GSWO: A programming model for GPU-enabled parallelization of sliding window operations in image processing
作者：
Highlights：
• A programming model is presented for automated CPU-to-GPU translation of SWO image processing.
• New easy-to-use pragmas are applicable to diversely parallelizable operations in SWO.
• Memory management hierarchy for effective memory creation and data transfer between CPU and GPU.
• A thorough performance evaluation of the model using benchmarks and practical applications.
• Results show performance gains and improved applicability and usability in state-of-the-art.
摘要
•A programming model is presented for automated CPU-to-GPU translation of SWO image processing.•New easy-to-use pragmas are applicable to diversely parallelizable operations in SWO.•Memory management hierarchy for effective memory creation and data transfer between CPU and GPU.•A thorough performance evaluation of the model using benchmarks and practical applications.•Results show performance gains and improved applicability and usability in state-of-the-art.
论文关键词：Parallel computing,Sliding window operation,CUDA,Automatic translation
论文评审过程：Received 17 February 2016, Revised 3 May 2016, Accepted 4 May 2016, Available online 2 July 2016, Version of Record 29 July 2016.
论文官网地址：https://doi.org/10.1016/j.image.2016.05.003
