Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 10,000 papers for “GPU computing”

Coprocessor Computing with FPGA and GPU

Song Jun Park, Dale R. Shires, Brian J. Henz · 2008

Specialized secondary processing units, such as field programmable gate arrays (FPGAs) and graphics processing units (GPUs), attempt to tackle the time consuming applications containing high computational requirements. In order to achieve acceleration, FPGAs allow a customizable architecture and Nvidia GPUs offer up to 16 cores with 128 stream processors. The following research presents the experiences of designing integer and floating-point based algorithms for Xilinx FPGAs and programming on NVIDIA graphics card. For test case applications, an encryption function and a sorting algorithm were investigated. The implementation of an encryption algorithm depicts the performance results of an integer application composed of bit operations and a simple sort algorithm tests the effects of a floating-point application containing large numbers of multiple independent sorting instructions.

Cited by 13

How is computing changing? Why GPU?

Fangzhou Xiao · 2014

What we are doing? GPUs are designed for compute-intensive, highly paralleled computation, rather than data caching and flow control. With hundreds of buildin cores and thousands of concurrent threads, the GPU is capable of handling enormous computations in parallel. Yet a single GPU core is much slower than CPU core. Originally designed for graphics acceleration, the GPU's highly capability of calculation has been applied to General Purpose Computations. Over 100 million GPUs have already been deployed in computer around the world. These can be used to improve the performance of your computer. The idea is to use the GPU to undertake some tasks that can be

Cited by 0

GPU computing for R Statistical Environment

Jaideep Singh, Ipseeta Aruni · 2011

The idea of offering Graphics Processing Unit (GPU) computing solutions using CUDA to R users has been in the form of adding new functions to R that can be used to transfer data and perform computations on the GPUs

Cited by 0

DEPRECATED: GPU Computing for Cognitive Robotics

Peniak, Martin · Plymouth University · 2014

This thesis presents the first investigation of the impact of GPU computing on cognitive robotics by providing a series of novel experiments in the area of action and language acquisition in humanoid robots and computer vision. Cognitive robotics is concerned with endowing robots with high-level cognitive capabilities to enable the achievement of complex goals in complex environments. Reaching the ultimate goal of developing cognitive robots will require tremendous amounts of computational power, which was until recently provided mostly by standard CPU processors. CPU cores are optimised for serial code execution at the expense of parallel execution, which renders them relatively inefficient when it comes to high-performance computing applications. The ever-increasing market demand for high-performance, real-time 3D graphics has evolved the GPU into a highly parallel, multithreaded, many-core processor extraordinary computational power and very high memory bandwidth. These vast computational resources of modern GPUs can now be used by the most of the cognitive robotics models as they tend to be inherently parallel. Various interesting and insightful cognitive models were developed and addressed important scientific questions concerning action-language acquisition and computer vision. While they have provided us with important scientific insights, their complexity and application has not improved much over the last years. The experimental tasks as well as the scale of these models are often minimised to avoid excessive training times that grow exponentially with the number of neurons and the training data. This impedes further progress and development of complex neurocontrollers that would be able to take the cognitive robotics research a step closer to reaching the ultimate goal of creating intelligent machines. This thesis presents several cases where the application of the GPU computing on cognitive robotics algorithms resulted in the development of large-scale neurocontrollers of previously unseen complexity enabling the conducting of the novel experiments described herein.

Cited by 0Open access

High Performance Computing via a GPU

Gang Chen, Guo‐Bo Li, Songwen Pei et al. · 2009

Graphics processor units (GPUs), such as the AMD FireStream series, offer a tremendous computing power that is frequently an order of magnitude larger than even the most modern multi-core CPUs, making them an attractive platform for high performance computing due to their relative cheapness compared with conventional PC clusters. General-purpose computing on GPUs (GPGPU) is becoming popular in HPC because of its high peak performance. This paper investigates current technology that enables a GPU to accelerate HPC applications. As a representative kernel program in HPC, the speed of matrix multiplication plays an important role in the whole performance of the application. We introduce a new parallel algorithm to accelerate this operation. Comparing the speed of the computation through the CPU and the GPU, the result demonstrates that calculations are preformed considerably faster through the GPU than through the CPU.

