TROOP: At-the-Roofline Performance for Vector Processors on Low Operational Intensity Workloads

General Matrix Multiplication (GEMM) is a crucial algorithm for various applications such as machine learning and scientific computing since an efficient GEMM implementation is essential for the performance of these calculations. While researchers often strive for faster performance by using large computing platforms, the increased scale of these systems can raise concerns about hardware and software reliability. In this paper, we present a design of a high-performance GPU-based GEMM that integrates an algorithm-based fault tolerance scheme that detects and corrects silent data corruptions at computing units on-the-fly. We explore fault-tolerant designs for GEMM at the thread, warp, and threadblock levels, and also provide a baseline GEMM implementation that is competitive with or faster than the state-of-the-art, closed-source cuBLAS GEMM. We present a kernel fusion strategy to overlap and mitigate the memory latency due to fault tolerance with the original GEMM computation. To support a wide range of input matrix shapes and reduce development costs, we present a template-based approach for automatic code generation for both fault-tolerant and non-fault-tolerant GEMM implementations. We evaluate our work on NVIDIA Tesla T4 and A100 server GPUs. Our experimental results demonstrate that our baseline GEMM shows comparable or superior performance compared to the closed-source cuBLAS. Compared with the prior state-of-the-art non-fused fault-tolerant GEMM, our optimal fused strategy achieves a 39.04% speedup on average. In addition, our fault-tolerant GEMM incurs only a minimal overhead (8.89% on average) compared to cuBLAS even with hundreds of errors injected per minute. For irregularly shaped inputs, the code generator-generated kernels show remarkable speedups of 160% ~ 183.5% and 148.55% ~ 165.12% for fault-tolerant and non-fault-tolerant GEMMs, respectively, which outperforms cuBLAS by up to 41.40%.

While parallel architectures based on clusters of Processing Elements (PEs) sharing L1 memory are widespread, there is no consensus on how lean their PE should be. Architecting PEs as vector processors holds the promise to greatly reduce their instruction fetch bandwidth, mitigating the Von Neumann Bottleneck (VNB). However, due to their historical association with supercomputers, classical vector machines include micro-architectural tricks to improve the Instruction Level Parallelism (ILP), which increases their instruction fetch and decode energy overhead. In this paper, we explore for the first time vector processing as an option to build small and efficient PEs for large-scale shared-L1 clusters. We propose Spatz, a compact, modular 32-bit vector processing unit based on the integer embedded subset of the RISC-V Vector Extension version 1.0. A Spatz-based cluster with four Multiply-Accumulate Units (MACUs) needs only 7.9 pJ per 32-bit integer multiply-accumulate operation, 40% less energy than an equivalent cluster built with four Snitch scalar cores. We analyzed Spatz' performance by integrating it within MemPool, a large-scale many-core shared-L1 cluster. The Spatz-based MemPool system achieves up to 285 GOPS when running a 256x256 32-bit integer matrix multiplication, 70% more than the equivalent Snitch-based MemPool system. In terms of energy efficiency, the Spatz-based MemPool system achieves up to 266 GOPS/W when running the same kernel, more than twice the energy efficiency of the Snitch-based MemPool system, which reaches 128 GOPS/W. Those results show the viability of lean vector processors as high-performance and energy-efficient PEs for large-scale clusters with tightly-coupled L1 memory.

