%0 Book Section %1 Huang2014-lv %A Huang, Dafei %A Wen, Mei %A Xun, Changqing %A Chen, Dong %A Cai, Xing %A Qiao, Yuran %A Wu, Nan %A Zhang, Chunyuan %B Euro-Par 2014 Parallel Processing %D 2014 %I Springer International Publishing %K Expose Memory_access Memory_hierarchy OpenCL %P 210--221 %T Automated Transformation of GPU-Specific OpenCL Kernels Targeting Performance Portability on Multi-Core/Many-Core CPUs %X When adapting GPU-specific OpenCL kernels to run on multi-core/many-core CPUs, coarsening the thread granularity is necessary and thus extensively used. However, locality concerns exposed in GPU-specific OpenCL code are usually inherited without analysis, which may give side-effects on the CPU performance. When executing GPU-specific kernels on CPUs, local-memory arrays no longer match well with the hardware and the associated synchronizations are costly. To solve this dilemma, we actively analyze the memory access patterns by using array-access descriptors derived from GPU-specific kernels, which can thus be adapted for CPUs by removing all the unwanted local-memory arrays together with the obsolete barrier statements. Experiments show that the automated transformation can satisfactorily improve OpenCL kernel performances on Sandy Bridge CPU and Intel's Many-Integrated-Core coprocessor.

@incollection{Huang2014-lv, abstract = {When adapting GPU-specific OpenCL kernels to run on multi-core/many-core CPUs, coarsening the thread granularity is necessary and thus extensively used. However, locality concerns exposed in GPU-specific OpenCL code are usually inherited without analysis, which may give side-effects on the CPU performance. When executing GPU-specific kernels on CPUs, local-memory arrays no longer match well with the hardware and the associated synchronizations are costly. To solve this dilemma, we actively analyze the memory access patterns by using array-access descriptors derived from GPU-specific kernels, which can thus be adapted for CPUs by removing all the unwanted local-memory arrays together with the obsolete barrier statements. Experiments show that the automated transformation can satisfactorily improve OpenCL kernel performances on Sandy Bridge CPU and Intel's Many-Integrated-Core coprocessor.}, added-at = {2015-04-10T18:02:47.000+0200}, author = {Huang, Dafei and Wen, Mei and Xun, Changqing and Chen, Dong and Cai, Xing and Qiao, Yuran and Wu, Nan and Zhang, Chunyuan}, biburl = {https://www.bibsonomy.org/bibtex/2fccf7487631bc118042781a584a26857/christophv}, booktitle = {{Euro-Par} 2014 Parallel Processing}, interhash = {c2c3eb9c6efdc9cd8a9ba38f76cf9893}, intrahash = {fccf7487631bc118042781a584a26857}, keywords = {Expose Memory_access Memory_hierarchy OpenCL}, pages = {210--221}, publisher = {Springer International Publishing}, series = {Lecture Notes in Computer Science}, timestamp = {2016-01-04T14:22:08.000+0100}, title = {Automated Transformation of {GPU-Specific} {OpenCL} Kernels Targeting Performance Portability on {Multi-Core/Many-Core} {CPUs}}, year = 2014 }