{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T21:44:13Z","timestamp":1788644653847,"version":"build-2803163510"},"reference-count":36,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Korea Institute for Advancement of Technology (KIAT)","award":["P0017011"],"award-info":[{"award-number":["P0017011"]}]},{"name":"Korea Institute for Advancement of Technology (KIAT)","award":["RS-2024-00345668"],"award-info":[{"award-number":["RS-2024-00345668"]}]},{"name":"National Research Foundation of Korea (NRF)","award":["P0017011"],"award-info":[{"award-number":["P0017011"]}]},{"name":"National Research Foundation of Korea (NRF)","award":["RS-2024-00345668"],"award-info":[{"award-number":["RS-2024-00345668"]}]},{"name":"Chung-Ang University Research Scholarship","award":["P0017011"],"award-info":[{"award-number":["P0017011"]}]},{"name":"Chung-Ang University Research Scholarship","award":["RS-2024-00345668"],"award-info":[{"award-number":["RS-2024-00345668"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Micromachines"],"abstract":"<jats:p>The rapid advancement of artificial intelligence (AI) technology, combined with the widespread proliferation of Internet of Things (IoT) devices, has significantly expanded the scope of AI applications, from data centers to edge devices. Running AI applications on edge devices requires a careful balance between data processing performance and energy efficiency. This challenge becomes even more critical when the computational load of applications dynamically changes over time, making it difficult to maintain optimal performance and energy efficiency simultaneously. To address these challenges, we propose a novel processing-in-memory (PIM) technology that dynamically optimizes performance and power consumption in response to real-time workload variations in AI applications. Our proposed solution consists of a new PIM architecture and an operational algorithm designed to maximize its effectiveness. The PIM architecture follows a well-established structure known for effectively handling data-centric tasks in AI applications. However, unlike conventional designs, it features a heterogeneous configuration of high-performance PIM (HP-PIM) modules and low-power PIM (LP-PIM) modules. This enables the system to dynamically adjust data processing based on varying computational load, optimizing energy efficiency according to the application\u2019s workload demands. In addition, we present a data placement optimization algorithm to fully leverage the potential of the heterogeneous PIM architecture. This algorithm predicts changes in application workloads and optimally allocates data to the HP-PIM and LP-PIM modules, improving energy efficiency. To validate and evaluate the proposed technology, we implemented the PIM architecture and developed an embedded processor that integrates this architecture. We performed FPGA prototyping of the processor, and functional verification was successfully completed. Experimental results from running applications with varying workload demands on the prototype PIM processor demonstrate that the proposed technology achieves up to 29.54% energy savings.<\/jats:p>","DOI":"10.3390\/mi15101222","type":"journal-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T04:57:28Z","timestamp":1727672248000},"page":"1222","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Dynamic Performance and Power Optimization with Heterogeneous Processing-in-Memory for AI Applications on Edge Devices"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9959-035X","authenticated-orcid":false,"given":"Sangmin","family":"Jeon","sequence":"first","affiliation":[{"name":"Department of Intelligent Semiconductor Engineering, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul 06974, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4412-8600","authenticated-orcid":false,"given":"Kangju","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Intelligent Semiconductor Engineering, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul 06974, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0505-3753","authenticated-orcid":false,"given":"Kyeongwon","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Intelligent Semiconductor Engineering, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul 06974, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5736-4583","authenticated-orcid":false,"given":"Woojoo","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Intelligent Semiconductor Engineering, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul 06974, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Bourechak, A., Zedadra, O., Kouahla, M.N., Guerrieri, A., Seridi, H., and Fortino, G. (2023). At the confluence of artificial intelligence and edge computing in iot-based applications: A review and new perspectives. Sensors, 23.","DOI":"10.3390\/s23031639"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3555802","article-title":"Edge computing with artificial intelligence: A