Filters








719 Hits in 4.4 sec

Booster: a high-level language for portable parallel algorithms

Edwin M. Paalvast, Henk J. Sips, Leo C. Breebaart
1991 Applied Numerical Mathematics  
The development of programming languages suitable to express parallel algorithms in is crucial to the pace of acceptance of parallel processors for production applications.  ...  The language has been designed to program parallel algorithms for a wide variety of target parallel architectures.  ...  This insight has led to the approach of parallelism through program annotations, incorporating -explicit -data decompositions.  ... 
doi:10.1016/0168-9274(91)90050-a fatcat:c7ab6iy42nckvks5zidry5xeda

Language Constructs for Data Partitioning and Distribution

P. Crooks, R. H. Perrott
1995 Scientific Programming  
Programs are written according to the shared memory programming paradigm but the programmer is required to specify, by means of directives, additional syntax or interactive methods, how the data of the  ...  In these systems the programmer is freed from consideration of the low-level details of the target architecture in that there is no need to program explicit processes or specify interprocess communication  ...  O to Barabara Chapman of the University of Vienna for information regarding the SCPERB system and for her helpful comments.  ... 
doi:10.1155/1995/656010 fatcat:in6wyqvy55azblafnfmpbmtiz4

JUWELS Booster – A Supercomputer for Large-Scale AI Research [article]

Stefan Kesselheim, Andreas Herten, Kai Krajsek, Jan Ebert, Jenia Jitsev, Mehdi Cherti, Michael Langguth, Bing Gong, Scarlet Stadtler, Amirpasha Mozaffari, Gabriele Cavallaro, Rocco Sedona (+6 others)
2021 arXiv   pre-print
In this article, we present JUWELS Booster, a recently commissioned high-performance computing system at the J\"ulich Supercomputing Center.  ...  We detail its system architecture, parallel, distributed model training, and benchmarks indicating its outstanding performance.  ...  (www.gauss-centre.eu) for funding this work by providing computing time through the John von Neumann Institute for Computing (NIC) on the GCS Supercomputers JUWELS, JUWELS Booster at Jülich Supercomputing  ... 
arXiv:2108.11976v1 fatcat:22wyf42eordsrekcutoadpujd4

Boosting Bitext Compression [chapter]

Joaquín Adiego, Miguel A. Martínez-Prieto, Javier E. Hoyos-Torío, Felipe Sánchez-Martínez
2011 Advances in Intelligent and Soft Computing  
When encoded models are used as compression boosters we achieve compression ratios improving state-of-the-art compressors up to 6.5 percentage points, being up to 40% faster.  ...  The properties of these approaches are analysed from a statistical point of view and tested as a preprocessing step to general purpose compressors.  ...  When encoded models are used as a preprocessing step to general-purpose compressors, the experiments show that they improve the compression ratio as well as their performance in both compression and decompression  ... 
doi:10.1007/978-3-642-19931-8_14 dblp:conf/paams/AdiegoMHS11 fatcat:d5nqpo7vnbg47o634wrw55abry

Increased throughput and ultra-high mass resolution in DESI FT-ICR MS imaging through new-generation external data acquisition system and advanced data processing approaches

Pieter C. Kooijman, Konstantin O. Nagornov, Anton N. Kozhinov, David P. A. Kilgour, Yury O. Tsybin, Ron M. A. Heeren, Shane R. Ellis
2019 Scientific Reports  
To achieve that, first, we developed and coupled an external high-performance data acquisition system to an FT-ICR MS instrument to record the time-domain signals (transients) in parallel with the instrument's  ...  Using this approach, we not only demonstrate the record 1 million mass resolution for lipid imaging from brain tissue, but explicitly show such mass resolution is required to resolve the complexity of  ...  The research received funding from the Netherlands Organisation for Scientific Research (NWO) in the framework of the Technology Area COAST of the Fund New Chemical Innovations as part of the PolyImage  ... 
doi:10.1038/s41598-018-36957-1 pmid:30626890 pmcid:PMC6327097 fatcat:cgekusdgrvg3do7cgp3eon2kra

