Filters








3,966 Hits in 3.7 sec

OpenMP Extensions for Heterogeneous Architectures [chapter]

Leo White
2011 Lecture Notes in Computer Science  
How can we write programs for multiple similar architectures?  ...  These are implementation-defined expressions with new type omp procs t, whose values represent sets of processors in an architecture.  ...  architectures for OpenMP: 1. OpenMP assumes a single shared address space. 2. There is no mechanism to allocate work to specific processors.  ... 
doi:10.1007/978-3-642-21487-5_8 fatcat:ivigmb4libfshpim356c5sxoze

Extending OpenMP for heterogeneous chip multiprocessors

F. Liu, V. Chaudhary
2003 2003 International Conference on Parallel Processing, 2003. Proceedings.  
Incorporating different processors into OpenMP is challenging. We present our solutions to extend OpenMP directives to tackle this heterogeneity.  ...  In this paper, we propose that high-level abstraction of parallel programming like OpenMP is suitable for chip multiprocessors.  ...  Singh for his contribution of the Double Buffering concept.  ... 
doi:10.1109/icpp.2003.1240577 dblp:conf/icpp/LiuC03 fatcat:qg25r3k6unazviftohe6z7pvoa

HSTREAM: A directive-based language extension for heterogeneous stream computing [article]

Suejb Memeti, Sabri Pllana
2018 arXiv   pre-print
In this paper, we present HSTREAM, a compiler directive-based language extension to support programming stream computing applications for heterogeneous parallel computing systems.  ...  Programming such systems require advanced knowledge of several hardware architectures and device-specific programming models, including OpenMP and CUDA.  ...  HSTREAM source-to-source compiler can automatically generate device-specific code, such as OpenMP for CPUs, CUDA for GPUs, and Intel Language Extension for Offloading for Intel Xeon Phi, from a high-level  ... 
arXiv:1809.09387v1 fatcat:iwenfyvdlzdudoitudszyvfdci

EXOCHI

Perry H. Wang, Jamison D. Collins, Gautham N. Chinya, Hong Jiang, Xinmin Tian, Milind Girkar, Nick Y. Yang, Guei-Yuan Lueh, Hong Wang
2007 SIGPLAN notices  
The CHI compiler extends the OpenMP pragma for heterogeneous multithreading programming, and produces a single fat binary with code sections corresponding to different instruction sets.  ...  In this paper, we present EXOCHI: (1) Exoskeleton Sequencer (EXO), an architecture to represent heterogeneous accelerators as ISA-based MIMD architecture resources, and a shared virtual memory heterogeneous  ...  CHI Extensions to OpenMP Pragmas lel region.  ... 
doi:10.1145/1273442.1250753 fatcat:kecpgrwcaneopjizq6iorj5wla

EXOCHI

Perry H. Wang, Jamison D. Collins, Gautham N. Chinya, Hong Jiang, Xinmin Tian, Milind Girkar, Nick Y. Yang, Guei-Yuan Lueh, Hong Wang
2007 Proceedings of the 2007 ACM SIGPLAN conference on Programming language design and implementation - PLDI '07  
The CHI compiler extends the OpenMP pragma for heterogeneous multithreading programming, and produces a single fat binary with code sections corresponding to different instruction sets.  ...  In this paper, we present EXOCHI: (1) Exoskeleton Sequencer (EXO), an architecture to represent heterogeneous accelerators as ISA-based MIMD architecture resources, and a shared virtual memory heterogeneous  ...  CHI Extensions to OpenMP Pragmas lel region.  ... 
doi:10.1145/1250734.1250753 dblp:conf/pldi/WangCCJTGYLW07 fatcat:72glznuq4zewfl3iezwdzggsum

Evaluating OpenMP 4.0's Effectiveness as a Heterogeneous Parallel Programming Model

Matt Martineau, Simon McIntosh-Smith, Wayne Gaudin
2016 2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)  
THE OPENMP 4.0 STANDARD OpenMP is undoubtedly one of the most adopted parallel programming models, and represents a highly usable interface for targeting multi-core CPU architectures.  ...  Overall, we find that OpenMP 4.0 is a highly usable open standard capable of performant heterogeneous execution, making it a promising option for scientific application developers. II.  ...  We conclude that, as compiler support improves, and awareness of the capabilities of OpenMP 4.x spreads, the model has the potential to become the defacto standard for targeting heterogeneous architectures  ... 
doi:10.1109/ipdpsw.2016.70 dblp:conf/ipps/MartineauMG16 fatcat:4mrzdvrc4nfj7mylg4io5jwgym

Implementing OpenMP on a high performance embedded multicore MPSoC

Barbara Chapman, Lei Huang, Eric Biscondi, Eric Stotzer, Ashish Shrivastava, Alan Gatherer
2009 2009 IEEE International Symposium on Parallel & Distributed Processing  
In this paper we discuss our initial experiences adapting OpenMP to enable it to serve as a programming model for high performance embedded systems.  ...  A high-level programming model such as OpenMP has the potential to increase programmer productivity, reducing the design/development costs and time to market for such systems.  ...  Its set of OpenMP extensions target heterogeneous shared and distributed memory systems and allow for the specification of procedures that will be executed on an accelerator.  ... 
doi:10.1109/ipdps.2009.5161107 dblp:conf/ipps/ChapmanHBSSG09 fatcat:prqzkfif4fhc7m2di7gbnejqeq

Benchmarking OpenCL, OpenACC, OpenMP, and CUDA: programming productivity, performance, and energy consumption [article]

