This paper presents a 4 + 2T SRAM for embedded searching and in-memory-computing applications. The proposed SRAM cell uses the n-well as the write wordline to perform write operations and eliminate the write access transistors, achieving 15% area saving compared with conventional 8T SRAM. The decoupled differential read paths significantly improve read noise margin, and therefore reliable multi-word activation can be enabled to perform in-memory Boolean logic functions. Reconfigurable differential sense amplifiers are employed to realize fast normal read or multi-functional logic operations. Moreover, the proposed 4 + 2T SRAM can be reconfigured as binary content-addressable memory (BCAM) or ternary content-addressable memory (TCAM) for searching operations, achieving 0.13 fJ/search/bit at 0.35 V. The chip is fabricated in 55-nm deeply depleted channel technology. The area efficiency is 65% for a 128 x 128 pushed-rule array including all peripherals such as column-wise sense amplifier for read/logic and row-wise sense amplifier for BCAM/TCAM operations. Forty dies across five wafers in different corners are measured, showing a worst-case read/write VDDmin of 0.3 V.
This paper presents a single-chip, high-performance, and energy-efficient stereo vision depth-estimation processor for micro aerial vehicles (MAVs). The proposed processor implements the state-of-the-art semi-global matching (SGM) algorithm to deliver full high-definition (HD, 1920 x 1080) stereo-depth outputs with a maximum of 38 frames/s throughput. Algorithm-architecture co-optimization is conducted, introducing overlapping block-based processing that eliminates very large on-chip memory and off-chip DRAM. We exploit inherent data parallelism in the algorithm by processing 128 local disparity costs and aggregating the SGM costs along four paths for all 128 disparities in parallel. A dependence-resolving scan associated with 16-stage deep pipeline is introduced to hide the data dependence between neighboring pixels in the SGM algorithm. Moreover, we propose a customized ultra-high bandwidth dual-port SRAM that utilizes the unique memory access characteristic of SGM to achieve highly energy-efficient memory access at a very high on-chip memory bandwidth of 1.64 Tb/s. The fabricated processor produces 512 levels of depth information for each pixel at full HD resolution with 30-frames/s performance, consuming 836 mW from a 0.75-V supply in TSMC 40-nm GP CMOS. We ported the design on a quadcopter MAV to demonstrate its performance in realistic real-time flight.
Current approaches to Analog Layout Automation apply ML techniques such as Graph Convolutional Neural Networks (GCN) to translate netlist to layout. While these ML approaches have proven to be effective, they lack the powerful reasoning capabilities, an intuitive human interface, and standard evaluation benchmarks that have been improving at a rapid development pace in Large Language Models (LLMs). The GLayout framework introduced in this work translates analog layout into an expressive, technology generic, compact text representation. Then, an LLM is taught to understand analog layout through fine-tuning and in-context learning using Retrieval Augmented Generation (RAG). The LLM is able to successfully layout unseen circuits based on new information provided in-context. We train 3.8, 7, and 22 Billion parameter quantized LLMs on a dataset of less than 50 unique circuits, and text documents providing layout knowledge. The 22B parameter model is tuned in 2 hours on a single NVIDIA A100 GPU. The open-source evaluation set is proposed as an automation benchmark for LLM layout automation tasks, and ranges from 2-transistor circuits to a ΔΣ ADC. The 22B model completes 70% of the tasks in the evaluation set, and passes DRC and LVS verification on 44% of evaluations with verified correct blocks up to 4 transistors in size.
On recent years, researchers across diverse disciplines have become increasingly interested in low-temperature electronics, which encompasses electronic engineering, material research, sensing, and computing. Among the myriad applications, notable domains include liquid nitrogen-cooled high-performance computing, quantum computing, and deep space exploration [1] . This dynamic landscape has witnessed the culmination of numerous research studies, as evidenced by the rich array of findings outlined in references [2] , [3] , [4] , [5] , and [6] . This field is particularly fascinating due to its multifaceted applications, requiring a comprehensive understanding of knowledge, data, and tools that operate across varying temperature ranges, as detailed in [7] , where the goal is to move the control logic closer to the cryogenic device being tested. This task highlights the significant obstacles that arise when dealing with cryogenic circuitry. As temperatures drop below a certain threshold, the behavior of transistors and passive devices undergoes a significant transformation. Designers must carefully measure and model these devices internally, adjusting circuit scaling based on basic models. This process demands significantly more man-hours compared with conventional circuit design methodologies. The task could be streamlined with the presence of a shared metrology device modeling database among institutions. Such a resource would alleviate the need for redundant efforts and foster efficiency in cryogenic circuit design.
1 January 2024 in IEEE Solid-State Circuits Letters
This letter presents a fully integrated recursive successive-approximation switched capacitor (RSC) DC–DC converter implemented using an automatic cell-based layout generation in 12-nm FinFET technology. A novel design methodology is demonstrated based on the theoretical analyses of the optimal energy operation of the switched-capacitor (SC) DC–DC converter and directly finds the optimal design parameters from the given input specifications. The converter maintains >75% efficiency across a vast range of output currents and temperatures. Our design targets voltage scaling for applications, such as cryo-computing, cryo-sensing, and parts of quantum computing, to achieve high-system power efficiency.