An increasing number of researchers are finding use for nth-order gradient computations for a wide variety of applications, including graphics, meta-learning (MAML), scientific computing, and most recently, implicit neural representations (INRs). Recent work shows that the gradient of an INR can be used to edit the data it represents directly without needing to convert it back to a discrete representation. However, given a function represented as a computation graph, traditional architectures face challenges in efficiently computing its nth-order gradient due to the higher demand for computing power and higher complexity in data movement. This makes it a promising target for FPGA acceleration. In this work, we introduce INR-Arch, a framework that transforms the computation graph of an nth-order gradient into a hardware-optimized dataflow architecture. We address this problem in two phases. First, we design a dataflow architecture that uses FIFO streams and an optimized computation kernel library, ensuring high memory efficiency and parallel computation. Second, we propose a compiler that extracts and optimizes computation graphs, automatically configures hardware parameters such as latency and stream depths to optimize throughput, while ensuring deadlock-free operation, and outputs High-Level Synthesis (HLS) code for FPGA implementation. We utilize INR editing as our benchmark, presenting results that demonstrate 1.8-4.8x and 1.5-3.6x speedup compared to CPU and GPU baselines respectively. Furthermore, we obtain 3.1-8.9x and 1.7-4.3x lower memory usage, and 1.7-11.3x and 5.5-32.8x lower energy-delay product. Our framework will be made open-source and available on GitHub.
When dealing with giga-pixel digital pathology in whole-slide imaging, a notable proportion of data records holds relevance during each analysis operation. For instance, when deploying an image analysis algorithm on whole-slide images (WSI), the computational bottleneck often lies in the input-output (I/O) system. This is particularly notable as patch-level processing introduces a considerable I/O load onto the computer system. However, this data management process could be further paralleled, given the typical independence of patch-level image processes across different patches. This paper details our endeavors in tackling this data access challenge by implementing the Adaptable IO System version 2 (ADIOS2). Our focus has been constructing and releasing a digital pathology-centric pipeline using ADIOS2, which facilitates streamlined data management across WSIs. Additionally, we've developed strategies aimed at curtailing data retrieval times. The performance evaluation encompasses two key scenarios: (1) a pure CPU-based image analysis scenario ("CPU scenario"), and (2) a GPU-based deep learning framework scenario ("GPU scenario"). Our findings reveal noteworthy outcomes. Under the CPU scenario, ADIOS2 showcases an impressive two-fold speed-up compared to the brute-force approach. In the GPU scenario, its performance stands on par with the cutting-edge GPU I/O acceleration framework, NVIDIA Magnum IO GPU Direct Storage (GDS). From what we know, this appears to be among the initial instances, if any, of utilizing ADIOS2 within the field of digital pathology. The source code has been made publicly available at https://github.com/hrlblab/adios.
Utilizing optical fibers to detect and pinpoint vibrations, Distributed Optical Fiber Vibration Sensing (DVS) technology provides real-time monitoring and surveillance of wide-reaching areas. This field has been leveraging Convolutional Neural Networks (CNN). Recently, a study has accomplished end-to-end vibration event recognition, enabling utilization of CNN-based DVS algorithms as real-time embedded system for edge computing in practical application situations. Considering the power consumption of central processing unit (CPU) and graphics processing unit (GPU), and the inflexibility of application-specific integrated circuit (ASIC), field-Programmable gate array (FPGA) is the optimal computing platform for the system. This paper proposes to compress pre-trained network and adopt a novel hardware structure, to design a fully on-chip, pipelined inference accelerator for CNN-based DVS algorithm, without fine tuning or re-training. This design allows for real-time processing with low power consumption and system requirement.An examination has been executed on an existing DVS algorithm based on a 40-layer CNN model comprising 2.7 million parameters. It is completely implemented on-chip, pipelined, with no reduction in accuracy.
We replace the multiplication and sigmoid function of the conventional recurrent gate with addition and ReLU activation. This mechanism is designed to maintain long-term memory for sequence processing but at a reduced computational cost, thereby opening up for more efficient execution or larger models on restricted hardware. Recurrent Neural Networks (RNNs) with gating mechanisms such as LSTM and GRU have been widely successful in learning from sequential data due to their ability to capture long-term dependencies. Conventionally, the update based on current inputs and the previous state history is each multiplied with dynamic weights and combined to compute the next state. However, multiplication can be computationally expensive, especially for certain hardware architectures or alternative arithmetic systems such as homomorphic encryption. It is demonstrated that the novel gating mechanism can capture long-term dependencies for a standard synthetic sequence learning task while significantly reducing computational costs such that execution time is reduced by half on CPU and by one-third under encryption. Experimental results on handwritten text recognition tasks furthermore show that the proposed architecture can be trained to achieve comparable accuracy to conventional GRU and LSTM baselines. The gating mechanism introduced in this paper may enable privacy-preserving AI applications operating under homomorphic encryption by avoiding the multiplication of encrypted variables. It can also support quantization in (unencrypted) plaintext applications, with the potential for substantial performance gains since the addition-based formulation can avoid the expansion to double precision often required for multiplication.
