{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T19:23:53Z","timestamp":1774121033434,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,15]]},"DOI":"10.1109\/hpec67600.2025.11196674","type":"proceedings-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T17:35:37Z","timestamp":1760636137000},"page":"1-7","source":"Crossref","is-referenced-by-count":2,"title":["Performance-Energy Characterization of ML Inference on Heterogeneous Edge AI Platforms"],"prefix":"10.1109","author":[{"given":"Palash","family":"Kohli","sequence":"first","affiliation":[{"name":"BITS Pilani,Pilani,India"}]},{"given":"Rakshith","family":"Jayanth","sequence":"additional","affiliation":[{"name":"University of Southern California,Los Angeles,USA"}]},{"given":"Neelesh","family":"Gupta","sequence":"additional","affiliation":[{"name":"University of Southern California,Los Angeles,USA"}]},{"given":"Haoyang","family":"Fan","sequence":"additional","affiliation":[{"name":"University of Southern California,Los Angeles,USA"}]},{"given":"Viktor","family":"Prasanna","sequence":"additional","affiliation":[{"name":"University of Southern California,Los Angeles,USA"}]}],"member":"263","reference":[{"issue":"3","key":"ref1","article-title":"Architecting agentic ai for real-time autonomous edge systems in next-gen mobile devices","volume":"2","author":"Sheelam","year":"2025","journal-title":"Advances in Consumer Research"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2025.06.027"},{"key":"ref3","article-title":"From large ai models to agentic ai: A tutorial on future intelligent communications","author":"Jiang","year":"2025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2025.3544940"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2025.100399"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895532"},{"key":"ref7","article-title":"Exploration of the amd ryzen npu for real-time signal processing","author":"Capetillo"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2025.3568807"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/s25020472"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/info16020107"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128791"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-97401-9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03425-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-025-02954-4"},{"key":"ref15","article-title":"Dapo: An open-source llm reinforcement learning system at scale","author":"Yu","year":"2025"},{"key":"ref16","article-title":"Sled: A speculative llm decoding framework for efficient edge serving","author":"Li","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW66978.2025.00173"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.8322"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2931922"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/f12020212"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcce.2021.02.002"},{"key":"ref22","article-title":"Llama 3.1: An in-depth analysis of the next-generation large language model","author":"Vavekanand","year":"2024"},{"key":"ref23","article-title":"Phi-4-reasoning technical report","author":"Abdin","year":"2025"},{"key":"ref24","article-title":"Ryzen ai processor"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2024.3423692"},{"key":"ref26","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3113475"},{"key":"ref28","article-title":"Multi-head or single-head? an empirical comparison for transformer training","author":"Liu","year":"2021"},{"key":"ref29","article-title":"Kvlink: Accelerating large language models via efficient kv cache reuse","author":"Yang","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.125"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.631"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IC2E52221.2021.00016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2025.3559346"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3490422.3502359"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC56025.2022.00015"},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.1145\/3767742","article-title":"Sustainable llm inference for edge ai: Evaluating quantized llms for energy efficiency, output accuracy, and inference latency","author":"Husom","year":"2025"},{"key":"ref37","article-title":"Ryzen ai software"},{"key":"ref38","article-title":"Onnx runtime"},{"key":"ref42","article-title":"Transformers are ssms: Generalized models and efficient algorithms through structured state space duality","author":"Dao","year":"2024"},{"key":"ref43","article-title":"Viterbi-iusstf research program"},{"key":"ref44","article-title":"Nsf-iucrc-ideas-center"}],"event":{"name":"2025 IEEE High Performance Extreme Computing Conference (HPEC)","location":"Wakefield, MA, USA","start":{"date-parts":[[2025,9,15]]},"end":{"date-parts":[[2025,9,19]]}},"container-title":["2025 IEEE High Performance Extreme Computing Conference (HPEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11196085\/11196088\/11196674.pdf?arnumber=11196674","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T04:50:23Z","timestamp":1760676623000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11196674\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,15]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/hpec67600.2025.11196674","relation":{},"subject":[],"published":{"date-parts":[[2025,9,15]]}}}