Ultralow Power In-Sensor Neuronal Computing with Oscillatory Retinal Neurons for Frequency-Multiplexed, Parallel Machine Vision.

In-sensor and near-sensor computing architectures enable multiply accumulate operations to be carried out directly at the point of sensing. In-sensor architectures offer dramatic power and speed improvements over traditional von Neumann architectures by eliminating multiple analog-to-digital conversions, data storage, and data movement operations. Current in-sensor processing approaches rely on tunable sensors or additional weighting elements to perform linear functions such as multiply accumulate operations as the sensor acquires data. This work implements in-sensor computing with an oscillatory retinal neuron device that converts incident optical signals into voltage oscillations. A computing scheme is introduced based on the frequency shift of coupled oscillators that enables parallel, frequency multiplexed, nonlinear operations on the inputs. An experimentally implemented 3 × 3 focal plane array of coupled neurons shows that functions approximating edge detection, thresholding, and segmentation occur in parallel. An example of inference on handwritten digits from the MNIST database is also experimentally demonstrated with a 3 × 3 array of coupled neurons feeding into a single hidden layer neural network, approximating a liquid-state machine. Finally, the equivalent energy consumption to carry out image processing operations, including peripherals such as the Fourier transform circuits, is projected to be <20 fJ/OP, possibly reaching as low as 15 aJ/OP.

A distributed software system for integrating data-intensive imaging methods in a hard X-ray nanoprobe beamline at the SSRF.

The development of hard X-ray nanoprobe techniques has given rise to a number of experimental methods, like nano-XAS, nano-XRD, nano-XRF, ptychography and tomography. Each method has its own unique data processing algorithms. With the increase in data acquisition rate, the large amount of generated data is now a big challenge to these algorithms. In this work, an intuitive, user-friendly software system is introduced to integrate and manage these algorithms; by taking advantage of the loosely coupled, component-based design approach of the system, the data processing speed of the imaging algorithm is enhanced through optimization of the parallelism efficiency. This study provides meaningful solutions to tackle complexity challenges faced in synchrotron data processing.

A Robust Parallel Computing Data Extraction Framework for Nanopore Experiments.

The success of a nanopore experiment relies not only on the quality of the experimental design but also on the performance of the analysis program utilized to decipher the ionic perturbations necessary for understanding the fundamental molecular intricacies. An event extraction framework is developed that leverages parallel computing, efficient memory management, and vectorization, yielding significant performance enhancement. The newly developed abf-ultra-simple function extracts key parameters from the header critical for the operation of open-seek-read-close data loading architecture running on multiple cores. This underpins the swift analysis of large files where an ≈ × 18 improvement is found for a 100 min-long file (≈4.5 GB) compared to the more traditional single (cell) array data loading method. The application is benchmarked against five other analysis platforms showcasing significant performance enhancement (>2 ×-1120 ×). The integrated provisions for batch analysis enable concurrently analyzing multiple files (vital for high-bandwidth experiments). Furthermore, the application is equipped with multi-level data fitting based on abrupt changes in the event waveform. The application condenses the extracted events to a single binary file improving data portability (e.g., 16 GB file with 28 182 events reduces to 47.9 MB-343 × size reduction) and enables a multitude of post-analysis extractions to be done efficiently.

GPU-accelerated parallel image reconstruction strategies for magnetic particle imaging.