Accelerating neural network training with distributed asynchronous and selective optimization (DASO)

Daniel Coquelin, Charlotte Debus, Markus Götz, Fabrice von der Lehr, James Kahn, Martin Siggel, Achim Streit
2022 Journal of Big Data  
This synchronization is the central algorithmic bottleneck.  ...  To address the exponential rise in training time, users are turning to data parallel neural networks (DPNN) and large-scale distributed resources on computer clusters.  ...  Acknowledgements This work is supported by the Helmholtz Association Initiative and Networking Fund under project number ZT-I-0003, the Helmholtz AI platform grant and the HAICORE@KIT partition.  ... 
doi:10.1186/s40537-021-00556-1 fatcat:c7jysa5xtref7am5uxplmd3xoa

The Amalgamation of the Object Detection and Semantic Segmentation for Steel Surface Defect Detection

Mansi Sharma, Jongtae Lim, Hansung Lee
2022 Applied Sciences  
The proposed approach has a hierarchical structure of the binary classifier at the first stage and the object detection and semantic segmentation algorithms at the second stage.  ...  To resolve the atypical defects problem, we introduce a hierarchical approach for the classification and detection of defects on the steel surface.  ...  It has a parallel computing environment. Th of boosters, gbtree and linear.  ... 
doi:10.3390/app12126004 fatcat:777zjsxirrg6rgkb5wjt6e2zdu

Computational Identification and Analysis of Ubiquinone-Binding Proteins

Chang Lu, Wenjie Jiang, Hang Wang, Jinxiu Jiang, Zhiqiang Ma, Han Wang
2020 Cells  
In this work, we were the first to propose a UBPs predictor (UBPs-Pred).  ...  Analyzing and identifying UBPs via a computational approach will provide insights into the pathways associated with ubiquinones.  ...  "booster" controls the type of booster to be run at each iteration, which can be gbtree (tree-based booster, which is the default) or gblinear (linear booster).  ... 
doi:10.3390/cells9020520 pmid:32102444 pmcid:PMC7072731 fatcat:cymot4mwxjbo7ndbmi4ymupemm

Embracing heterogeneity with dynamic core boosting

Hyoun Kyu Cho, Scott Mahlke
2014 Proceedings of the 11th ACM Conference on Computing Frontiers - CF '14  
Even for embarrassingly parallel programs in the form of SPMD (single program multiple data), the threads are not perfectly balanced due to control flow divergence, non-deterministic memory latencies,  ...  However, in any parallel segment, execution time is determined by the longest running thread.  ...  They propose two boosting algorithms: Booster VAR and Booster SYNC.  ... 
doi:10.1145/2597917.2597932 dblp:conf/cf/ChoM14 fatcat:tx22yxw3mnbu7dpe5ccwealwua

Supporting automatic recovery in offloaded distributed programming models through MPI-3 techniques

Antonio J. Peña, Vicenç Beltran, Carsten Clauss, Thomas Moschny
2017 Proceedings of the International Conference on Supercomputing - ICS '17  
Using ParaStation MPI, a production MPI-3.1 implementation, we explore the features that, being standard compliant, an MPI stack must support to provide the necessary fault tolerance guarantees, based  ...  Our results, including synthetic benchmarks and applications, reveal low runtime overhead and efficient recovery, demonstrating that the existing MPI standard provided us with sufficient mechanisms to  ...  Apart from mapping greatly to some algorithms, these ease the efficient use of heterogeneous compute nodes by enabling the offload of tasks to compute nodes featuring the most suitable architecture.  ... 
doi:10.1145/3079079.3079093 dblp:conf/ics/PenaBCM17 fatcat:ealhsmdha5hodimimkdldxyy7i

BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation [article]

