Quantcast
Channel: Intel® Software - Intel® Integrated Performance Primitives
Viewing all 1489 articles
Browse latest View live
↧

Effect of disable FTZ mode.

July 6, 2015, 1:55 am
$
0
0

In this link : https://software.intel.com/en-us/forums/topic/542786

The effect describe as this sentence: "This bit doesn't affect correctness of IPP functions, in some rare cases it can affect performance only."

 

1. Correctness of calculation

When program disables FTZ mode, this mode doesn't affect correctness of IPP functions.
However, is correctness of other functions of Intel affected? (Ex: SIMD)

 

2. Decrease in performance
When does decrease in performance occur?
Does it happen in float calculation when underflow occurs?
Do you have any detail information (such as, how many percents, how may seconds ...) about "decrease in performance" in following cases?
- In case of one calculation.
- In case of one hundred million calculations.
If this phenomenon gives a serious effect in performance, what should do I in order to resolve this problem(avoid underflow exception)?
If you have any hint for this case, please tell me. I appreciate for your support.

↧
Search

FFT 16bits

July 6, 2015, 2:26 am
$
0
0

Hello,

I try to change the exemple found on https://software.intel.com/en-us/articles/how-to-use-intel-ipp-s-1d-four...

To use 16 bits instead of 32, but I have linking problems:

icc fftIPP_16.c -o fftIPP_16 -L/opt/intel/composer_xe_2015.3.187/ipp/../compiler/lib -lm -lippcore -lipps -lippi

Undefined symbols for architecture x86_64:

  "_ippsDFTFwd_CToC_16sc", referenced from:

      _main in iccGavA8K.o

  "_ippsDFTGetSize_C_16sc", referenced from:

      _main in iccGavA8K.o

  "_ippsDFTInit_C_16sc", referenced from:

      _main in iccGavA8K.o

  "_ippsDFTInv_CToC_16sc", referenced from:

      _main in iccGavA8K.o

ld: symbol(s) not found for architecture x86_64

Any Idea of what's wrong? Which library should I use instead?

↧
↧

Why ippiFilter should be deprecated?

July 6, 2015, 8:05 am
$
0
0

 Hello,

 I'm a ten-year user of the IPP.
 I've been using ippiFilter in many parts of my codes. And I found that the function is deprecated.

 The manual recommends that I should use ippiFilterBorder instead.
 But I wonder why ippiFilter is obsolete.

 I think that ippiFilterBorder has the function of ippiFilter with some border options.
 But there are many cases that border options don't be needed or a user may want to copy borders by oneself.
 So, I think that ippiFilter is still needed in these cases and should not be replaced with ippiFilterBorder.
 ippiFilter is very important base function in the image processing as you know.

 Do I use ippiFilterBorder even when I don't need arguments like border, borderValue, pSpec and pBuffer?
 Should I copy borders even if I filter a small inner ROI which don't need to extend borders?
 I don't want to add allocate and initialize functions like ippiFilterBorderGetSize, ippsMalloc and ippiFilterBorderInit, either.
 It doesn't have any benefit even for speed issue.

 I hope that ippiFilter is not deprecated even for backward compatibility.
 ippiFilterRow and ippiFilterColumn functions are not deprecated, either.

 Thank & regards,

 Dongkyu

↧

Linux support of ippsVLCDecodeOne

July 8, 2015, 1:38 pm
$
0
0

Hi,

I have a Windows application developed a while ago using the Intel IPP 7. One of the function that it uses is ippsVLCDecodeOne(). Now I am trying to port that code to Linux. I downloaded and installed the latest Composer XE 2015 for C++ Linux Update 3, but I am not able to find that function.

Can you tell me if that function is not supported in Linux?

I try to install the latest Windows version of Composer XE, and I can find the function, although its marked as deprecated. In fact, I notice Linux has less header files than Windows, e.g. ippac.h, ippsc.h, ippvc.h are not in Linux.

Thanks

Steve

 

↧

how can i get ipp example.

July 10, 2015, 1:05 am
$
0
0

I purchased Intel Integrated Native Developer Experience (Intel INDE) Ultimate Edition,and got a setup file(w_inde_2015.2.027.exe).
In the installation directory where the IPP file is very small, only:
sources/ipp-examples/common
sources/ipp-examples/ipp_fft
sources/ipp-examples/ipp_resize_mt
sources/ipp-examples/ipp_thread
sources/ipp-examples/ipp_thread_mic

do not know where to get IPP sample ?

