Understanding Data Movement in AMD Multi-GPU Systems with Infinity Fabric

Authors: Schieffer, Gabin, Shi, Ruimin, Markidis, Stefano, Herten, Andreas, Faj, Jennifer, Peng, Ivy

Source: SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis SC-W High Performance Computing, Networking, Storage and Analysis, SC24-W: Workshops of the International Conference for. :567-576 Nov, 2024

Relation: SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis

Multi-GPU GEMM Algorithm Performance Analysis for Nvidia and AMD GPUs Connected by NVLink and PCIe

Authors: Choi, Yea Rem^Aff8, Stegailov, Vladimir^{Aff8, Aff9, Aff10}

Contributors: Filipe, Joaquim, Editorial Board Member^Aff1, Ghosh, Ashish, Editorial Board Member^Aff2, Prates, Raquel Oliveira, Editorial Board Member^Aff3, Zhou, Lizhu, Editorial Board Member^Aff4, Balandin, Dmitry, editor^Aff5, Barkalov, Konstantin, editor^Aff6, Meyerov, Iosif, editor^Aff7

Source: Mathematical Modeling and Supercomputer Technologies : 22nd International Conference, MMST 2022, Nizhny Novgorod, Russia, November 14–17, 2022, Revised Selected Papers. 1750:281-292

Tuning of a Matrix-Matrix Multiplication Algorithm for Several GPUs Connected by Fast Communication Links

Authors: Choi, Yea Rem^Aff7, Nikolskiy, Vsevolod^{Aff7, Aff8}, Stegailov, Vladimir^{Aff7, Aff8, Aff9}

Contributors: Filipe, Joaquim, Editorial Board Member^Aff1, Ghosh, Ashish, Editorial Board Member^Aff2, Prates, Raquel Oliveira, Editorial Board Member^Aff3, Zhou, Lizhu, Editorial Board Member^Aff4, Sokolinsky, Leonid, editor^Aff5, Zymbler, Mikhail, editor^Aff6

Source: Parallel Computational Technologies : 16th International Conference, PCT 2022, Dubna, Russia, March 29–31, 2022, Revised Selected Papers. 1618:158-171

MRT Lattice Boltzmann Method on multiple Graphics Processing Units with halo sharing over PCI-e for non-contiguous memory

Authors: Forslund, Tobias O.M., 1992

Source: Proceedings of the Eleventh International Conference on Engineering Computational Technology Civil-Comp Conferences.

Subject Terms: lattice Boltzmann method, GPU, multi-GPU programming, Strömningslära, Fluid Mechanics

File Description: print

Access URL: https://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-93180
https://doi.org/10.4203/ccc.2.8.5

Automatic execution of single-GPU computations across multiple GPUs

Authors: Cabezas, Javier, Vilanova, Lluis, Geladeno, Isaac, Jablin, Thomas B., Navarro, Nacho, Hwu, Wen-mei

Source: 2014 23rd International Conference on Parallel Architecture and Compilation Techniques (PACT) Parallel Architecture and Compilation Techniques (PACT), 2014 23rd International Conference on. :467-468 Aug, 2014

Relation: 2014 23rd International Conference on Parallel Architecture and Compilation Techniques (PACT)

Memory access patterns : the missing piece of the multi-GPU puzzle

Authors: Ben-Nun, Tal, Levy, Ely, Barak, Amnon, Rubin, Eri

Source: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. :1-12

Availability: http://dl.acm.org/doi/10.1145/2807591.2807611

Automatic Parallelization of Kernels in Shared-Memory Multi-GPU Nodes

Authors: Cabezas, Javier, Vilanova, Lluís, Gelado, Isaac, Jablin, Thomas B., Navarro, Nacho, Hwu, Wen-mei W.

Source: Proceedings of the 29th ACM on International Conference on Supercomputing. :3-13

Availability: http://dl.acm.org/doi/10.1145/2751205.2751218

Computer simulation process parallel image processing technology based on Nvidia Cuda and Openmp ; Компьютерное моделирование процесса параллельного обработки изображений на основе технологий Openmp и Nvidia Cuda ; Комп'ютерне моделювання процесу паралельного оброблення зображень на основі технологій Openmp та Nvidia Cuda

Authors: Яровий, А. А., Кулик, О. О., Арсенюк, І. Р.

Source: Optoelectronic Information-Power Technologies; Vol. 30 No. 2 (2015); 33-39 ; Оптико-електроннi iнформацiйно-енергетичнi технологiї; Том 30 № 2 (2015); 33-39 ; 2311-2662 ; 1681-7893

Subject Terms: parallel computing, heterogeneous computing, multithreading, image processing, GPGPU, CUDA, Multi-GPU Programming, OpenMP, параллельные вычисления, гетерогенные вычисления, многопоточность, обработка изображений, паралельні обчислення, гетерогенні обчислення, багатопоточність, обробка зображень

File Description: application/pdf

Relation: https://oeipt.vntu.edu.ua/index.php/oeipt/article/view/421/419; https://oeipt.vntu.edu.ua/index.php/oeipt/article/view/421

Availability: https://oeipt.vntu.edu.ua/index.php/oeipt/article/view/421

The parallel-hierarchical transformation of spot images on the base of Multi-GPU systems ; Параллельно-иерархическое преобразование пятенных изображений на базе Multi-GPU систем ; Паралельно-ієрархічне перетворення плямоподібних зображень на основі Multi-GPU систем

Authors: Яровий, Андрій Анатолійович, Кулик, Олександр Олександрович, Кокряцька, Наталія Іванівна

Source: Information Technology and Computer Engineering; Vol. 34 No. 3 (2015): Information Technology and Computer Engineering; 72-80 ; Інформаційні технології та комп'ютерна інженерія; Том 34 № 3 (2015): Інформаційні технології та комп'ютерна інженерія; 72-80 ; 2078-6387 ; 1999-9941

Subject Terms: parallel computing, parallel-hierarchical transformation, image processing, GPGPU, CUDA, OpenMP, Multi-GPU Programming, паралельні обчислення, паралельно-ієрархічне перетворення, обробка зображень, параллельные вычисления, параллельно-иерархическое преобразование, обработка изображений

File Description: application/pdf

Relation: https://itce.vntu.edu.ua/index.php/itce/article/view/210/214; https://itce.vntu.edu.ua/index.php/itce/article/view/210

Availability: https://itce.vntu.edu.ua/index.php/itce/article/view/210