Depth estimation is a fundamental knowledge for autonomous systems that need to assess their own state and perceive the surrounding environment. Deep learning algorithms for depth estimation have gained significant interest in recent years, owing to the potential benefits of this methodology in overcoming the limitations of active depth sensing systems. Moreover, due to the low cost and size of monocular cameras, researchers have focused their attention on monocular depth estimation (MDE), which consists in estimating a dense depth map from a single RGB video frame. State of the art MDE models typically rely on vision transformers (ViT) architectures that are highly deep and complex, making them unsuitable for fast inference on devices with hardware constraints. Purposely, in this paper, we address the problem of exploiting ViT in MDE on embedded devices. Those systems are usually characterized by limited memory capabilities and low-power CPU/GPU. We propose METER, a novel lightweight vision transformer architecture capable of achieving state of the art estimations and low latency inference performances on the considered embedded hardwares: NVIDIA Jetson TX1 and NVIDIA Jetson Nano. We provide a solution consisting of three alternative configurations of METER, a novel loss function to balance pixel estimation and reconstruction of image details, and a new data augmentation strategy to improve the overall final predictions. The proposed method outperforms previous lightweight works over the two benchmark datasets: the indoor NYU Depth v2 and the outdoor KITTI.
Addressing the so-called ``Red-AI'' trend of rising energy consumption by large-scale neural networks, this study investigates the actual energy consumption, as measured by node-level watt-meters, of training various fully connected neural network architectures. We introduce the BUTTER-E dataset, an augmentation to the BUTTER Empirical Deep Learning dataset, containing energy consumption and performance data from 63,527 individual experimental runs spanning 30,582 distinct configurations: 13 datasets, 20 sizes (number of trainable parameters), 8 network ``shapes'', and 14 depths on both CPU and GPU hardware collected using node-level watt-meters. This dataset reveals the complex relationship between dataset size, network structure, and energy use, and highlights the impact of cache effects. We propose a straightforward and effective energy model that accounts for network size, computing, and memory hierarchy. Our analysis also uncovers a surprising, hardware-mediated non-linear relationship between energy efficiency and network design, challenging the assumption that reducing the number of parameters or FLOPs is the best way to achieve greater energy efficiency. Highlighting the need for cache-considerate algorithm development, we suggest a combined approach to energy efficient network, algorithm, and hardware design. This work contributes to the fields of sustainable computing and Green AI, offering practical guidance for creating more energy-efficient neural networks and promoting sustainable AI.
Early Exit Neural Networks (EENNs) present a solution to enhance the efficiency of neural network deployments. However, creating EENNs is challenging and requires specialized domain knowledge, due to the large amount of additional design choices. To address this issue, we propose an automated augmentation flow that focuses on converting an existing model into an EENN. It performs all required design decisions for the deployment to heterogeneous or distributed hardware targets: Our framework constructs the EENN architecture, maps its subgraphs to the hardware targets, and configures its decision mechanism. To the best of our knowledge, it is the first framework that is able to perform all of these steps. We evaluated our approach on a collection of Internet-of-Things and standard image classification use cases. For a speech command detection task, our solution was able to reduce the mean operations per inference by 59.67%. For an ECG classification task, it was able to terminate all samples early, reducing the mean inference energy by 74.9% and computations by 78.3%. On CIFAR-10, our solution was able to achieve up to a 58.75% reduction in computations. The search on a ResNet-152 base model for CIFAR-10 took less than nine hours on a laptop CPU. Our proposed approach enables the creation of EENN optimized for IoT environments and can reduce the inference cost of Deep Learning applications on embedded and fog platforms, while also significantly reducing the search cost - making it more accessible for scientists and engineers in industry and research. The low search cost improves the accessibility of EENNs, with the potential to improve the efficiency of neural networks in a wide range of practical applications.
In Internet of Things (IoT) networks, the amount of data sensed by user devices may be huge, resulting in the serious network congestion. To solve this problem, intelligent data compression is critical. The variational information bottleneck (VIB) approach, combined with machine learning, can be employed to train the encoder and decoder, so that the required transmission data size can be reduced significantly. However, VIB suffers from the computing burden and network insecurity. In this paper, we propose a blockchain-enabled VIB (BVIB) approach to relieve the computing burden while guaranteeing network security. Extensive simulations conducted by Python and C++ demonstrate that BVIB outperforms VIB by 36%, 22% and 57% in terms of time and CPU cycles cost, mutual information, and accuracy under attack, respectively.