Cited by 17

A systems perspective on GPU computing

Naila Farooqui · 2016

Over a distinguished career, Regents Professor Karsten Schwan has made significant contributions across a diverse array of topics in computer systems, including operating systems for multi-core platforms, virtualization technologies, enterprise middleware, and high-performance computing. In this paper, we summarize his legacy of key research contributions in general-purpose GPU computing. His vision encompassed the conceptualization, implementation, and demonstration of systems abstractions and runtime methods to elevate GPUs into first-class citizens in today's and future heterogeneous computing environments. To this end, his contributions include novel scheduling and resource management abstractions, runtime specialization, and novel data management techniques to support scalable, distributed GPU frameworks.

Cited by 1

The Rise of GPU Computing - Things You Must Know About GPU

dereckshayes · Zenodo (CERN European Organization for Nuclear Research) · 2020

There are loads of speaking happening within the pc graphics industry like 3D games and the best plant identification app. NVIDIA woke up the world to the power of graphics when it invented the GPU long back in October 1999.\n\nBefore that nobody knew what is GPU and how does it work. However, since then there was persistently new standards set in visual computing with breathtaking interactive graphics accessible on gadgets starting from potable media participant to notebooks to workstations.\n\nThe graphics card manufacturer’s expertise in programmable GPUs has led to breakthroughs in parallel processing which makes supercomputing inexpensive and widely accessible. The GPU was conceived primarily for the task of rendering graphics. For the avid teen gamer.\n\nHowever, in the early 2000's, the engineers at NVIDIA decided that the GPU rendering shaders and high throughout ALU/arithmetic units meant that the GPU made for an exceptional parallel computing platform. Before parallel algorithms were implemented using awkward OpenGL/DirectX techniques that were terribly cumbersome for the non-graphics programmer.\n\nThus the Compute Unified architecture was born and paved the way for the CUDA programming language. It’s a language that can be accessible to anyone who knows C and C++ and they could well know how CUDA works.\n\nOne of the main reasons for the move towards parallel processing is that we have reached the point where increasing clock speed on the processor is no longer available. The only substantial way of increasing overall processor speed is to increase the numbers of processors. Even in the CPU world, once the Pentium 4's reached, Intel had no choice but to move to Dual Core and Quad Core architectures.\n\nIn the world of GPU vs CPU computing, there is a number of games currently played by all parties. Intel recently made claims that the GPU is only about 10-14 x faster than their CPU cores, while NVIDIA claimed that performance is really 60x-100x. Unsurprisingly both of these companies employed professional engineers to implement extremely low-level optimizations to swing the odds in their favor.\n\nThe latest about mobile graphics throw light on the latest going on mobile graphics technology. The latest trend in power management is delivered by energy-efficient technology like Switchable Graphics. Imagine combining the low power advantages of an integrated graphics processor with the performances of a discrete graphics processor.\n\nWith Switchable Graphics now you can have the best of both worlds with maximum performance when you need it and long battery life when on the go. Thanks to the booming video game industry and the fierce competition between ATI and NVIDIA, the unending thirst for better graphics cards is likely for the next decade. In all its significant boon for all the computational scientists.

Cited by 0Open access

GPU computing in discrete optimization. Part I: Introduction to the GPU

André R. Brodtkorb, Trond Runar Hagen, Christian Schulz et al. · EURO Journal on Transportation and Logistics · 2013

In many cases there is still a large gap between the performance of current optimization technology and the requirements of real world applications. As in the past, performance will improve through a combination of more powerful solution methods and a general performance increase of computers. These factors are not independent. Due to physical limits, hardware development no longer results in higher speed for sequential algorithms, but rather in increased parallelism. Modern commodity PCs include a multi-core CPU and at least one GPU, providing a low cost, easily accessible heterogeneous environment for high performance computing. New solution methods that combine task parallelization and stream processing are needed to fully exploit modern computer architectures and profit from future hardware developments. This paper is the first part of a series of two, where the goal of this first part is to give a tutorial style introduction to modern PC architectures and GPU programming. We start with a short historical account of modern mainstream computer architectures, and a brief description of parallel computing. This is followed by the evolution of modern GPUs, before a GPU programming example is given. Strategies and guidelines for program development are also discussed. Part II gives a broad survey of the existing literature on parallel computing targeted at modern PCs in discrete optimization, with special focus on papers on routing problems. We conclude with lessons learnt, directions for future research, and prospects.

Cited by 42Open access

Computación de Alto Desempeño en GPU (High Performance Computing in GPU)

María Fabiana Piccoli · SHILAP Revista de lepidopterología · 2012

Through this textbook (written in Spanish), the author introduces the GPU as a parallel computer that is able to solve general-propose problems. The book has a didactic approach, it includes the first steps to CUDA programming, some tips to take account to develop good applications performance, many examples and exercises.

Cited by 0Open access