The OpenCL specification

By A. Munshi. IEEE Hot Chips Symposium, 2009

1,099 citations recorded by the source corpus.

How researchers see this paper

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

An adaptive performance modeling tool for GPU architectures (2010, background): “Hwu University ofIllinois atUrbana-Champaign Urbana,IL61801 {bsadeghi, matthieu, sjp, wgropp, hwu}@illinois.edu Abstract Thispaperpresents an analytical model topredict theperformance ofgeneral-purpose applicationsonaGPU architecture.”
Pegasus: Coordinated Scheduling for Virtualized Accelerator-based Systems (2011, background): “Exacerbating these hardware differences are software challenges, like those caused by the fact that there is no general agreement about programming models and runtimes for accelerator-based systems [19, 28].”
OWL: cooperative thread array aware scheduling techniques for improving GPGPU performance (2013, methodology): “To facilitate ease of programming on these systems, programming models like CUDA [46] and OpenCL [39] have been developed.”
FPGA-Based Accelerators of Deep Learning Networks for Learning and Classification: A Review (2019, methodology): “The adoption of software-level programming models such as the open computing language (OpenCL) standard [93], [94] in FPGA tools made them more attractive to use for deep learning [95], [96].”
Computational Physics on Graphics Processing Units (2012, methodology): “While most of the groups use exclusively NVIDIA’s CUDA-implementation [2], which offers good reliability, flexibility and stability, there are also some groups using the OpenCL standard [99].”