Quantcast
Channel: Intel® Integrated Performance Primitives
Viewing all 1294 articles
Browse latest View live

Parallelize single threaded IPP functions

$
0
0

Hi,

is there any description available that describes how to use single threaded IPP functions in a multithreaded environment?

'Simple' functions such as ippiHSVToRGB_8u_C3R that do not use buffers, specs or borders are no problem. Each thread works on its own roi. But what about roi sizes (cpu caches, memory alignment and so on).

And how do I use filters with borders (ippiFilterScharrHorizMaskBorder_8u16s_C1R) , or fft with a spec (ippiFFTFwd_RToPack_32f_C1R), or others using a buffer (ippiFastMarching_8u32f_C1R)?


New requirement on svml_disp.lib?

$
0
0

I'm working on upgrading from IPP 8.1 upd1 to 8.2, and it looks like there is a new dependency on the svml_disp.lib library.  Note that I'm linking against the 64-bit static sequential libraries under Windows.  What is this new dependency?

Thanks,

Peter

Massive deprecation list in 8.2!

$
0
0

Boy was I shocked to find that entire domains in IPP 8.2 have been marked deprecated.  I am a heavy user of routines in the video coding domain and am extremely worried about this wholesale deprecation of probably hundreds of routines.  Where is IPP headed and is there any way to get a stay of execution and have Intel continue to maintain these routines?

Is anyone else worried about this disturbing trend?  Ever since IPP 7.1 I've been replacing deprecated routines with replacements when available, and pragma'ing out warnings.

Thanks,

Peter

Webinar : Build and Optimize Embedded, Mobile, and Internet of Things Applications

$
0
0

Hi,

Now Intel® IPP is available with Intel® System Studio also. We are organizing webinar on Nov. 5 – 9am PDT, register to participate in the online presentation/demo.

Title: Build and Optimize Embedded, Mobile, and Internet of Things Applications
Day /Time: Nov. 5 – 9am PDT
Registration link https://www1.gotomeeting.com/register/702604128

 

Regards,

Naveen Gv

Intel System Studio Team

DUAL LUT

$
0
0

Hi

 

I have the following CPU: i5-4670K (which have the HD graphics 4600).

I would like to know if the HD graphics 4600 has distinct lookup table (LUT) for each video output (HDMI and DVI)? I would like to use two calibrated monitor (one using HDMI output and the other one the DVI output). Thanks Jules

ipp_resize_mt example access violation with TBB

$
0
0

Hello,

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?

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

$
0
0

Hi,

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 6.1 version linked with 8.2 version sample  avg per/frame encode time: 42 microsec

IPP 8.0 version linked with 8.2 version sample  avg per/frame encode time: 46 microsec

Current platform is:

OS: windriver (3.4.43-WR5.0.1.13_standard)

Hardware:  Intel(R) Xeon(R) CPU E5-2650 v2 @ 2.60GHz

Regards

Santosh kasula

ippsSet_32fc throws memory error on "l9" CPUs

$
0
0

Using IPP 8.0.1 on Core i7-4500U and -4600U CPUs (using "l9" IPP) , the ippsSet_32fc() function throws a memory access fault in the following code.  Application built with VS2010.  It does not happen with i7-2600 processor ("e9" IPP).

void bugTest_ippsSet_32fc()
{
    Ipp32fc val;
    val.re = val.im = 0.0f;
   
    int bufflen = 2097152;  //L
    Ipp32fc* buf = ippsMalloc_32fc(bufflen);
    int offset = 446157;  //M
    int setlen = bufflen - (offset+624176-1);  //L-(M+N-1)
   
    ippsSet_32fc(val, buf+offset, setlen);   // Memory fault thrown in this function

    ippsFree(buf);
}

CPU feature value is 0x0000efff for the CPUs that have the error.  IPP version info:

IPP  : Name:ippCore  Ver:8.0.1 (r40318)  Build:8.0.1.40318
IPPs : Name:ippSP AVX2 (l9)  Ver:8.0.1 (r40318)  Build:8.0.1.40318
 


Ipp 8.2 compiling ippiHoughProbLineGetSize_8u_C1R

$
0
0

Hi,

ippcv.h shows ippiHoughProbLineGetSize_8u_C1R, like ippiHoughLineGetSize_8u_C1R, but the following code I cannot compile with VS2010

ippiHoughLineGetSize_8u_C1R( size, delta, 1000, &iBufferSize);

ippiHoughProbLineGetSize_8u_C1R( size, delta, &iSpecSize, &iBufSize);

Only ippiHoughLineGetSize can be compiled, ProbLine fails due to 'identifier not found'.

