FPGAs are quickly becoming available in the cloud as a one more heterogeneous processing element complementing CPUs and GPUs. There are many reports in the literature showing the potential for FPGAs to accelerate a wide variety of algorithms, which combined with their growing availability, would seem to also indicate a widespread use in many applications. Unfortunately, there is not much published research exploring what it takes to integrate an FPGA into an existing application in a cost-effective way and keeping the algorithmic performance advantages. Building on recent results exploring how to employ FPGAs to improve the search engines used in the travel industry, this paper analyses the end-to-end performance of the search engine when using FPGAs, as well as the necessary changes to the software and the cost of such deployments. The results provide important insights on current FPGA deployments and what needs to be done to make FPGAs more widely used. For instance, the large potential performance gains provided by an FPGA are greatly diminished in practice if the application cannot submit request in the most optimal way, something that is not always possible and might require significant changes to the application. Similarly, some existing cloud deployments turn out to use a very imbalanced architecture: a powerful FPGA connected to a not so powerful CPU. The result is that the CPU cannot generate enough load for the FPGA, which potentially eliminates all performance gains and might even result in a more expensive system. In this paper, we report on an extensive study and development effort to incorporate FPGAs into a search engine and analyse the issues encountered and their practical impact. We expect that these results will inform the development and deployment of FPGAs in the future by providing important insights on the end-to-end integration of FPGAs within existing systems.
相關內容
The civil aviation community is actively exploring and developing the solutions of single pilot operations SPO for large commercial aircraft. Human factors engineering research for SPO has been launched, and the research mainly focuses on three research solutions: flight deck airborne equipment upgrade, flight support from ground stations, and the combined SPO solution of "flight deck airborne equipment upgrade, flight support from ground stations". This paper reviews and analyzez the progress of human factors engineering research on SPO. The preliminary research outcome tends to support the combined SPO solution. However, the current human factors engineering research is not comprehensive and cannot provide a complete human factors engineering solution for SPO. For future human factors engineering research, this paper analyzes the key human factors issues on SPO and points out the gaps in the current research and the areas for future work. Finally, this paper puts forward an overall strategy and recommendations for future human factors engineering research on SPO.
While search technologies have evolved to be robust and ubiquitous, the fundamental interaction paradigm has remained relatively stable for decades. With the maturity of the Brain-Machine Interface, we build an efficient and effective communication system between human beings and search engines based on electroencephalogram~(EEG) signals, called Brain-Machine Search Interface(BMSI) system. The BMSI system provides functions including query reformulation and search result interaction. In our system, users can perform search tasks without having to use the mouse and keyboard. Therefore, it is useful for application scenarios in which hand-based interactions are infeasible, e.g, for users with severe neuromuscular disorders. Besides, based on brain signals decoding, our system can provide abundant and valuable user-side context information(e.g., real-time satisfaction feedback, extensive context information, and a clearer description of information needs) to the search engine, which is hard to capture in the previous paradigm. In our implementation, the system can decode user satisfaction from brain signals in real-time during the interaction process and re-rank the search results list based on user satisfaction feedback. The demo video is available at //www.thuir.cn/group/YQLiu/datasets/BMSISystem.mp4.
It requires significant energy to manufacture and deploy computational devices. Traditional discussions of the energy-efficiency of compute measure operational energy, i.e.\ how many FLOPS in a 50\,MW datacenter. However, if we consider the true lifetime energy use of modern devices, the majority actually comes not from runtime use but from manufacture and deployment. In this paper, then, we suggest that perhaps the most climate-impactful action we can take is to extend the service lifetime of existing compute. We design two new metrics to measure how to balance continued service of older devices with the superlinear runtime improvements of newer machines. The first looks at carbon per raw compute, amortized across the operation and manufacture of devices. The second considers use of components beyond compute, such as batteries or radios in smartphone platforms. We use these metrics to redefine device service lifetime in terms of carbon efficiency. We then realize a real-world ``junkyard datacenter'' made up of Nexus 4 and Nexus 5 phones, which are nearly a decade past their official end-of-life dates. This new-old datacenter is able to nearly match and occasionally exceed modern cloud compute offerings.
Designing complex architectures has been an essential cogwheel in the revolution deep learning has brought about in the past decade. When solving difficult problems in a datadriven manner, a well-tried approach is to take an architecture discovered by renowned deep learning scientists as a basis (e.g. Inception) and try to apply it to a specific problem. This might be sufficient, but as of now, achieving very high accuracy on a complex or yet unsolved task requires the knowledge of highly-trained deep learning experts. In this work, we would like to contribute to the area of Automated Machine Learning (AutoML), specifically Neural Architecture Search (NAS), which intends to make deep learning methods available for a wider range of society by designing neural topologies automatically. Although several different approaches exist (e.g. gradient-based or evolutionary algorithms), our focus is on one of the most promising research directions, reinforcement learning. In this scenario, a recurrent neural network (controller) is trained to create problem-specific neural network architectures (child). The validation accuracies of the child networks serve as a reward signal for training the controller with reinforcement learning. The basis of our proposed work is Efficient Neural Architecture Search (ENAS), where parameter sharing is applied among the child networks. ENAS, like many other RL-based algorithms, emphasize the learning of child networks as increasing their convergence result in a denser reward signal for the controller, therefore significantly reducing training times. The controller was originally trained with REINFORCE. In our research, we propose to modify this to a more modern and complex algorithm, PPO, which has demonstrated to be faster and more stable in other environments. Then, we briefly discuss and evaluate our results.
