Hyperdimensional computing (HDC) has emerged as an alternative lightweight learning solution to deep neural networks. A key characteristic of HDC is the great extent of parallelism that can facilitate hardware acceleration. However, previous hardware implementations of HDC seldom focus on GPU designs, which were also inefficient partly due to the complexity of accelerating HDC on GPUs. In this paper, we present OpenHD, a flexible and high-performance GPU-powered framework for automating the mapping of general HDC applications including classification and clustering to GPUs. OpenHD takes advantage of memory optimization strategies specialized for HDC, minimizing the access time to different memory subsystems, and removing redundant operations. We also propose a novel training method to enable data parallelism in HDC training. Our evaluation result shows that the proposed training rapidly achieves the target accuracy, reducing the required training epochs by 4×. With OpenHD, users can deploy GPU-accelerated HDC applications without domain expert knowledge. Compared to the state-of-the-art GPU-powered HDC implementation, our evaluation on NVIDIA Jetson TX2 shows that OpenHD is up to 10.5× and 314× faster for HDC-based classification and clustering, respectively. Compared with non-HDC classification and clustering on GPUs, OpenHD-based HDC is 11.7× and 53× faster at comparable accuracy. OpenHD is available at: https://github.com/UCSD-SEELab/openhd .

Schools are high-risk settings for SARS-CoV-2 transmission, but necessary for children's educational and social-emotional wellbeing. Previous research suggests that wastewater monitoring can detect SARS-CoV-2 infections in controlled residential settings with high levels of accuracy. However, its effective accuracy, cost, and feasibility in non-residential community settings is unknown. The objective of this study was to determine the effectiveness and accuracy of community-based passive wastewater and surface (environmental) surveillance to detect SARS-CoV-2 infection in neighborhood schools compared to weekly diagnostic (PCR) testing. We implemented an environmental surveillance system in nine elementary schools with 1700 regularly present staff and students in southern California. The system was validated from November 2020 to March 2021. In 447 data collection days across the nine sites 89 individuals tested positive for COVID-19, and SARS-CoV-2 was detected in 374 surface samples and 133 wastewater samples. Ninety-three percent of identified cases were associated with an environmental sample (95% CI: 88%-98%); 67% were associated with a positive wastewater sample (95% CI: 57%-77%), and 40% were associated with a positive surface sample (95% CI: 29%-52%). The techniques we utilized allowed for near-complete genomic sequencing of wastewater and surface samples. Passive environmental surveillance can detect the presence of COVID-19 cases in non-residential community school settings with a high degree of accuracy. County of San Diego, Health and Human Services Agency, National Institutes of Health, National Science Foundation, Centers for Disease Control.

This paper proposes a distributed energy-efficient clustering protocol for wireless sensor networks (WSNs). Based on low-energy adaptive clustering hierarchy (LEACH) protocol, the proposed LEACH-eXtended Message-Passing (LEACH-XMP) substantially improves a cluster formation algorithm, which is critical for WSN operations. Unlike the previous approaches, a realistic non-linear energy consumption model is considered, which renders the clustering optimization highly nonlinear and challenging. To this end, a state-of-the-art message-passing approach is introduced to develop an efficient distributed algorithm. The main benefits of the proposed technique are its inherent nature of a distributed algorithm and the saving of computational load imposed for each node. Thus, it proves useful for a practical deployment. In addition, the proposed algorithm rapidly converges to a very accurate solution within a few iterations. Simulation results ensure that the proposed LEACH-XMP maximizes the network lifetime and outperforms existing techniques consistently.