↧
↧

how can i get ipp example.

July 10, 2015, 1:05 am
$
0
0

I purchased Intel Integrated Native Developer Experience (Intel INDE) Ultimate Edition,and got a setup file(w_inde_2015.2.027.exe).
In the installation directory where the IPP file is very small, only:
sources/ipp-examples/common
sources/ipp-examples/ipp_fft
sources/ipp-examples/ipp_resize_mt
sources/ipp-examples/ipp_thread
sources/ipp-examples/ipp_thread_mic

do not know where to get IPP sample ?

↧

Filter with single diagonal kernel

July 10, 2015, 3:06 am
$
0
0

 Hello,

 I've been filtering with 8 single width directional kernels.(0, 45, 90,..., 270 and 315 degrees)

 For horizontal and vertical kernels I use FilterRow and FilterColumn.
 But for diagonal directions there's no filter for single width kernel like FilterRow and FilterColumn. 

 So, I've been using kernels like below for diagonal directions.

 0 0 0 0 k4
 0 0 0 k3 0
 0 0 k2 0 0
 0 k1 0 0 0
 k0 0 0 0 0

 Filtering with these kernels is much slower than single row or column filtering.

 How can I boost up the speed for filtering with single width diagonal kernels?
 Any good idea?

 Thanks & regards.

 Dongkyu.

↧

Setting FTZ mode using Intel Compiler Option.

July 12, 2015, 8:11 pm
$
0
0

Have two conflictual points as below:

1. Can setting

The /Qftz- option used to disable FTZ mode.

It is descripts as these sentence "The -ftz and /Qftz options, when applied to the main program, set the FTZ and the DAZ hardware flags. The -no-ftz and /Qftz- options leave the flags as they are". Reference following link:https://software.intel.com/sites/products/documentation/doclib/iss/2013/compiler/cpp-lin/GUID-1659EAE1-583E-44EE-BDEA-7C68C46061C7.htm

 

2. Can’t setting

Can’t set FTZ mode by using Intel Compiler Option.

It is descripts as these sentence "I've said that IPP is built without this switch and FTZ bit is set to 1 in the IPP dllMailn() function - this behavior can't be changed in your app.".  Reference following link: https://software.intel.com/en-us/forums/topic/542786

 

So, can set FTZ mode using Intel Compiler Option or can’t?

If can set, why I doesn’t used /Qftz- option? The reason is version of IPP, isn’t it?

(I use: Visual Studio 2008 SP1, Intel Parallel Studio 2011)

↧
Search

Effect of disable FTZ mode.

July 12, 2015, 11:42 pm
$
0
0

In this link : https://software.intel.com/en-us/forums/topic/542786

The effect describe as this sentence: "This bit doesn't affect correctness of IPP functions, in some rare cases it can affect performance only."

 

1. Correctness of calculation

When program disables FTZ mode, this mode doesn't affect correctness of IPP functions.
However, is correctness of other functions of Intel affected? (Ex: SIMD)

↧
↧

Is it still possible to purchase Intel IPP 6.1

July 13, 2015, 7:23 am
$
0
0

Hello,

My company purchased a software where we have become resposible of development, maintenance and sale. IPP 6.1 was used for developing the SW using C++ under windows.

Correct me if I am wrong, but as per other posts I have concluded the following:

1- IPP is no longer available as a standalone product. This means we have to buy one of the suites. From what I saw, the most cost efficient would be Intel® Parallel Studio XE with a price of around $700

2- With a new license, it is possible to download older product versions.

This being said, I want to make sure that it is possible to download IPP 6.1 in case we buy a new license.

I would appreciate it if you clarify any misunderstanding from my side and if you could advise if the above is the most suitable approach for my case.

Best Regards,

↧

IPP Huffman encoding/decoding functions deprecated, substituation?

July 13, 2015, 1:07 pm
$
0
0

I'am wondering why all the Huffman encoding/decoding functions are deprecated. What functions should I use instead, or will Huffman encoding/decoding no longer be supported in future releases of IPP?

Regards Torsten

Spelling mistake in topic, correct is substitution.