But this works

typedef IppStatus (__stdcall *pippiHoughProbLineGetSize_8u_C1R)( IppiSize      roiSize,
      IppPointPolar delta,
      int*          pSpecSize,
      int*          pBufSize);

typedef IppStatus (__stdcall *pippiHoughProbLineInit_8u32f_C1R)(
       IppiSize       roiSize,
       IppPointPolar  delta,
       IppHintAlgorithm hint,
       void*  pSpec);

typedef IppStatus (__stdcall *pippiHoughProbLine_8u32f_C1R)(
  const Ipp8u*         pSrc,
        int            srcStep,
        IppiSize       roiSize,
        int            threshold,
        int            lineLength,
        int            lineGap,
        IppiPoint*     pLine,
        int            maxLineCount,
        int*           pLineCount,
        Ipp8u*         pBuffer,
        void* pSpec );

HINSTANCE hInst= LoadLibrary( L"ippcv-8.2.dll");

    HoughProp= (pippiHoughProbLineGetSize_8u_C1R)GetProcAddress( hInst, "ippiHoughProbLineGetSize_8u_C1R");
    HoughProp( size, delta, &iSpecSize, &iBufSize);

The results are correct, in my case 16 lines are returned by

pippiHoughProbLine_8u32f_C1R HoughPropDo;
    HoughPropDo= (pippiHoughProbLine_8u32f_C1R)GetProcAddress( hInst, "ippiHoughProbLine_8u32f_C1R");
    //ippiHoughProbLine_8u32f_C1R( (Ipp8u*)cRes.GetPtr(), cRes.GetWidthStep(), size, 400, 40, 20, LineP, 128, &iLineCount, pBuffer, pSpec);
    HoughPropDo( (Ipp8u*)cRes.GetPtr(), cRes.GetWidthStep(), size, 400, 40, 20, LineP, 128, &iLineCount, pBuffer, pSpec);

So what is the problem with your Header? The functions are in the DLL, I do not know if they are in the LIB.

Performance issue with IPP 8.2 crypto libs

$
0
0

Hello,

I'm faced with performance issue after switching to new IPP 8.2 libraries. I have tested methods of calculating MD5, SHA256 hash and saw that new implementation ippsHashMessage working much more slower than old implementation ippsMD5MessageDigest, ippsSHA256MessageDigest (IPP 7.0.6). Could you please clarify me if this is known issue? And what I can do with this? I'm really don't want downgrade IPP to 7.0.6 version.

Thanks.

Intel® IPP 8.2 Update 1 is now available

$
0
0

Intel® IPP 8.2 Update 1 packages are now ready for download. Intel® IPP is available as part of Intel® Parallel Studio XEIntel® System Studio,  Intel® Integrated Native Developer Experience (Intel® INDE), Intel® Integrated Native Developer Experience 2015 Build Edition for OS X*

What's New in Intel® IPP 8.2 Update 1

  • Added additional optimization for the newest Intel® Atom™ and 4th generation Intel® Core™ (code-named Haswell) processors.
  • Fixed a number of known in the previous release issues and detected later internal and external defects. In particular, the issue 'Flavors of Pyramid functions that operate on 16-bit data overflow on some images and produce incorrect results' is fixed.
  • No changes are made to the functions API and libraries content to maintain binary compatibility with the previous major release.

What's New in Intel® IPP 8.2

  • Core:
    • The ippGetCpuType and ippInitCpu functions are deprecated. Use ippGetCpuFeatures and newly added ippSetCpuFeatures instead.
    • The ippSetAffinity function is deprecated. Internal threading will be disabled in a future Intel IPP release.
  • Signal Processing:
    • Added the following functionality:
      • New multi-rate FIR filters
      • Delay line manipulation functions for FIR Sparse filters
  • Image Processing and Computer Vision:
    • Added the following functionality:
      • Gaussian mixture model (GMM)
      • FastN
      • Line Suppression
      • Histogram of Oriented Gradients (HOG)
      • New Histogram
      • LBPImage with mode support
      • Adaptive Threshold
      • Warp Affine
      • Several new color format conversion functions

For the detailed list of new functions refer to NewFunctionsList.txt available in the documentation directory.

