Journal of Parallel and Distributed Computing

As convolution layers have been proved to be the most time-consuming operation in convolutional neural network (CNN) algorithms, many efficient CNN accelerators have been designed to boost the performance of convolution operations. Previous works ...

• A dataflow optimization method for efficient design space explorations is proposed.
• It narrows the design space and enumerates solutions to select the optimal variables.
• The optimization is validated on accelerator for computing ...

The definition of protein structures is an important research topic in molecular biology currently, since there is a direct relationship between the function of the protein in the organism and the 3D geometric configuration it adopts. The ...

• We propose an adaptive strategy to better adapt the protein folding simulation box.
• We include atomic burial forces to enhance parallel protein folding simulation.
• We show that our techniques are able to reduce the simulation time.

Cloud storage auditing is a technique that enables a user to remotely check the integrity of the outsourced data in the cloud storage. Although researchers have proposed various protocols for cloud storage auditing, the proposed schemes are ...

• We conducted real-world requirement analysis of a cloud storage auditing system.
• We proposed, implemented, open-sourced, and evaluated a practical cloud storage auditing system.
• We also presented a cost model that allows a user to ...

In order to deal with the fast changing requirements of container based services in clouds, auto-scaling is used as an essential mechanism for adapting the number of provisioned resources with the variable service workloads. However, the latest ...

• We design a hybrid auto-scaling system architecture for multi-type cloud services.
• We propose a workload prediction model based on ensemble learning.
• We propose a DRL based auto-scaling mechanism for multi-type cloud services.
• ...

The cloud-edge-end architecture satisfies the execution requirements of various workflow applications. However, owing to the diversity of resources, the complex hierarchical structure, and different privacy requirements for users, determining how ...

• We investigated the workflow scheduling with end-edge-cloud severs to minimize the rental cost with deadline constraints.
• An algorithm is proposed for workflows with multi-privacy level tasks including partition, generation, scheduling,...

Comprehensive workload characterization plays a pivotal role in comprehending Spark applications, as it enables the analysis of diverse aspects and behaviors. This understanding is indispensable for devising downstream tuning objectives, such as ...

• Building robust and scalable workload vector descriptors in a generic manner.
• Recognizing workload patterns in latent space using unsupervised ML techniques.
• Evaluates 24 Spark workloads with geometric, internal, and external ...

While it is now routine to search for data on a personal computer or discover data online, there is no such equivalent method for discovering data on large parallel and distributed file systems commonly deployed on HPC systems. In contrast to web ...