dr hab. inż. Paweł Czarnul
Zatrudnienie
- Kierownik katedry w Katedra Architektury Systemów Komputerowych
- Prodziekan ds. współpracy i promocji w Wydział Elektroniki, Telekomunikacji i Informatyki
- Profesor uczelni w Katedra Architektury Systemów Komputerowych
Publikacje
Filtry
wszystkich: 117
Katalog Publikacji
Rok 2018
-
Parallel Programming for Modern High Performance Computing Systems
PublikacjaIn view of the growing presence and popularity of multicore and manycore processors, accelerators, and coprocessors, as well as clusters using such computing devices, the development of efficient parallel applications has become a key challenge to be able to exploit the performance of such systems. This book covers the scope of parallel programming for modern high performance computing systems. It first discusses selected and...
-
Parallelization of large vector similarity computations in a hybrid CPU+GPU environment
PublikacjaThe paper presents design, implementation and tuning of a hybrid parallel OpenMP+CUDA code for computation of similarity between pairs of a large number of multidimensional vectors. The problem has a wide range of applications, and consequently its optimization is of high importance, especially on currently widespread hybrid CPU+GPU systems targeted in the paper. The following are presented and tested for computation of all vector...
-
Three levels of fail-safe mode in MPI I/O NVRAM distributed cache
PublikacjaThe paper presents architecture and design of three versions for fail-safe data storage in a distributed cache using NVRAM in cluster nodes. In the first one, cache consistency is assured through additional buffering write requests. The second one is based on additional write log managers running on different nodes. The third one benefits from synchronization with a Parallel File System (PFS) for saving data into a new file which...
Rok 2017
-
A distributed system for conducting chess games in parallel
PublikacjaThis paper proposes a distributed and scalable cloud based system designed to play chess games in parallel. Games can be played between chess engines alone or between clusters created by combined chess engines. The system has a built-in mechanism that compares engines, based on Elo ranking which finally presents the strength of each tested approach. If an approach needs more computational power, the design of the system allows...
-
Distributed NVRAM Cache – Optimization and Evaluation with Power of Adjacency Matrix
PublikacjaIn this paper we build on our previously proposed MPI I/O NVRAM distributed cache for high performance computing. In each cluster node it incorporates NVRAMs which are used as an intermediate cache layer between an application and a file for fast read/write operations supported through wrappers of MPI I/O functions. In this paper we propose optimizations of the solution including handling of write requests with a synchronous mode,...
-
MERPSYS: An environment for simulation of parallel application execution on large scale HPC systems
PublikacjaIn this paper we present a new environment called MERPSYS that allows simulation of parallel application execution time on cluster-based systems. The environment offers a modeling application using the Java language extended with methods representing message passing type communication routines. It also offers a graphical interface for building a system model that incorporates various hardware components such as CPUs, GPUs, interconnects...
-
Multi-agent large-scale parallel crowd simulation
PublikacjaThis paper presents design, implementation and performance results of a new modular, parallel, agent-based and large scale crowd simulation environment. A parallel application, implemented with C and MPI, was implemented and run in this parallel environment for simulation and visualization of an evacuation scenario at Gdansk University of Technology, Poland and further in the area of districts of Gdansk. The application uses a...
-
Parallelization of Selected Algorithms on Multi-core CPUs, a Cluster and in a Hybrid CPU+Xeon Phi Environment
PublikacjaIn the paper we present parallel implementations as well as execution times and speed-ups of three different algorithms run in various environments such as on a workstation with multi-core CPUs and a cluster. The parallel codes, implementing the master-slave model in C+MPI, differ in computation to communication ratios. The considered problems include: a genetic algorithm with various ratios of master processing time to communication...
-
Performance evaluation of unified memory and dynamic parallelism for selected parallel CUDA applications
PublikacjaThe aim of this paper is to evaluate performance of new CUDA mechanisms—unified memory and dynamic parallelism for real parallel applications compared to standard CUDA API versions. In order to gain insight into performance of these mechanisms, we decided to implement three applications with control and data flow typical of SPMD, geometric SPMD and divide-and-conquer schemes, which were then used for tests and experiments. Specifically,...
Rok 2016
-
A Fail-Safe NVRAM Based Mechanism for Efficient Creation and Recovery of Data Copies in Parallel MPI Applications
PublikacjaThe paper presents a fail-safe NVRAM based mechanism for creation and recovery of data copies during parallel MPI application runtime. Specifically, we target a cluster environment in which each node has an NVRAM installed in it. Our previously developed extension to the MPI I/O API can take advantage of NVRAM regions in order to provide an NVRAM based cache like mechanism to significantly speed up I/O operations and allow to preload...
