Optimization strategies in different CUDA architectures using llCoMP

Reyes, Ruyman; Sande, Francisco de

doi:10.1016/j.micpro.2011.05.006

Cited by 15 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another drawback of this model is the manual management of kernel compilation at run-time, for different architectures in different contexts, that is desired to be generalized and simplified. The llCoMP tool (Reyes and de Sande, 2012) is a source-to-source compiler that translates C annotated code to MPI + OpenMP or CUDA. However, it does not support the joint use of CUDA with the other parallel models.…”

Section: Related Workmentioning

confidence: 99%

Controllers: An abstraction to ease the use of hardware accelerators

Moreton-Fernandez

Ortega–Arranz

González-Escribano

2017

The International Journal of High Performance Computing Applica

View full text Add to dashboard Cite

Nowadays the use of hardware accelerators, such as the Graphics Processing Units (GPUs) or XeonPhi coprocessors, is key to solve computationally costly problems that require High Performance Computing (HPC). However, programming solutions for an efficient deployment in this kind of devices is a very complex task that relies on the manual management of memory transfers and configuration parameters. The programmer has to carry out a deep study of the particular data needed to be computed at each moment, in different computing platforms, also considering architectural details. We introduce the Controller concept as an abstract entity that allows the programmer to easily manage the communications and kernel launching details on hardware accelerators in a transparent way. This model also provides the possibility of defining and launching CPU kernels in multi-core processors with the same abstraction and methodology used for the accelerators. It internally combines different native programming models and technologies to exploit the potential of each kind of device. Additionally, the model also allows the programmer to simplify the proper selection of values for several configuration parameters that can be selected when a kernel is launched. This is done through a qualitative characterization process of the kernel code to be executed. Finally, we present the implementation of the Controller model in a prototype library, together with its application in several case studies. Its use has led to reductions in the development and porting costs, with significantly low overheads in the execution times when compared to manually programmed and optimized solutions using directly CUDA and OpenMP.

show abstract

Section: Related Workmentioning

confidence: 99%

Controllers: An abstraction to ease the use of hardware accelerators

Moreton-Fernandez

Ortega–Arranz

González-Escribano

2017

The International Journal of High Performance Computing Applica

View full text Add to dashboard Cite

show abstract

“…accULL [17] is the first open source OpenACC compiler that has already implemented some major directives and runtime calls of OpenACC. It used YaCF compiler framework [16] and a standalone runtime library Frangollo that is independent of any compiler. This implementation supports both CUDA and OpenCL platforms.…”

Section: Related Workmentioning

confidence: 99%

Exploring Programming Multi-GPUs Using OpenMP and OpenACC-Based Hybrid Model

Chandrasekaran

Chapman

2013

2013 IEEE International Symposium on Parallel &Amp; Distributed Processing, Workshops and PHD Forum

View full text Add to dashboard Cite

Heterogeneous computing come with tremendous potential and is a leading candidate for scientific applications that are becoming more and more complex. Accelerators such as GPUs whose computing momentum is growing faster than ever offer application performance when compute intensive portions of an application are offloaded to them. It is quite evident that future computing architectures are moving towards hybrid systems consisting of multi-GPUs and multicore CPUs. A variety of high-level languages and software tools can simplify programming these systems. Directive-based programming models are being embraced since they not only ease programming complex systems but also abstract low-level details from the programmer. We already know that OpenMP has been making programming CPUs easy and portable. Similarly, a directive-based programming model for accelerators is OpenACC that is gaining popularity since the directives play an important role in developing portable software for GPUs. A combination of OpenMP and OpenACC, a hybrid model, is a plausible solution to port scientific applications to heterogeneous architectures especially when there is more than one GPU on a single node to port an application to. However OpenACC meant for accelerators is yet to provide support for multi-GPUs. But using OpenMP we could conveniently exploit features such as for and section to distribute compute intensive kernels to more than one GPU. We demonstrate the effectiveness of this hybrid approach with some case studies in this paper.

show abstract

“…The first one is the lack of computing frameworks that can easily schedule the workload in such complex environments. Some works have been presented to integrate the use of different programming languages or tools [189,190]. However, the programmer still needs to tackle different design and implementation problems related with each level of parallelism.…”

Section: Problem Description: the Need For Speed And The Lack Of An Umentioning

confidence: 99%

“…However, it does not support conversions for CUDA. Similar to the previous approach, the tool llCoMP [189] is another source-to-source compiler that translates C annotated code to MPI + OpenMP or CUDA code, that is only focused in parallel-loop problems. Additionally, this compiler does not support the joint use of CUDA with the other parallel models, leaving its suitability for heterogeneous environments limited.…”

Section: State Of the Art: Looking For One Tool To Rule All Parallel mentioning

confidence: 99%

Parallel approaches to shortest-path problems for multilevel heterogeneous computing

Arranz¹

View full text Add to dashboard Cite

Modelo paralelo abstracto, APSP, tuning automático de kernels, Boost Graph Library, configuración de la Cache L1, ejecución concurrente de kernels, CUDA, Dijkstra, GPGPU, sistemas heterogéneos, framework HPC, modelo de caracterización de kernels, proceso de caracterización de kernels, balanceo de carga, MPI, comparativa de plataformas de NVIDIA, OpenMP, técnicas de optimización, algoritmos paralelos, SSSP, geometría del bloque de hilos.

show abstract

Optimization strategies in different CUDA architectures using llCoMP

Cited by 15 publications

References 28 publications

Controllers: An abstraction to ease the use of hardware accelerators

Controllers: An abstraction to ease the use of hardware accelerators

Exploring Programming Multi-GPUs Using OpenMP and OpenACC-Based Hybrid Model

Parallel approaches to shortest-path problems for multilevel heterogeneous computing

Contact Info

Product

Resources

About