how do you check the dependencies in a parallel code? I have developed a parallel code using openmp.

2 posts / 0 new
Last post
For more complete information about compiler optimizations, see our Optimization Notice.

Hi Shiva,

The only way you can do so is by usingthe static verifier tool that you can use to do a static check for data dependency. Please refer to the Composer documentation on its usage. For runtime check you should use the Intel Parallel Inspector, and for fine-tuning the parallel application Intel Parallel Amplifier can be used. To get help on where to add parallelism to existing source code, the Intel Parallel Advisor can be used. Please refer to NOTE below on these products.

Also, just as an FYI, you can use the Qopenmp-report[n] compiler option where n is a number between 0 and 2 can be used to control the OpenmMP* parallelizers level of diagnostic messages. To use this option, you must also specify the /Qopenmp option. If you do not specify n, the default option is /Qopenmp-report1 which displays diagnostic messages indicating loops, regions, and sections successfully parallelized. Because only directives are inserted into the code, it is possible to make incremental code changes

NOTE:Presently, only theIntel Parallel Composer is presently available as part of this Studio product, but please look for e-mails announcing Beta availability of Intel Parallel Studio products in early 2009, including Parallel Advisor, Parallel Inspector, and Parallel Amplifier.

Hope that helps



Leave a Comment

Please sign in to add a comment. Not a member? Join today