We introduce Branched Latent Neural Maps (BLNMs) to learn finite dimensional input-output maps encoding complex physical processes. A BLNM is defined by a simple and compact feedforward partially-connected neural network that structurally disentangles inputs with different intrinsic roles, such as the time variable from model parameters of a differential equation, while transferring them into a generic field of interest. BLNMs leverage latent outputs to enhance the learned dynamics and break the curse of dimensionality by showing excellent generalization properties with small training datasets and short training times on a single processor. Indeed, their generalization error remains comparable regardless of the adopted discretization during the testing phase. Moreover, the partial connections significantly reduce the number of tunable parameters. We show the capabilities of BLNMs in a challenging test case involving electrophysiology simulations in a biventricular cardiac model of a pediatric patient with hypoplastic left heart syndrome. The model includes a 1D Purkinje network for fast conduction and a 3D heart-torso geometry. Specifically, we trained BLNMs on 150 in silico generated 12-lead electrocardiograms (ECGs) while spanning 7 model parameters, covering cell-scale and organ-level. Although the 12-lead ECGs manifest very fast dynamics with sharp gradients, after automatic hyperparameter tuning the optimal BLNM, trained in less than 3 hours on a single CPU, retains just 7 hidden layers and 19 neurons per layer. The resulting mean square error is on the order of $10^{-4}$ on a test dataset comprised of 50 electrophysiology simulations. In the online phase, the BLNM allows for 5000x faster real-time simulations of cardiac electrophysiology on a single core standard computer and can be used to solve inverse problems via global optimization in a few seconds of computational time.
Graph Neural Networks (GNNs) have revolutionized many Machine Learning (ML) applications, such as social network analysis, bioinformatics, etc. GNN inference can be accelerated by exploiting data sparsity in the input graph, vertex features, and intermediate data in GNN computations. For dynamic sparsity exploitation, we leverage the heterogeneous computing capabilities of AMD Versal ACAP architecture to accelerate GNN inference. We develop a custom hardware module that executes the sparse primitives of the computation kernel on the Programmable Logic (PL) and efficiently computes the dense primitives using the AI Engine (AIE). To exploit data sparsity during inference, we devise a runtime kernel mapping strategy that dynamically assigns computation tasks to the PL and AIE based on data sparsity. Our implementation on the VCK5000 ACAP platform leads to superior performance compared with the state-of-the-art implementations on CPU, GPU, ACAP, and other custom GNN accelerators. Compared with these implementations, we achieve significant average runtime speedup across various models and datasets of 162.42x, 17.01x, 9.90x, and 27.23x, respectively. Furthermore, for Graph Convolutional Network (GCN) inference, our approach leads to a speedup of 3.9-96.7x compared to designs using PL only on the same ACAP device.
Detecting human presence indoors with millimeter-wave frequency-modulated continuous-wave (FMCW) radar faces challenges from both moving and stationary clutter. This work proposes a robust and real-time capable human presence and out-of-distribution (OOD) detection method using 60 GHz short-range FMCW radar. HOOD solves the human presence and OOD detection problems simultaneously in a single pipeline. Our solution relies on a reconstruction-based architecture and works with radar macro and micro range-Doppler images (RDIs). HOOD aims to accurately detect the presence of humans in the presence or absence of moving and stationary disturbers. Since HOOD is also an OOD detector, it aims to detect moving or stationary clutters as OOD in humans' absence and predicts the current scene's output as "no presence." HOOD performs well in diverse scenarios, demonstrating its effectiveness across different human activities and situations. On our dataset collected with a 60 GHz short-range FMCW radar, we achieve an average AUROC of 94.36%. Additionally, our extensive evaluations and experiments demonstrate that HOOD outperforms state-of-the-art (SOTA) OOD detection methods in terms of common OOD detection metrics. Importantly, HOOD also perfectly fits on Raspberry Pi 3B+ with an ARM Cortex-A53 CPU, which showcases its versatility across different hardware environments. Videos of our human presence detection experiments are available at: https://muskahya.github.io/HOOD
While a practical wireless network has many tiers where end users do not directly communicate with the central server, the users' devices have limited computation and battery powers, and the serving base station (BS) has a fixed bandwidth. Owing to these practical constraints and system models, this paper leverages model pruning and proposes a pruning-enabled hierarchical federated learning (PHFL) in heterogeneous networks (HetNets). We first derive an upper bound of the convergence rate that clearly demonstrates the impact of the model pruning and wireless communications between the clients and the associated BS. Then we jointly optimize the model pruning ratio, central processing unit (CPU) frequency and transmission power of the clients in order to minimize the controllable terms of the convergence bound under strict delay and energy constraints. However, since the original problem is not convex, we perform successive convex approximation (SCA) and jointly optimize the parameters for the relaxed convex problem. Through extensive simulation, we validate the effectiveness of our proposed PHFL algorithm in terms of test accuracy, wall clock time, energy consumption and bandwidth requirement.
