Computation-in-memory (CIM) is a promising candidate to improve the energy efficiency of multiply-and-accumulate (MAC) operations of artificial intelligence (AI) chips. This work presents an static ...random access memory (SRAM) CIM unit-macro using: 1) compact-rule compatible twin-8T (T8T) cells for weighted CIM MAC operations to reduce area overhead and vulnerability to process variation; 2) an even-odd dual-channel (EODC) input mapping scheme to extend input bandwidth; 3) a two's complement weight mapping (C2WM) scheme to enable MAC operations using positive and negative weights within a cell array in order to reduce area overhead and computational latency; and 4) a configurable global-local reference voltage generation (CGLRVG) scheme for kernels of various sizes and bit precision. A 64 × 60 b T8T unit-macro with 1-, 2-, 4-b inputs, 1-, 2-, 5-b weights, and up to 7-b MAC-value (MACV) outputs was fabricated as a test chip using a foundry 55-nm process. The proposed SRAM-CIM unit-macro achieved access times of 5 ns and energy efficiency of 37.5-45.36 TOPS/W under 5-b MACV output.
Computing-in-memory (CIM) based on embedded nonvolatile memory is a promising candidate for energy-efficient multiply-and-accumulate (MAC) operations in artificial intelligence (AI) edge devices. ...However, circuit design for NVM-based CIM (nvCIM) imposes a number of challenges, including an arealatency-energy tradeoff for multibit MAC operations, patterndependent degradation in signal margin, and small read margin. To overcome these challenges, this article proposes the following: 1) a serial-input non-weighted product (SINWP) structure; 2) a down-scaling weighted current translator (DSWCT) and positive-negative current-subtractor (PN-ISUB); 3) a currentaware bitline clamper (CABLC) scheme; and 4) a triple-margin small-offset current-mode sense amplifier (TMCSA). A 55-nm 1-Mb ReRAM-CIM macro was fabricated to demonstrate the MAC operation of 2-b-input, 3-b-weight with 4-b-out. This nvCIM macro achieved T MAC = 14.6 ns at 4-b-out with peak energy efficiency of 53.17 TOPS/W.
Previous SRAM-based computing-in-memory (SRAM-CIM) macros suffer small read margins for high-precision operations, large cell array area overhead, and limited compatibility with many input and weight ...configurations. This work presents a 1-to-8-bit configurable SRAM CIM unit-macro using: 1) a hybrid structure combining 6T-SRAM based in-memory binary product-sum (PS) operations with digital near-memory-computing multibit PS accumulation to increase read accuracy and reduce area overhead; 2) column-based place-value-grouped weight mapping and a serial-bit input (SBIN) mapping scheme to facilitate reconfiguration and increase array efficiency under various input and weight configurations; 3) a self-reference multilevel reader (SRMLR) to reduce read-out energy and achieve a sensing margin 2<inline-formula> <tex-math notation="LaTeX">\times </tex-math></inline-formula> that of the mid-point reference scheme; and 4) an input-aware bitline voltage compensation scheme to ensure successful read operations across various input-weight patterns. A 4-Kb configurable 6T-SRAM CIM unit-macro was fabricated using a 55-nm CMOS process with foundry 6T-SRAM cells. The resulting macro achieved access times of 3.5 ns per cycle (pipeline) and energy efficiency of 0.6-40.2 TOPS/W under binary to 8-b input/8-b weight precision.
The development of high-performance near-infrared organic light-emitting diodes is hindered by strong non-radiative processes as governed by the energy gap law. Here, we show that exciton ...delocalization, which serves to decouple the exciton band from highly vibrational ladders in the S0 ground state, can bring substantial enhancements in the photoluminescence quantum yield of emitters, bypassing the energy gap law. Experimental proof is provided by the design and synthesis of a series of new Pt(ii) complexes with a delocalization length of 5–9 molecules that emit at 866–960 nm with a photoluminescence quantum yield of 5–12% in solid films. The corresponding near-infrared organic light-emitting diodes emit light with a 930 nm peak wavelength and a high external quantum efficiency up to 2.14% and a radiance of 41.6 W sr−1 m−2. Both theoretical and experimental results confirm the exciton–vibration decoupling strategy, which should be broadly applicable to other well-aligned molecular solids.Pt(ii) complexes allow the fabrication of efficient near-infrared organic light-emitting diodes that operate beyond the 900 nm region.
Applying the wireless sensor network of the Industrial Internet of Things and the radio frequency identification technology to the production workshop of the discrete manufacturing industry, the ...real-time status of the shop floor can be automatically collected, providing a powerful decision-making basis for the upper-level planning management department. This paper proposes a reference architecture and construction path for smart factories by analyzing industrial IoT technology and its application in manufacturing workshops. Combined with the analysis of the status quo and needs of the discrete manufacturing enterprise workshop, this paper designs the overall architecture and theoretical model of the system. In view of the variety of on-site manufacturing data, large amount of data, variable status, heterogeneity, and strong correlation between data, integrated key technologies such as WSN and RFID, the industrial IoTs solution for manufacturing workshops is given. The multi-thread data real-time collection, storage technology and product tracking monitoring of the workshop are studied. Finally, the performance of the system is analyzed from the perspective of real-time and quality. The results show that the system is effective in the monitoring of production line data.
