Demeter: A Fast and Energy-Efficient Food Profiler Using Hyperdimensional Computing in Memory
Open Access
- 1 August 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 82493-82510
Abstract
Food profiling is an essential step in any food monitoring system needed to prevent health risks and potential frauds in the food industry. Significant improvements in sequencing technologies are pushing food profiling to become the main computational bottleneck. State-of-the-art profilers are unfortunately too costly for food profiling. Our goal is to design a food profiler that solves the main limitations of existing profilers, namely (1) working on massive data structures and (2) incurring considerable data movement, for a real-time monitoring system. To this end, we propose Demeter, the first platform-independent framework for food profiling. Demeter overcomes the first limitation through the use of hyperdimensional computing (HDC) and efficiently performs the accurate few-species classification required in food profiling. We overcome the second limitation by the use of an in-memory hardware accelerator for Demeter (named Acc-Demeter) based on memristor devices. Acc-Demeter actualizes several domain-specific optimizations and exploits the inherent characteristics of memristors to improve the overall performance and energy consumption of Acc-Demeter. We compare Demeter’s accuracy with other industrial food profilers using detailed software modeling. We synthesize Acc-Demeter’s required hardware using UMC’s 65nm library by considering an accurate PCM model based on silicon-based prototypes. Our evaluations demonstrate that Acc-Demeter achieves a (1) throughput improvement of $192\times $ and $724\times $ and (2) memory reduction of $36\times $ and $33\times $ compared to Kraken2 and MetaCache (2 state-of-the-art profilers), respectively, on typical food-related databases. Demeter maintains an acceptable profiling accuracy (within 2% of existing tools) and incurs a very low area overhead.
Keywords
All Related Versions
Funding Information
- Q&CE Department, Delft University of Technology
- SAFARI Research Group’s industrial partners, especially AMSL, Facebook, Google, Huawei, Intel, Microsoft, VMware, Xilinx
- AMSL
- Huawei
- Intel
- Microsoft
- VMware
- Xilinx
- ETH Future Computing Laboratory, and Semiconductor Research Corporation
This publication has 85 references indexed in Scilit:
- SOAP3-dp: Fast, Accurate and Sensitive GPU-Based Short Read AlignerPLOS ONE, 2013
- CUDASW++ 3.0: accelerating Smith-Waterman protein database search by coupling CPU and GPU SIMD instructionsBMC Bioinformatics, 2013
- Metagenomic microbial community profiling using unique clade-specific marker genesNature Methods, 2012
- PhymmBL expanded: confidence scores, custom databases, parallelization and moreNature Methods, 2011
- Phase change memory architecture and the quest for scalabilityCommunications of the ACM, 2010
- A Primer on MetagenomicsPLOS Computational Biology, 2010
- Redox‐Based Resistive Switching Memories – Nanoionic Mechanisms, Prospects, and ChallengesAdvanced Materials, 2009
- Estimating the Worldwide Extent of Illegal FishingPLOS ONE, 2009
- Representation and processing of structures with binary sparse distributed codesIEEE Transactions on Knowledge and Data Engineering, 2001
- Holographic reduced representationsIEEE Transactions on Neural Networks, 1995