Suejb Memeti and Lu Li and Sabri Pllana and Joanna Kolodziej and Christoph Kessler
2017 arXiv   pre-print
However, exploiting the available performance of heterogeneous architectures may be challenging.  ...  There are various parallel programming frameworks (such as, OpenMP, OpenCL, OpenACC, CUDA) and selecting the one that is suitable for a target context is not straightforward.  ...  Acknowledgment This article is based upon work from COST Action IC1406 High-Performance Modelling and Simulation for Big Data Applications (cHiPSet), supported by COST (European Cooperation in Science  ... 
arXiv:1704.05316v1 fatcat:lax3kghaxnanxixklx3haavlxa

libEOMP

Cheng Wang, Sunita Chandrasekaran, Barbara Chapman, Jim Holt
2013 Proceedings of the 2013 International Workshop on Programming Models and Applications for Multicores and Manycores - PMAM '13  
In recent years rapid revolution of Multiprocessor Systemon-Chip (MPSoC) poses new challenges for programming such architectures in an efficient manner.  ...  To address the architectural challenges, we propose a lightweight unified OpenMP runtime library, libEOMP, by leveraging the MCA (Multicore Association) APIs as the target of our OpenMP translation.  ...  [11] proposed an extension for OpenMP tasks on the Cell BE. However, the major drawback of this extension is that it has not been standardized.  ... 
doi:10.1145/2442992.2443001 dblp:conf/ppopp/WangCCH13 fatcat:hpivtj2kijb3nfu6zakmzpxjsa

Parallel Programming Models for Heterogeneous Many-Cores : A Survey [article]

Jianbin Fang, Chun Huang, Tao Tang, Zheng Wang
2020 arXiv   pre-print
In this article, we provide a comprehensive survey for parallel programming models for heterogeneous many-core architectures and review the compiling techniques of improving programmability and portability  ...  We examine various software optimization techniques for minimizing the communicating overhead between heterogeneous computing devices.  ...  Figure 1 summarizes the family of parallel programming models for heterogeneous many-core architectures.  ... 
arXiv:2005.04094v1 fatcat:e2psrdnyajh3hih3znnjjbezae

OmpSs: A PROPOSAL FOR PROGRAMMING HETEROGENEOUS MULTI-CORE ARCHITECTURES

ALEJANDRO DURAN, EDUARD AYGUADÉ, ROSA M. BADIA, JESÚS LABARTA, LUIS MARTINELL, XAVIER MARTORELL, JUDIT PLANAS
2011 Parallel Processing Letters  
architectures and clusters • Proposes OmpSs ○ A solution to ease the programming of heterogeneous architectures • Developed to run on SMP with / without GPUs.  ...  -And cluster environments. ○ Unify SMP, heterogeneous and cluster programming in one model • OpenMP achieves high expressiveness using tasks. • StarSs allow runtime analysis between tasks, and automatic  ... 
doi:10.1142/s0129626411000151 fatcat:6lenourgorh73im73cymewlb7q

Multiple Target Task Sharing Support for the OpenMP Accelerator Model [chapter]

Guray Ozen, Sergi Mateo, Eduard Ayguadé, Jesús Labarta, James Beyer
2016 Lecture Notes in Computer Science  
In this paper we propose an extension to the OpenMP 4.5 directive-based programming model to support the specification and execution of multiple instances of task regions on different devices (i.e. accelerators  ...  The compiler is responsible for the generation of device-specific code for each device kind, delegating to the runtime system the dynamic schedule of the tasks to the available devices.  ...  on different devices in an heterogenous architecture.  ... 
doi:10.1007/978-3-319-45550-1_19 fatcat:7jx3aneqhnhhnhloug2hgruc6m

Task-Based Programming with OmpSs and Its Application [chapter]

Alejandro Fernández, Vicenç Beltran, Xavier Martorell, Rosa M. Badia, Eduard Ayguadé, Jesus Labarta
2014 Lecture Notes in Computer Science  
The main extension of OmpSs, now incorporated in the recent OpenMP 4.0 standard, is the concept of data dependences between tasks.  ...  OmpSs targets the programming of heterogeneous and multi-core architectures and offers asynchronous parallelism in the execution of the tasks.  ...  While OmpSs extensions to support heterogeneous environments are designed to simplify the synchronization and data transfers required between host and accelerator codes, OpenMP tries to generate parallel  ... 
doi:10.1007/978-3-319-14313-2_51 fatcat:ddw5himjkjb7tf7s6x7duu5c7e

Parallel programming models for heterogeneous many-cores: a comprehensive survey

Jianbin Fang, Chun Huang, Tao Tang, Zheng Wang
2020 CCF Transactions on High Performance Computing  
In this article, we provide a comprehensive survey for parallel programming models for heterogeneous many-core architectures and review the compiling techniques of improving programmability and portability  ...  We examine various software optimization techniques for minimizing the communicating overhead between heterogeneous computing devices.  ...  We had expected that, OpenCL became the unified de facto standard programming model for heterogeneous many-core processors, like OpenMP for multi-core CPUs (The OpenMP API specification for parallel programming  ... 
doi:10.1007/s42514-020-00039-4 fatcat:nn56xhjm6rcu7kya6gfnyjg66q

FOTV: A Generic Device Offloading Framework for OpenMP [chapter]

Jose Luis Vazquez, Pablo Sanchez
2021 Lecture Notes in Computer Science  
AbstractSince the introduction of the "target" directive in the 4.0 specification, the usage of OpenMP for heterogeneous computing programming has increased significantly.  ...  The framework has an API that provides support for new devices and accelerated code without additional OpenMP compiler modifications.  ...  The complex integration of new devices could limit the usage of OpenMP for heterogeneous computing.  ... 
doi:10.1007/978-3-030-85262-7_12 fatcat:qowtimiuzbfrxfxelz2duzc56e
« Previous Showing results 1 — 15 out of 3,966 results