 

 

↧

Non existing ipps Random 64f variants as ippsRandGauss_64f

July 15, 2015, 7:25 am
$
0
0

Hi all,

I am currently facing a problem:

ipp 8.2.2 ipps documentation refers that ippsRandGauss_Direct_64f is marked as deprecated, and that the replacement would be ippsRandGauss_64f Nevertheless, the same document only presents up to the 32f variant, and in ipps.h we can not also find the 64f variant. This situation also happens for uniform random.

Does intel have a solution?

Kind regards,

Tiago

↧

IPP 6.1 Crypto Libraries

July 16, 2015, 3:40 am
$
0
0

Our product uses IPP 6.1 and i'm trying to get the matching cryptography libraries for 6.1.6.

They dont appear in the legacy download list at the registrationcenter, only version 7 and 8 appear.

I downloaded the 32bit version for 6.1.4 back in 2010, so I'm sure we did the registration stuff ok.

Any help much appreciated, thanks..

↧
↧

UMC libraries for AAC Encoder and support for Constant Bit Rate Mode

July 16, 2015, 7:38 am
$
0
0

Helllo,

I have question regarding the Bit rate Mode for AAC Encoder. I am trying to encode the audio file using UMC::AAC_Encoder and I am looking for a way to encoder it in a Constant Bit Rate mode.Currently, it is encoding in a Variable Bit Rate Mode as default, but I looked around UMC manual and there is no parameter declared in AAC encoder that can control the bit rate mode to constant or variable. So my question is does Intel libraries support Constant Bit Rate mode for AAC encoding ? If it does then how to do it.

I know for MP3 there is a parameter called mode which can be assigned by using MP3EncodeParams.mode = "0" or "1", but couldnt find the similar thing in AAC.

Thanks for your help.

 

↧

Watershed Function

July 16, 2015, 11:23 am
$
0
0

Hello,

I'm trying to work with the Intel IPP Watershed Segmentation function.

I'm not sure what should I send as pMarker image.

I have an Image I want to segment using The Watershed.
I want to get back the segmented image and use the Gradient Norm as reference.

Now I calculate the image gradient norm, send it as source image and pMarker is all zero.

I want to get back segmented image but all I get is an image all zeroed.

How should I use this function?
What actually is being done in this specific image?

↧
Search

Use IPP static library in Windows Kernel Mode

July 26, 2015, 9:02 pm
$
0
0

How to use IPP  static library in Windows Kernel Mode ?

and where  can  I download  a sample of driver develop?

↧

Is H265 supported in IPP or not?

July 27, 2015, 3:38 pm
$
0
0

Is H265 supported in IPP or not? I am using IPP 8.0. If it is not supported yet, does Intel has plan to support it in next IPP release?

↧
↧

Does IPP 8.0 support 640x480, 30FPS?

July 27, 2015, 3:45 pm
$
0
0

Hi, there

Does IPP 8.0 support 640x480 resolution and 30FPS? I am using IPP 8.0 and I can make it work with 640x480, 15FPS, but it cannot work with 30FPS. Not sure why. SPS setting and SDP setting shall be right (SPS setting: Level_id 2.2, time_scale=60 & num_units_in_tick=1; SDP: framerate=30, Level_id=2.2, AS:4000).

↧

Where are available codes of Intel® IPP UIC Sample Application – Picnic

July 30, 2015, 7:53 am
↧

link error with libippcc.a on linux: "unresolvable R_386_GOTOFF"

August 6, 2015, 4:31 am
$
0
0

 

Hi,

we met a link error on Linux platform

/usr/bin/ld: /opt/intel/ipp/lib/ia32/libippcc.a(jmp_ippiYUV420ToRGB_8u_P3C3_as.o)(.text+0x10): unresolvable R_386_GOTOFF relocation against symbol `ippJumpIndexForMergedLibs'
/usr/bin/ld: final link failed: Nonrepresentable section on output
collect2: error: ld returned 1 exit status

Could you help to take a look how to fix this? the intel compiler version is  l_ipp_8.2.2.187 l_ccompxe_2015.3.187 l_compxe_2015.3.187

 

Thanks,

Peng

↧
Viewing all 1489 articles
Browse latest View live
Search
<script src="https://jsc.adskeeper.com/r/s/rssing.com.1596347.js" async> </script>