Questions and Answers from webinar "Image Processing: Stop Developing Code from Scratch"

The following is a selected list of questions and answers from one of Intel® Parallel Studio webinars "Image Processing: Stop Developing Code from Scratch", we thought these may be useful to other developers as reference. If you are interested in taking this recorded webinar, please register it here.

Q: Could you comment on Linux* usage of these tools?
A: Intel® Parallel Studio is mainly targeted to the Windows* C/C++ developers. Intel also offers other software solutions to support Linux, please find more information on other operating systems support at Intel Software Development Product website (including Intel® Integrated Performance Primitives product)

Q: What are the licensing terms for using Intel® Integrated Performance Primitive (Intel® IPP) in commercial products? What about demo / prototype products?
A: Please refer to Intel Software Products end user license agreement document at http://software.intel.com/en-us/articles/intel-software-development-products-license-agreement/.

Also, licensing policy questions are documented in Intel IPP knowledge Base at, http://software.intel.com/en-us/articles/intel-integrated-performance-primitives-faq/

Free code samples/demo are located at http://software.intel.com/en-us/articles/intel-integrated-performance-primitives-samples-license-agreement/

Q: Novice question: With all the efficiency (over handwritten C/C code) that the Intel IPP brings in does it close-in to the performance of image processing and allied ASICs or is it that ASICs are in a totally different level of solution space?
A: When you call Intel IPP , you do not need to deal with ASIC level as the Intel IPP libraries are internally implemented in ASIC, it is transparent for users.

Q: Can you control when Intel IPP will use threading?
A: Yes, you can control threading in Intel IPP by calling ippSetNumThreads() function. Check more on Intel IPP threading FAQs at: http://software.intel.com/en-us/articles/intel-integrated-performance-primitives-intel-ipp-threading-openmp-faq/

Q: In the H.264 example showing performance improvement from 1 thread to 8 threads, is this data on single core? OR multiple threads mean multiple cores in the underlying hardware?
A: Multiple threads on multi core machine.

This article applies to: Intel® Integrated Performance Primitives Knowledge Base, Intel® Parallel Amplifier Knowledge Base, Intel® Parallel Composer Knowledge Base, Intel® Parallel Inspector Knowledge Base