  • In preparation for deprecation in a future release, the following domains are no longer installed by default:
    • Audio Coding (ippAC)
    • Speech Coding (ippSC)
    • Image Compression (ippJP)
    • Video Coding (ippVC)
    • Small Matrices (ippMX)
    • Realistic Rendering (ippRR)
    • Generated Transforms (ippGEN)
    • Data Integrity (ippDI)

For this release, the domains are still available for installation, see below for details. Further details on the deprecation plans for these domains will be provided at http://software.intel.com/sites/products/ipp-deprecated-features-feedback/ when appropriate.

  • Fixed a number of internal and external defects.

 

Image / video codecs with IPP 8

$
0
0

I noticed that both "Image Compression" and "Video Coding" functions are marked as deprecated in ippi.pdf manual.  If I would like to use IPP 8, what do I do for image codec functions?  With 7.1 and earlier, I had used UIC for decoding.  Does UIC still exist?  If not, then what provisions are there for these high-level domains with IPP going forward?

-many thanks

0xFF

$
0
0

Dear Community

Very kindly pleasant about information : wht is it 0x in 0xFF .

Getting started with IPP

$
0
0

Hi,

I have not used IPP before and was tasked to do benchmarking of 2D correlation/convolution function with IPP. I have some questions which will aid in my development works.

1. How do I get a copy of the IPP? I need to use IPP on both Ubuntu and Windows machine, does it mean I need to get 2 license of IPP? How much does it cost?

2. Installation guide. Is there a easy-to-follow installation guide to install IPP on Windows and Ubuntu

3. What IPP functions is available for doing 2D correlation/convolution?

4. I intend to divide a image into overlapping image blocks and apply 2D correlation on each image blocks to achieve some performance boost. Is there similar works done previously?

Thanks.

 

 

static linking with IPP 8.1 -> error ipps-8.0.dll is missing

$
0
0

Hello,

I have a dll project in VS2013 and IPP 8.1 installed. I'm linking the project statically with the ipp 8.1 by setting the option "Use Intel IPP" to "Single-threaded Static Library" in the VS2013 project settings.

The project compiles fine and all the files are found.

However, when I try to load the dll (the final dll of the project, not any intel dll) I get an error that the dll could not be loaded because:
"ipps-8.0.dll is missing".

I don't know why it tries to load the ipps-8.0.dll because I'm using static linking and I'm not using version 8.0 but version 8.1.

Any help appreciated.
Thanks.

Jan Weigel


Usage of different IPP versions. Is it possible?

$
0
0

Hi all!

I use IPP 7.1 in my project.

Everything was fine before one of customers installed our application on PC with application of other vendor. This old application uses Intel Open MP.

Unfortunately dynamic-linking version of IPP uses Open MP too.

So we have 2 different versions of libiomp5md.dll inside PC.

Is it possible to set for IPP correct location of libiomp5md.dll inside C++ code file (without Control Panel settings modification)?

 

Best regards,

Roman

compile a windows driver with ipp8.0

$
0
0

are there some samples?

I dowload the w_ipp_8.0.0.005_legacy_samples, but don't find the code for driver

with ipp5.0 samples, I find some codes in ipp-samples\advanced-usage

thanks

detailed explanation about DPD200259470

Plan for supporting H.265

$
0
0

<p>Dear all,</p>

<p>I am researching several methods to support H.265 decoding feature in my project.</p>

<p>One of our projects are using IPP to decode H.264 video.</p>

<p>Currently IPP does not support H.265 in the latest release.</p>

<p>Is there any plan or schedule to support H.265 codec in IPP?</p>

<p>&nbsp;</p>

<p>Regards,</p>

How to upgrade to 7.1 Update 1

$
0
0

Hello All,

 I need to upgrade current IPP (linux) 7.0.6 to 7.1u1. how to find it ? I tried to contact the sales team (using the online form) but no reply. Any help will be highly appreciable.

 Regards,

Soumit

Viewing all 1294 articles
Browse latest View live


<script src="https://jsc.adskeeper.com/r/s/rssing.com.1596347.js" async> </script>