Advanced thread synchronization for multithreaded MPI implementations

HV Dang, S Seo, A Amer… - 2017 17th IEEE/ACM …, 2017 - ieeexplore.ieee.org
Concurrent multithreaded access to the Message Passing Interface (MPI) is gaining
importance to support emerging hybrid MPI applications. The interoperability between …

An efficient abortable-locking protocol for multi-level NUMA systems

M Chabbi, A Amer, S Wen, X Liu - … on Principles and Practice of Parallel …, 2017 - dl.acm.org
The popularity of Non-Uniform Memory Access (NUMA) architectures has led to numerous
locality-preserving hierarchical lock designs, such as HCLH, HMCS, and cohort locks …

Lock contention management in multithreaded mpi

A Amer, H Lu, P Balaji, M Chabbi, Y Wei… - ACM Transactions on …, 2019 - dl.acm.org
In this article, we investigate contention management in lock-based thread-safe MPI
libraries. Specifically, we make two assumptions:(1) locks are the only form of …

Using relaxed concurrent data structures for contention minimization in multithreaded MPI programs

AV Tabakov, AA Paznikov - Journal of Physics: Conference …, 2019 - iopscience.iop.org
Parallel computing is one of the top priorities in computer science. The main means of
parallel processing information is a distributed computing system (CS)-a composition of …

Optimisation of the parallel performances of a CFD solver for emerging computational platforms

F Gava - 2022 - theses.hal.science
The importance of Computational Fluid Dynamics in the industrial design process has
increased dramatically in the last two decades. This is mainly due to the technological …

Scalable Concurrency Control Methods for Modern Database Systems

JD Böttcher - 2023 - mediatum.ub.tum.de
In the era of many-core systems, we propose a hybrid lock that synchronizes the data
structures of a database system optimistically or pessimistically. Waiting threads enter a" …

An offline recognition method of handwritten primitive Manchu characters based on strokes

G Zhang, J Li, R He, A Wang - Ninth International Workshop on …, 2004 - ieeexplore.ieee.org
Probing into the features of Manchu language especially its characters or letters, the stroke
elements of primitive Manchu are defined. Then, a system of offline handwritten primitive …

Modelling of parallel threads synchronization in hybrid MPI+ Threads programs

AV Tabakov, AA Paznikov - 2019 XXII International Conference …, 2019 - ieeexplore.ieee.org
Parallel computing is one of the top priorities in computer science. The main means of
parallel processing information is a distributed computing system (CS)–a composition of …

Inter-process communication, MPI and MPICH in microkernel environment: A comparative analysis

M Khan, MA Shah - 2017 23rd International Conference on …, 2017 - ieeexplore.ieee.org
Inter-process communication (IPC) is one of the crucial aspects of every microkernel. The
message-passing interface (MPI) is a specification between different processes, which is …

[图书][B] Supporting Efficient Graph Analytics and Scientific Computation Using Asynchronous Distributed-Memory Programming Models

S Ghosh - 2019 - search.proquest.com
Abstract Future High Performance Computing (HPC) nodes will have many more processors
than the contemporary architectures. In such a system with massive parallelism it will be …