We show that it is possible to achieve the same accuracy, on average, as the most accurate existing interval methods for time series classification on a standard set of benchmark datasets using a single type of feature (quantiles), fixed intervals, and an 'off the shelf' classifier. This distillation of interval-based approaches represents a fast and accurate method for time series classification, achieving state-of-the-art accuracy on the expanded set of 142 datasets in the UCR archive with a total compute time (training and inference) of less than 15 minutes using a single CPU core.
Datacenters are increasingly becoming heterogeneous, and are starting to include specialized hardware for networking, video processing, and especially deep learning. To leverage the heterogeneous compute capability of modern datacenters, we develop an approach for compiler-level partitioning of deep neural networks (DNNs) onto multiple interconnected hardware devices. We present a general framework for heterogeneous DNN compilation, offering automatic partitioning and device mapping. Our scheduler integrates both an exact solver, through a mixed integer linear programming (MILP) formulation, and a modularity-based heuristic for scalability. Furthermore, we propose a theoretical lower bound formula for the optimal solution, which enables the assessment of the heuristic solutions' quality. We evaluate our scheduler in optimizing both conventional DNNs and randomly-wired neural networks, subject to latency and throughput constraints, on a heterogeneous system comprised of a CPU and two distinct GPUs. Compared to na\"ively running DNNs on the fastest GPU, he proposed framework can achieve more than 3$\times$ times lower latency and up to 2.9$\times$ higher throughput by automatically leveraging both data and model parallelism to deploy DNNs on our sample heterogeneous server node. Moreover, our modularity-based "splitting" heuristic improves the solution runtime up to 395$\times$ without noticeably sacrificing solution quality compared to an exact MILP solution, and outperforms all other heuristics by 30-60% solution quality. Finally, our case study shows how we can extend our framework to schedule large language models across multiple heterogeneous servers by exploiting symmetry in the hardware setup. Our code can be easily plugged in to existing frameworks, and is available at https://github.com/abdelfattah-lab/diviml.
Deviations from the approved design or processes during mass production can lead to unforeseen risks. However, these changes are sometimes necessary due to changes in the product design characteristics or an adaptation in the manufacturing process. A major challenge is to identify these risks early in the workflow so that failures leading to warranty claims can be avoided. We developed Fountain as a contextual assistant integrated in the deviation management workflow that helps in identifying the risks based on the description of the existing design and process criteria and the proposed deviation. In the manufacturing context, it is important that the assistant provides recommendations that are explainable and consistent. We achieve this through a combination of the following two components 1) language models finetuned for domain specific semantic similarity and, 2) knowledge representation in the form of a property graph derived from the bill of materials, Failure Modes and Effect Analysis (FMEA) and prior failures reported by customers. Here, we present the nuances of selecting and adapting pretrained language models for an engineering domain, continuous model updates based on user interaction with the contextual assistant and creating the causal chain for explainable recommendations based on the knowledge representation. Additionally, we demonstrate that the model adaptation is feasible using moderate computational infrastructure already available to most engineering teams in manufacturing organizations and inference can be performed on standard CPU only instances for integration with existing applications making these methods easily deployable.
In this work, we design, analyze, and optimize sequential and shared-memory parallel algorithms for partitioned local depths (PaLD). Given a set of data points and pairwise distances, PaLD is a method for identifying strength of pairwise relationships based on relative distances, enabling the identification of strong ties within dense and sparse communities even if their sizes and within-community absolute distances vary greatly. We design two algorithmic variants that perform community structure analysis through triplet comparisons of pairwise distances. We present theoretical analyses of computation and communication costs and prove that the sequential algorithms are communication optimal, up to constant factors. We introduce performance optimization strategies that yield sequential speedups of up to $29\times$ over a baseline sequential implementation and parallel speedups of up to $19.4\times$ over optimized sequential implementations using up to $32$ threads on an Intel multicore CPU.