Radio Access Networks (RAN) workloads are rapidly scaling up in data processing intensity and throughput as the 5G (and beyond) standards grow in number of antennas and sub-carriers. Offering flexible Processing Elements (PEs), efficient memory access, and a productive parallel programming model, many-core clusters are a well-matched architecture for next-generation software-defined RANs, but staggering performance requirements demand a high number of PEs coupled with extreme Power, Performance and Area (PPA) efficiency. We present the architecture, design, and full physical implementation of Terapool-SDR, a cluster for Software Defined Radio (SDR) with 1024 latency-tolerant, compact RV32 PEs, sharing a global view of a 4 MiB, 4096-banked, L1 memory. We report various feasible configurations of TeraPool-SDR featuring an ultra-high bandwidth PE-to-L1-memory interconnect, clocked at 730 MHz, 880 MHz, and 924 MHz (TT/0.80 V/<Formula format="inline"><TexMath><?TeX $25 \,\mathrm{ \mathrm{^{\circ }\mathrm{\mathrm{C}}}}$?></TexMath><AltText>Math 1</AltText><File name="glsvlsi24-40-inline1" type="svg"/></Formula>) in 12 nm FinFET technology. The TeraPool-SDR cluster achieves high energy efficiency on all SDR key kernels for 5G RANs: Fast Fourier Transform (93 GOPSW− 1), Matrix-Multiplication (125 GOPSW− 1), Channel Estimation (96 GOPSW− 1), and Linear System Inversion (61 GOPSW− 1). For all the kernels, it consumes less than 10 W, in compliance with industry standards.

The instruction set architecture of vector processors operates on vectors stored in the vector register file which needs to handle several concurrent accesses by functional units with multiple ports. When the vector processor is running with high utilization, access conflicts become a major source of performance degradation. With a software model of a vector processor, we take a deep dive into the runtime impact of conflicts and their characteristics, and on ways to manage them, i.e., avoidance, resolution, and mitigation. For conflict avoidance, we study the existing approaches of banking with different static bank layouts and propose a dynamic bank layout to overcome their shortcomings. Our approach assigns newly written registers a temporarily unique starting bank. For conflict resolution, we compare different arbitration algorithms and optimize round-robin arbitration for mixed-width arithmetics by prioritizing wide operands. For conflict mitigation, operand queues of varying depths are studied. Our inventions are likely to increase the area efficiency of vector processors, either because they allow to use shallower operand queues while keeping the same performance, or reduce the area even further by using less banks, albeit at a performance impairment of 10% or less. The insights of the study can further be applied to other shared memory systems.

Enhanced bifunctional electrocatalysis of Co5.47N nanocrystals in porous carbon nanofibers for high-efficiency zinc-air batteries

In the automotive industry, exterior lighting systems play a critical role in enhancing vehicle safety and improving aesthetic visibility. This study focuses on the advantages offered by powering Downlighter-type LED lighting systems—specifically positioned at the rear of commercial vehicles—using a PWM (Pulse Width Modulation) source. In modern vehicle design, exterior lighting systems have become a key component both for safety and aesthetic purposes. Especially for commercial vehicles, providing adequate lighting during loading and unloading operations at the rear door area directly impacts operational safety. Downlighter-type LED systems, which offer homogeneous light distribution at the rear, enhance environmental visibility and contribute to safety, while also providing an aesthetically pleasing appearance. The high energy efficiency, long lifespan, and lower power consumption offered by LED technology ensure high performance. Additionally, thanks to their dimmable feature, these systems allow light intensity to be adjusted according to different usage scenarios, resulting in energy savings and offering a flexible lighting solution to the user. Downlighter-type LED lighting systems present a significant solution in the automotive industry in terms of both safety and cost-effectiveness. In particular, they enhance the safety of night-time operations in commercial vehicles by providing lighting support, while their energy efficiency and adjustable brightness meet the needs of modern automotive designs. This study discusses a PWM (Pulse Width Modulation)-based LED driver application designed for use in vehicle exterior lighting systems. The system is specifically developed for Downlighter-type LED lighting solutions located at the rear of commercial vehicles. The design offers advantages not only in terms of precise light intensity control but also in terms of energy efficiency and cost-effectiveness. Exterior lighting systems in the automotive industry are of great importance for increasing safety and ensuring safer night-time operations. In commercial vehicles where loading and unloading operations are performed at the rear, Downlighter-type LED systems that provide uniform light distribution play a critical role. In this context, there is an increasing need for energy-efficient systems with effective light intensity control. The designed PWM-based LED driver can precisely control LED brightness by adjusting the pulse width. This control technique enables high lighting performance with low energy consumption. With its dimmable feature, the system allows flexible adjustment of light levels based on usage scenarios while also saving energy. Moreover, instead of the conventional 3-pin circuit topology, a 2-pin design was preferred, and the sizes of the input filter capacitors used in the circuit were optimized, resulting in PCB space savings and cost reduction. These improvements provide significant economic benefits in high-volume automotive production. The PWM-controlled LED driver design is a technically and economically suitable solution for Downlighter-type automotive exterior lighting systems. The ability to precisely adjust light intensity, high energy efficiency, and low system cost increase the product’s appeal for both OEMs and end users.

