<--- Back to Details
First PageDocument Content
Computing / Computer architecture / Concurrent computing / Parallel computing / GPGPU / OpenCL / Linux kernel / Kernel / Thread / Compute kernel / CUDA / Loadable kernel module
Date: 2014-12-23 06:10:55
Computing
Computer architecture
Concurrent computing
Parallel computing
GPGPU
OpenCL
Linux kernel
Kernel
Thread
Compute kernel
CUDA
Loadable kernel module

Exploiting heterogeneous parallelism with the Heterogeneous Programming Library

Add to Reading List

Source URL: www.des.udc.es

Download Document from Source Website

File Size: 2,77 MB

Share Document on Facebook

Similar Documents

Computing / Software engineering / Computer programming / Parallel computing / Graphics hardware / Object-oriented programming languages / GPGPU / Cross-platform software / CUDA / General-purpose computing on graphics processing units / AOS and SOA / Thread

Object Support in an Array-Based GPGPU Extension for Ruby Matthias Springer Hidehiko Masuhara Department of Mathematical and Computing Sciences, Tokyo Institute of Technology, Japan

DocID: 1xV2l - View Document

45 Introduction to GPGPU for AI Conan Bourke and Tomasz Bednarz 45.1 45.2

DocID: 1v5LF - View Document

Fast GPGPU Based Quadtree Construction Joshua Gluck Advisor: Andrew Danner May 1, 2014 Abstract We introduce a method for fast quadtree construction on the Graphics Processing

DocID: 1tLKy - View Document

OWL: Cooperative Thread Array Aware Scheduling Techniques for Improving GPGPU Performance Adwait Jog† Onur Kayiran† Mahmut T. Kandemir†

DocID: 1tLqi - View Document

Specification and verification of GPGPU programs Stefan Blom, Marieke Huisman and Matej Mihelˇci´c University of Twente, Enschede, The Netherlands {s.c.c.blom,m.huisman}@utwente.nl November 8, 2013

DocID: 1tqg6 - View Document