2013 · 27 citations · 16 references
ComputingComputer ScienceHigh-performance ComputingComputer ArchitectureComputer GraphicsProgramming LanguagesAccelerator ArchitectureComputer Graphics HardwareGraphics Processing Unit ArchitectureGraphics Processing Unit ComputingGraphics Processing UnitsHardware AccelerationAcceleratorsAuto-tuningCompiler SupportCompute Unified Device ArchitectureDirective-based Programming ModelsGpgpu ComputingGpgpu ProgrammingGpu Accelerators
The difficulties posed by GPGPU programming and the need to increase productivity have guided research towards directive-based high-level programs for accelerators. This effort has led to the definition of the OpenACC industry standard. It significantly simplifies writing code for graphics engines leaving the programmer the opportunity to tune the application for the target hardware and input.
16
Nearest neighbor pattern classification
Thomas M. Cover, Peter E. Hart · IEEE Transactions on Information Theory · 1967 · 16.1K citations
The Design and Implementation of FFTW3
Matteo Frigo, Steven G. Johnson · Proceedings of the IEEE · 2005 · 5.2K citations
Auto-tuning a high-level language targeted to GPU codes
Scott Grauer-Gray, Lifan Xu, Robert Searles et al. · 2012 · 460 citations
Using Machine Learning to Focus Iterative Optimization
Felix Agakov, Edwin V. Bonilla, José E Cavazos et al. · 2006 · 427 citations