Objective. Image reconstruction is a fundamental step in magnetic particle imaging (MPI). One of the main challenges is the fact that the reconstructions are computationally intensive and time-consuming, so choosing an algorithm presents a compromise between accuracy and execution time, which depends on the application. This work proposes a method that provides both fast and accurate image reconstructions.Approach. Image reconstruction algorithms were implemented to be executed in parallel ingraphics processing units(GPUs) using the CUDA framework. The calculation of the model-based MPI calibration matrix was also implemented in GPU to allow both fast and flexible reconstructions.Main results. The parallel algorithms were able to accelerate the reconstructions by up to about6,100times in comparison to the serial Kaczmarz algorithm executed in the CPU, allowing for real-time applications. Reconstructions using the OpenMPIData dataset validated the proposed algorithms and demonstrated that they are able to provide both fast and accurate reconstructions. The calculation of the calibration matrix was accelerated by up to about 37 times.Significance. The parallel algorithms proposed in this work can provide single-frame MPI reconstructions in real time, with frame rates greater than 100 frames per second. The parallel calculation of the calibration matrix can be combined with the parallel reconstruction to deliver images in less time than the serial Kaczmarz reconstruction, potentially eliminating the need of storing the calibration matrix in the main memory, and providing the flexibility of redefining scanning and reconstruction parameters during execution.

Accelerating spliced alignment of long RNA sequencing reads using parallel maximal exact match retrieval.

The genomics landscape has undergone a revolutionary transformation with the emergence of third-generation sequencing technologies. Fueled by the exponential surge in sequencing data, there is an urgent demand for accurate and rapid algorithms to effectively handle this burgeoning influx. Under such circumstances, we developed a parallelized, yet accuracy-lossless algorithm for maximal exact match (MEM) retrieval to strategically address the computational bottleneck of uLTRA, a leading spliced alignment algorithm known for its precision in handling long RNA sequencing (RNA-seq) reads. The design of the algorithm incorporates a multi-threaded strategy, enabling the concurrent processing of multiple reads simultaneously. Additionally, we implemented the serialization of index required for MEM retrieval to facilitate its reuse, resulting in accelerated startup for practical tasks. Extensive experiments demonstrate that our parallel algorithm achieves significant improvements in runtime, speedup, throughput, and memory usage. When applied to the largest human dataset, the algorithm achieves an impressive speedup of 10.78 × , significantly improving throughput on a large scale. Moreover, the integration of the parallel MEM retrieval algorithm into the uLTRA pipeline introduces a dual-layered parallel capability, consistently yielding a speedup of 4.99 × compared to the multi-process and single-threaded execution of uLTRA. The thorough analysis of experimental results underscores the adept utilization of parallel processing capabilities and its advantageous performance in handling large datasets. This study provides a showcase of parallelized strategies for MEM retrieval within the context of spliced alignment algorithm, effectively facilitating the process of RNA-seq data analysis. The code is available at https://github.com/RongxingWong/AcceleratingSplicedAlignment.

A systematic 3-D magnetic particle imaging simulation model for quantitative analysis of reconstruction image quality.

BACKGROUND AND OBJECTIVE: Magnetic particle imaging (MPI) is an emerging imaging technology in medical tomography that utilizes the nonlinear magnetization response of superparamagnetic iron oxide (SPIO) particles to determine the in vivo spatial distribution of nanoparticle contrast agents. The reconstruction image quality of MPI is determined by the characteristics of magnetic particles, the setting of the MPI scanner parameters, and the hardware interference of MPI systems. We explore a feasible method to systematically and quickly analyze the impact of these factors on MPI reconstruction image quality. METHODS: We propose a systematic 3-D MPI simulation model. The MPI simulation model has the capability of quickly producing the simulated reconstruction images of a scanned phantom, and quantitative analysis of MPI reconstruction image quality can be achieved by comparing the differences between the input image and output image. These factors are mainly classified as imaging parameters and interference parameters in our model. In order to reduce the computational time of the simulation model, we introduce GPU parallel programming to accelerate the processing of large complex matrix data. For ease of use, we also construct a reliable, high-performance, and open-source 3-D MPI simulation software tool based on our model. The efficiency of our model is evaluated by using OpenMPIData. To demonstrate the capabilities of our model, we conduct simulation experiments using parameters consistent with a real MPI scanner for improving MPI image quality. RESULTS: The experimental results show that our simulation model can systematically and quickly evaluate the impact of imaging parameters and interference parameters on MPI reconstruction image quality. CONCLUSIONS: We developed an easy-to-use and open-source 3-D MPI simulation software tool based on our simulation model incorporating all the stages of MPI formation, from signal acquisition to image reconstruction. In the future, our simulation model has potential guiding significance to practical MPI images.

