Using Nested Parallelism in OpenMP*

  • Overview

Multi-level parallelism with OpenMP* deserves your consideration—even if you've rejected it in the past. OpenMP nesting is turned off by default by most implementations. Developers generally consider it unsafe due to concerns about oversubscription and the resulting poor application performance. But today—finally—there are better options. Proper considerations of how to express and use nested parallelism can have a profound impact on performance. This webinar discusses successful examples of using nesting with OpenMP using hot teams and explains best practices for exploiting nested parallelism opportunities overall.

Download Slides [PDF 819KB]

Benchmark results were obtained prior to the implementation of recent software patches and firmware updates intended to address exploits referred to as "Spectre" and "Meltdown". Implementation of these updates may make these results inapplicable to your device or system.

Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors. Performance tests, such as SYSmark and MobileMark, are measured using specific computer systems, components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products. For more information, see Performance Benchmark Test Disclosure.

Categories: