Edge accelerators such as Nvidia Jetsons are an integral part of the computing continuum, and are used for DNN inference and training. Jetson edge devices have 2000+ CUDA cores within a 70W power envelope and offer 1000s of power modes to customize CPU, GPU and memory frequencies, enabling diverse power–performance tra...
P. K, Kunal Kumar Sahoo, Amartya Ranjan Saikia et al.· Proceedings of the Internati...· 0 citations
This work develops time and energy roofline characterizations for Orin AGX across power modes, coupled with analytical models of compute and memory for DNN inference, and extends these models to DNN training, and demonstrates power-mode tuning that achieves up to \(15\%\) lower energy with small inference-time impact f...
P. K, Kunal Kumar Sahoo, Amartya Ranjan Saikia et al.· Proceedings of the Internati...· 0 citations
Taurus is presented, a single-machine system for GNN inference on graphs that do not fit in RAM, supporting both full-graph inference and fanout-sampled inference, and outperforms the strongest layer-wise baseline, DGI.
Pranjal Naman, Yogesh L. Simmhan· arXiv.org· 0 citations
This work proposes and develops an open-source policy simulation framework, LoadStar, which forms a reusable benchmark pipeline for validating policies for resource-centric NoSQL workloads, and defines a resource optimization problem for placing Cosmos DB replicas onto VM nodes, and develops the Luna model for forecast...
Gunika Verma, V. AashutoshA, P. Srinivas et al.· Proceedings of the VLDB Endo...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