Robots in our daily surroundings are increasing day by day. Their usability and acceptability largely depend on their explicit and implicit interaction capability with fellow human beings. As a result, social behavior is one of the most sought-after qualities that a robot can possess. However, there is no specific aspect and/or feature that defines socially acceptable behavior and it largely depends on the situation, application, and society. In this article, we investigate one such social behavior for collocated robots. Imagine a group of people is interacting with each other and we want to join the group. We as human beings do it in a socially acceptable manner, i.e., within the group, we do position ourselves in such a way that we can participate in the group activity without disturbing/obstructing anybody. To possess such a quality, first, a robot needs to determine the formation of the group and then determine a position for itself, which we humans do implicitly. The theory of f-formation can be utilized for this purpose. As the types of formations can be very diverse, detecting the social groups is not a trivial task. In this article, we provide a comprehensive survey of the existing work on social interaction and group detection using f-formation for robotics and other applications. We also put forward a novel holistic survey framework combining all the possible concerns and modules relevant to this problem. We define taxonomies based on methods, camera views, datasets, detection capabilities and scale, evaluation approaches, and application areas. We discuss certain open challenges and limitations in current literature along with possible future research directions based on this framework. In particular, we discuss the existing methods/techniques and their relative merits and demerits, applications, and provide a set of unsolved but relevant problems in this domain.
Threats associated with the untrusted fabrication of integrated circuits (ICs) are numerous: piracy, overproduction, reverse engineering, hardware trojans, etc. The use of reconfigurable elements (i.e., look-up tables as in FPGAs) is a known obfuscation technique. In the extreme case, when the circuit is entirely implemented as an FPGA, no information is revealed to the adversary but at a high cost in area, power, and performance. In the opposite extreme, when the same circuit is implemented as an ASIC, best-in-class performance is obtained but security is compromised. This paper investigates an intermediate solution between these two. Our results are supported by a custom CAD tool that explores this FPGA-ASIC design space and enables a standard-cell based physical synthesis flow that is flexible and compatible with current design practices. Layouts are presented for obfuscated circuits in a 65nm commercial technology, demonstrating the attained obfuscation both graphically and quantitatively. Furthermore, our security analysis revealed that for truly hiding the circuit's intent (not only portions of its structure), the obfuscated design also has to chiefly resemble an FPGA: only some small amount of logic can be made static for an adversary to remain unaware of what the circuit does.
This book is to help undergraduate and graduate students of electrical and computer engineering disciplines with their job interviews. It may also be used as a practice resource while taking courses in VLSI, logic and computer architecture design. The first edition consists of more than 200 problems and their solutions which the author has used in his VLSI, logic, and architectures courses while teaching at USC. The author wishes this book to be available to students and engineers free of charge, subject to the copyright policy on page 3.
To make deliberate progress towards more intelligent and more human-like artificial systems, we need to be following an appropriate feedback signal: we need to be able to define and evaluate intelligence in a way that enables comparisons between two systems, as well as comparisons with humans. Over the past hundred years, there has been an abundance of attempts to define and measure intelligence, across both the fields of psychology and AI. We summarize and critically assess these definitions and evaluation approaches, while making apparent the two historical conceptions of intelligence that have implicitly guided them. We note that in practice, the contemporary AI community still gravitates towards benchmarking intelligence by comparing the skill exhibited by AIs and humans at specific tasks such as board games and video games. We argue that solely measuring skill at any given task falls short of measuring intelligence, because skill is heavily modulated by prior knowledge and experience: unlimited priors or unlimited training data allow experimenters to "buy" arbitrary levels of skills for a system, in a way that masks the system's own generalization power. We then articulate a new formal definition of intelligence based on Algorithmic Information Theory, describing intelligence as skill-acquisition efficiency and highlighting the concepts of scope, generalization difficulty, priors, and experience. Using this definition, we propose a set of guidelines for what a general AI benchmark should look like. Finally, we present a benchmark closely following these guidelines, the Abstraction and Reasoning Corpus (ARC), built upon an explicit set of priors designed to be as close as possible to innate human priors. We argue that ARC can be used to measure a human-like form of general fluid intelligence and that it enables fair general intelligence comparisons between AI systems and humans.
Deep Learning has enabled remarkable progress over the last years on a variety of tasks, such as image recognition, speech recognition, and machine translation. One crucial aspect for this progress are novel neural architectures. Currently employed architectures have mostly been developed manually by human experts, which is a time-consuming and error-prone process. Because of this, there is growing interest in automated neural architecture search methods. We provide an overview of existing work in this field of research and categorize them according to three dimensions: search space, search strategy, and performance estimation strategy.
Music recommender systems (MRS) have experienced a boom in recent years, thanks to the emergence and success of online streaming services, which nowadays make available almost all music in the world at the user's fingertip. While today's MRS considerably help users to find interesting music in these huge catalogs, MRS research is still facing substantial challenges. In particular when it comes to build, incorporate, and evaluate recommendation strategies that integrate information beyond simple user--item interactions or content-based descriptors, but dig deep into the very essence of listener needs, preferences, and intentions, MRS research becomes a big endeavor and related publications quite sparse. The purpose of this trends and survey article is twofold. We first identify and shed light on what we believe are the most pressing challenges MRS research is facing, from both academic and industry perspectives. We review the state of the art towards solving these challenges and discuss its limitations. Second, we detail possible future directions and visions we contemplate for the further evolution of the field. The article should therefore serve two purposes: giving the interested reader an overview of current challenges in MRS research and providing guidance for young researchers by identifying interesting, yet under-researched, directions in the field.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191