The Experts below are selected from a list of 81 Experts worldwide ranked by ideXlab platform
Michael Gerndt - One of the best experts on this subject based on the ideXlab platform.
-
HICSS - Tuning OpenCL Applications with the Periscope Tuning Framework
2016 49th Hawaii International Conference on System Sciences (HICSS), 2016Co-Authors: Enes Bajrovic, Robert Mijakovic, Jiri Dokulil, Siegfried Benkner, Michael GerndtAbstract:Due to the complexity and diversity of new parallel architectures automatic tuning of parallel applications has become increasingly important for achieving acceptable performance levels as well as performance portability. The European AutoTune project developed a tuning framework which closely integrates and automates performance analysis and performance tuning. The Periscope Tuning Framework relies on a flexible plugin mechanism providing tuning plugins for different tuning aspects. This paper presents plugins for tuning the execution time of OpenCL Kernels on three different architectures, namely standard multicore CPUs, Xeon Phi coprocessors, and GPUs. We present OpenCL tuning via the flags used during offline Kernel Compilation as well as through the selection of the most appropriate NDRange configuration, which defines the organization of parallel threads used for Kernel execution. Both tuning plugins show significant performance impact and a clear dependence on the target architecture and thus improve performance portability via automatic tuning.
-
Tuning OpenCL Applications with the Periscope Tuning Framework
2016 49th Hawaii International Conference on System Sciences (HICSS), 2016Co-Authors: Enes Bajrovic, Robert Mijakovic, Jiri Dokulil, Siegfried Benkner, Michael GerndtAbstract:Due to the complexity and diversity of new parallel architectures automatic tuning of parallel applications has become increasingly important for achieving acceptable performance levels as well as performance portability. The European AutoTune project developed a tuning framework which closely integrates and automates performance analysis and performance tuning. The Periscope Tuning Framework relies on a flexible plugin mechanism providing tuning plugins for different tuning aspects. This paper presents plugins for tuning the execution time of OpenCL Kernels on three different architectures, namely standard multicore CPUs, Xeon Phi coprocessors, and GPUs. We present OpenCL tuning via the flags used during offline Kernel Compilation as well as through the selection of the most appropriate NDRange configuration, which defines the organization of parallel threads used for Kernel execution. Both tuning plugins show significant performance impact and a clear dependence on the target architecture and thus improve performance portability via automatic tuning.
Enes Bajrovic - One of the best experts on this subject based on the ideXlab platform.
-
HICSS - Tuning OpenCL Applications with the Periscope Tuning Framework
2016 49th Hawaii International Conference on System Sciences (HICSS), 2016Co-Authors: Enes Bajrovic, Robert Mijakovic, Jiri Dokulil, Siegfried Benkner, Michael GerndtAbstract:Due to the complexity and diversity of new parallel architectures automatic tuning of parallel applications has become increasingly important for achieving acceptable performance levels as well as performance portability. The European AutoTune project developed a tuning framework which closely integrates and automates performance analysis and performance tuning. The Periscope Tuning Framework relies on a flexible plugin mechanism providing tuning plugins for different tuning aspects. This paper presents plugins for tuning the execution time of OpenCL Kernels on three different architectures, namely standard multicore CPUs, Xeon Phi coprocessors, and GPUs. We present OpenCL tuning via the flags used during offline Kernel Compilation as well as through the selection of the most appropriate NDRange configuration, which defines the organization of parallel threads used for Kernel execution. Both tuning plugins show significant performance impact and a clear dependence on the target architecture and thus improve performance portability via automatic tuning.
-
Tuning OpenCL Applications with the Periscope Tuning Framework
2016 49th Hawaii International Conference on System Sciences (HICSS), 2016Co-Authors: Enes Bajrovic, Robert Mijakovic, Jiri Dokulil, Siegfried Benkner, Michael GerndtAbstract:Due to the complexity and diversity of new parallel architectures automatic tuning of parallel applications has become increasingly important for achieving acceptable performance levels as well as performance portability. The European AutoTune project developed a tuning framework which closely integrates and automates performance analysis and performance tuning. The Periscope Tuning Framework relies on a flexible plugin mechanism providing tuning plugins for different tuning aspects. This paper presents plugins for tuning the execution time of OpenCL Kernels on three different architectures, namely standard multicore CPUs, Xeon Phi coprocessors, and GPUs. We present OpenCL tuning via the flags used during offline Kernel Compilation as well as through the selection of the most appropriate NDRange configuration, which defines the organization of parallel threads used for Kernel execution. Both tuning plugins show significant performance impact and a clear dependence on the target architecture and thus improve performance portability via automatic tuning.
Robert Mijakovic - One of the best experts on this subject based on the ideXlab platform.
-
HICSS - Tuning OpenCL Applications with the Periscope Tuning Framework
2016 49th Hawaii International Conference on System Sciences (HICSS), 2016Co-Authors: Enes Bajrovic, Robert Mijakovic, Jiri Dokulil, Siegfried Benkner, Michael GerndtAbstract:Due to the complexity and diversity of new parallel architectures automatic tuning of parallel applications has become increasingly important for achieving acceptable performance levels as well as performance portability. The European AutoTune project developed a tuning framework which closely integrates and automates performance analysis and performance tuning. The Periscope Tuning Framework relies on a flexible plugin mechanism providing tuning plugins for different tuning aspects. This paper presents plugins for tuning the execution time of OpenCL Kernels on three different architectures, namely standard multicore CPUs, Xeon Phi coprocessors, and GPUs. We present OpenCL tuning via the flags used during offline Kernel Compilation as well as through the selection of the most appropriate NDRange configuration, which defines the organization of parallel threads used for Kernel execution. Both tuning plugins show significant performance impact and a clear dependence on the target architecture and thus improve performance portability via automatic tuning.
