Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 60 for “"compute in-memory"”.
-
Compute-In-Memory Deep Learning Using Memristor Crossbars
Deep learning redefines computing and greatly impacts our daily lives, but it comes at the cost of massive energy consumption and intensive memory requirements from large-scale data centers driven by exploding data collection and artificial intelligence. This challenge demands an intense search for …
-
Architecture and Circuit Design Optimization for Compute-In-Memory
… of the proposed research is to optimize computing-in-memory (CIM) design for accelerating Deep Neural Network (DNN) algorithms. As compute peripheries such as analog-to-digital converter (ADC) introduce significant overhead in CIM inference design, the research first focuses on the circuit …
-
Efficient and Robust Compute-in-Memory for Edge Intelligence
With deep neural networks (DNNs) fueling major advancements in artificial intelligence (AI), the demand for efficient computing solutions has never been higher. This dissertation delves into the challenges and innovations in the field of compute-in-memory (CIM) technologies, a key area for …
-
COMPUTE-IN-MEMORY ON EMERGING MEMORY TECHNOLOGY: FROM DEVICE TO ALGORITHM
Present-day computing systems largely adhere to the von Neumann architecture, which necessitates data transfer from memory to a processing unit. This architecture presents a significant latency issue when accessing data from memory units, which is a primary performance hindrance for various …
-
Cryogenic Compute-In-Memory Circuits and Architectures for Spiking Neural Networks
This work presents a Computing-In-Memory (CIM)-based Spiking Neural Network (SNN) architecture for energy-efficient, low-latency inference in cryogenic conditions. The proposed CIM-SNN integrates current-domain 8T SRAM vector-matrix multiplication, cryogenic-aware temporal encoding, and …
-
Benchmarking Test-Time DNN Adaptation at Edge with Compute-In-Memory
… the edge can deteriorate over time due to shifts in the data distribution. For heightened robustness, it’s crucial for DNNs to continually refine and improve their predictive capabilities. However, adaptation in resource-limited edge environments is fraught with challenges: (i) new labeled data …
-
DURACIM: Durable compute-in-memory (CiM) inference for resource-limited environments
… encounter a performance bottleneck known as the memory wall, where the compute units are faster and consume less energy than data movement from memory. Compute-in-Memory (CIM) architectures can support MAC operations within memory arrays, helping to resolve the memory wall. However, they suffer …
-
Reliability and Security of Compute-In-Memory Based Deep Neural Network Accelerators
Compute-In-Memory (CIM) is a promising solution for accelerating DNNs at edge devices, utilizing mixed-signal computations. However, it requires more cross-layer designs from algorithm levels to hardware implementations as it behaves differently from the pure digital system. On one side, the …
-
Compute-in-memory designs for deep neural network and combinatorial optimization problems accelerators
The unprecedented growth in Deep Neural Networks (DNN) model size has resulted into a massive amount of data movement from off-chip memory to on-chip processing cores in modern Machine Learning (ML) accelerators. Compute-In-Memory (CIM) designs performing analog DNN computations within a memory …
-
COMPUTE-IN-MEMORY WITH EMERGING NON-VOLATILE MEMORIES FOR ACCELERATING DEEP NEURAL NETWORKS
… accelerate deep neural networks (DNNs) with emerging non-volatile memories (eNVMs) based compute-in-memory (CIM) architecture. The research first focuses on the inference acceleration and proposes a resistive random access memory (RRAM) based CIM architecture. Two generations of RRAM testchips …
-
Design of a non-volatile capacitor-based compute-in memory neural network accelerator
To avoid growing challenges with existing neural network accelerators which have sig- nificant energy requirements, the design for a compute-in-memory (CIM) chip is presented and demonstrated in simulation. The CIM aspect is based off a ferroelectric memory de- vice which allows for both storing …
-
Overcoming Device Level Challenges to Enable Compute In-Memory with Emerging Non-Volatile Memory
… research is to overcome challenges faced by compute in-memory (CIM) and embedded non-volatile memory (eNVM). The combination of eNVM and CIM can greatly increase memory bandwidth and memory density, perform computation on the bitline of memory sub-arrays, and minimize data transport. Despite …
-
Compute-in-memory for Efficient AI: Cross-layer Modeling and Hardware-software Co-Design
Modern deep learning is bottlenecked by the memory wall, where moving weights and activations consumes several times the energy of doing computations. Compute-in-memory (CIM) is one of the main ways around the wall; by performing multiply-accumulate operations inside the memory arrays that store …
-
Design and calibration of current-mode compute-in-memory integrated circuits for neural network processing
The growing use of artificial intelligence (AI) in edge devices has increased the need for hardware that can run neural network inference with higher energy efficiency than conventional digital processors. Compute-in-memory (CIM) addresses this challenge by reducing data movement and performing the …
-
An energy efficient compute-in-memory SRAM for low power CNN based machine learning application
With the increase in computational parallelism and low-power Integrated Circuits (ICs) design, neuromorphic technologies and machine learning algorithms have returned to spotlight as practical solutions for implementing complex classification problems. Although GPUs have significantly advanced the …
-
Analysis and Implementation of Dense On-Die Memories Using Traditional and Compute-in-Memory Approaches
For processors and application accelerators executing data-intensive tasks, including machine learning inference, accessing data from dense memory arrays can be a limiting factor for energy efficiency and/or throughput (performance). The high cost of off-chip accesses has led to the extensive use …
-
Benchmark Framework for 2-D/3-D Integrated Compute-in-Memory Based Machine Learning Accelerator
… frameworks, to evaluate the state-of-the-art compute-in-memory (CIM) accelerators, by considering the hardware performance with the impacts from device options, circuit topologies, architecture hierarchy and data flow, as well as the software accuracy with non-ideal hardware properties. The …
Page 1 of 3