I try to use Advisor XE to parallelize my code written in Fortran. Unfortunately the compliler does not recognize the USE ADVISOR_ANNOTATE statement, and I get the error message upon compiling:
error #7002: Error in opening the compiled module file. Check INCLUDE paths. [ADVISOR_ANNOTATE]
I tried to set compiler options and settings according to the Advisor Tutorial, but seemingly I did something wrong, some library is certainly missing. Could you pls. help what to do?
After you launch the Microsoft Visual Studio* or Intel® Advisor GUI environment and choose your target, you can begin the process of using the Intel Advisor tools to help you add parallelism into parts of your program.
To launch the Intel Advisor tools, use one of the following:
To launch the Intel AdvisorStandalone GUI, use the advixe-gui command after you set up your command line environment or use the supplied Start > Intel Parallel Studio XE > Analyzers menu shortcut.
A project serves as a reusable container for your application. It contains the location of the target executable and its associated properties, as well as a previously collected result from Intel Advisor tool analysis.
The Trip Counts tool runs and watches your running serial program's target executable. After it analyzes (profiles) your target's execution, it updates the Survey Report window with information about loop trip counts.
This topic describes two fundamental types of program execution - data parallelism and task parallelism - and the task patterns of each.
Task overhead is the time spent creating a task and getting it assigned to a thread, and also the time spent stopping or pausing the thread when the task is complete.
The compiler attempts to produce high-performance code by implementing all sorts of optimizations. But, in some cases, the compiler cannot vectorize code because of non-unit memory strides, or the arrangement of data structures (for example, by using "arrays of structures" instead of "structures of arrays").
Before you can add parallel code , you must first choose a parallel framework.
There are two popular mechanisms for using threads - either use high-level parallel frameworks or explicit threading APIs. Intel recommends using parallel frameworks for both ease of use and their ability to optimize for different situations.