-
Tuning OpenCL Applications with the Periscope Tuning Framework
2016 49th Hawaii International Conference on System Sciences (HICSS), 2016Co-Authors: Enes Bajrovic, Robert Mijakovic, Jiri Dokulil, Siegfried Benkner, Michael GerndtAbstract:Due to the complexity and diversity of new parallel architectures automatic tuning of parallel applications has become increasingly important for achieving acceptable performance levels as well as performance portability. The European AutoTune project developed a tuning framework which closely integrates and automates performance analysis and performance tuning. The Periscope Tuning Framework relies on a flexible plugin mechanism providing tuning plugins for different tuning aspects. This paper presents plugins for tuning the execution time of OpenCL Kernels on three different architectures, namely standard multicore CPUs, Xeon Phi coprocessors, and GPUs. We present OpenCL tuning via the flags used during offline Kernel Compilation as well as through the selection of the most appropriate NDRange configuration, which defines the organization of parallel threads used for Kernel execution. Both tuning plugins show significant performance impact and a clear dependence on the target architecture and thus improve performance portability via automatic tuning.
Jiri Dokulil - One of the best experts on this subject based on the ideXlab platform.
-
HICSS - Tuning OpenCL Applications with the Periscope Tuning Framework
2016 49th Hawaii International Conference on System Sciences (HICSS), 2016Co-Authors: Enes Bajrovic, Robert Mijakovic, Jiri Dokulil, Siegfried Benkner, Michael GerndtAbstract:Due to the complexity and diversity of new parallel architectures automatic tuning of parallel applications has become increasingly important for achieving acceptable performance levels as well as performance portability. The European AutoTune project developed a tuning framework which closely integrates and automates performance analysis and performance tuning. The Periscope Tuning Framework relies on a flexible plugin mechanism providing tuning plugins for different tuning aspects. This paper presents plugins for tuning the execution time of OpenCL Kernels on three different architectures, namely standard multicore CPUs, Xeon Phi coprocessors, and GPUs. We present OpenCL tuning via the flags used during offline Kernel Compilation as well as through the selection of the most appropriate NDRange configuration, which defines the organization of parallel threads used for Kernel execution. Both tuning plugins show significant performance impact and a clear dependence on the target architecture and thus improve performance portability via automatic tuning.
-
Tuning OpenCL Applications with the Periscope Tuning Framework
2016 49th Hawaii International Conference on System Sciences (HICSS), 2016Co-Authors: Enes Bajrovic, Robert Mijakovic, Jiri Dokulil, Siegfried Benkner, Michael GerndtAbstract:Due to the complexity and diversity of new parallel architectures automatic tuning of parallel applications has become increasingly important for achieving acceptable performance levels as well as performance portability. The European AutoTune project developed a tuning framework which closely integrates and automates performance analysis and performance tuning. The Periscope Tuning Framework relies on a flexible plugin mechanism providing tuning plugins for different tuning aspects. This paper presents plugins for tuning the execution time of OpenCL Kernels on three different architectures, namely standard multicore CPUs, Xeon Phi coprocessors, and GPUs. We present OpenCL tuning via the flags used during offline Kernel Compilation as well as through the selection of the most appropriate NDRange configuration, which defines the organization of parallel threads used for Kernel execution. Both tuning plugins show significant performance impact and a clear dependence on the target architecture and thus improve performance portability via automatic tuning.
Siegfried Benkner - One of the best experts on this subject based on the ideXlab platform.
-
HICSS - Tuning OpenCL Applications with the Periscope Tuning Framework
2016 49th Hawaii International Conference on System Sciences (HICSS), 2016Co-Authors: Enes Bajrovic, Robert Mijakovic, Jiri Dokulil, Siegfried Benkner, Michael GerndtAbstract:Due to the complexity and diversity of new parallel architectures automatic tuning of parallel applications has become increasingly important for achieving acceptable performance levels as well as performance portability. The European AutoTune project developed a tuning framework which closely integrates and automates performance analysis and performance tuning. The Periscope Tuning Framework relies on a flexible plugin mechanism providing tuning plugins for different tuning aspects. This paper presents plugins for tuning the execution time of OpenCL Kernels on three different architectures, namely standard multicore CPUs, Xeon Phi coprocessors, and GPUs. We present OpenCL tuning via the flags used during offline Kernel Compilation as well as through the selection of the most appropriate NDRange configuration, which defines the organization of parallel threads used for Kernel execution. Both tuning plugins show significant performance impact and a clear dependence on the target architecture and thus improve performance portability via automatic tuning.
-
Tuning OpenCL Applications with the Periscope Tuning Framework
2016 49th Hawaii International Conference on System Sciences (HICSS), 2016Co-Authors: Enes Bajrovic, Robert Mijakovic, Jiri Dokulil, Siegfried Benkner, Michael GerndtAbstract:Due to the complexity and diversity of new parallel architectures automatic tuning of parallel applications has become increasingly important for achieving acceptable performance levels as well as performance portability. The European AutoTune project developed a tuning framework which closely integrates and automates performance analysis and performance tuning. The Periscope Tuning Framework relies on a flexible plugin mechanism providing tuning plugins for different tuning aspects. This paper presents plugins for tuning the execution time of OpenCL Kernels on three different architectures, namely standard multicore CPUs, Xeon Phi coprocessors, and GPUs. We present OpenCL tuning via the flags used during offline Kernel Compilation as well as through the selection of the most appropriate NDRange configuration, which defines the organization of parallel threads used for Kernel execution. Both tuning plugins show significant performance impact and a clear dependence on the target architecture and thus improve performance portability via automatic tuning.
