Results 171 to 180 of about 926 (201)

Accelerating Hydrocodes with OpenACC, OpenCL and CUDA

2012 SC Companion: High Performance Computing, Networking Storage and Analysis, 2012
Hardware accelerators such as GPGPUs are becoming increasingly common in HPC platforms and their use is widely recognised as being one of the most promising approaches for reaching exascale levels of performance. Large HPC centres, such as AWE, have made huge investments in maintaining their existing scientific software codebases, the vast majority of ...
J. A. Herdman, W. P. Gaudin, Simon McIntosh-Smith, Michael Boulton, D. A. Beckingsale, A. C. Mallinson, Stephen A. Jarvis   +6 more
openaire   +3 more sources

Multidevice programming with OpenACC

2017
exaly   +2 more sources

An OpenACC Extension for Data Layout Transformation

2014 First Workshop on Accelerator Programming using Directives, 2014
OpenACC is gaining momentum as an implicit and portable interface in porting legacy CPU-based applications to heterogeneous, highly parallel computational environment involving many-core accelerators such as GPUs and Intel Xeon Phi. OpenACC provides a set of loop directives similar to OpenMP for the parallelization and also to manage data movement ...
Tetsuya Hoshino, Naoya Maruyama, Satoshi Matsuoka   +2 more
openaire   +1 more source

Understanding Performance Portability of OpenACC for Supercomputers

2015 IEEE International Parallel and Distributed Processing Symposium Workshop, 2015
Scientific applications need to be moved among supercomputers, such as Tianhe-2 and TSUBAME 2.5. OpenACC provides a directive-based approach for a single source code base with function portability across different accelerators used in the supercomputers. However, the performance portability is not guaranteed by the OpenACC standard.
Suttinee Sawadsitang, James Lin 0001, Simon See, François Bodin, Satoshi Matsuoka   +4 more
openaire   +1 more source

Translating OpenACC program for HAS environment

2017 International Conference on Computer, Information and Telecommunication Systems (CITS), 2017
Heterogeneous System Architecture (HSA) is a newly arising heterogeneous multiprocessor platform which may improve the heavy data transmission between CPU and GPU in traditional heterogeneous multiprocessor platforms through shared virtual memory. However, as other heterogeneous multiprocessor platforms, it is complex and error-prone to write HSA ...
Han-Ping Lo, Jean Jyh-Jiun Shann
openaire   +1 more source

Employing Compression Solutions under OpenACC

2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2016
For GPUs to achieve their peak performance, effective and efficient usage of memory bandwidth is necessary. To this end, programmers invest extensive development effort to optimize a GPU program, specially its memory bandwidth usage. The OpenACC programming model has been introduced to tackle the accelerators programming complexity. However, this model'
Ebad Salehi, Ahmad Lashgar, Amirali Baniasadi   +2 more
openaire   +1 more source

Experiences in extending parallware to support OpenACC

Proceedings of the Second Workshop on Accelerator Programming using Directives, 2015
Porting scientific codes to accelerator-based computers using OpenACC and OpenMP is an important topic for the HPC community. Programmability, performance portability and developer productivity are key issues for the widespread use of these systems.
Jacobo Lobeiras, Manuel Arenaz, Oscar Hernández   +2 more
openaire   +1 more source

A Source-to-Source OpenACC Compiler for CUDA

2014
OpenACC is a new directive-based programming interface for accelerators such as GPGPU. OpenACC allows the programmer to express the offloading of data and computations to accelerators to simplify the porting process for legacy CPU-based applications.
Akihiro Tabuchi, Masahiro Nakao, Mitsuhisa Sato   +2 more
openaire   +1 more source

KokkACC: Enhancing Kokkos with OpenACC

2022 Workshop on Accelerator Programming Using Directives (WACCPD), 2022
Pedro Valero-Lara, Seyong Lee, Marc González Tallada, Joel E. Denny, Jeffrey S. Vetter   +4 more
openaire   +1 more source

Hybrid Programming Using OpenSHMEM and OpenACC

2014
With high performance systems exploiting multicore and accelerator-based architectures on a distributed shared memory system, heterogenous hybrid programming models are the natural choice to exploit all the hardware made available on these systems. Previous efforts looking into hybrid models have primarily focused on using OpenMP directives (for shared
Matthew B. Baker, Swaroop Pophale, Jean-Charles Vasnier, Haoqiang Jin, Oscar R. Hernandez   +4 more
openaire   +1 more source