Extremely low loading of carbon quantum dots for high energy density in polyetherimide nanocomposites

1. Introduction 1.1 Introduce the Problem Increase of energy efficiency and energy saving are important on a global scale. And the reason lies in not only limited resources, but also in increasing negative impact of emissions on the environment and climate. National economies are interested in preservation of natural potential for future generations, reduction of production costs by decreasing the share of consumed energy and fuel resources and increasing the manufacturing with high added value. This can be realized in two main ways. Firstly, through changing the fuel balance by using less dirty technologies and alternative energy sources. Secondly, through wide implementation of energy-saving technologies and water/wastewater treatment facilities. Implementation of these measures is associated with high costs. However, business in modern Russia lacks both own funds and borrowing assets due to high interest rates. In addition, it does not have enough stimulations in market economy to expand costs when there are cheaper ways to get results. The government must provide its citizens with public benefits and it has necessary financial resources for that. Therefore, it must take on costs of the energy efficiency of the economy, including tax expenses. Developed countries solve these problems by increasing the tax burden for the production and consumption of energy and fuel resources, implementing environmental taxes and stimulating energy production from renewable sources of energy. In countries with developing economies a greater share of the industry is occupied by high-energy demanding spheres. Rise of taxes and cost of energy to the world level may have a limiting effect on economic growth. Model of resourcebased economy and de-industrialization of the Russian economy on the background of financial crisis significantly complicates the task of construction of an effective mechanism of tax incentive for energy efficient investments, and as a result, for environmental efficiency. Neoindustrialization requires implementation of major projects and improvement of power loading in a number of sectors of the economy with the aim of increase of share of import-substituting industries with high added value. 1.2 Explore Importance of the Problem The importance of the study of tax incentive for energy saving and increase of energy efficiency within a neo-industrial paradigm is conditioned by a need to study both its theoretical base and practical recommendations. The need for, on the one hand, increase of industry capacities, and, on the other hand, for compliance with the Kyoto protocol and reducing of harmful emissions into the atmosphere, requires special attention of the government to the formation of tax policy in this area. Currently, the existing tax legislation in Russia has only three preferences aimed at the investments in facilities exclusively with high energy efficiency. Only fuel resources are listed as excisable, which has no significant limiting effect on demand and consumption of objects with high energy efficiency. Negative impact on the environment are charged with fees of non-tax nature. It does not bear any fiscal or regulatory role due to unessential size and a number of disadvantages concerning calculation pattern and payment (Koroleva & Maskaeva, 2014). In 2015, the tax maneuver was implemented. It is aimed at increasing of cost of fuel and energy resources in the national market by increasing environmental taxes and reducing export duties. This measure will reduce the profitability of main customers in heavy industrial manufacturing. But is does not stimulate technological upgrades in order to save resources of the mining industry itself. In the Russian Federation it is necessary to form a complex system of tax measures aimed at improving the energy efficiency of industrial manufacturing, allowing to have a double effect. Ecological one--by reducing harmful emissions into the atmosphere, economical one--by increasing the rates of economic growth based on resource saving. …

