Intel® IPP 2017 Bug Fixes

NOTE: Defects and feature requests described below represent specific issues with specific test cases. It is difficult to succinctly describe an issue and how it impacted the specific test case. Some of the issues listed may impact multiple architectures, operating systems, and/or languages. If you have any questions about the issues discussed in this report, please visit our Get Help page for support options.

Intel® IPP 2017 Update 3 (28 Apr 2017)

IPPD-1764Added the AVX512 optimization for ippiResize functions.
IPPD-1933ippsFilterMedian_32s overriding the dst buffer
IPPD-2019ippiDilateBorder document error
IPPD-12

IPP Performance Tools document error


Intel® IPP 2017 Update 2 (23 Feb 2017)

DPD200416859ippiFilterBorder_16u_C1R performance regression in 2017 Update 1
DPD200416809some headers files is not "strictly" C, and some compilers reports comping warnings
DPD200590067ippiFilterBorder_8u_C4R bug on the SSE4 optimization code
DPD200589438

multiple definition for "__libm_exp_hi_table_64 symbol", and the compile reports the “__libm_exp_hi_table_64 already defined in libmmt.lib” error

DPD200415831ippInit function reports unknown feature  on the processors with the MPX feature support
DPD200415672wrong result of Image histogram ippiHistogram_8u_C1R function
DPD200588425ippsSqrt_64f_A53 returning the wrong result for the input value DBL_MAX
DPD200414562wrong result by using IPP_INPAINT_TELEA as flag for ippiInpaint function
DPD200588877add AVX512 optimization for ippsFFTwd_CToC_32fc function
DPD200415944document improvement:  improve the description on ippSetNumThreads functions for ippStsNoOperation return value
DPD200415944document improvement: ippiResizeGetSize function returns a minimal non-zero value for the BuffSize size

 

Intel® IPP 2017 Update 1 (1 Nov 2016)

DPD200588266the version number error in the ThreadedFunctionsList.txt file
DPD200414513ippiErode_8u_C1R performance regression for the image size with 640x480
DPD200588147Documentation error for the ippsFilterMedian_64f_I function
DPD200587882ippiFilter_64f_C1R bug creating wrong result for for 1xH mask
Workaround: use ippiFilter_64f_C1R with 2xH mask and set last column as zero.
DPD200585146ippsMax_32f and ippsMin_32f providing inconsistent results for the NaN values in the AVX2 and SSE4.2 processors
DPD200414601the RGBToHLS functions documentation error

Intel® IPP 2017  (6 Sep 2016)

DPD200581260ippsRegExpFind_8u generating stack overflow 
DPD200583297ippiCopy_32f_C1R producing wrong results on AVX optimization code.  Workaround: use ippsCopy_32f on each image line
DPD200583697documentation problems in ippi.h headers:  the descriptions for the filter functions with fixed kernel were wrong
For more complete information about compiler optimizations, see our Optimization Notice.