In the area of bio-informatics and pattern recognition, sequence alignment and pattern matching are important operations, respectively. Finding the Longest Common Subsequence(LCS) plays an essential role in sequential...
详细信息
In digital communication there are various single and double bit error correcting and detecting codes are available. The efficiency of an error correcting code is evaluated by its errors correction capabilities and re...
详细信息
In the digital realm, constant attempts are made to enhance system performance and user engagement. The Large Action Model's (LAM's), a whole architecture with the power to fundamentally alter the online and a...
详细信息
As the transportation sector moves towards electrification, the development of power electronic components becomes increasingly important, with MOSFETs playing a crucial role in electric and hybrid vehicles (EHVs). Ra...
详细信息
ISBN:
(数字)9798350391107
ISBN:
(纸本)9798350391114
As the transportation sector moves towards electrification, the development of power electronic components becomes increasingly important, with MOSFETs playing a crucial role in electric and hybrid vehicles (EHVs). Raised Source Drain Double Gate Junctionless Field Effect Transistor (RSD-DG JLFET) simulation study is presented here. The study compares the electrical properties of an RSD-DG JLFET with PMOSFET and JLFET. A 2D device simulation platform is used to compare the subthreshold swing, threshold voltage, and Ion/Ioff ratio of the proposed structure, PMOSFET, and JLFET. The simulation results indicate that the RSD-DG JLFET offers significant improvements in efficiency and reliability for EV applications.
In this paper, the damping properties of two different grid-forming (GFM) control strategies, namely direct control of converter voltage (DCCV) and virtual-admittance based control (VABC) are investigated. The investi...
详细信息
SiC double trench MOSFETs have the advantage of generating a deep P+ layers through the trench source, effectively mitigating electric field crowding at the bottom edge of the gate oxide. However, the depletion region...
详细信息
This paper introduces an RL-driven algorithm for fine-grained power gating of functional units in superscalar processors. The proposed algorithm leverages a Multi-Layer Perceptron (MLP) neural network as a policy mode...
详细信息
ISBN:
(数字)9798331509422
ISBN:
(纸本)9798331509439
This paper introduces an RL-driven algorithm for fine-grained power gating of functional units in superscalar processors. The proposed algorithm leverages a Multi-Layer Perceptron (MLP) neural network as a policy model, trained by a reinforcement learning (RL) agent, to optimize power states across four modes: On, Sleep-on, Sleep-off, and Off. By statically analyzing features extracted from the control flow graph (CFG) and execution profile of the program, the RL-driven model selects the most energy-efficient power states for each functional unit without compromising performance. Traditional power gating techniques often struggle with tradeoffs between minimizing performance loss (wake-up latency) and reducing power consumption, necessitating a reevaluation of power management strategies. Next-generation complex SoC designs at < 7nm technology nodes require a finer granularity approach to effectively manage power states. Our AI-based algorithm provides an optimized trade-off between power efficiency and performance by enabling power gating across multiple power states and selecting the power state that has the effectively least energy-delay product. Additionally, we propose an architectural circuit design for power gating multiple FU's within a superscalar processor, enabling efficient state transitions. Preliminary experimental results show that the proposed AI-based method achieves 10-20% energy savings while improving performance by 1.5% compared to traditional power gating algorithms.
Time-series SAR images exhibit spatial and temporal correlations, providing richer information about temporal variations. However, effectively utilizing the information from time-series images is a significant task in...
详细信息
Colorectal cancer is one of the prevalent forms of fatal cancer. The presence of tumors inside the colon is identified through colonoscopy which helps to determine whether the polyp is benign or malignant. Prediction ...
详细信息
Industrial computed laminography (ICL) is a three-dimensional (3D) non-destructive imaging method widely used in industrial digital imaging of plate-shell components. However, for imaging aero-engine turbine discs wit...
详细信息
暂无评论