von Neumann architecture with its physical separation of processing and memory, which motivates the development of in-memory computing. Here we report an integrated 32 × 32 vector–matrix multiplier with 1,024 floating-gate field-effect transistors that use monolayer molybdenum disulfide as the channel material. In our wafer-scale fabrication process, we achieve a high yield and low device-to-device variability, which are prerequisites for practical applications. A statistical analysis highlights the potential for multilevel and analogue storage with a single programming pulse, allowing our accelerator to be programmed using an efficient open-loop programming scheme. We also demonstrate reliable, discrete signal processing in a parallel manner.

Schottky barrier reduction on optoelectronic responses in heavy ion irradiated WSe2 memtransistors

“…2 Large-scale integration of 2D materials as semiconducting channels in an in-memory processor has been demonstrated. 3 The application of 2D semiconductors could reduce the complexity of future integration with complementary metal-oxide-semiconductor (CMOS) technology. 4,5 However, there are experimental difficulties for designing electronic devices due to the inevitable defects introduced in the materials during transfer or chemical growth processes.…”

Integration of MoS2 Memtransistor Devices and Analogue Circuits for Sensor Fusion in Autonomous Vehicle Target Localization

“…Consequently, this approach not only ensures great energy efficiency but also significantly improves the processing speed. So far, memtransistors based on continuous MoS 2 films have already demonstrated scalable applications with the advancement of wafer-scale material growth and device fabrication technique. ,,− Recently, memtransistors have been successfully applied in various advanced data processing fields, such as collision detection, artificial visuotactile neurons, and spiking neural networks algorithms . While memtransistors hold great potential as a hardware platform for analogue Kalman filtering, there is currently a lack of well-established methodologies for implementing them in the field of autonomous vehicle target localization.…”