OpenCL: A Parallel Programming Standard for Heterogeneous Computing Systems

By John E. Stone, D. Gohara, G. Shi. Computing in science & engineering (Print), 2010

1,695 citations recorded by the source corpus.

The OpenCL standard offers a common API for program execution on systems composed of different types of computational devices such as multicore CPUs, GPUs, or other accelerators.

Subfields: Computer Networks and Communications, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/03ff27135b30927ea2a314247fb690b7e56c4215

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

RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing (2019, methodology): “We also present a hardware/software (HW/SW) interface for host-NMP coordination by adopting a heterogeneous computing programming model, similar to OpenCL [35].”
Deep Learning on Image Denoising: An overview (2019, positive): “The GPU uses the CUDA [162], OpenCL [193] and cuDNN [37] platforms to strengthen its parallel computing ability, which exceeds the speed of the CPU by 10 to 30 times.”
AvA: Accelerated Virtualization of Accelerators (2020, background): “Virtualizing an API framework using AvA requires modest developer effort: a single developer virtualized OpenCL in a handful of days, a stark contrast to the person-years of developer effort for VMware’s SVGA II [38] or BitFusion’s FlexDirect [5].”
Horton Tables: Fast Hash Tables for In-Memory Data-Intensive Computing (2016, methodology): “For each of the hash table variants, lookup routines are implemented in OpenCL [66] and run on the GPU, with each implementation independently autotuned for fairness of comparison.”
Where is the data? Why you cannot debate CPU vs. GPU performance without the answer (2011, background): “1 [25], and the OpenCL API supports asynchronous data transfer as well [26].”
A Survey of CPU-GPU Heterogeneous Computing Techniques (2015, positive): “OpenCL [Stone et al. 2010] is an open standard and has been adopted by several vendors.”
The fast azimuthal integration Python library: pyFAI (2015, methodology): “PyOpenCL remains an optional dependency; therefore all OpenCL code features a Python or Cython implementation as well.”
An efficient automated parameter tuning framework for spiking neural networks (2014, methodology): “With the development of mature GPU parallel computing platforms like CUDA (Nickolls et al., 2008) and OpenCL (Stone et al., 2010), GPU accelerated algorithms have been applied to a variety of tasks in scientiﬁc computing.”
Heterogeneity in Mobile Cloud Computing: Taxonomy and Open Challenges (2014, background): “To address these problems, Stone et al. [70] propose OpenCL as a parallel programming standard for heterogeneous computing devices.”
GPU-Accelerated Molecular Modeling Coming Of Age (2010, background): “Although OpenCL provides portability and correctness guarantees across architectures, different architectures have varying warp or wavefront sizes and memorycoalescingrequirements,necessitatingtheuseofplatform oraccelerator-dependentoptimizationsforpeakperformance[36].”
Accelerating Wright–Fisher Forward Simulations on the Graphics Processing Unit (2016, positive): “…another popular low-level language for parallel programming and can be used to program NVIDIA, AMD, Altera, Xilinx, and Intel solutions for massively parallel computation, which include GPUs, CPUs, and even Field Programmable Gate Arrays (Stone et al. 2010; Czajkowski et al. 2012; Jha et al. 2015).”
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].”