The rapid advancement of AI-enabled applications has resulted in an increasing need for energy-efficient computing hardware.Logic-in-memory is a promising approach for processing the data stored in memory,wherein fast...The rapid advancement of AI-enabled applications has resulted in an increasing need for energy-efficient computing hardware.Logic-in-memory is a promising approach for processing the data stored in memory,wherein fast and efficient computations are possible owing to the parallel execution of reconfigurable logic operations.In this study,a dual-logic-in-memory device,which can simultaneously perform two logic operations in four states,is demonstrated using van der Waals ferroelectric field-effect transistors(vdW FeFETs).The proposed dual-logic-in-memory device,which also acts as a twobit storage device,is a single bidirectional polarization-integrated ferroelectric field-effect transistor(BPI-FeFET).It is fabricated by integrating an in-plane vdW ferroelectric semiconductor SnS and an out-of-plane vdW ferroelectric gate dielectric material—CuInP_(2)S_(6).Four reliable resistance states with excellent endurance and retention characteristics were achieved.The two-bit storage mechanism in a BPI-FeFET was analyzed from two perspectives:carrier density and carrier injection controls,which originated from the out-of-plane polarization of the gate dielectric and in-plane polarization of the semiconductor,respectively.Unlike conventional multilevel FeFETs,the proposed BPIFeFET does not require additional pre-examination or erasing steps to switch from/to an intermediate polarization,enabling direct switching between the four memory states.To utilize the fabricated BPI-FeFET as a dual-logic-inmemory device,two logical operations were selected(XOR and AND),and their parallel execution was demonstrated.Different types of logic operations could be implemented by selecting different initial states,demonstrating various types of functions required for numerous neural network operations.The flexibility and efficiency of the proposed dual-logic-in-memory device appear promising in the realization of next-generation low-power computing systems.展开更多
Artificial vision is crucial for most artificial intelligence applications.Conventional artificial visual systems have been facing challenges in terms of real-time information processing due to the physical separation...Artificial vision is crucial for most artificial intelligence applications.Conventional artificial visual systems have been facing challenges in terms of real-time information processing due to the physical separation of sensors,memories,and processors,which results in the production of a large amount of redundant data as well as the data conversion and transfer between these three components consuming most of the time and energy.Emergent optoelectronic memristors with the ability to realize integrated sensing-computing-memory(ISCM)are key candidates for solving such challenges and therefore attract increasing attention.At present,the memristive ISCM devices can only perform primary-level computing with external light signals due to the fact that only monotonic increase of memconductance upon light irradiation is achieved in most of these devices.Here,we propose an all-optically controlled memristive ISCM device based on a simple structure of Au/ZnO/Pt with the ZnO thin film sputtered at pure Ar atmosphere.This device can perform advanced computing tasks such as nonvolatile neuromorphic computing and complete Boolean logic functions only by light irradiation,owing to its ability to reversibly tune the memconductance with light.Moreover,the device shows excellent operation stability ascribed to a purely electronic memconductance tuning mechanism.Hence,this study is an important step towards the next generation of artificial visual systems.展开更多
基金Korean Government(MSIP),Grant/Award Numbers:RS-2023-00281048,2022R1A2C3003068,2022M3F3A2A01072215supported by Samsung Electronics Co.,Ltd.(IO201215-08197-01).
文摘The rapid advancement of AI-enabled applications has resulted in an increasing need for energy-efficient computing hardware.Logic-in-memory is a promising approach for processing the data stored in memory,wherein fast and efficient computations are possible owing to the parallel execution of reconfigurable logic operations.In this study,a dual-logic-in-memory device,which can simultaneously perform two logic operations in four states,is demonstrated using van der Waals ferroelectric field-effect transistors(vdW FeFETs).The proposed dual-logic-in-memory device,which also acts as a twobit storage device,is a single bidirectional polarization-integrated ferroelectric field-effect transistor(BPI-FeFET).It is fabricated by integrating an in-plane vdW ferroelectric semiconductor SnS and an out-of-plane vdW ferroelectric gate dielectric material—CuInP_(2)S_(6).Four reliable resistance states with excellent endurance and retention characteristics were achieved.The two-bit storage mechanism in a BPI-FeFET was analyzed from two perspectives:carrier density and carrier injection controls,which originated from the out-of-plane polarization of the gate dielectric and in-plane polarization of the semiconductor,respectively.Unlike conventional multilevel FeFETs,the proposed BPIFeFET does not require additional pre-examination or erasing steps to switch from/to an intermediate polarization,enabling direct switching between the four memory states.To utilize the fabricated BPI-FeFET as a dual-logic-inmemory device,two logical operations were selected(XOR and AND),and their parallel execution was demonstrated.Different types of logic operations could be implemented by selecting different initial states,demonstrating various types of functions required for numerous neural network operations.The flexibility and efficiency of the proposed dual-logic-in-memory device appear promising in the realization of next-generation low-power computing systems.
基金This work was supported in part by the National Natural Science Foundation of China(U20A20209 and 61874125)the Strategic Priority Research Program of Chinese Academy of Sciences(XDB32050204)+1 种基金the Zhejiang Provincial Natural Science Foundation of China(LD19E020001 and LQ22F040003)the State Key Laboratory of Silicon Materials(SKL2021-03).
文摘Artificial vision is crucial for most artificial intelligence applications.Conventional artificial visual systems have been facing challenges in terms of real-time information processing due to the physical separation of sensors,memories,and processors,which results in the production of a large amount of redundant data as well as the data conversion and transfer between these three components consuming most of the time and energy.Emergent optoelectronic memristors with the ability to realize integrated sensing-computing-memory(ISCM)are key candidates for solving such challenges and therefore attract increasing attention.At present,the memristive ISCM devices can only perform primary-level computing with external light signals due to the fact that only monotonic increase of memconductance upon light irradiation is achieved in most of these devices.Here,we propose an all-optically controlled memristive ISCM device based on a simple structure of Au/ZnO/Pt with the ZnO thin film sputtered at pure Ar atmosphere.This device can perform advanced computing tasks such as nonvolatile neuromorphic computing and complete Boolean logic functions only by light irradiation,owing to its ability to reversibly tune the memconductance with light.Moreover,the device shows excellent operation stability ascribed to a purely electronic memconductance tuning mechanism.Hence,this study is an important step towards the next generation of artificial visual systems.
