Sparse matrices are an integral part of scientific simulations. As hardware evolves new sparse matrix storage formats are proposed aiming to exploit optimizations specific to the new hardware. In the era of heterogeneous computing, users often are required to use multiple formats for their applications to remain optimal across the different available hardware, resulting in larger development times and maintenance overhead. A potential solution to this problem is the use of a lightweight auto-tuner driven by Machine Learning (ML) that would select for the user an optimal format from a pool of available formats that will match the characteristics of the sparsity pattern, target hardware and operation to execute. In this paper, we introduce Morpheus-Oracle, a library that provides a lightweight ML auto-tuner capable of accurately predicting the optimal format across multiple backends, targeting the major HPC architectures aiming to eliminate any format selection input by the end-user. From more than 2000 real-life matrices, we achieve an average classification accuracy and balanced accuracy of 92.63% and 80.22% respectively across the available systems. The adoption of the auto-tuner results in average speedup of 1.1x on CPUs and 1.5x to 8x on NVIDIA and AMD GPUs, with maximum speedups reaching up to 7x and 1000x respectively.
相關內容
Integer linear programming models a wide range of practical combinatorial optimization problems and has significant impacts in industry and management sectors. This work develops the first standalone local search solver for general integer linear programming validated on a large heterogeneous problem dataset. We propose a local search framework that switches in three modes, namely Search, Improve, and Restore modes, and design tailored operators adapted to different modes, thus improve the quality of the current solution according to different situations. For the Search and Restore modes, we propose an operator named tight move, which adaptively modifies variables' values trying to make some constraint tight. For the Improve mode, an efficient operator lift move is proposed to improve the quality of the objective function while maintaining feasibility. Putting these together, we develop a local search solver for integer linear programming called Local-ILP. Experiments conducted on the MIPLIB dataset show the effectiveness of our solver in solving large-scale hard integer linear programming problems within a reasonably short time. Local-ILP is competitive and complementary to the state-of-the-art commercial solver Gurobi and significantly outperforms the state-of-the-art non-commercial solver SCIP. Moreover, our solver establishes new records for 6 MIPLIB open instances.
Theoretical studies on transfer learning or domain adaptation have so far focused on situations with a known hypothesis class or model; however in practice, some amount of model selection is usually involved, often appearing under the umbrella term of hyperparameter-tuning: for example, one may think of the problem of tuning for the right neural network architecture towards a target task, while leveraging data from a related source task. Now, in addition to the usual tradeoffs on approximation vs estimation errors involved in model selection, this problem brings in a new complexity term, namely, the transfer distance between source and target distributions, which is known to vary with the choice of hypothesis class. We present a first study of this problem, focusing on classification; in particular, the analysis reveals some remarkable phenomena: adaptive rates, i.e., those achievable with no distributional information, can be arbitrarily slower than oracle rates, i.e., when given knowledge on distances.
Small-scale automation services in Software Engineering, known as SE Bots, have gradually infiltrated every aspect of daily software development with the goal of enhancing productivity and well-being. While leading the OSS development, elite developers have often burned out from holistic responsibilities in projects and looked for automation support. Building on prior research in BotSE and our interviews with elite developers, this paper discusses how to design and implement SE bots that integrate into the workflows of elite developers and meet their expectations. We present six main design guidelines for implementing SE bots for elite developers, based on their concerns about noise, security, simplicity, and other factors. Additionally, we discuss the future directions of SE bots, especially in supporting elite developers' increasing workload due to rising demands.
Web browsers have come a long way since their inception, evolving from a simple means of displaying text documents over the network to complex software stacks with advanced graphics and network capabilities. As personal computers grew in popularity, developers jumped at the opportunity to deploy cross-platform games with centralized management and a low barrier to entry. Simply going to the right address is now enough to start a game. From text-based to GPU-powered 3D games, browser gaming has evolved to become a strong alternative to traditional console and mobile-based gaming, targeting both casual and advanced gamers. Browser technology has also evolved to accommodate more demanding applications, sometimes even supplanting functions typically left to the operating system. Today, websites display rich, computationally intensive, hardware-accelerated graphics, allowing developers to build ever-more impressive applications and games.In this paper, we present the evolution of browser gaming and the technologies that enabled it, from the release of the first text-based games in the early 1990s to current open-world and game-engine-powered browser games. We discuss the societal impact of browser gaming and how it has allowed a new target audience to accessdigital gaming. Finally, we review the potential future evolution ofthe browser gaming industry.
Widely used compilers like GCC and LLVM usually have hundreds of optimizations controlled by optimization flags, which are enabled or disabled during compilation to improve runtime performance (e.g., small execution time) of the compiler program. Due to the large number of optimization flags and their combination, it is difficult for compiler users to manually tune compiler optimization flags. In the literature, a number of auto-tuning techniques have been proposed, which tune optimization flags for a compiled program by comparing its actual runtime performance with different optimization flag combination. Due to the huge search space and heavy actual runtime cost, these techniques suffer from the widely-recognized efficiency problem. To reduce the heavy runtime cost, in this paper we propose a lightweight learning approach which uses a small number of actual runtime performance data to predict the runtime performance of a compiled program with various optimization flag combination. Furthermore, to reduce the search space, we design a novel particle swarm algorithm which tunes compiler optimization flags with the prediction model. To evaluate the performance of the proposed approach CompTuner, we conduct an extensive experimental study on two popular C compilers GCC and LLVM with two widely used benchmarks cBench and PolyBench. The experimental results show that CompTuner significantly outperforms the five compared techniques, including the state-of-art technique BOCA.