While GPU clusters are the de facto choice for training large deep neural network (DNN) models today, several reasons including ease of workflow, security and cost have led to efforts investigating whether CPUs may be viable for inference in routine use in many sectors of the industry. But the imbalance between the compute capabilities of GPUs and CPUs is huge. Motivated by these considerations, we study a module which is a workhorse within modern DNN architectures, GEMM based Feed Forward Networks (FFNs), and assess the extent to which it can be made compute- (or FLOP-) lite. Specifically, we propose an alternative formulation (we call it LookupFFN) to GEMM based FFNs inspired by the recent studies of using Locality Sensitive Hashing (LSH) to approximate FFNs. Our formulation recasts most essential operations as a memory look-up, leveraging the trade-off between the two resources on any platform: compute and memory (since CPUs offer it in abundance). For RoBERTa language model pretraining, our formulation achieves similar performance compared to GEMM based FFNs, while dramatically reducing the required FLOP. Our development is complemented with a detailed hardware profiling of strategies that will maximize efficiency -- not just on contemporary hardware but on products that will be offered in the near/medium term future. Code is avaiable at \url{https://github.com/mlpen/LookupFFN}.
Machine Learning (ML) has become ubiquitous, fueling data-driven applications across various organizations. Contrary to the traditional perception of ML in research, ML workflows can be complex, resource-intensive, and time-consuming. Expanding an ML workflow to encompass a wider range of data infrastructure and data types may lead to larger workloads and increased deployment costs. Currently, numerous workflow engines are available (with over ten being widely recognized). This variety poses a challenge for end-users in terms of mastering different engine APIs. While efforts have primarily focused on optimizing ML Operations (MLOps) for a specific workflow engine, current methods largely overlook workflow optimization across different engines. In this work, we design and implement Couler, a system designed for unified ML workflow optimization in the cloud. Our main insight lies in the ability to generate an ML workflow using natural language (NL) descriptions. We integrate Large Language Models (LLMs) into workflow generation, and provide a unified programming interface for various workflow engines. This approach alleviates the need to understand various workflow engines' APIs. Moreover, Couler enhances workflow computation efficiency by introducing automated caching at multiple stages, enabling large workflow auto-parallelization and automatic hyperparameters tuning. These enhancements minimize redundant computational costs and improve fault tolerance during deep learning workflow training. Couler is extensively deployed in real-world production scenarios at Ant Group, handling approximately 22k workflows daily, and has successfully improved the CPU/Memory utilization by more than 15% and the workflow completion rate by around 17%.
The ongoing trend of hardware specialization has led to a growing use of custom data formats when processing sparse workloads, which are typically memory-bound. These formats facilitate optimized software/hardware implementations by utilizing sparsity pattern- or target-aware data structures and layouts to enhance memory access latency and bandwidth utilization. However, existing sparse tensor programming models and compilers offer little or no support for productively customizing the sparse formats. Additionally, because these frameworks represent formats using a limited set of per-dimension attributes, they lack the flexibility to accommodate numerous new variations of custom sparse data structures and layouts. To overcome this deficiency, we propose UniSparse, an intermediate language that provides a unified abstraction for representing and customizing sparse formats. Unlike the existing attribute-based frameworks, UniSparse decouples the logical representation of the sparse tensor (i.e., the data structure) from its low-level memory layout, enabling the customization of both. As a result, a rich set of format customizations can be succinctly expressed in a small set of well-defined query, mutation, and layout primitives. We also develop a compiler leveraging the MLIR infrastructure, which supports adaptive customization of formats, and automatic code generation of format conversion and compute operations for heterogeneous architectures. We demonstrate the efficacy of our approach through experiments running commonly-used sparse linear algebra operations with specialized formats on multiple different hardware targets, including an Intel CPU, an NVIDIA GPU, an AMD Xilinx FPGA, and a simulated processing-in-memory (PIM) device.