Deep learning has achieved remarkable success in the field of bearing fault diagnosis. However, this success comes with larger models and more complex computations, which cannot be transferred into industrial fields requiring models to be of high speed, strong portability, and low power consumption. In this paper, we propose a lightweight and deployable model for bearing fault diagnosis, referred to as BearingPGA-Net, to address these challenges. Firstly, aided by a well-trained large model, we train BearingPGA-Net via decoupled knowledge distillation. Despite its small size, our model demonstrates excellent fault diagnosis performance compared to other lightweight state-of-the-art methods. Secondly, we design an FPGA acceleration scheme for BearingPGA-Net using Verilog. This scheme involves the customized quantization and designing programmable logic gates for each layer of BearingPGA-Net on the FPGA, with an emphasis on parallel computing and module reuse to enhance the computational speed. To the best of our knowledge, this is the first instance of deploying a CNN-based bearing fault diagnosis model on an FPGA. Experimental results reveal that our deployment scheme achieves over 200 times faster diagnosis speed compared to CPU, while achieving a lower-than-0.4\% performance drop in terms of F1, Recall, and Precision score on our independently-collected bearing dataset. Our code is available at \url{https://github.com/asdvfghg/BearingPGA-Net}.
We present YOLOBench, a benchmark comprised of 550+ YOLO-based object detection models on 4 different datasets and 4 different embedded hardware platforms (x86 CPU, ARM CPU, Nvidia GPU, NPU). We collect accuracy and latency numbers for a variety of YOLO-based one-stage detectors at different model scales by performing a fair, controlled comparison of these detectors with a fixed training environment (code and training hyperparameters). Pareto-optimality analysis of the collected data reveals that, if modern detection heads and training techniques are incorporated into the learning process, multiple architectures of the YOLO series achieve a good accuracy-latency trade-off, including older models like YOLOv3 and YOLOv4. We also evaluate training-free accuracy estimators used in neural architecture search on YOLOBench and demonstrate that, while most state-of-the-art zero-cost accuracy estimators are outperformed by a simple baseline like MAC count, some of them can be effectively used to predict Pareto-optimal detection models. We showcase that by using a zero-cost proxy to identify a YOLO architecture competitive against a state-of-the-art YOLOv8 model on a Raspberry Pi 4 CPU. The code and data are available at https://github.com/Deeplite/deeplite-torch-zoo
Neuromorphic processors have garnered considerable interest in recent years for their potential in energy-efficient and high-speed computing. The Locally Competitive Algorithm (LCA) has been utilized for power efficient sparse coding on neuromorphic processors, including the first Loihi processor. With the Loihi 2 processor enabling custom neuron models and graded spike communication, more complex implementations of LCA are possible. We present a new implementation of LCA designed for the Loihi 2 processor and perform an initial set of benchmarks comparing it to LCA on CPU and GPU devices. In these experiments LCA on Loihi 2 is orders of magnitude more efficient and faster for large sparsity penalties, while maintaining similar reconstruction quality. We find this performance improvement increases as the LCA parameters are tuned towards greater representation sparsity. Our study highlights the potential of neuromorphic processors, particularly Loihi 2, in enabling intelligent, autonomous, real-time processing on small robots, satellites where there are strict SWaP (small, lightweight, and low power) requirements. By demonstrating the superior performance of LCA on Loihi 2 compared to conventional computing device, our study suggests that Loihi 2 could be a valuable tool in advancing these types of applications. Overall, our study highlights the potential of neuromorphic processors for efficient and accurate data processing on resource-constrained devices.
Learned cardinality estimation methods have achieved high precision compared to traditional methods. Among learned methods, query-driven approaches have faced the workload drift problem for a long time. Although both data-driven and hybrid methods are proposed to avoid this problem, most of them suffer from high training and estimation costs, limited scalability, instability, and long-tail distribution problems on high-dimensional tables, which seriously affects the practical application of learned cardinality estimators. In this paper, we prove that most of these problems are directly caused by the widely used progressive sampling. We solve this problem by introducing predicate information into the autoregressive model and propose Duet, a stable, efficient, and scalable hybrid method to estimate cardinality directly without sampling or any non-differentiable process, which can not only reduce the inference complexity from $O(n)$ to $O(1)$ compared to Naru and UAE but also achieve higher accuracy on high cardinality and high-dimensional tables. Experimental results show that Duet can achieve all the design goals above and be much more practical. Besides, Duet even has a lower inference cost on CPU than that of most learned methods on GPU.
