Translating Multicore Power Into Application Performance
You first need to know when it is okay for threads to terminate
 |
To upload an avatar photo, first complete your Disqus profile. | View the list of supported HTML tags you can use to style comments. | Please read our commenting policy. |
Data dependence between statements is a straightjacket on the compiler's ability to optimize code for parallelism. So to get the maximum benefit from parallel code, data dependence must be carefully managed
User feedback inspired the flow graph feature in Intel Threading Building Blocks, which allows programmers to express static and dynamic dependency graphs, as well as reactive or event-based graphs.
Manage the data pipelines rather than webs of threads and processes
The latest C/C++ language extension to facilitate parallel programming
