Accelerator: using data parallelism to program GPUs for general-purpose uses

By David Tarditi, Sidd Puri, Jose Oglesby. ASPLOS XII, 2006

355 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/abefa9dca1fe0c8999d45ccdbed44f28c66a737b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Hardware and Architecture

Citations in the corpus

A performance study of general-purpose applications on graphics processors using CUDA (2008, background): “Brook [4], Sh [15] and its commercial successor RapidMind, and Microsoft's Accelerator [27] are notable examples.”
Merge: a programming model for heterogeneous multi-core systems (2008, background): “The Merge framework has been prototyped on a heterogeneous platform consistingofan IntelCore2DuoCPUand an 8-core 32-thread Intel Graphics and Media Accelerator X3000, and a homogeneous 32-way Unisys SMP system with Intel Xeon processors.”
The jabberwocky programming environment for structured social computing (2011, background): “ManReduce takes its inspiration from MapReduce [4], Dryad [12], and GPU shader languages [22].”
GPU Computing (2008, methodology): “Similar to Accelerator, RapidMind uses delayed evaluation and online compilation to capture and optimize the user’s application code along with operator and type extensions to C++ to provide direct support for arrays.”
Accelerating Advanced MRI Reconstructions on GPUs (2008, background): “… on a quad- Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies arenot made or distributed for pro.t or commercial advantage and that copies bear this notice and the full citation on the .rst page.”
Mars: A MapReduce Framework on graphics processors (2008, neutral): “They usually expose a general-purpose, massively multithreaded parallel computing architecture and provide a programming environment similar to multi-threaded C/C++. High-level programming frameworks such as Accelerator [30] and Brook [5] are also developed to better facilitate GPGPU programmin”
Relational joins on graphics processors (2008, methodology): “Accelerator: using data parallelism to program GPUs for generalpurpose uses.”
PyCUDA and PyOpenCL: A scripting-based approach to GPU run-time code generation (2009, neutral): “In the context of GPUs, metaprogramming has so far been applied mainly in a graphics and image processing context [26, 54] and to ease the use of a standard rendering pipeline for general-purpose uses [46].”
Evolution of image filters on graphics processor units using Cartesian Genetic Programming (2008, methodology): “The API allows one to perform parallel operations on the arrays, largely in matrix type operations.”
Optimization principles and application performance evaluation of a multithreaded GPU using CUDA (2008, background): “Accelerator [26] is another system that uses data-parallel arrays to perform general-purpose computation on the GPU.”
Dryad: distributed data-parallel programs from sequential building blocks (2007, neutral): “Condor [37] was an early example of such a system in a distributed setting, and we take more direct inspiration from three other models: shader languages developed for graphic processing units (GPUs) [30, 36], Google s MapReduce system [16], and parallel databases [18].”
vCUDA: GPU accelerated high performance computing in virtual machines (2009, background): “The modern GPU is not only a powerful graphics engine but also a highly parallel programmable processor featuring peak arithmetic and memory bandwidth [10, 28, 29].”