Achieving high-performance computation on quantum systems presents a formidable challenge that necessitates bridging the capabilities between quantum hardware and classical computing resources. This study introduces an innovative distribution-aware Quantum-Classical-Quantum (QCQ) architecture, which integrates cutting-edge quantum software framework works with high-performance classical computing resources to address challenges in quantum simulation for materials and condensed matter physics. At the heart of this architecture is the seamless integration of VQE algorithms running on QPUs for efficient quantum state preparation, Tensor Network states, and QCNNs for classifying quantum states on classical hardware. For benchmarking quantum simulators, the QCQ architecture utilizes the cuQuantum SDK to leverage multi-GPU acceleration, integrated with PennyLane's Lightning plugin, demonstrating up to tenfold increases in computational speed for complex phase transition classification tasks compared to traditional CPU-based methods. This significant acceleration enables models such as the transverse field Ising and XXZ systems to accurately predict phase transitions with a 99.5% accuracy. The architecture's ability to distribute computation between QPUs and classical resources addresses critical bottlenecks in Quantum-HPC, paving the way for scalable quantum simulation. The QCQ framework embodies a synergistic combination of quantum algorithms, machine learning, and Quantum-HPC capabilities, enhancing its potential to provide transformative insights into the behavior of quantum systems across different scales. As quantum hardware continues to improve, this hybrid distribution-aware framework will play a crucial role in realizing the full potential of quantum computing by seamlessly integrating distributed quantum resources with the state-of-the-art classical computing infrastructure.
In this paper, we present two multidimensional power flow formulations based on a fixed-point iteration (FPI) algorithm to efficiently solve hundreds of thousands of power flows in distribution systems. The presented algorithms are the base for a new TensorPowerFlow (TPF) tool and shine for their simplicity, benefiting from multicore \gls{cpu} and \gls{gpu} parallelization. We also focus on the mathematical convergence properties of the algorithm, showing that its unique solution is at the practical operational point, which is the solution of high-voltage and low-current. The proof is validated using numerical simulations showing the robustness of the FPI algorithm compared to the classical \gls{nr} approach. In the case study, a benchmark with different PF solution methods is performed, showing that for applications requiring a yearly simulation at 1-minute resolution the computation time is decreased by a factor of 164, compared to the NR in its sparse formulation.
The integration of sensing capabilities into communication systems, by sharing physical resources, has a significant potential for reducing spectrum, hardware, and energy costs while inspiring innovative applications. Cooperative networks, in particular, are expected to enhance sensing services by enlarging the coverage area and enriching sensing measurements, thus improving the service availability and accuracy. This paper proposes a cooperative integrated sensing and communication (ISAC) framework by leveraging information-bearing orthogonal frequency division multiplexing (OFDM) signals transmitted by access points (APs). Specifically, we propose a two-stage scheme for target localization, where communication signals are reused as sensing reference signals based on the system information shared at the central processing unit (CPU). In Stage I, we propose a twodimensional fast Fourier transform (2D-FFT)-based algorithm to measure the ranges of scattered paths induced by targets, through the extraction of delay and Doppler information from the sensing channels between APs. Then, the target locations are estimated in Stage II based on these range measurements. Considering the potential occurrence of ill-conditioned measurements with large error during the extraction of time-frequency information, we propose an efficient algorithm to match the range measurements with the targets while eliminating ill-onditioned measurements, achieving high-accuracy target localization. In addition, based on the transmission configurations defined in the fifth generation (5G) standards, we elucidate the performance trade-offs in both communication and sensing, and extend the proposed sensing scheme for general scenarios. Finally, numerical results confirm the effectiveness of our sensing scheme and the cooperative gain of the ISAC framework.
In lung radiotherapy, infrared cameras can track reflective objects on the chest to estimate tumor motion due to breathing, but treatment system latencies hinder radiation beam precision. Real-time recurrent learning (RTRL) is a potential solution that can learn patterns within non-stationary respiratory data but has high complexity. This study assesses the capabilities of resource-efficient online RNN algorithms, namely unbiased online recurrent optimization (UORO), sparse-1 step approximation (SnAp-1), and decoupled neural interfaces (DNI) to forecast respiratory motion during radiotherapy treatment accurately. We use time series containing the 3D positions of external markers on the chest of healthy subjects. We propose efficient implementations for SnAp-1 and DNI that compress the influence and immediate Jacobian matrices and accurately update the linear coefficients used in credit assignment estimation, respectively. Data was originally sampled at 10Hz; we resampled it at 3.33Hz and 30Hz to analyze the effect of the sampling rate on performance. We use UORO, SnAp-1, and DNI to forecast each marker's 3D position with horizons h<=2.1s (the time interval in advance for which the prediction is made) and compare them with RTRL, least mean squares, kernel support vector regression, and linear regression. RNNs trained online achieved similar or better accuracy than most previous works using larger training databases and deep learning, even though we used only the first minute of each sequence to predict motion within that exact sequence. SnAp-1 had the lowest normalized root mean square errors (nRMSEs) averaged over the horizon values considered, equal to 0.335 and 0.157, at 3.33Hz and 10.0Hz, respectively. Similarly, UORO had the lowest nRMSE at 30Hz, equal to 0.086. DNI's inference time (6.8ms per time step at 30Hz, Intel Core i7-13700 CPU) was the lowest among the RNN methods.
