CMOS-Based HW Topology For Single-Cycle In-Memory XOR/XNOR Operations


A technical paper titled “CMOS-based Single-Cycle In-Memory XOR/XNOR” was published by researchers at University of Tennessee, University of Virginia, and Oak Ridge National Laboratory (ORNL). Abstract: "Big data applications are on the rise, and so is the number of data centers. The ever-increasing massive data pool needs to be periodically backed up in a secure environment. Moreover, a ... » read more

Research Bits: November 6


Fast superatomic semiconductor Researchers from Columbia University created a fast and efficient superatomic semiconductor material based on rhenium called Re6Se8Cl2. Rather than scattering when they come into contact with phonons, excitons in Re6Se8Cl2 bind with phonons to create new quasiparticles called acoustic exciton-polarons. Although polarons are found in many materials, those in Re6Se... » read more

Design Optimization Of Split-Gate NOR Flash For Compute-In-Memory


A technical paper titled “Design Strategies of 40 nm Split-Gate NOR Flash Memory Device for Low-Power Compute-in-Memory Applications” was published by researchers at Seoul National University of Science and Technology and University of Seoul. Abstract: "The existing von Neumann architecture for artificial intelligence (AI) computations suffers from excessive power consumption and memo... » read more

Architectural Considerations For Compute-In-Memory In AI Inference


Can Compute-in-Memory (CIM) bring new benefits to AI (Artificial Intelligence) inference? CIM is not an AI solution; rather, it is a memory management solution. CIM could bring advantages to AI processing by speeding up the multiplication operation at the heart of AI model execution. To read more, click here. » read more

Can Compute-In-Memory Bring New Benefits To Artificial Intelligence Inference?


Compute-in-memory (CIM) is not necessarily an Artificial Intelligence (AI) solution; rather, it is a memory management solution. CIM could bring advantages to AI processing by speeding up the multiplication operation at the heart of AI model execution. However, for that to be successful, an AI processing system would need to be explicitly architected to use CIM. The change would entail a shift ... » read more

A Hierarchical And Tractable Mixed-Signal Verification Methodology For First-Generation Analog AI Processors


Artificial intelligence (AI) is now the key driving force behind advances in information technology, big data and the internet of things (IoT). It is a technology that is developing at a rapid pace, particularly when it comes to the field of deep learning. Researchers are continually creating new variants of deep learning that expand the capabilities of machine learning. But building systems th... » read more

Co-Design View of Cross-Bar Based Compute-In-Memory


A new review paper titled "Compute in-Memory with Non-Volatile Elements for Neural Networks: A Review from a Co-Design Perspective" was published by researchers at Argonne National Lab, Purdue University, and Indian Institute of Technology Madras. "With an over-arching co-design viewpoint, this review assesses the use of cross-bar based CIM for neural networks, connecting the material proper... » read more

Research Bits: Jan. 24


Transistor-free compute-in-memory Researchers from the University of Pennsylvania, Sandia National Laboratories, and Brookhaven National Laboratory propose a transistor-free compute-in-memory (CIM) architecture to overcome memory bottlenecks and reduce power consumption in AI workloads. "Even when used in a compute-in-memory architecture, transistors compromise the access time of data," sai... » read more

Transistor-Free Compute-In-Memory Architecture


A new technical paper titled "Reconfigurable Compute-In-Memory on Field-Programmable Ferroelectric Diodes" was recently published by researchers at University of Pennsylvania, Sandia National Labs, and Brookhaven National Lab. The compute-in-memory design is different as it is completely transistor-free. “Even when used in a compute-in-memory architecture, transistors compromise the access... » read more

Simulation Framework to Evaluate the Feasibility of Large-scale DNNs based on CIM Architecture & Analog NVM


Technical paper titled "Accuracy and Resiliency of Analog Compute-in-Memory Inference Engines" from researchers at UCLA. Abstract "Recently, analog compute-in-memory (CIM) architectures based on emerging analog non-volatile memory (NVM) technologies have been explored for deep neural networks (DNNs) to improve scalability, speed, and energy efficiency. Such architectures, however, leverage ... » read more

← Older posts Newer posts →