Intel® Integrated Performance Primitives

G729 Codec IPP 8.2 doesn't perform better than non IPP implementation


we recently bought Intel® Parallel Studio XE 2015 which has IPP 8.2 version. we are using them with Intel samples for G729 speech codec. I tried using intel 8.0 samples and Intel 6.1 samples. Both of them are not giving better performance than our own implementation. we also have IPP of 6.1 version which is giving better performance than 8.2.

I linked 6.1 G729 samples with 6.1 version and 8.2 version of IPPs out of both 6.1 version gives better performance.

IPP 6.1 version linked with 6.1 version sample  avg per/frame encode time: 21 microsec

ipp_resize_mt example access violation with TBB


I found a read access violation while testing the ipp_resize_mt example. It happens with all ippResize_XXX functions except the nearest neighbor interpolation.

I've checked the cause and found out that it depends on the border flags set:

      if (r.rows().end() != pSrcImage->m_iHeight) // non-bottom
        border = (IppiBorderType)(border | ippBorderInMemBottom);

Why does this produce an access violation with ippResizeLinear but not with ippResizeNearest?

Intel® Parallel Studio XE 2015 Update 1 Composer Edition for C++ Linux*

Intel® Parallel Studio XE 2015 Update 1 Composer Edition for C++ Linux includes the latest Intel C/C++ compilers and performance libraries for IA-32, Intel® 64, and Intel® Many Integrated Core (Intel® MIC) architecture systems.

  • Developers
  • Linux*
  • C/C++
  • Intel® C++ Compiler
  • Intel® C++ Composer XE
  • Intel® Composer XE
  • Intel® Integrated Performance Primitives
  • Intel® Math Kernel Library
  • Intel® Threading Building Blocks
  • Subscribe to Intel® Integrated Performance Primitives