machine learning perspective","volume":"55","author":"Hua","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"85714","DOI":"10.1109\/ACCESS.2020.2991734","article-title":"An overview on edge computing research","volume":"8","author":"Cao","year":"2020","journal-title":"IEEE Access"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Lee, S.Y., Lee, J.H., Lee, J., and Lee, W. (2021). TEI-DTA: Optimizing a Vehicular Sensor Network Operating with Ultra-Low Power System-on-Chips. Electronics, 10.","DOI":"10.3390\/electronics10151789"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Alajlan, N.N., and Ibrahim, D.M. (2022). TinyML: Enabling of inference deep learning models on ultra-low-power IoT edge devices for AI applications. Micromachines, 13.","DOI":"10.3390\/mi13060851"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"O\u2019Connor, O., Elfouly, T., and Alouani, A. (2023). Survey of Novel Architectures for Energy Efficient High-Performance Mobile Computing Platforms. Energies, 16.","DOI":"10.3390\/en16166043"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/JSSC.2022.3220195","article-title":"T-PIM: An energy-efficient processing-in-memory accelerator for end-to-end on-device training","volume":"58","author":"Heo","year":"2022","journal-title":"IEEE J.-Solid-State Circuits"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hu, H., Feng, C., Zhou, H., Dong, D., Pan, X., Wang, X., Zhang, L., Cheng, S., Pang, W., and Liu, J. (2023). Simulation of a fully digital computing-in-memory for non-volatile memory for artificial intelligence edge applications. Micromachines, 14.","DOI":"10.3390\/mi14061175"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Santoro, G., Turvani, G., and Graziano, M. (2019). New logic-in-memory paradigms: An architectural and technological perspective. Micromachines, 10.","DOI":"10.3390\/mi10060368"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1109\/ISSCC42613.2021.9365766","article-title":"16.4 An 89TOPS\/W and 16.3 TOPS\/mm 2 all-digital SRAM-based full-precision compute-in memory macro in 22nm for machine-learning edge applications","volume":"Volume 64","author":"Chih","year":"2021","journal-title":"Proceedings of the 2021 IEEE International Solid-State Circuits Conference (ISSCC)"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1773","DOI":"10.1109\/TCSI.2021.3064189","article-title":"Challenges and trends of SRAM-based computing-in-memory for AI edge devices","volume":"68","author":"Jhang","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Regul. Pap."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"93745","DOI":"10.1109\/ACCESS.2022.3203053","article-title":"Distributed real-time object detection based on edge-cloud collaboration for smart video surveillance applications","volume":"10","author":"Chen","year":"2022","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1697","DOI":"10.1109\/JPROC.2019.2915983","article-title":"Edge computing for autonomous driving: Opportunities and challenges","volume":"107","author":"Liu","year":"2019","journal-title":"Proc. IEEE"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Lin, W., Adetomi, A., and Arslan, T. (2021). Low-power ultra-small edge AI accelerators for image recognition with convolution neural networks: Analysis and future directions. Electronics, 10.","DOI":"10.20944\/preprints202107.0375.v1"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"146","DOI":"10.5573\/JSTS.2022.22.3.146","article-title":"A Study on SRAM Designs to Exploit the TEI-aware Ultra-low Power Techniques","volume":"22","author":"Lee","year":"2022","journal-title":"J. Semicond. Technol. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Ben Dhaou, I., Ebrahimi, M., Ben Ammar, M., Bouattour, G., and Kanoun, O. (2021). Edge devices for internet of medical things: Technologies, techniques, and implementation. Electronics, 10.","DOI":"10.3390\/electronics10172104"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Martin Wisniewski, L., Bec, J.M., Boguszewski, G., and Gamati\u00e9, A. (2022). Hardware solutions for low-power smart edge computing. J. Low Power Electron. Appl., 12.","DOI":"10.3390\/jlpea12040061"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"556","DOI":"10.1016\/j.comcom.2020.01.004","article-title":"Energy aware edge computing: A survey","volume":"151","author":"Jiang","year":"2020","journal-title":"Comput. Commun."