Given 2D point correspondences between an image pair, inferring the camera motion is a fundamental issue in the computer vision community. The existing works generally set out from the epipolar constraint and estimate the essential matrix, which is not optimal in the maximum likelihood (ML) sense. In this paper, we dive into the original measurement model with respect to the rotation matrix and normalized translation vector and formulate the ML problem. We then propose a two-step algorithm to solve it: In the first step, we estimate the variance of measurement noises and devise a consistent estimator based on bias elimination; In the second step, we execute a one-step Gauss-Newton iteration on manifold to refine the consistent estimate. We prove that the proposed estimate owns the same asymptotic statistical properties as the ML estimate: The first is consistency, i.e., the estimate converges to the ground truth as the point number increases; The second is asymptotic efficiency, i.e., the mean squared error of the estimate converges to the theoretical lower bound -- Cramer-Rao bound. In addition, we show that our algorithm has linear time complexity. These appealing characteristics endow our estimator with a great advantage in the case of dense point correspondences. Experiments on both synthetic data and real images demonstrate that when the point number reaches the order of hundreds, our estimator outperforms the state-of-the-art ones in terms of estimation accuracy and CPU time.
Large language model inference on Central Processing Units (CPU) is challenging due to the vast quantities of expensive Multiply-Add (MAD) matrix operations in the attention computations. In this paper, we argue that there is a rare gem in modern CPUs, Single-Instruction-Multiple-Data (SIMD) registers, which allow for ultra-low-latency lookups in batch. We leverage this unique capability of CPUs to propose NoMAD-Attention, an efficient attention algorithm that replaces MAD operations with in-register lookups. Through hardware-aware algorithmic designs, NoMAD-Attention achieves the computation of attention scores using repeated fast accesses to SIMD registers despite their highly limited sizes. Moreover, NoMAD-Attention works with pre-trained attention-based LLMs without model finetuning. Empirical evaluations demonstrate that NoMAD-Attention maintains the quality of the original LLMs well, and speeds up the 4-bit quantized LLaMA-7B-based model by up to 2$\times$ at 16k context length. Our results are reproducible at https://github.com/tonyzhang617/nomad-dist.
Traditional deep learning often overlooks bytes, the basic units of the digital world, where all forms of information and operations are encoded and manipulated in binary format. Inspired by the success of next token prediction in natural language processing, we introduce bGPT, a model with next byte prediction to simulate the digital world. bGPT matches specialized models in performance across various modalities, including text, audio, and images, and offers new possibilities for predicting, simulating, and diagnosing algorithm or hardware behaviour. It has almost flawlessly replicated the process of converting symbolic music data, achieving a low error rate of 0.0011 bits per byte in converting ABC notation to MIDI format. In addition, bGPT demonstrates exceptional capabilities in simulating CPU behaviour, with an accuracy exceeding 99.99% in executing various operations. Leveraging next byte prediction, models like bGPT can directly learn from vast binary data, effectively simulating the intricate patterns of the digital world.
Side-channel attacks allow extracting secret information from the execution of cryptographic primitives by correlating the partially known computed data and the measured side-channel signal. However, to set up a successful side-channel attack, the attacker has to perform i) the challenging task of locating the time instant in which the target cryptographic primitive is executed inside a side-channel trace and then ii)the time-alignment of the measured data on that time instant. This paper presents a novel deep-learning technique to locate the time instant in which the target computed cryptographic operations are executed in the side-channel trace. In contrast to state-of-the-art solutions, the proposed methodology works even in the presence of trace deformations obtained through random delay insertion techniques. We validated our proposal through a successful attack against a variety of unprotected and protected cryptographic primitives that have been executed on an FPGA-implemented system-on-chip featuring a RISC-V CPU.
Recently, the increasing use of deep reinforcement learning for flow control problems has led to a new area of research, focused on the coupling and the adaptation of the existing algorithms to the control of numerical fluid dynamics environments. Although still in its infancy, the field has seen multiple successes in a short time span, and its fast development pace can certainly be partly imparted to the open-source effort that drives the expansion of the community. Yet, this emerging domain still misses a common ground to (i) ensure the reproducibility of the results, and (ii) offer a proper ad-hoc benchmarking basis. To this end, we propose Beacon, an open-source benchmark library composed of seven lightweight 1D and 2D flow control problems with various characteristics, action and observation space characteristics, and CPU requirements. In this contribution, the seven considered problems are described, and reference control solutions are provided. The sources for the following work are available at https://github.com/jviquerat/beacon.
