English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Automatic compiler phase selection/ordering has traditionally been focused onCPUs and, to a lesser extent, FPGAs. We present experiments regarding compilerphase ordering specialization of OpenCL kernels targeting a GPU. We useiterative exploration to specialize LLVM phase orders on 15 OpenCL benchmarksto an NVIDIA GPU. We analyze the generated NVIDIA PTX code for the variousversions to identify the main causes of the most significant improvements andpresent results of a set of experiments that demonstrate the importance ofusing specific phase orders. Using specialized compiler phase orders, we wereable to achieve geometric mean improvements of 1.54x (up to 5.48x) and 1.65x(up to 5.7x) over PTX generated by the NVIDIA CUDA compiler from CUDA versionsof the same kernels, and over execution of the OpenCL kernels compiled fromsource with the NVIDIA OpenCL driver, respectively. We also evaluate the use ofcode-features in the OpenCL kernels. More specifically, we evaluate an approachthat achieves geometric mean improvements of 1.49x and 1.56x over the sameOpenCL baseline, by using the compiler sequences of the 1 or 3 most similarbenchmarks, respectively.

Improving OpenCL Performance by Specializing Compiler Phase Selection and Ordering