Design and optimization of haze prediction model based on particle swarm optimization algorithm and graphics processor.

With the rapid expansion of industrialization and urbanization, fine Particulate Matter (PM2.5) pollution has escalated into a major global environmental crisis. This pollution severely affects human health and ecosystem stability. Accurately predicting PM2.5 levels is essential. However, air quality forecasting currently faces challenges in processing vast data and enhancing model accuracy. Deep learning models are widely applied for their superior learning and fitting abilities in haze prediction. Yet, they are limited by optimization challenges, long training periods, high data quality needs, and a tendency towards overfitting. Furthermore, the complex internal structures and mechanisms of these models complicate the understanding of haze formation. In contrast, traditional Support Vector Regression (SVR) methods perform well with complex non-linear data but struggle with increased data volumes. To address this, we developed CUDA-based code to optimize SVR algorithm efficiency. We also combined SVR with Genetic Algorithms (GA), Sparrow Search Algorithm (SSA), and Particle Swarm Optimization (PSO) to identify the optimal haze prediction model. Our results demonstrate that the model combining intelligent algorithms with Central Processing Unit-raphics Processing Unit (CPU-GPU) heterogeneous parallel computing significantly outpaces the PSO-SVR model in training speed. It achieves a computation time that is 6.21-35.34 times faster. Compared to other models, the Particle Swarm Optimization-Central Processing Unit-Graphics Processing Unit-Support Vector Regression (PSO-CPU-GPU-SVR) model stands out in haze prediction, offering substantial speed improvements and enhanced stability and reliability while maintaining high accuracy. This breakthrough not only advances the efficiency and accuracy of haze prediction but also provides valuable insights for real-time air quality monitoring and decision-making.

Exponential family measurement error models for single-cell CRISPR screens.

CRISPR genome engineering and single-cell RNA sequencing have accelerated biological discovery. Single-cell CRISPR screens unite these two technologies, linking genetic perturbations in individual cells to changes in gene expression and illuminating regulatory networks underlying diseases. Despite their promise, single-cell CRISPR screens present considerable statistical challenges. We demonstrate through theoretical and real data analyses that a standard method for estimation and inference in single-cell CRISPR screens-"thresholded regression"-exhibits attenuation bias and a bias-variance tradeoff as a function of an intrinsic, challenging-to-select tuning parameter. To overcome these difficulties, we introduce GLM-EIV ("GLM-based errors-in-variables"), a new method for single-cell CRISPR screen analysis. GLM-EIV extends the classical errors-in-variables model to responses and noisy predictors that are exponential family-distributed and potentially impacted by the same set of confounding variables. We develop a computational infrastructure to deploy GLM-EIV across hundreds of processors on clouds (e.g. Microsoft Azure) and high-performance clusters. Leveraging this infrastructure, we apply GLM-EIV to analyze two recent, large-scale, single-cell CRISPR screen datasets, yielding several new insights.

Junctionless Negative-Differential-Resistance Device Using 2D Van-Der-Waals Layered Materials for Ternary Parallel Computing.

Negative-differential-resistance (NDR) devices offer a promising pathway for developing future computing technologies characterized by exceptionally low energy consumption, especially multivalued logic computing. Nevertheless, conventional approaches aimed at attaining the NDR phenomenon involve intricate junction configurations and/or external doping processes in the channel region, impeding the progress of NDR devices to the circuit and system levels. Here, an NDR device is presented that incorporates a channel without junctions. The NDR phenomenon is achieved by introducing a metal-insulator-semiconductor capacitor to a portion of the channel area. This approach establishes partial potential barrier and well that effectively restrict the movement of hole and electron carriers within specific voltage ranges. Consequently, this facilitates the implementation of both a ternary inverter and a ternary static-random-access-memory, which are essential components in the development of multivalued logic computing technology.