Deep neural networks (DNNs) have succeeded in many different perception tasks, e.g., computer vision, natural language processing, reinforcement learning, etc. The high-performed DNNs heavily rely on intensive resource consumption. For example, training a DNN requires high dynamic memory, a large-scale dataset, and a large number of computations (a long training time); even inference with a DNN also demands a large amount of static storage, computations (a long inference time), and energy. Therefore, state-of-the-art DNNs are often deployed on a cloud server with a large number of super-computers, a high-bandwidth communication bus, a shared storage infrastructure, and a high power supplement. Recently, some new emerging intelligent applications, e.g., AR/VR, mobile assistants, Internet of Things, require us to deploy DNNs on resource-constrained edge devices. Compare to a cloud server, edge devices often have a rather small amount of resources. To deploy DNNs on edge devices, we need to reduce the size of DNNs, i.e., we target a better trade-off between resource consumption and model accuracy. In this dissertation, we studied four edge intelligence scenarios, i.e., Inference on Edge Devices, Adaptation on Edge Devices, Learning on Edge Devices, and Edge-Server Systems, and developed different methodologies to enable deep learning in each scenario. Since current DNNs are often over-parameterized, our goal is to find and reduce the redundancy of the DNNs in each scenario.
Classic algorithms and machine learning systems like neural networks are both abundant in everyday life. While classic computer science algorithms are suitable for precise execution of exactly defined tasks such as finding the shortest path in a large graph, neural networks allow learning from data to predict the most likely answer in more complex tasks such as image classification, which cannot be reduced to an exact algorithm. To get the best of both worlds, this thesis explores combining both concepts leading to more robust, better performing, more interpretable, more computationally efficient, and more data efficient architectures. The thesis formalizes the idea of algorithmic supervision, which allows a neural network to learn from or in conjunction with an algorithm. When integrating an algorithm into a neural architecture, it is important that the algorithm is differentiable such that the architecture can be trained end-to-end and gradients can be propagated back through the algorithm in a meaningful way. To make algorithms differentiable, this thesis proposes a general method for continuously relaxing algorithms by perturbing variables and approximating the expectation value in closed form, i.e., without sampling. In addition, this thesis proposes differentiable algorithms, such as differentiable sorting networks, differentiable renderers, and differentiable logic gate networks. Finally, this thesis presents alternative training strategies for learning with algorithms.
Since the 1950s, machine translation (MT) has become one of the important tasks of AI and development, and has experienced several different periods and stages of development, including rule-based methods, statistical methods, and recently proposed neural network-based learning methods. Accompanying these staged leaps is the evaluation research and development of MT, especially the important role of evaluation methods in statistical translation and neural translation research. The evaluation task of MT is not only to evaluate the quality of machine translation, but also to give timely feedback to machine translation researchers on the problems existing in machine translation itself, how to improve and how to optimise. In some practical application fields, such as in the absence of reference translations, the quality estimation of machine translation plays an important role as an indicator to reveal the credibility of automatically translated target languages. This report mainly includes the following contents: a brief history of machine translation evaluation (MTE), the classification of research methods on MTE, and the the cutting-edge progress, including human evaluation, automatic evaluation, and evaluation of evaluation methods (meta-evaluation). Manual evaluation and automatic evaluation include reference-translation based and reference-translation independent participation; automatic evaluation methods include traditional n-gram string matching, models applying syntax and semantics, and deep learning models; evaluation of evaluation methods includes estimating the credibility of human evaluations, the reliability of the automatic evaluation, the reliability of the test set, etc. Advances in cutting-edge evaluation methods include task-based evaluation, using pre-trained language models based on big data, and lightweight optimisation models using distillation techniques.
Modern neural network training relies heavily on data augmentation for improved generalization. After the initial success of label-preserving augmentations, there has been a recent surge of interest in label-perturbing approaches, which combine features and labels across training samples to smooth the learned decision surface. In this paper, we propose a new augmentation method that leverages the first and second moments extracted and re-injected by feature normalization. We replace the moments of the learned features of one training image by those of another, and also interpolate the target labels. As our approach is fast, operates entirely in feature space, and mixes different signals than prior methods, one can effectively combine it with existing augmentation methods. We demonstrate its efficacy across benchmark data sets in computer vision, speech, and natural language processing, where it consistently improves the generalization performance of highly competitive baseline networks.
Recently, deep learning has achieved very promising results in visual object tracking. Deep neural networks in existing tracking methods require a lot of training data to learn a large number of parameters. However, training data is not sufficient for visual object tracking as annotations of a target object are only available in the first frame of a test sequence. In this paper, we propose to learn hierarchical features for visual object tracking by using tree structure based Recursive Neural Networks (RNN), which have fewer parameters than other deep neural networks, e.g. Convolutional Neural Networks (CNN). First, we learn RNN parameters to discriminate between the target object and background in the first frame of a test sequence. Tree structure over local patches of an exemplar region is randomly generated by using a bottom-up greedy search strategy. Given the learned RNN parameters, we create two dictionaries regarding target regions and corresponding local patches based on the learned hierarchical features from both top and leaf nodes of multiple random trees. In each of the subsequent frames, we conduct sparse dictionary coding on all candidates to select the best candidate as the new target location. In addition, we online update two dictionaries to handle appearance changes of target objects. Experimental results demonstrate that our feature learning algorithm can significantly improve tracking performance on benchmark datasets.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191