Motivation: Driven by technological advances, the throughput and cost of mass spectrometry (MS) proteomics experiments have improved by orders of magnitude in recent decades. Spectral library searching is a common approach to annotating experimental mass spectra by matching them against large libraries of reference spectra corresponding to known peptides. An important disadvantage, however, is that only peptides included in the spectral library can be found, whereas novel peptides, such as those with unexpected post-translational modifications (PTMs), will remain unknown. Open modification searching (OMS) is an increasingly popular approach to annotate modified peptides based on partial matches against their unmodified counterparts. Unfortunately, this leads to very large search spaces and excessive runtimes, which is especially problematic considering the continuously increasing sizes of MS proteomics datasets. Results: We propose an OMS algorithm, called HOMS-TC, that fully exploits parallelism in the entire pipeline of spectral library searching. We designed a new highly parallel encoding method based on the principle of hyperdimensional computing to encode mass spectral data to hypervectors while minimizing information loss. This process can be easily parallelized since each dimension is calculated independently. HOMS-TC processes two stages of existing cascade search in parallel and selects the most similar spectra while considering PTMs. We accelerate HOMS-TC on NVIDIA’s tensor core units, which is emerging and readily available in the recent graphics processing unit (GPU). Our evaluation shows that HOMS-TC is 31× faster on average than alternative search engines and provides comparable accuracy to competing search tools. Availability and implementation: HOMS-TC is freely available under the Apache 2.0 license as an open-source software project at https://github.com/tycheyoung/homs-tc.

Mass spectrometry, commonly used for protein identification, generates a massive number of spectra that need to be matched against a large database. In reality, most of them remain unidentified or mismatched due to unexpected post-translational modifications. Open modification search (OMS) has been proposed as a strategy to improve the identification rate by considering changes in spectra, but it expands the search space exponentially. In this work, we propose HyperOMS, an algorithm-hardware co-design for boosted OMS, to cope with the enlarged database and expanded search space. HyperOMS encodes spectral data into binary vectors and performs the efficient OMS in high-dimensional space. We accelerate the HyperOMS algorithm using a DRAM-based processing-in-memory accelerator, which combines processing-using-memory and near-memory processing technologies. In order to maximize the parallelization and efficiency of the accelerator, we optimize the data allocation and devise an approximation strategy for similarity computation. Experimental results show that the HyperOMS accelerator yields up to $3.8\times $ speedup and $119\times $ higher energy efficiency compared to running HyperOMS on GPU, and up to $99\times $ speedup and $1984\times $ higher energy efficiency over the state-of-the-art OMS tool, ANN-SoLo (Bittremieux et al., 2019), while providing comparable search quality to competing tools.

Machine learning algorithms, especially deep neural networks (DNNs), are computationally expensive and vulnerable to privacy breaches. Hyperdimensional Computing (HDC) is a brain-inspired machine learning paradigm which offers a potential alternative for efficient and private learning. HDC encodes dense, sensory inputs into sparse, high-dimensional vectors of 10,000 bits or more, and learns using well-defined and lightweight operations on these vectors. However, naïve HDC is vulnerable to privacy attacks as the encoding process can be reversely determined. In this paper, we systematically study the fundamental privacy challenges of HDC due to reversibility and propose an end-to-end private training and inference framework for HDC with efficient hardware implementation. We first show that HDC is not naturally private as the original data and encoding parameters can be reconstructed from the encoded vector, regardless of the encoding methods applied. We term this attack as the feature extraction attack. We then propose a locally sparse encoding method to obfuscate the encoded information for protecting inference privacy, leading to computational and communication savings. We further propose Privé -HDnn which uses a hybrid architecture of Convolutional Neural Network (CNN) as feature extractors and private-preserved HDC classifier for complex tasks such as image classification. Thanks to the noise tolerance of HDC, Privé-HDnn enables private single- and multi-pass training of HDC by differential privacy-guaranteed noise injection. Results show that our new encoding method defends against decoding attacks with an RMSE deviation of 0.42, while also speeding up encoding by 2.6-5.3× (19-79×) compared to the FPGA (CPU) baseline. For privacy-preserved training, Privé - HDnn achieves comparable or up to 5.8% better accuracy than DNNs with up to 1231× faster training time on GPU as compared to the state-of-the-art NNs.