The rise of Decentralized Federated Learning (DFL) has enabled the training of machine learning models across federated participants, fostering decentralized model aggregation and reducing dependence on a server. However, this approach introduces unique communication security challenges that have yet to be thoroughly addressed in the literature. These challenges primarily originate from the decentralized nature of the aggregation process, the varied roles and responsibilities of the participants, and the absence of a central authority to oversee and mitigate threats. Addressing these challenges, this paper first delineates a comprehensive threat model focused on DFL communications. In response to these identified risks, this work introduces a security module to counter communication-based attacks for DFL platforms. The module combines security techniques such as symmetric and asymmetric encryption with Moving Target Defense (MTD) techniques, including random neighbor selection and IP/port switching. The security module is implemented in a DFL platform, Fedstellar, allowing the deployment and monitoring of the federation. A DFL scenario with physical and virtual deployments have been executed, encompassing three security configurations: (i) a baseline without security, (ii) an encrypted configuration, and (iii) a configuration integrating both encryption and MTD techniques. The effectiveness of the security module is validated through experiments with the MNIST dataset and eclipse attacks. The results showed an average F1 score of 95%, with the most secure configuration resulting in CPU usage peaking at 68% (+-9%) in virtual deployments and network traffic reaching 480.8 MB (+-18 MB), effectively mitigating risks associated with eavesdropping or eclipse attacks.
Multi-tenancy in public clouds may lead to co-location interference on shared resources, which possibly results in performance degradation of cloud applications. Cloud providers want to know when such events happen and how serious the degradation is, to perform interference-aware migrations and alleviate the problem. However, virtual machines (VM) in Infrastructure-as-a-Service public clouds are black-boxes to providers, where application-level performance information cannot be acquired. This makes performance monitoring intensely challenging as cloud providers can only rely on low-level metrics such as CPU usage and hardware counters. We propose a novel machine learning framework, Alioth, to monitor the performance degradation of cloud applications. To feed the data-hungry models, we first elaborate interference generators and conduct comprehensive co-location experiments on a testbed to build Alioth-dataset which reflects the complexity and dynamicity in real-world scenarios. Then we construct Alioth by (1) augmenting features via recovering low-level metrics under no interference using denoising auto-encoders, (2) devising a transfer learning model based on domain adaptation neural network to make models generalize on test cases unseen in offline training, and (3) developing a SHAP explainer to automate feature selection and enhance model interpretability. Experiments show that Alioth achieves an average mean absolute error of 5.29% offline and 10.8% when testing on applications unseen in the training stage, outperforming the baseline methods. Alioth is also robust in signaling quality-of-service violation under dynamicity. Finally, we demonstrate a possible application of Alioth's interpretability, providing insights to benefit the decision-making of cloud operators. The dataset and code of Alioth have been released on GitHub.
Perception and control systems for autonomous vehicles are an active area of scientific and industrial research. These solutions should be characterised by high efficiency in recognising obstacles and other environmental elements in different road conditions, real-time capability, and energy efficiency. Achieving such functionality requires an appropriate algorithm and a suitable computing platform. In this paper, we have used the MultiTaskV3 detection-segmentation network as the basis for a perception system that can perform both functionalities within a single architecture. It was appropriately trained, quantised, and implemented on the AMD Xilinx Kria KV260 Vision AI embedded platform. By using this device, it was possible to parallelise and accelerate the computations. Furthermore, the whole system consumes relatively little power compared to a CPU-based implementation (an average of 5 watts, compared to the minimum of 55 watts for weaker CPUs, and the small size (119mm x 140mm x 36mm) of the platform allows it to be used in devices where the amount of space available is limited. It also achieves an accuracy higher than 97% of the mAP (mean average precision) for object detection and above 90% of the mIoU (mean intersection over union) for image segmentation. The article also details the design of the Mecanum wheel vehicle, which was used to test the proposed solution in a mock-up city.
Artificial intelligence onboard satellites has the potential to reduce data transmission requirements, enable real-time decision-making and collaboration within constellations. This study deploys a lightweight foundational model called RaVAEn on D-Orbit's ION SCV004 satellite. RaVAEn is a variational auto-encoder (VAE) that generates compressed latent vectors from small image tiles, enabling several downstream tasks. In this work we demonstrate the reliable use of RaVAEn onboard a satellite, achieving an encoding time of 0.110s for tiles of a 4.8x4.8 km$^2$ area. In addition, we showcase fast few-shot training onboard a satellite using the latent representation of data. We compare the deployment of the model on the on-board CPU and on the available Myriad vision processing unit (VPU) accelerator. To our knowledge, this work shows for the first time the deployment of a multi-task model on-board a CubeSat and the on-board training of a machine learning model.