Machine learning (ML) models provide more choices to patients with diabetes mellitus (DM) to more properly manage blood glucose (BG) levels. However, because of numerous types of ML algorithms, choosing an appropriate model is vitally important. In a systematic review and network meta-analysis, this study aimed to comprehensively assess the performance of ML models in predicting BG levels. In addition, we assessed ML models used to detect and predict adverse BG (hypoglycemia) events by calculating pooled estimates of sensitivity and specificity. PubMed, Embase, Web of Science, and Institute of Electrical and Electronics Engineers Explore databases were systematically searched for studies on predicting BG levels and predicting or detecting adverse BG events using ML models, from inception to November 2022. Studies that assessed the performance of different ML models in predicting or detecting BG levels or adverse BG events of patients with DM were included. Studies with no derivation or performance metrics of ML models were excluded. The Quality Assessment of Diagnostic Accuracy Studies tool was applied to assess the quality of included studies. Primary outcomes were the relative ranking of ML models for predicting BG levels in different prediction horizons (PHs) and pooled estimates of the sensitivity and specificity of ML models in detecting or predicting adverse BG events. In total, 46 eligible studies were included for meta-analysis. Regarding ML models for predicting BG levels, the means of the absolute root mean square error (RMSE) in a PH of 15, 30, 45, and 60 minutes were 18.88 (SD 19.71), 21.40 (SD 12.56), 21.27 (SD 5.17), and 30.01 (SD 7.23) mg/dL, respectively. The neural network model (NNM) showed the highest relative performance in different PHs. Furthermore, the pooled estimates of the positive likelihood ratio and the negative likelihood ratio of ML models were 8.3 (95% CI 5.7-12.0) and 0.31 (95% CI 0.22-0.44), respectively, for predicting hypoglycemia and 2.4 (95% CI 1.6-3.7) and 0.37 (95% CI 0.29-0.46), respectively, for detecting hypoglycemia. Statistically significant high heterogeneity was detected in all subgroups, with different sources of heterogeneity. For predicting precise BG levels, the RMSE increases with a rise in the PH, and the NNM shows the highest relative performance among all the ML models. Meanwhile, current ML models have sufficient ability to predict adverse BG events, while their ability to detect adverse BG events needs to be enhanced. PROSPERO CRD42022375250; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=375250.

Processing-in-Memory (PIM) has been widely explored for accelerating data-intensive machine learning computation that mainly consists of general-matrix-multiplication (GEMM), by mitigating the burden of data movements and exploiting the ultra-high memory parallelism. The two mainstreams of PIM, the analog- and digital-type, have both been exploited in accelerating machine learning workloads by numerous outstanding prior works. Currently, the digital-PIM is increasingly favored due to the broader computing support and the avoidance of errors caused by intrinsic non-idealities, e.g., process variation. Nevertheless, it still lacks further optimization considering the characteristics of the GEMM computation, including better efficient data layout and scheduling, and the ability to handle the sparsity of activations at the bit-level. To boost the performance and efficiency of digital SRAM PIM, we propose the architecture called VSPIM that performs the computation in a bit-serial fashion, with unique support of vector-scalar computing pattern. The novelties of the VSPIM can be concluded as follows: 1) support bit-serial based scalar-vector computing via ingenious parallel bit-broadcasting; 2) refine the GEMM mapping strategy and computing pattern to enhance performance and efficiency; 3) powered by the introduced scalar-vector operation, the bit-sparsity of activation is leveraged to halt unnecessary computation to maximize efficiency and throughput. Our comprehensive evaluation shows that, compared to the state-of-the-art SRAM-based digital-PIM design (Neural Cache), VSPIM can significantly boost the performance and energy efficiency by up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$8.87\times$</tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$4.81\times$</tex-math></inline-formula> respectively, with negligible area overhead, upon multiple representative neural networks.

Systematic literature review of machine learning based software development effort estimation models

