Locality-Aware CTA Scheduling for Gaming Applications

The compute work rasterizer or the GigaThread Engine of a modern NVIDIA GPU focuses on maximizing compute work occupancy across all streaming multiprocessors in a GPU while retaining design simplicity. In this article, we identify the operational aspects of the GigaThread Engine that help it meet those goals but also lead to less-than-ideal cache locality for texture accesses in 2D compute shaders, which are an important optimization target for gaming applications. We develop three software techniques, namely LargeCTAs , Swizzle , and Agents , to show that it is possible to effectively exploit the texture data working set overlap intrinsic to 2D compute shaders. We evaluate these techniques on gaming applications across two generations of NVIDIA GPUs, RTX 2080 and RTX 3080, and find that they are effective on both GPUs. We find that the bandwidth savings from all our software techniques on RTX 2080 is much higher than the bandwidth savings on baseline execution from inter-generational cache capacity increase going from RTX 2080 to RTX 3080. Our best-performing technique, Agents , records up to a 4.7% average full-frame speedup by reducing bandwidth demand of targeted shaders at the L1-L2 and L2-DRAM interfaces by 23% and 32%, respectively, on the latest generation RTX 3080. These results acutely highlight the sensitivity of cache locality to compute work rasterization order and the importance of locality-aware cooperative thread array scheduling for gaming applications.

Machine Learning at the Network Edge: A Survey

Resource-constrained IoT devices, such as sensors and actuators, have become ubiquitous in recent years. This has led to the generation of large quantities of data in real-time, which is an appealing target for AI systems. However, deploying machine learning models on such end-devices is nearly impossible. A typical solution involves offloading data to external computing systems (such as cloud servers) for further processing but this worsens latency, leads to increased communication costs, and adds to privacy concerns. To address this issue, efforts have been made to place additional computing devices at the edge of the network, i.e., close to the IoT devices where the data is generated. Deploying machine learning systems on such edge computing devices alleviates the above issues by allowing computations to be performed close to the data sources. This survey describes major research efforts where machine learning systems have been deployed at the edge of computer networks, focusing on the operational aspects including compression techniques, tools, frameworks, and hardware used in successful applications of intelligent edge systems.

Reshaping Beverage Retail in Urban Communities Through a Connected Platform

Business organisations are attempting to transform themselves according to the paradigms of Industry 4.0. This chapter presents the case of Tapfrsh kiosk, an internet of things (IoT)-based beverage service platform for urban communities. It discusses the business ecosystem, system design, technology usage, machine design, aesthetics, and operational aspects of the Tapfrsh kiosk. The authors include a critical commentary on the kiosk using a multidimensional lens. Entrepreneurial insights are discussed.

Analysing the prospect of the maritime common information sharing environment’s implementation and feasibility in Montenegro

This paper outlines an extensive analysis of the case of Montenegro’s maritime surveillance system becoming integrated within the European Common Information Sharing Environment (CISE). Threats to secure maritime borders across Europe are ever-present and regularly demand coordinated efforts between the member states to tackle and prevent them, e.g. illegal immigration across the Mediterranean. Administration for Maritime Safety and Port Management (AMSPM) in Montenegro is a member of the ANDROMEDA EU project that seeks to facilitate deployments and demonstrations of CISE trials across the European regions, towards their endorsement readiness. AMSPM is now at the forefront of assessing and deploying the CISE components in Montenegro. It thus appropriately evaluates the operational aspects, observes the CISE implementations in some European states, formulates the impact for other national stakeholders, as well as the very prospect of the resulting augmented maritime surveillance in the country. This substantiates the content of this paper as the feasibility of the CISE deployment in Montenegro, supported by a snapshot of the cost-benefit analysis. We aspire to offer novel perspectives and insights that could be a universally useful experience to different CISE implementation initiatives, especially for countries or regions of similar smaller sizes and coastal area.

APPLICATION OF FUZZY FMEA TO PERFORM AN EXTENSIVE RISK ANALYSIS IN MARITIME TRANSPORTATION ENGINEERING

The nature of maritime transportation involves numerous hazards, which can lead to serious consequences for human life, marine environment and ship. Therefore, achieving a high level of safety is recognised as paramount in maritime industry (Akyuz, 2016). In order to achieve this purpose, this paper prompts a fuzzy based Failure Mode and Effects analysis (FMEA) to perform an extensive risk analysis in the maritime transportation industry. The method has capable of identifying potential failures and calculating risk priority number (RPN) by capturing nonlinear casual relationships between the failures. The proposed method is applied to hatch cover failures in operational aspects in bulk carrier ships since potential failures of hydraulic hatch covers have serious concerns for ship owners. Besides its theoretical insight, the paper has practical benefits to ship owners, superintendents as well as safety professionals by identifying potential failure and offering early corrective actions.

Applications of artificial intelligence with cloud computing in promoting social distancing to combat COVID-19

The emergence of Coronavirus disease 2019 (COVID-19) disease and its rapid spread around the world has serious impacts on people's lives in addition to its effects on many aspects, including the economic and educational sectors. Researches have proved that social distance is effective in combating COVID-19. Maintaining social distance is hard to be handled by humans especially in crowded areas such as airports and campuses. So, there is a need to apply a robust and proactive design to manage this process automatically and smartly. This paper presents a design system to fight COVID-19 by maintaining the social distance with effective monitoring for suspected cases. This has been done using cloud computing and a framework including Arduino (node microcontroller unit (NodeMCU)) with several sensors. The operational aspects of this design system using cloud computing have been discussed. Generally, NodeMCU has been involved in checking the conditions, comparison processing, and communication with the webserver. Moreover, the webserver has been used for determining the maximum number of persons allowed to enter. The results state that this design system is effective in combating COVID-19 through maintaining the social distance and collecting information about suspected cases. This system is valuable, dependable, and stable since the whole process is contactless.