IPRI - www.ipri.kiev.ua -  IPRI - www.ipri.kiev.ua -
Title (journal) Data Rec., Storage & Processing. — 2013. — Vol. 15, N 1.
Pages 71-81
PDF,DOC, full text
Title (article) Modern Videoadapter Architectures. GPGPU Technology (Part 2)
Authors Pogorilyy S.D, Vitel D.Yu, Vereshchynsky O.A.
Kiev, Ukraine
Annotation General principles of a shared and distributed memory are described in detail for NVidia CUDA technology. Basic patterns of the thread interaction and globals synchronization problems are analyzed. A comparative analysis of the main GPGPU technologies — Nvidia CUDA, OpenCL, Direct Compute — has been provided. Tabl.: 3. Fig.: 3. Refs: 9 titles.
Key words General-purpose graphics processing units (GPGPU), NVidia Compute Unified Device Architecture (CUDA), DirectCompute, OpenCL, Single Instruction Multiple Data (SIMD), Single In¬struction Multiple Threads (SIMT), shaders, Message Passing Interface (MPI), hierarchical thread organi¬zation, synchronization model, memory model, heterogeneous distributed systems, dynamical parallelism, dynamical memory allocation, videoadapter architectures (Tesla, Fermi, Kepler).
File 1-8.pdf