Multi-Device Parallel MRI Reconstruction: Efficient Partitioning for Undersampled 5D Cardiac CINE.

Cardiac CINE, a form of dynamic cardiac MRI, is indispensable in the diagnosis and treatment of heart conditions, offering detailed visualization essential for the early detection of cardiac diseases. As the demand for higher-resolution images increases, so does the volume of data requiring processing, presenting significant computational challenges that can impede the efficiency of diagnostic imaging. Our research presents an approach that takes advantage of the computational power of multiple Graphics Processing Units (GPUs) to address these challenges. GPUs are devices capable of performing large volumes of computations in a short period, and have significantly improved the cardiac MRI reconstruction process, allowing images to be produced faster. The innovation of our work resides in utilizing a multi-device system capable of processing the substantial data volumes demanded by high-resolution, five-dimensional cardiac MRI. This system surpasses the memory capacity limitations of single GPUs by partitioning large datasets into smaller, manageable segments for parallel processing, thereby preserving image integrity and accelerating reconstruction times. Utilizing OpenCL technology, our system offers adaptability and cross-platform functionality, ensuring wider applicability. The proposed multi-device approach offers an advancement in medical imaging, accelerating the reconstruction process and facilitating faster and more effective cardiac health assessment.

SPANA: Spatial decomposition analysis for cellular-scale molecular dynamics simulations.

The rapid increase in computational power with the latest supercomputers has enabled atomistic molecular dynamics (MDs) simulations of biomolecules in biological membrane, cytoplasm, and other cellular environments. These environments often contain a million or more atoms to be simulated simultaneously. Therefore, their trajectory analyses involve heavy computations that can become a bottleneck in the computational studies. Spatial decomposition analysis (SPANA) is a set of analysis tools in the Generalized-Ensemble Simulation System (GENESIS) software package that can carry out MD trajectory analyses of large-scale biological simulations using multiple CPU cores in parallel. SPANA applies the spatial decomposition of a large biological system to distribute structural and dynamical analyses into individual CPU cores, which reduces the computational time and the memory size, significantly. SPANA opens new possibilities for detailed atomistic analyses of biomacromolecules as well as solvent water molecules, ions, and metabolites in MD simulation trajectories of very large biological systems containing more than millions of atoms in cellular environments.

An algorithm for computing Schubert varieties of best fit with applications.

We propose the geometric framework of the Schubert variety as a tool for representing a collection of subspaces of a fixed vector space. Specifically, given a collection of l-dimensional subspaces V1, …, Vr of ℝn, represented as the column spaces of matrices X1, …, Xr, we seek to determine a representative matrix K∈ℝn×k such that each subspace Vi intersects (or comes close to intersecting) the span of the columns of K in at least c dimensions. We formulate a non-convex optimization problem to determine such a K along with associated sets of vectors {ai} and {bi} used to express linear combinations of the columns of the Xi that are close to linear combinations of the columns of K. Further, we present a mechanism for integrating this representation into an artificial neural network architecture as a computational unit (which we refer to as an abstract node). The representative matrix K can be learned in situ, or sequentially, as part of a learning problem. Additionally, the matrix K can be employed as a change of coordinates in the learning problem. The set of all l-dimensional subspaces of ℝn that intersects the span of the columns of K in at least c dimensions is an example of a Schubert subvariety of the Grassmannian GR(l, n). When it is not possible to find a Schubert variety passing through a collection of points on GR(l, n), the goal of the non-convex optimization problem is to find the Schubert variety of best fit, i.e., the Schubert variety that comes as close as possible to the points. This may be viewed as an analog of finding a subspace of best fit to data in a vector space. The approach we take is well-suited to the modeling of collections of sets of data either as a stand-alone Schubert variety of best fit (SVBF), or in the processing workflow of a deep neural network. We present applications to some classification problems on sets of data to illustrate the behavior of the method.

Intelligent Modelling of the Real Dynamic Viscosity of Rubber Blends Using Parallel Computing.