Changqian Yu, Changxin Gao, Jingbo Wang, Gang Yu, Chunhua Shen, Nong Sang
2020 arXiv   pre-print
However, to speed up the model inference, current approaches almost always sacrifice the low-level details, which leads to a considerable accuracy decrease.  ...  Besides, a booster training strategy is designed to improve the segmentation performance without any extra inference cost.  ...  Acknowledgment This work is supported by the National Natural Science Foundation of China (No. 61433007 and 61876210).  ... 
arXiv:2004.02147v1 fatcat:6346xyihnreyrpc3pdnxj7jqvi

Quantitative single-cell proteomics as a tool to characterize cellular hierarchies

Erwin M. Schoof, Benjamin Furtwängler, Nil Üresin, Nicolas Rapin, Simonas Savickas, Coline Gentil, Eric Lechman, Ulrich auf dem Keller, John E. Dick, Bo T. Porse
2021 Nature Communications  
The approach presented here lays a foundation for implementing global single-cell proteomics studies across the world.  ...  AbstractLarge-scale single-cell analyses are of fundamental importance in order to capture biological heterogeneity within complex cell systems, but have largely been limited to RNA-based technologies.  ...  Finally, missing values of the remaining proteins were imputed using the nearest neighbor algorithm and subsequently scaled to unit variance and zero mean.  ... 
doi:10.1038/s41467-021-23667-y pmid:34099695 fatcat:2gh2j4pbwbegrd7f6nkfocuqhi

A review of protein–protein interaction network alignment: From pathway comparison to global alignment

Cheng-Yu Ma, Chung-Shou Liao
2020 Computational and Structural Biotechnology Journal  
We also introduce the most popular evaluation measures in the literature to benchmark the performance of these approaches.  ...  In this survey paper, we focus on protein-protein interaction networks and review some representative algorithms for network alignment in the past two decades as well as the state-of-the-art aligners.  ...  Moreover, PISwap and MAGNA can be used as a booster to refine the alignment generated by other approaches.  ... 
doi:10.1016/j.csbj.2020.09.011 pmid:33033584 pmcid:PMC7533294 fatcat:6ghgd4e3grejzkvxqozqnbaxdi

Massive-Parallel Trajectory Calculations version 2.2 (MPTRAC-2.2): Lagrangian transport simulations on graphics processing units (GPUs)

Lars Hoffmann, Paul F. Baumeister, Zhongyin Cai, Jan Clemens, Sabine Griessbach, Gebhard Günther, Yi Heng, Mingzhao Liu, Kaveh Haghighi Mood, Olaf Stein, Nicole Thomas, Bärbel Vogel (+2 others)
2022 Geoscientific Model Development  
of a factor of 16 due to the utilization of GPUs compared to CPU-only runs on the JUWELS Booster.  ...  We ported the Massive-Parallel Trajectory Calculations (MPTRAC) model to GPUs using the open accelerator (OpenACC) programming model.  ...  Next to describing the different implemented algorithms and the requirements and options for model input and output data, we discuss the parallelization strategy and the porting of the code to GPUs in  ... 
doi:10.5194/gmd-15-2731-2022 fatcat:6w2ynkwjazcgrkas5jf46xtfpi

iMOKA: k-mer based software to analyze large collections of sequencing data

Claudio Lorenzi, Sylvain Barriere, Jean-Philippe Villemin, Laureline Dejardin Bretones, Alban Mancheron, William Ritchie
2020 Genome Biology  
rapidly reduce the search space.  ...  iMOKA (interactive multi-objective k-mer analysis) is a software that enables comprehensive analysis of sequencing data from large cohorts to generate robust classification models or explore specific genetic  ...  Acknowledgements We wish to acknowledge the Genotoul platform (genotoul.fr) for providing us with calculation time on their servers.  ... 
doi:10.1186/s13059-020-02165-2 pmid:33050927 fatcat:4nar7r5zkfd4nnxrzxrrnkupeu
« Previous Showing results 1 — 15 out of 719 results