Today's applications are using machine learning algorithms to analyze the data collected from a swarm of devices on the Internet of Things (IoT). However, most existing learning algorithms are overcomplex to enable real-time learning on IoT devices with limited resources and computing power. Recently, Hyperdimensional computing (HDC) is introduced as an alternative computing paradigm for enabling efficient and robust learning. HDC emulates the cognitive task by representing the values as patterns of neural activity in high-dimensional space. HDC first encodes all data points to high-dimensional vectors. It then efficiently performs the learning task using a well-defined set of operations. Existing HDC solutions have two main issues that hinder their deployments on low-power embedded devices: (i) the encoding module is costly, dominating 80% of the entire training performance, (ii) the HDC model size and the computation cost grow significantly with the number of classes in online inference.In this paper, we proposed a novel architecture, LookHD, which enables real-time HDC learning on low-power edge devices. LookHD exploits computation reuse to memorize the encoding module and simplify its computation with single memory access. LookHD also address the inference scalability by exploiting HDC governing mathematics that compresses the HDC trained model into a single hypervector. We present how the proposed architecture can be implemented on the existing low power architectures: ARM processor and FPGA design. We evaluate the efficiency of the proposed approach on a wide range of practical classification problems such as activity recognition, face recognition, and speech recognition. Our evaluations show that LookHD can achieve, on average, $ 28.3\times$ faster and $ 97.4\times$ more energy-efficient training as compared to the state-of-the-art HDC implemented on the FPGA. Similarly, in the inference, LookHD is $ 2.2\times$ faster, $ 4.1\times$ more energy-efficient, and has $ 6.3\times$ smaller model size than the same state-of-the-art algorithms.

Sequence alignment is a core component of many biological applications. As the advancement in sequencing technologies produces a tremendous amount of data on an hourly basis, this alignment is becoming the critical bottleneck in bioinformatics analysis. Even though large clusters and highly-parallel processing nodes can carry out sequence alignment, in addition to the exacerbated power consumption, they cannot afford to concurrently process the massive amount of data generated by sequencing machines. In this paper, we propose a novel processing in-memory (PIM) architecture suited for DNA sequence alignment, called RAPID. We revise the state-of-the-art alignment algorithm to make it compatible with in-memory parallel computations, and process DNA data completely inside memory without requiring additional processing units. The main advantage of RAPID over the other alignment accelerators is a dramatic reduction in internal data movement while maintaining a remarkable degree of parallelism provided by PIM. The proposed architecture is also highly scalable, facilitating precise alignment of lengthy sequences. We evaluated the efficiency of the proposed architecture by aligning chromosome sequences from human and chimpanzee genomes. The results show that RAPID is at least 2× faster and 7× more power efficient than BioSEAL, the best DNA sequence alignment accelerator.

Next generation sequencing of viral populations has advanced our understanding of viral population dynamics, the development of drug resistance, and escape from host immune responses. Many applications require complete gene sequences, which can be impossible to reconstruct from short reads. HIV env, the protein of interest for HIV vaccine studies, is exceptionally challenging for long-read sequencing and analysis due to its length, high substitution rate, and extensive indel variation. While long-read sequencing is attractive in this setting, the analysis of such data is not well handled by existing methods. To address this, we introduce FLEA (Full-Length Envelope Analyzer), which performs end-to-end analysis and visualization of long-read sequencing data. FLEA consists of both a pipeline (optionally run on a high-performance cluster), and a client-side web application that provides interactive results. The pipeline transforms FASTQ reads into high-quality consensus sequences (HQCSs) and uses them to build a codon-aware multiple sequence alignment. The resulting alignment is then used to infer phylogenies, selection pressure, and evolutionary dynamics. The web application provides publication-quality plots and interactive visualizations, including an annotated viral alignment browser, time series plots of evolutionary dynamics, visualizations of gene-wide selective pressures (such as dN/dS) across time and across protein structure, and a phylogenetic tree browser. We demonstrate how FLEA may be used to process Pacific Biosciences HIV env data and describe recent examples of its use. Simulations show how FLEA dramatically reduces the error rate of this sequencing platform, providing an accurate portrait of complex and variable HIV env populations. A public instance of FLEA is hosted at http://flea.datamonkey.org. The Python source code for the FLEA pipeline can be found at https://github.com/veg/flea-pipeline. The client-side application is available at https://github.com/veg/flea-web-app. A live demo of the P018 results can be found at http://flea.murrell.group/view/P018.