Modelling the flow properties of rubber blends makes it possible to predict their rheological behaviour during the processing and production of rubber-based products. As the nonlinear nature of such complex processes complicates the creation of exact analytical models, it is appropriate to use artificial intelligence tools in this modelling. The present study was implemented to develop a highly efficient artificial neural network model, optimised using a novel training algorithm with fast parallel computing to predict the results of rheological tests of rubber blends performed under different conditions. A series of 120 real dynamic viscosity-time curves, acquired by a rubber process analyser for styrene-butadiene rubber blends with varying carbon black contents vulcanised at different temperatures, were analysed using a Generalised Regression Neural Network. The model was optimised by limiting the fitting error of the training dataset to a pre-specified value of less than 1%. All repeated calculations were made via parallel computing with multiple computer cores, which significantly reduces the total computation time. An excellent agreement between the predicted and measured generalisation data was found, with an error of less than 4.7%, confirming the high generalisation performance of the newly developed model.

Ultra-Fast Approximate Inference Using Variational Functional Mixed Models.

While Bayesian functional mixed models have been shown effective to model functional data with various complex structures, their application to extremely high-dimensional data is limited due to computational challenges involved in posterior sampling. We introduce a new computational framework that enables ultra-fast approximate inference for high-dimensional data in functional form. This framework adopts parsimonious basis to represent functional observations, which facilitates efficient compression and parallel computing in basis space. Instead of performing expensive Markov chain Monte Carlo sampling, we approximate the posterior distribution using variational Bayes and adopt a fast iterative algorithm to estimate parameters of the approximate distribution. Our approach facilitates a fast multiple testing procedure in basis space, which can be used to identify significant local regions that reflect differences across groups of samples. We perform two simulation studies to assess the performance of approximate inference, and demonstrate applications of the proposed approach by using a proteomic mass spectrometry dataset and a brain imaging dataset. Supplementary materials are available online.

neuroAIx-Framework: design of future neuroscience simulation systems exhibiting execution of the cortical microcircuit model 20× faster than biological real-time.

Introduction: Research in the field of computational neuroscience relies on highly capable simulation platforms. With real-time capabilities surpassed for established models like the cortical microcircuit, it is time to conceive next-generation systems: neuroscience simulators providing significant acceleration, even for larger networks with natural density, biologically plausible multi-compartment models and the modeling of long-term and structural plasticity. Methods: Stressing the need for agility to adapt to new concepts or findings in the domain of neuroscience, we have developed the neuroAIx-Framework consisting of an empirical modeling tool, a virtual prototype, and a cluster of FPGA boards. This framework is designed to support and accelerate the continuous development of such platforms driven by new insights in neuroscience. Results: Based on design space explorations using this framework, we devised and realized an FPGA cluster consisting of 35 NetFPGA SUME boards. Discussion: This system functions as an evaluation platform for our framework. At the same time, it resulted in a fully deterministic neuroscience simulation system surpassing the state of the art in both performance and energy efficiency. It is capable of simulating the microcircuit with 20× acceleration compared to biological real-time and achieves an energy efficiency of 48nJ per synaptic event.

P-FARFAR2: A multithreaded greedy approach to sampling low-energy RNA structures in Rosetta FARFAR2.

RNA (ribonucleic acid) structure prediction finds many applications in health science and drug discovery due to its importance in several life regulatory processes. But despite significant advances in the close field of protein prediction, RNA 3D structure still poses a tremendous challenge to predict, especially for large sequences. In this regard, the approach unfolded by Rosetta FARFAR2 (Fragment Assembly of RNA with Full-Atom Refinement, version 2) has shown promising results, but the algorithm is non-deterministic by nature. In this paper, we develop P-FARFAR2: a parallel enhancement of FARFAR2 that increases its ability to assemble low-energy structures via multithreaded exploration of random configurations in a greedy manner. This strategy, appearing in the literature under the term "parallel mechanism", is made viable through two measures: first, the synchronization window is coarsened to several Monte Carlo cycles; second, all but one of the threads are differentiated as auxiliary and set to perform a weakened version of the problem. Following empirical analysis on a diverse range of RNA structures, we report achieving statistical significance in lowering the energy levels of ensuing samples. And consequently, despite the moderate-to-weak correlation between energy levels and prediction accuracy, this achievement happens to propagate to accuracy measurements.

