Deyu Wang, Xiaoze Yan, Yu Yang, Dimitrios Stathis, Ahmed Hemani, Anders Lansner, Jiawei Xu, Li-Rong Zheng, Zhuo Zou
{"title":"Scalable Multi-FPGA HPC Architecture for Associative Memory System.","authors":"Deyu Wang, Xiaoze Yan, Yu Yang, Dimitrios Stathis, Ahmed Hemani, Anders Lansner, Jiawei Xu, Li-Rong Zheng, Zhuo Zou","doi":"10.1109/TBCAS.2024.3446660","DOIUrl":null,"url":null,"abstract":"<p><p>Associative memory is a cornerstone of cognitive intelligence within the human brain. The Bayesian confidence propagation neural network (BCPNN), a cortex-inspired model with high biological plausibility, has proven effective in emulating high-level cognitive functions like associative memory. However, the current approach using GPUs to simulate BCPNN-based associative memory tasks encounters challenges in latency and power efficiency as the model size scales. This work proposes a scalable multi-FPGA high performance computing (HPC) architecture designed for the associative memory system. The architecture integrates a set of hypercolumn unit (HCU) computing cores for intra-board online learning and inference, along with a spike-based synchronization scheme for inter-board communication among multiple FPGAs. Several design strategies, including population-based model mapping, packet-based spike synchronization, and cluster-based timing optimization, are presented to facilitate the multi-FPGA implementation. The architecture is implemented and validated on two Xilinx Alveo U50 FPGA cards, achieving a maximum model size of 200×10 and a peak working frequency of 220 MHz for the associative memory system. Both the memory-bounded spatial scalability and compute-bounded temporal scalability of the architecture are evaluated and optimized, achieving a maximum scale-latency ratio (SLR) of 268.82 for the two-FPGA implementation. Compared to a two-GPU counterpart, the two-FPGA approach demonstrates a maximum latency reduction of 51.72× and a power reduction exceeding 5.28× under the same network configuration. Compared with the state-of-the-art works, the two-FPGA implementation exhibits a high pattern storage capacity for the associative memory task.</p>","PeriodicalId":94031,"journal":{"name":"IEEE transactions on biomedical circuits and systems","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on biomedical circuits and systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TBCAS.2024.3446660","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Associative memory is a cornerstone of cognitive intelligence within the human brain. The Bayesian confidence propagation neural network (BCPNN), a cortex-inspired model with high biological plausibility, has proven effective in emulating high-level cognitive functions like associative memory. However, the current approach using GPUs to simulate BCPNN-based associative memory tasks encounters challenges in latency and power efficiency as the model size scales. This work proposes a scalable multi-FPGA high performance computing (HPC) architecture designed for the associative memory system. The architecture integrates a set of hypercolumn unit (HCU) computing cores for intra-board online learning and inference, along with a spike-based synchronization scheme for inter-board communication among multiple FPGAs. Several design strategies, including population-based model mapping, packet-based spike synchronization, and cluster-based timing optimization, are presented to facilitate the multi-FPGA implementation. The architecture is implemented and validated on two Xilinx Alveo U50 FPGA cards, achieving a maximum model size of 200×10 and a peak working frequency of 220 MHz for the associative memory system. Both the memory-bounded spatial scalability and compute-bounded temporal scalability of the architecture are evaluated and optimized, achieving a maximum scale-latency ratio (SLR) of 268.82 for the two-FPGA implementation. Compared to a two-GPU counterpart, the two-FPGA approach demonstrates a maximum latency reduction of 51.72× and a power reduction exceeding 5.28× under the same network configuration. Compared with the state-of-the-art works, the two-FPGA implementation exhibits a high pattern storage capacity for the associative memory task.