A Remote Memory Sharing System for Virtualized Computing Infrastructures

Kocharyan, Aram; Ekane, Brice; Teabe, Boris; Tran, Giang Son; Astsatryan, Hrachya; Hagimont, Daniel

doi:10.1109/tcc.2020.3018089

Cited by 5 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to reduce the processing time of phase unwrapping, shared memory technology is used to improve the computational efficiency [44,45]. Prior to any calculations in phase unwrapping, the data are fetched from the embedded GPU memory and entered into the shared memory within the confines of the CUDA kernel.…”

Section: Central Processing Unit (Cpu) and Gpu Processingmentioning

confidence: 99%

Fast and accurate phase processing in off-axis digital holography combining adaptive spatial filtering and an embedded GPU platform

Bai,

Li,

Sun

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Parallel-phase processing enables rapid phase extraction from off-axis digital holograms. To achieve fast and accurate results, the phase reconstruction processes were parallelized using improved filter algorithms and optimized programming strategies. First, an adaptive filtering method based on the Chan-Vese (CV) model which better suits parallelism was designed to extract the +1 term spectrum. We selected suitable computer unified device architecture (CUDA) libraries according to the characteristics of the key phase reconstruction steps. Acceleration technologies, such as virtual memory and shared memory, were used to improve the computational efficiency. Furthermore, we combined an improved 4f optical imaging system with an embedded graphic processing unit (GPU) platform to design a low-cost phase reconstruction system for off-axis digital holography. To verify the feasibility of our method, the reconstructed quality of the CV filtering method was estimated, and the run times of phase retrieval on the central processing unit (CPU) and embedded GPU were compared for off-axis holograms with different pixel sizes. Additionally, the dynamic fluctuation phase maps of water droplet evaporation were retrieved to demonstrate the real-time capability of the method.

show abstract

Section: Central Processing Unit (Cpu) and Gpu Processingmentioning

confidence: 99%

Fast and accurate phase processing in off-axis digital holography combining adaptive spatial filtering and an embedded GPU platform

Bai,

Li,

Sun

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Premises for the design and implementation of the cloud platform following modern requirements are our offered and approved solutions in building high-performance computing infrastructures [11][12], AI-based big data gathering, classification, and processing [13][14], optimizing cloud computing environments [15], optimizing energy consumption in electronic infrastructures [16], efficiently using HPC resources in linear arithmetic calculations [17] and disposing of cloud services [18].…”

Section: Introductionmentioning

confidence: 99%

Cloud-Based Self-Organizing UAV Swarm Simulation Platform

Poghosyan,

Lazyan

et al. 2023

Proceedings of Computer Science and Information Technologies 2023 Conference

View full text Add to dashboard Cite

Unmanned aerial vehicle (UAV) swarms offer a cost-effective and time-efficient data collection and analysis solution across various applications. The study presents a cutting-edge self-organizing UAV swarm simulation platform empowered by collective artificial intelligence designed to facilitate terrain monitoring and optimize task performance using a fleet of UAVs. The cloud-based multi-user platform provides users with interactive features for seamless user collaboration and real-time video viewing for collective exploration of dynamic terrain imagery. This integrated data fuels the formation of essential swarm and target tasks, determining key parameters such as swarm participant count, initial relative coordinate positions, and statuses (imager and/or strike). The server employs advanced algorithms to achieve these functionalities, including the research road graph based on the rotor-router model and the comprehensive information exchange graph using the gossip/broadcast model. These algorithms work synergistically within the server environment, enabling efficient task planning and coordination among the UAV swarm. Furthermore, the platform allows for the seamless transmission of the formed target tasks to the memory of individual swarm participants, enhancing their decision-making capabilities and overall swarm performance.

show abstract

“…Before processing data, the framework decompresses the data if the input file is compressed in HDFS. Our recent studies show [7,8,9] that the average memory usage for selected scientific workflows is 13-17% for Hadoop and 20-40% for Spark jobs, which neglect the full utilization of the RAM of HDFS nodes. Therefore, the usage of RAM-free space may boost the performance of HDFS processing.…”

Section: Introductionmentioning

confidence: 99%

Performance-efficient Recommendation and Prediction Service for Big Data frameworks focusing on Data Compression and In-memory Data Storage Indicators

Astsatryan

Lalayan

Kocharyan³

et al. 2021

SCPE

Self Cite

View full text Add to dashboard Cite

The MapReduce framework manages Big Data sets by splitting the large datasets into a set of distributed blocks and processes them in parallel. Data compression and in-memory file systems are widely used methods in Big Data processing to reduce resource-intensive I/O operations and improve I/O rate correspondingly. The article presents a performance-efficient modular and configurable decision-making robust service relying on data compression and in-memory data storage indicators. The service consists of Recommendation and Prediction modules, predicts the execution time of a given job based on metrics, and recommends the best configuration parameters to improve Hadoop and Spark frameworks' performance. Several CPU and data-intensive applications and micro-benchmarks have been evaluated to improve the performance, including Log Analyzer, WordCount, and K-Means.

show abstract

A Remote Memory Sharing System for Virtualized Computing Infrastructures

Cited by 5 publications

References 34 publications

Fast and accurate phase processing in off-axis digital holography combining adaptive spatial filtering and an embedded GPU platform

Fast and accurate phase processing in off-axis digital holography combining adaptive spatial filtering and an embedded GPU platform

Cloud-Based Self-Organizing UAV Swarm Simulation Platform

Performance-efficient Recommendation and Prediction Service for Big Data frameworks focusing on Data Compression and In-memory Data Storage Indicators

Contact Info

Product

Resources

About