6 November 2020 in IEEE Journal of Solid-State Circuits
In this work, we present a compute-in-memory (CIM) macro built around a standard two-port compiler macro using foundry 8T bit-cell in 7-nm FinFET technology. The proposed design supports 1024 4 b x 4 b multiply-and-accumulate (MAC) computations simultaneously. The 4-bit input is represented by the number of read word-line (RWL) pulses, while the 4-bit weight is realized by charge sharing among binary-weighted computation caps. Each unit of computation cap is formed by the inherent cap of the sense amplifier (SA) inside the 4-bit Flash ADC, which saves area and minimizes kick-back effect. Access time is 5.5 ns with 0.8-V power supply at room temperature. The proposed design achieves energy efficiency of 351 TOPS/W and throughput of 372.4 GOPS. Implications of our design from neural network implementation and accuracy perspectives are also discussed.
11 January 2023 in Proceedings of the IEEE
For many decades, progress in computing hardware has been closely associated with CMOS logic density, performance, and cost. As such, slowdown in 2-D scaling, frequency saturation in CPUs, and increased cost of design and chip fabrication for advanced technology nodes since the early 2000s have led to concerns about how semiconductor technology may evolve in the future. However, the last two decades have also witnessed a parallel development in the application landscape: the advent of big data and consequent rise of data-intensive computing, using techniques such as machine learning. In this article, we advance the idea that data-intensive computing would further cement semiconductor technology as a foundational technology with multidimensional pathways for growth. Continued progress of semiconductor technology in this new context would require the adoption of a system-centric perspective to holistically harness logic, memory, and packaging resources. After examining the performance metrics for data-intensive computing, we present the historical trends for general-purpose graphics processing unit (GPGPU) as a representative data-intensive computing hardware. Thereon, we estimate the values of the key data-intensive computing parameters for the next decade, and our projections may serve as a precursor for a dedicated technology roadmap. By analyzing the compiled data, we identify and discuss specific opportunities and challenges for data-intensive computing hardware technology.
1 December 2007 in Microelectronics Reliability
15 May 2009 in ECS Transactions
Electromechanical relays exhibit inherently zero leakage and sharp hysteresis, which are compelling for logic and memory applications. We present an overview of the nano-scale electromechanical logic and memory devices, investigate their performance, and make a comparison with state-of-the-art logic and memory technologies. We show that nanoelectromechanical logic relays and memory cells can provide significant benefit in terms of operating voltage and energy dissipation -beyond the capability of current technologies- if the technological challenges related to surface adhesion and contact reliability can be overcome.
7 October 2010 in IEEE Transactions on Nuclear Science
We have characterized the total ionizing dose (TID) response of SOI FinFETs, fabricated in two different technologies, operated in 1T-DRAM mode, one with poly-crystalline Si gates and a SiO2 gate dielectric, and the other with metal gates and a high-K gate dielectric. These devices were programmed using both back-gate pulse and gate induced drain leakage (GIDL) programming methods. 1T-DRAM cells programmed with back-gate pulses are quite sensitive to total ionizing dose radiation, with the memory sensing margin and retention time decreasing significantly with increasing dose. In contrast, the sensing margin and retention time show high tolerance to total ionizing dose irradiation when the 1T-DRAM cells are programmed via GIDL. The sensing margin increases significantly with decreasing gate length for 1T-DRAM cells programmed via GIDL. We conclude that capacitor-less 1T-DRAMs programmed via GIDL are strong candidates for embedded memory applications for ultimately scaled CMOS devices in high-TID applications.
15 November 2023 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
TCTsung-Yung Jonathan Chang
Tsung-Yung Jonathan Chang
+5
Compute-in-memory (CIM) has recently emerged as a promising design paradigm to accelerate deep neural network (DNN) processing. Continuously better energy and area efficiency at the macrolevel had been reported through many testchips over the last few years. However, in those macro design-oriented studies, accelerator-level considerations, such as memory accesses and processing of entire DNN workloads have not been investigated in-depth. In this article, we aim to fill this gap starting with the characteristics of our latest CIM macro fabricated with cutting-edge FinFET CMOS technology at 4-nm node. We then study, through an accelerator simulator developed in-house, three key items that would determine the efficiency of our CIM macro in the accelerator context while running MLPerf Mobile suite: 1) dataflow optimization; 2) optimal selection of CIM macro dimensions to further improve macro utilization; and 3) optimal combination of multiple CIM macros. Although there is typically a stark contrast between macro-level peak and accelerator-level average throughput and energy efficiency, the aforementioned optimizations are shown to improve the macro utilization by $3.04\times $ and reduce the energy-delay product (EDP) to $0.34\times $ compared to the original macro on MLPerf Mobile inference workloads. While we exploit a digital CIM macro in this study, the findings and proposed methods remain valid for other types of CIM (such as analog CIM and analog–digital–hybrid CIM) as well.