Quantum‐dot‐tagged reduced graphene oxide (QD‐rGO) nanocomposites (left) internalized into targeted tumor cells display bright fluorescence from the QDs (right); by absorbing NIR radiation incident ...on the rGO and converting it into heat, they also cause simultaneous cell death and fluorescence reduction (bottom). The nanocomposite is thus capable of tumor imaging, photothermal therapy and in situ monitoring of treatment in progress.
Deeply involved with dyslipidemia, cardiovascular disease has becoming the leading cause of mortality since the early twentieth century in the modern world. Whose correlation with metabolic syndrome ...(MetS), hypertension and type 2 diabetes mellitus (T2DM) has been well established. We conducted a 9-year longitudinal study to identify the association between easily measured lipid parameters, future MetS, hypertension and T2DM by gender and age distribution. Divided into three groups by age (young age: < 40, middle age: ≥ 40 and < 65 and old age: ≥ 65), 7670 participants, receiving standard medical inspection at Tri-Service General Hospital (TSGH) in Taiwan, had been enrolled in this study. Atherogenic index of plasma (AIP) was a logarithmically transformed ratio of triglyceride (TG)/high-density lipoprotein cholesterol (HDL-C). Through multivariate regression analyses, the hazard ratio (HR) of AIP for MetS, hypertension and T2DM were illustrated. AIP revealed significant association with all the aforementioned diseases through the entire three models for both genders. Additionally, AIP revealed significant correlation which remained still after fully adjustment in MetS, hypertension, and T2DM groups for subjects aged 40-64-year-old. Nevertheless, for participants aged above 65-year-old, AIP only demonstrated significant association in MetS group. Our results explore the promising value of AIP to determine the high-risk subjects, especially meddle-aged ones, having MetS, hypertension, and T2DM in the present and the future.
A unique “clean‐lifting transfer” (CLT) technique that applies a controllable electrostatic force to transfer large‐area and high‐quality CVD‐grown graphene onto various rigid or flexible substrates ...is reported. The CLT technique without using any organic support or adhesives can produce residual‐free graphene films with large‐area processability, and has great potential for future industrial production of graphene‐based electronics or optoelectronics.
Functional magnetic resonance imaging (fMRI) maps cerebral activation in response to stimuli but this activation is often difficult to detect, especially in low-signal contexts and single-subject ...studies. Accurate activation detection can be guided by the fact that very few voxels are, in reality, truly activated and that these voxels are spatially localized, but it is challenging to incorporate both these facts. We address these twin challenges to single-subject and low-signal fMRI by developing a computationally feasible and methodologically sound model-based approach, implemented in the R package MixfMRI, that bounds the a priori expected proportion of activated voxels while also incorporating spatial context. An added benefit of our methodology is the ability to distinguish voxels and regions having different intensities of activation. Our suggested approach is evaluated in realistic two- and three-dimensional simulation experiments as well as on multiple real-world datasets. Finally, the value of our suggested approach in low-signal and single-subject fMRI studies is illustrated on a sports imagination experiment that is often used to detect awareness and improve treatment in patients in persistent vegetative state (PVS). Our ability to reliably distinguish activation in this experiment potentially opens the door to the adoption of fMRI as a clinical tool for the improved treatment and therapy of PVS survivors and other patients.
This work reveals the intrinsic carrier transport behavior of 2D organolead halide perovskites based on phase‐pure homologous (n = 1, 2, and 3) Ruddelsden–Popper perovskite (RPP) (BA)2(MA)n−1PbnI3n+1 ...single crystals. The 2D perovskite field effect transistors with high‐quality exfoliated 2D perovskite bulk crystals are fabricated, and characteristic output and transfer curves are measured from individual single‐crystal flakes with various n values under different temperatures. Unipolar n‐type transport dominated the electrical properties of all these 2D RPP single crystals. The transport behavior of the 2D organolead halide hybrid perovskites exhibits a strong dependence on the n value and the mobility substantially increases as the ratio of the number of inorganic perovskite slabs per organic spacer increases. By extracting the effect of contact resistances, the corrected mobility values for n = 1, 2, and 3 are 2 × 10−3, 8.3 × 10−2, and 1.25 cm2 V−1 s−1 at 77 K, respectively. Furthermore, by combining temperature‐dependent electrical transport and optical measurements, it is found that the origin of the carrier mobility dependence on the phase transition for 2D organolead halide perovskites is very different from that of their 3D counterparts. Our findings offer insight into fundamental carrier transport behavior of 2D organic–inorganic hybrid perovskites based on phase‐pure homologous single crystals.
2D organolead halide perovskite field effect transistors, which are fabricated based on phase‐pure homologous (n = 1, 2, and 3) Ruddelsden–Popper perovskite (BA)2(MA)n−1PbnI3n+1 single crystals are demonstrated. A strong dependence of carrier transport behavior of the 2D organolead halide hybrid perovskites on the n value is revealed.
PDF
