Sparse matrix multiplication (SpGEMM) is a fundamental kernel used in many diverse application areas, both numerical and discrete. For example, many algebraic graph algorithms rely on SpGEMM in the tropical semiring t...
详细信息
ISBN:
(数字)9781665498562
ISBN:
(纸本)9781665498562
Sparse matrix multiplication (SpGEMM) is a fundamental kernel used in many diverse application areas, both numerical and discrete. For example, many algebraic graph algorithms rely on SpGEMM in the tropical semiring to compute shortest paths in graphs. Recently, SpGEMM has received growing attention regarding implementations for specific (parallel) architectures. Yet, this concerns only the static problem, where both input matrices do not change. In many applications, however, matrices (or their corresponding graphs) change over time. Although recomputing from scratch is very expensive, we are not aware of any dynamic SpGEMM algorithms in the literature. In this paper, we thus propose a batch-dynamic algorithm for MPI-based parallel computing. Building on top of a distributed graph/matrix data structure that allows for fast updates, our dynamic SpGEMM reduces the communication volume significantly. It does so by exploiting that updates change far fewer matrix entries than there are non-zeros in the input operands. Our experiments with popular benchmark graphs show that our approach pays off. For batches of insertions or removals of matrix entries, our dynamic SpGEMM is substantially faster (sometimes by orders of magnitude) than the static algorithms in the state-of-the-art competitors CombBLAS, CTF and PETSc.
The recognition of human activities in a smart home is an essential prerequisite in order to derive typical behaviors and needs of the inhabitants and adapt the functions of the smart home to them. Different sensor mo...
详细信息
ISBN:
(数字)9781665483568
ISBN:
(纸本)9781665483568
The recognition of human activities in a smart home is an essential prerequisite in order to derive typical behaviors and needs of the inhabitants and adapt the functions of the smart home to them. Different sensor modalities, such as video or audio data in combination with machine learning methods can be used for this purpose. However, the use of video and audio data is associated with a strong infringement on the privacy of the inhabitants. In this paper, we present an alternative approach that uses vibrational data that is acquired by stationary wall-mounted sensors to detect a specific set of inhabitant activities using machine learning. We compare different neural-network based time series classifiers and show that is possible to detect the selected activities with up to 95% accuracy.
With the advancement of renewable energy and energy storage systems, microgrid scheduling strategies face both opportunities and challenges. In response, this paper proposes an optimization strategy for combined heat ...
详细信息
Big data's impact is driving research into efficient solutions for managing growing datasets, with a focus on distributedsystems. Recent advancements in query processing, particularly the join operator, have been...
详细信息
ISBN:
(纸本)9798400710209
Big data's impact is driving research into efficient solutions for managing growing datasets, with a focus on distributedsystems. Recent advancements in query processing, particularly the join operator, have been significant. WebAssembly (Wasm), known for its efficiency, is increasingly adopted. This project aims to evaluate the efficiency of Wasm in serverless environments, addressing challenges posed by serverless architectures and comparing Wasm-based joins against native in performance. We propose Blossom, a Rust-based experimental platform, to give insights into Wasm-based joins. Our initial results reveal trade-offs between Wasm performance and its generality.
People all over the world are subject to cyber-attacks. The abundance of information on the internet gives hackers the tools to exploit vulnerabilities in computer systems, from home desktops to the most considerable ...
详细信息
A model of a two-level hierarchical system with many participants is studied assuming that lower-level elements choose Pareto optimal outcomes. Two classes of games are studied: without feedback and with feedback. The...
详细信息
Credit card fraud has grown increasingly common in today's age, and with the rise in cybercrimes with fraud, several examples have been recorded in the past. The use of a distributed search plays a pivotal role in...
详细信息
Transformer temperature monitoring is important to power system operation and maintenance. However, there is currently a lack of in-situ monitoring methods for the internal temperature of power transformers. This pape...
详细信息
The proceedings contain 34 papers. The topics discussed include: supporting disconnected operation of stateful services using an envoy enabled dynamic microservices approach;massivizing computer systems: VU on the sci...
ISBN:
(纸本)9789897586507
The proceedings contain 34 papers. The topics discussed include: supporting disconnected operation of stateful services using an envoy enabled dynamic microservices approach;massivizing computer systems: VU on the science, design, a engineering of distributedsystems and ecosystems;towards security-aware microservices: on extracting endpoint access operations to determine access rights;enabling quantum key distribution on a multi-cloud environment to secure distributed data lakes;towards optimizing the edge-to-cloud continuum resource allocation;simulation-based estimation of resource needs in fog robotics infrastructures;supporting disconnected operation of stateful services using an envoy enabled dynamic microservices approach;optimal static bidding strategy for running jobs with hard deadline constraints on spot instances;an evaluation method and comparison of modern cluster-based highly available database solutions;and an experimental evaluation of relations between architectural and runtime metrics in microservices systems.
This report presents the development of an Intrusion Detection System (IDS) designed to detect cyber-attacks in an Internet of Vehicles (IoV) environment. The IDS employs machine learning techniques, specifically Supp...
详细信息
暂无评论