|
General-purpose computing on graphics processing units (GPGPU, rarely GPGP or GP²U) is the use of a graphics processing unit (GPU), which typically handles computation only for computer graphics, to perform computation in applications traditionally handled by the central processing unit (CPU).〔(Fung, et al., "Mediated Reality Using Computer Graphics Hardware for Computer Vision" ), Proceedings of the International Symposium on Wearable Computing 2002 (ISWC2002), Seattle, Washington, USA, 7–10 October 2002, pp. 83–89.〕〔An EyeTap video-based featureless projective motion estimation assisted by gyroscopic tracking for wearable computer mediated reality, ACM Personal and Ubiquitous Computing published by Springer Verlag, Vol.7, Iss. 3, 2003.〕〔("Computer Vision Signal Processing on Graphics Processing Units", Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2004) ): Montreal, Quebec, Canada, 17–21 May 2004, pp. V-93 – V-96〕 The use of multiple graphics cards in one computer, or large numbers of graphics chips, further parallelizes the already parallel nature of graphics processing.〔("Using Multiple Graphics Cards as a General Purpose Parallel Computer: Applications to Computer Vision", Proceedings of the 17th International Conference on Pattern Recognition (ICPR2004) ), Cambridge, United Kingdom, 23–26 August 2004, volume 1, pages 805–808.〕 In addition, even a single GPU-CPU framework provides advantages that multiple CPUs on their own do not offer due to the specialization in each chip.〔S. Mittal and J. Vetter (2015), (A Survey of CPU-GPU Heterogeneous Computing Techniques ), ACM Computing Surveys.〕 Essentially, a GPGPU pipeline is a kind of parallel processing between one or more GPUs and CPUs that analyzes data as if it were in image or other graphic form. While GPUs generally operate at lower frequencies, they usually have many times more cores to make up for it (up to hundreds at least) and can, thus, operate on pictures and graphical data effectively much faster, dozens or even hundreds of times faster than a traditional CPU, migrating data into graphical form and then using the GPU to "look" at it and analyze it can result in profound speedup. GPGPU pipelines developed out of scientific computing. ==History== General-purpose computing on GPUs only became practical and popular after ca. 2001, with the advent of both programmable shaders and floating point support on graphics processors. In particular, problems involving matrices and/or vectors - especially two-, three-, or four-dimensional vectors - were easy to translate to a GPU, which acts with native speed and support on those types. The scientific computing community's experiments with the new hardware started with a matrix multiplication routine (2001); one of the first common scientific programs to run faster on GPUs than CPUs was an implementation of LU factorization (2005). These early efforts to use GPUs as general-purpose processors required reformulating computational problems in terms of graphics primitives, as supported by the two major APIs for graphics processors, OpenGL and DirectX. This cumbersome translation was obviated by the advent of general-purpose programming languages and APIs such as Sh/RapidMind, Brook and Accelerator. These were followed by Nvidia's CUDA, which allowed programmers to ignore the underlying graphical concepts in favor of more common high-performance computing concepts.〔 Newer, hardware vendor-independent offerings include Microsoft's DirectCompute and Apple/Khronos Group's OpenCL.〔 This means that modern GPGPU pipelines can leverage the speed of a GPU without requiring full and explicit conversion of the data to a graphical form. 抄文引用元・出典: フリー百科事典『 ウィキペディア（Wikipedia）』 ■ウィキペディアで「General-purpose computing on graphics processing units」の詳細全文を読む スポンサード リンク
|