NeuroPIM: Felxible Neural Accelerator for Processing-in-Memory ArchitecturesShow others and affiliations
2023 (English)In: Proceedings - 2023 26th International Symposium on Design and Diagnostics of Electronic Circuits and Systems, DDECS 2023, Institute of Electrical and Electronics Engineers Inc. , 2023, p. 51-56Conference paper, Published paper (Refereed)
Abstract [en]
The performance of microprocessors under many modern workloads is mainly limited by the off-chip memory bandwidth. The emerging process-in-memory paradigm present a unique opportunity to reduce data movement overheads by moving computation closer to memory. State-of-the-art processing-in-memory proposals stack a logic layer on top of one or multiple memory layers in a 3D fashion and leverage the logic layer to build near-memory processing units. Such processing units are either application-specific accelerators or general-purpose cores. In this paper, we present NeuroPIM, a new processing-in-memory architecture that uses a neural network as the memory-side general-purpose accelerator. This design is mainly motivated by the observation that in many real-world applications, some program regions, or even the entire program, can be replaced by a neural network that is learned to approximate the program's output. NeuroPIM benefits from both the flexibility of general-purpose processors and superior performance of application-specific accelerators. Experimental results show that NeuroPIM provides up to 41% speedup over a processor-side neural network accelerator and up to 8x speedup over a general-purpose processor.
Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc. , 2023. p. 51-56
Keywords [en]
Hardware acceleration, Neural network, Processing-in-memory, Application programs, Computation theory, Computer circuits, General purpose computers, Network architecture, Neural networks, Program processors, Application specific, General purpose processors, Logic layers, Memory bandwidths, Neural-networks, Off-chip memory, Performance, Processing units, Memory architecture
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:mdh:diva-63668DOI: 10.1109/DDECS57882.2023.10139567ISI: 001012062000009Scopus ID: 2-s2.0-85162274137ISBN: 9798350332773 (print)OAI: oai:DiVA.org:mdh-63668DiVA, id: diva2:1776893
Conference
26th International Symposium on Design and Diagnostics of Electronic Circuits and Systems, DDECS 2023, 3-5 May 2023, Tallin, Estonia
2023-06-282023-06-282023-12-04Bibliographically approved