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Lee, K.B., Park, J., Choi, E., Jeon, M., and Lee, W. (2022). Developing a TEI-Aware PMIC for Ultra-Low-Power System-on-Chips. Energies, 15.","DOI":"10.3390\/en15186780"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Haririan, P. (2020). DVFS and its architectural simulation models for improving energy efficiency of complex embedded systems in early design phase. Computers, 9.","DOI":"10.3390\/computers9010002"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Lee, S., Kang, S.H., Lee, J., Kim, H., Lee, E., Seo, S., Yoon, H., Lee, S., Lim, K., and Shin, H. (2021, January 14\u201318). Hardware architecture and software stack for PIM based on commercial DRAM technology: Industrial product. Proceedings of the 2021 ACM\/IEEE 48th Annual International Symposium on Computer Architecture (ISCA), Valencia, Spain.","DOI":"10.1109\/ISCA52012.2021.00013"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"He, M., Song, C., Kim, I., Jeong, C., Kim, S., Park, I., Thottethodi, M., and Vijaykumar, T. (2020, January 17\u201321). Newton: A DRAM-maker\u2019s accelerator-in-memory (AiM) architecture for machine learning. Proceedings of the 2020 53rd Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), Athens, Greece.","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kaur, R., Asad, A., and Mohammadi, F. (2024). A Comprehensive Review of Processing-in-Memory Architectures for Deep Neural Networks. Computers, 13.","DOI":"10.20944\/preprints202406.1486.v1"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Molas, G., and Nowak, E. (2021). Advances in emerging memory technologies: From data storage to artificial intelligence. Appl. Sci., 11.","DOI":"10.3390\/app112311254"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Qi, L., Fan, J., Cai, H., and Fang, Z. (2024). A Survey of Emerging Memory in a Microcontroller Unit. Micromachines, 15.","DOI":"10.3390\/mi15040488"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"4642","DOI":"10.1109\/JIOT.2020.3027479","article-title":"Developing TEI-aware ultralow-power SoC platforms for IoT end nodes","volume":"8","author":"Han","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_27","unstructured":"(2024, September 08). SiFIVE. Available online: https:\/\/github.com\/chipsalliance\/rocket-chip."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"4106","DOI":"10.1109\/TCSI.2024.3427681","article-title":"Designing Low-Power RISC-V Multicore Processors with a Shared Lightweight Floating Point Unit for IoT Endnodes","volume":"71","author":"Park","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Regul. Pap."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"103161","DOI":"10.1016\/j.sysarc.2024.103161","article-title":"Day\u2013Night architecture: Development of an ultra-low power RISC-V processor for wearable anomaly detection","volume":"152","author":"Choi","year":"2024","journal-title":"J. Syst. Archit."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Lee, P.H., Lee, C.F., Shih, Y.C., Lin, H.J., Chang, Y.A., Lu, C.H., Chen, Y.L., Lo, C.P., Chen, C.C., and Kuo, C.H. (2023, January 19\u201323). 33.1 A 16nm 32Mb embedded STT-MRAM with a 6ns read-access time, a 1M-cycle write endurance, 20-year retention at 150 \u00b0C and MTJ-OTP solutions for magnetic immunity. Proceedings of the 2023 IEEE International Solid-State Circuits Conference (ISSCC), San Francisco, CA, USA.","DOI":"10.1109\/ISSCC42615.2023.10067837"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chiu, Y.C., Khwa, W.S., Li, C.Y., Hsieh, F.L., Chien, Y.A., Lin, G.Y., Chen, P.J., Pan, T.H., You, D.Q., and Chen, F.Y. (2023, January 19\u201323). A 22nm 8Mb STT-MRAM Near-Memory-Computing Macro with 8b-Precision and 46.4-160.1 TOPS\/W for Edge-AI Devices. Proceedings of the 2023 IEEE International Solid-State Circuits Conference (ISSCC), San Francisco, CA, USA.","DOI":"10.1109\/ISSCC42615.2023.10067563"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"994","DOI":"10.1109\/TCAD.2012.2185930","article-title":"Nvsim: A circuit-level performance, energy, and area model for emerging nonvolatile memory","volume":"31","author":"Dong","year":"2012","journal-title":"IEEE Trans.-Comput.-Aided Des. Integr. Circuits Syst."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3085572","article-title":"CACTI 7: New tools for interconnect exploration in innovative off-chip memories","volume":"14","author":"Balasubramonian","year":"2017","journal-title":"ACM Trans. Archit. Code Optim. (Taco)"},{"key":"ref_34","unstructured":"(2024, September 08). Synopsys. Available online: https:\/\/www.synopsys.com\/implementation-and-signoff\/rtl-synthesis-test\/dc-ultra.html."},{"key":"ref_35","unstructured":"(2024, September 08). NCSU. Available online: https:\/\/eda.ncsu.edu\/freepdk\/freepdk45."},{"key":"ref_36","unstructured":"(2024, September 08). ARTY-A7. Available online: https:\/\/store.digilentinc.com\/arty-a7-artix-7-fpga-development-board-for-makers-and-hobbyists."}],"container-title":["Micromachines"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-666X\/15\/10\/1222\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:07:29Z","timestamp":1760112449000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-666X\/15\/10\/1222"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"references-count":36,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2024,10]]}},"alternative-id":["mi15101222"],"URL":"https:\/\/doi.org\/10.3390\/mi15101222","relation":{},"ISSN":["2072-666X"],"issn-type":[{"value":"2072-666X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]}}}