-
A Parallel MPI I/O Solution Supported by Byte-addressable Non-volatile RAM Distributed Cache
PublikacjaWhile many scientific, large-scale applications are data-intensive, fast and efficient I/O operations have become of key importance for HPC environments. We propose an MPI I/O extension based on in-system distributed cache with data located in Non-volatile Random Access Memory (NVRAM) available in each cluster node. The presented architecture makes effective use of NVRAM properties such as persistence and byte-level access behind...
-
Application of Web-GIS and Cloud Computing to Automatic Satellite Image Correction
PublikacjaRadiometric calibration of satellite imagery requires coupling of atmospheric and topographic parameters, which constitutes serious computational problems in particular in complex geographical terrain. Successful application of topographic normalization algorithms for calibration purposes requires integration of several types of high-resolution geographic datasets and their processing in a common context. This paper presents the...
-
Benchmarking Performance of a Hybrid Intel Xeon/Xeon Phi System for Parallel Computation of Similarity Measures Between Large Vectors
PublikacjaThe paper deals with parallelization of computing similarity measures between large vectors. Such computations are important components within many applications and consequently are of high importance. Rather than focusing on optimization of the algorithm itself, assuming specific measures, the paper assumes a general scheme for finding similarity measures for all pairs of vectors and investigates optimizations for scalability...
-
Checkpointing of Parallel MPI Applications using MPI One-sided API with Support for Byte-addressable Non-volatile RAM
PublikacjaThe increasing size of computational clusters results in an increasing probability of failures, which in turn requires application checkpointing in order to survive those failures. Traditional checkpointing requires data to be copied from application memory into persistent storage medium, which increases application execution time as it is usually done in a separate step. In this paper we propose to use emerging byte-addressable...
-
Considerations of Computational Efficiency in Volunteer and Cluster Computing
PublikacjaIn the paper we focus on analysis of performance and power consumption statistics for two modern environments used for computing – volunteer and cluster based systems. The former integrate computational power donated by volunteers from their own locations, often towards social oriented or targeted initiatives, be it of medical, mathematical or space nature. The latter is meant for high performance computing and is typically installed...
-
KernelHive: a new workflow-based framework for multilevel high performance computing using clusters and workstations with CPUs and GPUs
PublikacjaThe paper presents a new open-source framework called KernelHive for multilevel parallelization of computations among various clusters, cluster nodes, and finally, among both CPUs and GPUs for a particular application. An application is modeled as an acyclic directed graph with a possibility to run nodes in parallel and automatic expansion of nodes (called node unrolling) depending on the number of computation units available....
-
Modeling energy consumption of parallel applications
PublikacjaThe paper presents modeling and simulation of energy consumption of two types of parallel applications: geometric Single Program Multiple Data (SPMD) and divide-and-conquer (DAC). Simulation is performed in a new MERPSYS environment. Model of an application uses the Java language with extension representing message exchange between processes working in parallel. Simulation is performed by running threads representing distinct process...
-
Modeling Parallel Applications in the MERPSYS Environment
PublikacjaThe chapter presents how to model parallel computational applications for which simulation of execution in a large-scale parallel or distributed environment is performed within the MERPSYS environment. Specifically, it is shown what approaches can be adopted to model key paradigms often used for parallel applications: master-slave, geometric parallelism (single program multiple data), pipelined and divide-and-conquer applications....
-
Performance and Power-Aware Modeling of MPI Applications for Cluster Computing
PublikacjaThe paper presents modeling of performance and power consumption when running parallel applications on modern cluster-based systems. The model includes basic so-called blocks representing either computations or communication. The latter includes both point-to-point and collective communication. Real measurements were performed using MPI applications and routines run on three different clusters with both Infiniband and Gigabit Ethernet...
Rok 2015
-
BeesyCluster as Front-End for High Performance Computing Services
PublikacjaThe paper presents the BeesyCluster system as a middleware allowing invocation of services on high performance computing resources within the NIWA Centre of Competence project. Access is possible through both WWW and SOAP Web Service interfaces. The former allows non-experienced users to invoke both simple and complex services exposed through easyto-use servlets. The latter is meant for integration of external applications with...
wyświetlono 3665 razy