This study focuses on using various machine learning (ML) models to evaluate the shear behaviors of ultra-high-performance concrete (UHPC) beams reinforced with glass fiber-reinforced polymer (GFRP) bars. The main objective of the study is to predict the shear strength of UHPC beams reinforced with GFRP bars using ML models. We use four different ML models: support vector machine (SVM), artificial neural network (ANN), random forest (R.F.), and extreme gradient boosting (XGBoost). The experimental database used in the study is acquired from various literature sources and comprises 54 test observations with 11 input features. These input features are likely parameters related to the composition, geometry, and properties of the UHPC beams and GFRP bars. To ensure the ML models' generalizability and scalability, random search methods are utilized to tune the hyperparameters of the algorithms. This tuning process helps improve the performance of the models when predicting the shear strength. The study uses the ACI318M-14 and Eurocode 2 standard building codes to predict the shear capacity behavior of GFRP bars-reinforced UHPC I-shaped beams. The ML models' predictions are compared to the results obtained from these building code standards. According to the findings, the XGBoost model demonstrates the highest predictive test performance among the investigated ML models. The study employs the SHAP (SHapley Additive exPlanations) analysis to assess the significance of each input parameter in the ML models' predictive capabilities. A Taylor diagram is used to statistically compare the accuracy of the ML models. This study concludes that ML models, particularly XGBoost, can effectively predict the shear capacity behavior of GFRP bars-reinforced UHPC I-shaped beams.

Optimisation and interpretation of machine and deep learning models for improved water quality management in Lake Loktak

Accurate estimation of reference evapotranspiration (ETo) plays a vital role in irrigation and water resource planning. The Penman–Monteith method recommended by the Food and Agriculture Organization (FAO PM56) is widely used and considered a standard to calculate ETo. However, FAO PM56 cannot be used with limited meteorological variables, so it is compulsory to choose an alternative model for ETo estimation, which requires fewer variables. This study built ten machine learning (ML) models based on multi-function, neural network, and tree-based structure against the FAO PM56 method. For this purpose, time series temperature data on a monthly scale are only used to train ML models. The developed ML models were applied to estimate ETo at different test stations and the obtained results were compared with the FAO PM56 method to verify and validate their performance in ETo estimation for the selected stations. In addition, multiple statistical indicators, including root-mean-square error (RMSE), coefficient of determination (R2), mean absolute error (MAE), Nash–Sutcliffe efficiency (NSE), and correlation coefficient (r) were calculated to compare the performance of each ML model on ETo estimation. Among the applied ML models, the ETo tree boost (TB) ML model outperformed the other ML models in estimating ETo in diverse climatic conditions based on statistical indicators (R2, NSE, r, RMSE, and MAE). Moreover, the observed R2, NSE, and r were the highest for the TB ML model, while RMSE and MAE were found to be the lowest at the study sites compared to other applied ML models. Lastly, ETo point data yielded from the TB ML model was used in an interpolation process to create monthly and annual ETo maps. Based on the ETo maps, this study suggests mainly a focus on areas with high ETo values and proper irrigation scheduling of crops to ensure water sustainability.

Aim: The majority of machine learning (ML) models in healthcare are built on retrospective data, much of which is collected without explicit patient consent for use in artificial intelligence (AI) and ML applications. The primary aim of this study was to evaluate whether clinicians and scientific researchers themselves consent to provide their own data for the training of ML models. Materials and Methods: This survey was conducted through an anonymous online survey, utilizing platforms such as Telegram, LinkedIn, and Viber. The target audience comprised specific international groups, primarily Russian, German, and English-speaking, of clinicians and scientific researchers. These participants ranged in their levels of expertise and experience, from beginners to veterans. The survey centered on a singular, pivotal question: “Do You Consent to the Use of Your Biological and Private Data for Training Machine Learning and AI Models?” Respondents had the option to choose from three responses: “Yes” and “No”. Results: The survey was conducted in January 2024. A total of 119 unique and verified individuals participated in the survey. The results revealed that only 50% of respondents (63 persons) expressed consent to provide their own data for the training of ML and AI models. Conclusion: In the development of ML and AI models, particularly open-source ones, it is crucial to ascertain whether participants are willing to provide their private data. While ML algorithms can transform the nature of data, it is important to remember that the primary owner of this data is the individual. Our findings show that in 50% of the cases, even participants from scientific research and clinical backgrounds – individuals typically accountable for ensuring data quality in AI and ML model development – do not consent to the use of their data in AI and ML settings. This highlights the need for more stringent consent processes and ethical considerations in the utilization of personal data in AI and ML research.