Results 171 to 180 of about 4,239 (217)
Some of the next articles are maybe not open access.
Proceedings of ACM SIGPLAN International Workshop on Libraries, Languages, and Compilers for Array Programming, 2014
GPGPU programming promises high performance. However, to achieve it, developers must overcome several challenges. The main ones are: write and use hyper-parallel kernels on GPU, manage memory transfers between CPU and GPU, and compose kernels, keeping individual performance of components while optimizing the global performance.
Bourgoin, Mathias, Chailloux, Emmanuel
openaire +2 more sources
GPGPU programming promises high performance. However, to achieve it, developers must overcome several challenges. The main ones are: write and use hyper-parallel kernels on GPU, manage memory transfers between CPU and GPU, and compose kernels, keeping individual performance of components while optimizing the global performance.
Bourgoin, Mathias, Chailloux, Emmanuel
openaire +2 more sources
Supernode transformation on GPGPUs
International Journal of Parallel, Emergent and Distributed Systems, 2017AbstractSupernode transformation, or tiling, is a technique that partitions algorithms to improve data locality and parallelism to achieve shortest running time. It groups multiple iterations of nested loops into supernodes to be assigned to processors for processing in parallel.
Yong Chen, Weijia Shang
openaire +1 more source
ACM Transactions on Embedded Computing Systems, 2020
There is a growing number of application domains ranging from multimedia to machine learning where a certain level of inexactness can be tolerated. For these applications, approximate computing is an effective technique that trades off some loss in output data integrity for energy and/or performance gains.
openaire +1 more source
There is a growing number of application domains ranging from multimedia to machine learning where a certain level of inexactness can be tolerated. For these applications, approximate computing is an effective technique that trades off some loss in output data integrity for energy and/or performance gains.
openaire +1 more source
2014 Sixth International Symposium on Parallel Architectures, Algorithms and Programming, 2014
A runtime framework for GPGPU is proposed. It provides a unified interface for applications to easily take advantage of the various computation powers on a heterogeneous environment. Multiple devices and platforms, such as CUDA and OpenCL can be utilized at the same time to achieve a better performance.
Shang-Chieh Lin, Yarsun Hsu
openaire +1 more source
A runtime framework for GPGPU is proposed. It provides a unified interface for applications to easily take advantage of the various computation powers on a heterogeneous environment. Multiple devices and platforms, such as CUDA and OpenCL can be utilized at the same time to achieve a better performance.
Shang-Chieh Lin, Yarsun Hsu
openaire +1 more source
Cortical architectures on a GPGPU
Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Processing Units, 2010As the number of devices available per chip continues to increase, the computational potential of future computer architectures grows likewise. While this is a clear benefit for future computing devices, future chips will also likely suffer from more faulty devices and increased power consumption. It is also likely that these chips will be difficult to
Andrew Nere, Mikko H. Lipasti
openaire +1 more source
ACM SIGGRAPH 2004 Course Notes, 2004
The graphics processor (GPU) on today's commodity video cards has evolved into an extremely powerful and flexible processor. The latest graphics architectures provide tremendous memory bandwidth and computational horsepower, with fully programmable vertex and pixel processing units that support vector operations up to full IEEE floating point precision.
David Luebke +7 more
openaire +1 more source
The graphics processor (GPU) on today's commodity video cards has evolved into an extremely powerful and flexible processor. The latest graphics architectures provide tremendous memory bandwidth and computational horsepower, with fully programmable vertex and pixel processing units that support vector operations up to full IEEE floating point precision.
David Luebke +7 more
openaire +1 more source
2012
The methodological features of realization of neural-like parallel-hierarchical systems on the basis of technologies GPGPU, in a context of research of a hardware-software platform of GPGPU are considered in the work. The analysis of architecture of modern GPU and model of parallel programming GPU is carry out in researches. Also considered the methods
+6 more sources
The methodological features of realization of neural-like parallel-hierarchical systems on the basis of technologies GPGPU, in a context of research of a hardware-software platform of GPGPU are considered in the work. The analysis of architecture of modern GPU and model of parallel programming GPU is carry out in researches. Also considered the methods
+6 more sources
Towards predicting GPGPU performance for concurrent workloads in Multi-GPGPU environment
Cluster Computing, 2020General-purpose graphics processing units (GPGPUs) have been widely adapted to the industry due to the high parallelism of graphics processing units (GPUs) compared with central processing units (CPUs). Especially, a GPGPU device has been adopted for various scientific workloads which have high parallelism.
Sunggon Kim +2 more
exaly +2 more sources
Altis: Modernizing GPGPU Benchmarks
2020 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), 2020This paper presents ALTIS, a benchmark suite for modern GPGPU computing. Previous benchmark suites such as Rodinia and SHOC have served the research community well, but were developed years ago when hardware was more limited, software supported fewer features, and production hardware-accelerated workloads were scarce.
Bodun Hu, Christopher J. Rossbach
openaire +1 more source
ACM SIGPLAN Notices, 2009
GPGPUs have recently emerged as powerful vehicles for general-purpose high-performance computing. Although a new Compute Unified Device Architecture (CUDA) programming model from NVIDIA offers improved programmability for general computing, programming GPGPUs is still complex and error-prone.
Lee, Seyong +2 more
openaire +2 more sources
GPGPUs have recently emerged as powerful vehicles for general-purpose high-performance computing. Although a new Compute Unified Device Architecture (CUDA) programming model from NVIDIA offers improved programmability for general computing, programming GPGPUs is still complex and error-prone.
Lee, Seyong +2 more
openaire +2 more sources