This sample uses the same buffer in several different non-blocking sends at the same time. The MPI standard does not allow that because some MPI implementations might have to manipulate the memory.
Because a violation of this rule has no negative consequences with most MPI implementations and is convenient, many applications contain the same error. They should be fixed to increase portability.
Linux*:
Ensure that the corresponding compiler, Intel® MPI Library, and Intel® Trace Analyzer and Collector are already in your PATH, and complete these steps:
Build the sample:
$ make
Run the sample:
$ make run
Review the output.
Ensure that the corresponding compilers, Microsoft* Visual Studio*, Intel® MPI Library, and Intel® Trace Analyzer and Collector are already in your PATH, and complete these steps:
Build the sample:
> build.bat release
Run the sample:
> build.bat run
Review the output.