No article text was recorded for this version.
von Neumann bottleneck (data movement energy overhead)
Version 1 of 1347 papers365 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Communication Lower Bound in Convolution Accelerators
- Blog: Improving Efficiency in Neural Network Accelerator using Operands Hamming Distance Optimization
- Blog: NTX: An Energy-efficient Streaming Accelerator for Floating-point Generalized Reduction Workloads in 22nm FD-SOI
- Blog: Exploiting Inherent Error-Resiliency of Neuromorphic Computing to achieve Extreme Energy-Efficiency through Mixed-Signal Neurons
- Blog: A Survey on Design Methodologies for Accelerating Deep Learning on Heterogeneous Architectures
- Blog: The Future of Memory: Limits and Opportunities
- Blog: DOE Advanced Scientific Computing Advisory Subcommittee (ASCAC) Report: Top Ten Exascale Research Challenges
- Blog: A Beginner's Guide to Power and Energy Measurement and Estimation for Computing and Machine Learning
- Blog: A Survey of Methods For Analyzing and Improving GPU Energy Efficiency
- Blog: Quantized Spike-driven Transformer
- Blog: Mitigating Communication Costs in Neural Networks: The Role of Dendritic Nonlinearity
- Blog: Energy-Aware Deep Learning on Resource-Constrained Hardware
- Blog: Neuromorphic Artificial Intelligence Systems
- Blog: EDCompress: Energy-Aware Model Compression with Dataflow
- Blog: XNOR Neural Engine: a Hardware Accelerator IP for 21.6 fJ/op Binary Neural Network Inference
- Blog: The Future of Consumer Edge-AI Computing
- Blog: Zero-Space Cost Fault Tolerance for Transformer-based Language Models on ReRAM
- Blog: Processing-In-Memory Acceleration of Convolutional Neural Networks for Energy-Efficiency, and Power-Intermittency Resilience
- Blog: ChatGPT at the Speed of Light: Optical Comb-Based Monolithic Photonic-Electronic Linear-Algebra Accelerators
- Blog: Harnessing Intrinsic Noise in Memristor Hopfield Neural Networks for Combinatorial Optimization
- Blog: Fundamental Limits on Energy-Delay-Accuracy of In-memory Architectures in Inference Applications
- Blog: Analog In-Memory Computing with Uncertainty Quantification for Efficient Edge-based Medical Imaging Segmentation
- Blog: A Novel Non-Volatile Inverter-based CiM: Continuous Sign Weight Transition and Low Power on-Chip Training
- Blog: Modeling Data Reuse in Deep Neural Networks by Taking Data-Types into Cognizance
- Blog: Pipeline Gradient-based Model Training on Analog In-memory Accelerators
- Blog: A Customized NoC Architecture to Enable Highly Localized Computing-on-the-Move DNN Dataflow
- Blog: Recent Advances in Convolutional Neural Network Acceleration
- Blog: Proposal for a Leaky Integrate Fire Spiking Neuron Using Voltage Driven Domain Wall Motion
- Blog: Training Dynamical Binary Neural Networks With Equilibrium Propagation
- Blog: Precise deep neural network computation on imprecise low-power analog hardware
- Blog: CiMBA: Accelerating Genome Sequencing Through On-Device Basecalling via Compute-in-Memory
- Blog: Low Power and Temperature-Resilient Compute-In-Memory Based on Subthreshold-FeFET
- Blog: MX: Enhancing RISC-V's Vector ISA for Ultra-Low Overhead, Energy-Efficient Matrix Multiplication
- Blog: When Routers, Switches and Interconnects Compute: A processing-in-interconnect Paradigm for Scalable Neuromorphic AI
- Blog: Cryogenic Brain-inspired Hyperdimensional In-Memory Computing using 5nm Ferroelectric FinFET
- Blog: SupeRBNN: Randomized Binary Neural Network Using Adiabatic Superconductor Josephson Devices
- Blog: Prospects for Analog Circuits in Deep Networks
- Blog: Zero-shifting Technique for Deep Neural Network Training on Resistive Cross-point Arrays
- Blog: Implementation of Ternary Weights With Resistive RAM Using a Single Sense Operation Per Synapse
- Blog: XpulpNN: Enabling Energy Efficient and Flexible Inference of Quantized Neural Network on RISC-V based IoT End Nodes
- Blog: Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices
- Blog: DarwinWafer: A Wafer-Scale Neuromorphic Chip
- Blog: Difference Predictive Coding for Training Spiking Neural Networks
- Blog: Data Intensive Computing: From Modeling to Implementation
- Blog: A Scalable RISC-V Vector Processor Enabling Efficient Multi-Precision DNN Inference
- Blog: Understanding Reuse, Performance, and Hardware Cost of DNN Dataflows: A Data-Centric Approach
- Blog: Kernel Approximation using Analog In-Memory Computing
- Blog: A SOT-MRAM-based Processing-In-Memory Engine for Highly Compressed DNN Implementation
- Blog: A universal approximation theorem for nonlinear resistive networks
- Blog: End-to-end 100-TOPS/W Inference With Analog In-Memory Computing: Are We There Yet?
- Blog: NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds
- Blog: TReCiM: Lower Power and Temperature-Resilient Multibit 2FeFET-1T Compute-in-Memory Design
- Blog: SiTe CiM: Signed Ternary Computing-in-Memory for Ultra-Low Precision Deep Neural Networks
- Blog: Exploiting Oxide Based Resistive RAM Variability for Probabilistic AI Hardware Design
- Blog: MAESTRO: An Open-source Infrastructure for Modeling Dataflows within Deep Learning Accelerators
- Blog: Hierarchical Temporal Memory Based on Spin-Neurons and Resistive Memory for Energy-Efficient Brain-Inspired Computing
- Blog: FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs
- Blog: RESPARC: A Reconfigurable and Energy-Efficient Architecture with Memristive Crossbars for Deep Spiking Neural Networks
- Blog: Feature Map Transform Coding for Energy-Efficient CNN Inference
- Blog: Mixed-Precision Deep Learning Based on Computational Memory
Showing 60 of 347 papers.
History & citation
Current · Permanent link
- Analog In-Memory Computing for Energy Efficient AI merged into this direction (84% overlap)
- Intrinsic Hardware Regularization in Analog Computing merged into this direction (56% overlap)
- Latency Based State Detection in Memory Systems merged into this direction (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_von_neumann_bottleneck_data_movement_ene_8de701b9,
title = {von Neumann bottleneck (data movement energy overhead)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/von-neumann-bottleneck-data-movement-energy-overhead/rdr_8de701b9aa0144eea159cfdf45273c54},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_von_neumann_bottleneck_data_movement_ene_8de701b9_v1,
title = {von Neumann bottleneck (data movement energy overhead)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/von-neumann-bottleneck-data-movement-energy-overhead/rdr_8de701b9aa0144eea159cfdf45273c54/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}