Graph Neural Networks (GNNs) are emerging ML models to analyze graph-structure data. Graph Neural Network (GNN) execution involves both compute-intensive and memory-intensive kernels, the latter dominates the total time, being significantly bottlenecked by data movement between memory and processors. Processing-In-Memory (PIM) systems can alleviate this data movement bottleneck by placing simple processors near or inside to memory arrays. In this work, we introduce PyGim, an efficient ML library that accelerates GNNs on real PIM systems. We propose intelligent parallelization techniques for memory-intensive kernels of GNNs tailored for real PIM systems, and develop handy Python API for them. We provide hybrid GNN execution, in which the compute-intensive and memory-intensive kernels are executed in processor-centric and memory-centric computing systems, respectively. We extensively evaluate PyGim on a real-world PIM system with 1992 PIM cores using emerging GNN models, and demonstrate that it outperforms its state-of-the-art CPU counterpart on Intel Xeon by on average 3.04x, and achieves higher resource utilization than CPU and GPU systems. Our work provides useful recommendations for software, system and hardware designers. PyGim is publicly available at https://github.com/CMU-SAFARI/PyGim.
In this work, we propose an optimization framework for estimating a sparse robust one-dimensional subspace. Our objective is to minimize both the representation error and the penalty, in terms of the l1-norm criterion. Given that the problem is NP-hard, we introduce a linear relaxation-based approach. Additionally, we present a novel fitting procedure, utilizing simple ratios and sorting techniques. The proposed algorithm demonstrates a worst-case time complexity of $O(n^2 m \log n)$ and, in certain instances, achieves global optimality for the sparse robust subspace, thereby exhibiting polynomial time efficiency. Compared to extant methodologies, the proposed algorithm finds the subspace with the lowest discordance, offering a smoother trade-off between sparsity and fit. Its architecture affords scalability, evidenced by a 16-fold improvement in computational speeds for matrices of 2000x2000 over CPU version. Furthermore, this method is distinguished by several advantages, including its independence from initialization and deterministic and replicable procedures. Furthermore, this method is distinguished by several advantages, including its independence from initialization and deterministic and replicable procedures. The real-world example demonstrates the effectiveness of algorithm in achieving meaningful sparsity, underscoring its precise and useful application across various domains.
A cell-free network merged with active reconfigurable reflecting surfaces (RIS) is investigated in this paper. Based on the imperfect channel state information (CSI), the aggregated channel from the user to the access point (AP) is initially estimated using the linear minimum mean square error (LMMSE) technique. The central processing unit (CPU) then detects uplink data from individual users through the utilization of the maximum ratio combining (MRC) approach, relying on the estimated channel. Then, a closed-form expression for uplink spectral efficiency (SE) is derived which demonstrates its reliance on statistical CSI (S-CSI) alone. The amplitude gain of each active RIS element is derived in a closed-form expression as a function of the number of active RIS elements, the number of users, and the size of each reflecting element. A soft actor-critic (SAC) algorithm is utilized to design the phase shift of the active RIS to maximize the uplink SE. Simulation results emphasize the robustness of the proposed SAC algorithm, showcasing its effectiveness in cell-free networks under the influence of imperfect CSI.
In this work we show that the size versus accuracy trade-off of neural network quantization can be significantly improved by increasing the quantization dimensionality. We propose the GPTVQ method, a new fast method for post-training vector quantization (VQ) that scales well to Large Language Models (LLMs). Our method interleaves quantization of one or more columns with updates to the remaining unquantized weights, using information from the Hessian of the per-layer output reconstruction MSE. Quantization codebooks are initialized using an efficient data-aware version of the EM algorithm. The codebooks are then updated, and further compressed by using integer quantization and SVD-based compression. GPTVQ establishes a new state-of-the art in the size vs accuracy trade-offs on a wide range of LLMs such as Llama-v2 and Mistral. Furthermore, our method is efficient: on a single H100 it takes between 3 and 11 hours to process a Llamav2-70B model, depending on quantization setting. Lastly, with on-device timings for VQ decompression on a mobile CPU we show that VQ leads to improved latency compared to using a 4-bit integer format.