Acceleration of generalized replica exchange with solute tempering simulations of large biological systems on massively parallel supercomputer.

Generalized replica exchange with solute tempering (gREST) is one of the enhanced sampling algorithms for proteins or other systems with rugged energy landscapes. Unlike the replica-exchange molecular dynamics (REMD) method, solvent temperatures are the same in all replicas, while solute temperatures are different and are exchanged frequently between replicas for exploring various solute structures. Here, we apply the gREST scheme to large biological systems containing over one million atoms using a large number of processors in a supercomputer. First, communication time on a multi-dimensional torus network is reduced by matching each replica to MPI processors optimally. This is applicable not only to gREST but also to other multi-copy algorithms. Second, energy evaluations, which are necessary for the multistate bennet acceptance ratio (MBAR) method for free energy estimations, are performed on-the-fly during the gREST simulations. Using these two advanced schemes, we observed 57.72 ns/day performance in 128-replica gREST calculations with 1.5 million atoms system using 16,384 nodes in Fugaku. These schemes implemented in the latest version of GENESIS software could open new possibilities to answer unresolved questions on large biomolecular complex systems with slow conformational dynamics.

Individual level spatial-temporal modelling of exposure potential of livestock in the Cove Wash watershed, Arizona.

Personal exposure studies suffer from uncertainty issues, largely stemming from individual behavior uncertainties. Built on spatial-temporal exposure analysis and methods, this study proposed a novel approach to spatial-temporal modeling that incorporated behavior classifications taking into account uncertainties, to estimate individual livestock exposure potential. The new approach was applied in a community-based research project with a Tribal community in the southwest United States. The community project examined the geospatial and temporal grazing patterns of domesticated livestock in a watershed containing 52 abandoned uranium mines (AUMs). Thus, the study aimed to 1) classify Global Positioning System (GPS) data from livestock into three behavior subgroups - grazing, traveling or resting; 2) calculate the daily cumulative exposure potential for livestock; 3) assess the performance of the computational method with and without behavior classifications. Using Lotek Litetrack GPS collars, we collected data at a 20-minute-interval for 2 flocks of sheep and goats during the spring and summer of 2019. Analysis and modeling of GPS data demonstrated no significant difference in individual cumulative exposure potential within each flock when animal behaviors with probability/uncertainties were considered. However, when daily cumulative exposure potential was calculated without consideration of animal behavior or probability/uncertainties, significant differences among animals within a herd were observed, which does not match animal grazing behaviors reported by livestock owners. These results suggest that the proposed method of including behavior subgroups with probability/uncertainties more closely resembled the observed grazing behaviors reported by livestock owners. Results from the research may be used for future intervention and policy-making on remediation efforts in communities where grazing livestock may encounter environmental contaminants. This research also demonstrates a novel robust geographic information system (GIS)-based framework to estimate cumulative exposure potential to environmental contaminants and provides critical information to address community questions on livestock exposure to AUMs.

A proposed scenario to improve the Ncut algorithm in segmentation.

In image segmentation, there are many methods to accomplish the result of segmenting an image into k clusters. However, the number of clusters k is always defined before running the process. It is defined by some observation or knowledge based on the application. In this paper, we propose a new scenario in order to define the value k clusters automatically using histogram information. This scenario is applied to Ncut algorithm and speeds up the running time by using CUDA language to parallel computing in GPU. The Ncut is improved in four steps: determination of number of clusters in segmentation, computing the similarity matrix W, computing the similarity matrix's eigenvalues, and grouping on the Fuzzy C-Means (FCM) clustering algorithm. Some experimental results are shown to prove that our scenario is 20 times faster than the Ncut algorithm while keeping the same accuracy.