Search Results - computing+architecture

10 Results Sort By:
In-Memory Hardware-Software Co-design for Image Processing
A substantial part of high energy consumption (> 60%) and large latency (> 90%) of conventional von-Neumann architectures can be attributed to the unavoidable data movement between the processor and main memory (DRAM). This is perhaps the major limiting factor for big data and machine learning applications whose usage is permeating into practically...
Published: 5/22/2024   |   Inventor(s): Ayushi Dube, Ankit Wagle, Gian Singh, Sarma Vrudhula
Keywords(s): Algorithm Development, Computing Architecture, Imaging, Machine Learning, Performance Optimization, PS-Computing and Information Technology, Resource Management
Category(s): Computing & Information Technology, Imaging, Physical Science
Clock Skewing for Area and Power Optimization of ASICs Using Differential Flipflops and Local Clocking
Synchronous logic remains the dominant design paradigm of digital systems such as Application Specific Integrated Circuits (ASICs). The conventional design of sequential circuit networks is based on the assumption that every register receives the clock signal at the same time. However, guaranteeing the simultaneity of clock arrival times in practice...
Published: 1/10/2024   |   Inventor(s): Sarma Vrudhula, Ankit Wagle
Keywords(s): Circuits, Computing Architecture, Electronics, Integrated Circuits, PS-Applied Technologies, PS-Semiconductor Devices
Category(s): Applied Technologies, Physical Science, Semiconductor Devices
Dynamic and Efficient Hardware/Software Codesigns of Deep Learning Accelerators
Efficient hardware/software codesigns of deep learning accelerators are crucial for optimizing their performance in various applications, ranging from datacenters to mobile and wearable devices. The existing methods for optimizing deep learning accelerator designs are primarily black-box approaches, which do not consider crucial information about the...
Published: 9/27/2023   |   Inventor(s): Shail Dave, Aviral Shrivastava
Keywords(s): Algorithm Development, Computing Architecture, Machine Learning, PS-Computing and Information Technology, Software
Category(s): Computing & Information Technology, Physical Science
Single-Cycle Processing-in-SRAM Logic Circuit Design
Traditional von-Neumann computing architectures, such as CPUs and GPUs, demonstrate limitations in memory bandwidth and energy efficiency. However, their high demand lies in their programmability and flexible functionality. Such platforms execute a wide spectrum of bit-wise logic and arithmetic operations. In this regard, recent application-specific...
Published: 7/15/2023   |   Inventor(s): Deliang Fan, Shaahin Angizi
Keywords(s): Algorithm Development, Circuits, Computational Machine, Computing Architecture, Electronics, Memory, PS-Computing and Information Technology
Category(s): Computing & Information Technology, Physical Science
Masked-Based Learning Method for Neural Network Multiple Task Adaption
Nowadays, one practical limitation of deep neural networks (DNNs) is their high degree of specialization to a single task. This motivates researchers to develop algorithms that can adapt the DNN model to multiple tasks sequentially, while still performing well on past tasks. This process of gradually adapting the DNN model to learn from different...
Published: 4/19/2023   |   Inventor(s): Deliang Fan, Fan Zhang, Li Yang
Keywords(s): Algorithm Development, Computational Machine, Computing Architecture, Cyber-Physical System, Machine Learning, Neural Computing
Category(s): Computing & Information Technology, Physical Science
Processing-In-Memory (PIM) Platform for mRNA Quantification
­The study of human genetics is a rapidly expanding field, fueled in part by developments in large-scale protein and genomic sequencing technologies. Biopharmaceutical companies and modern healthcare rely heavily on sequencing technologies and the acquired data to develop new drugs and provide effective treatments to patients. However, the results...
Published: 2/23/2023   |   Inventor(s): Deliang Fan, Fan Zhang, Shaahin Angizi
Keywords(s): Algorithm Development, Biomarker discovery, Computing Architecture, DNA and protein sequencing, Genomics, Proteomics, Sequencing
Category(s): Physical Science, Computing & Information Technology, Bioanalytical Assays, Chemistries & Devices, Genomic Assays/Reagents/Tools
Fast and Efficient Max/Min Searching in DRAM
­In the era of big data, min/max searching from bulk data arrays is one of the most important and widely used fundamental operations in data-intensive applications such as sorting, ranking, bioinformatics, data mining, graph processing, and route planning. Online news and social media require real-time ranking using fast min/max searching from...
Published: 2/23/2023   |   Inventor(s): Deliang Fan, Fan Zhang, Shaahin Angizi
Keywords(s): Algorithm Development, Computational Machine, Computing Architecture, Data Center, Data Mining, Microprocessors, Processing
Category(s): Computing & Information Technology, Physical Science
One-Cycle Reconfigurable In-Memory Logic for Non-Volatile Memory
­Background Today’s computers are typically based on von-Neumann architecture with separate computing and memory units connected via buses. This configuration leads to high memory access latency, limited memory bandwidth, energy-hungry data transfer, and significant leakage power from holding data in volatile memory. These bottlenecks may...
Published: 2/23/2023   |   Inventor(s): Deliang Fan, Shaahin Angizi
Keywords(s): Circuits, Computational Machine, Computing Architecture, Electronics
Category(s): Physical Science, Computing & Information Technology
Flexible and Efficient XNOR Circuit Architecture for Neural Network Based Deep Learning
Background Neuro-inspired machine deep learning have demonstrated that they can perform complex tasks such as image and speech classification, object recognition, and real-time decision-making. The state-of-the-art deep learning algorithms employ neural networks which have millions of parameters. Deploying such deep neural networks onto mobile platforms...
Published: 2/23/2023   |   Inventor(s): Shimeng Yu, Rui Liu
Keywords(s): Circuits, Computing Architecture, Machine Learning, Memory, Neural Computing
Category(s): Computing & Information Technology, Physical Science, Semiconductor Devices, Semiconductors, Materials & Processes
Static and dynamic precision adaptation for hardware learning and classification
Artificial neural networks have countless applications with their ability for adaptive learning, recognition, and classification. When implemented in software, the artificial neural network algorithms often use a double-precision format. This can result in large area and power requirements for the hardware. Other approaches can be used to determine...
Published: 2/23/2023   |   Inventor(s): Jae-Sun Seo
Keywords(s): Circuits, Computing Architecture, Energy Efficiency, Neural Computing
Category(s): Applied Technologies, Computing & Information Technology, Physical Science, Wireless & Networking