%0 Book Section %1 Karrenberg2012-ca %A Karrenberg, Ralf %A Hack, Sebastian %B Compiler Construction %D 2012 %I Springer Berlin Heidelberg %K All Barrier_synchronisation CPU Contrinuations Control_flow_analysis Expose OpenCL Vectorization %P 1--20 %T Improving Performance of OpenCL on CPUs %X Data-parallel languages like OpenCL and CUDA are an important means to exploit the computational power of today's computing devices. In this paper, we deal with two aspects of implementing such languages on CPUs: First, we present a static analysis and an accompanying optimization to exclude code regions from control-flow to data-flow conversion, which is the commonly used technique to leverage vector instruction sets. Second, we present a novel technique to implement barrier synchronization. We evaluate our techniques in a custom OpenCL CPU driver which is compared to itself in different configurations and to proprietary implementations by AMD and Intel. We achieve an average speedup factor of 1.21 compared to na\"ıve vectorization and additional factors of 1.15--2.09 for suited kernels due to the optimizations enabled by our analysis. Our best configuration achieves an average speedup factor of 2.5 against the Intel driver.

@incollection{Karrenberg2012-ca, abstract = {Data-parallel languages like OpenCL and CUDA are an important means to exploit the computational power of today's computing devices. In this paper, we deal with two aspects of implementing such languages on CPUs: First, we present a static analysis and an accompanying optimization to exclude code regions from control-flow to data-flow conversion, which is the commonly used technique to leverage vector instruction sets. Second, we present a novel technique to implement barrier synchronization. We evaluate our techniques in a custom OpenCL CPU driver which is compared to itself in different configurations and to proprietary implementations by AMD and Intel. We achieve an average speedup factor of 1.21 compared to na{\"{\i}}ve vectorization and additional factors of 1.15--2.09 for suited kernels due to the optimizations enabled by our analysis. Our best configuration achieves an average speedup factor of 2.5 against the Intel driver.}, added-at = {2015-04-10T18:02:47.000+0200}, author = {Karrenberg, Ralf and Hack, Sebastian}, biburl = {https://www.bibsonomy.org/bibtex/270be730ec1f217d3f20f46743e108820/christophv}, booktitle = {Compiler Construction}, interhash = {1571e210fa371b32ef1c19695e0ba0bf}, intrahash = {70be730ec1f217d3f20f46743e108820}, keywords = {All Barrier_synchronisation CPU Contrinuations Control_flow_analysis Expose OpenCL Vectorization}, pages = {1--20}, publisher = {Springer Berlin Heidelberg}, series = {Lecture Notes in Computer Science}, timestamp = {2016-01-04T14:22:08.000+0100}, title = {Improving Performance of {OpenCL} on {CPUs}}, year = 2012 }