The growing complexity of data-intensive software demands constant innovation in computer hardware design. Performance is a critical factor in rapidly evolving applications such as artificial intelligence (AI). Transaction-level modeling (TLM) is a valuable technique used to represent hardware and software behavior in a simulated environment. However, extracting actionable insights from TLM simulations is not a trivial task. We present Netmemvisual, an interactive, cross-platform visualization tool for exposing memory bottlenecks in TLM simulations. We demonstrate how Netmemvisual helps system designers rapidly analyze complex TLM simulations to find memory contention. We describe the project’s current features, experimental results with two state-of-the-art deep neural networks (DNNs), and planned future work.
Technical Report Number
N. Farzan and E. Arasteh, “Visualizing Transaction-Level Modeling Simulations of Deep Neural Networks,” Chapman University Fowler School of Engineering, Department of Electrical Engineering and Computer Science, Orange, CA, USA, FSE-TR-23-01, Aug. 2023. [Online]. Available: https://digitalcommons.chapman.edu/engineering_technical_reports/1