Intel® IPP Library 6.1 Fixes List

The tables below summarize specific customer issues or feature requests that have been addressed by the indicated product releases. Some items span multiple architectures and/or operating systems and some relate only to a single architecture or operating system.

NOTE: The issues, defects, bug reports, and feature requests described below represent specific issues with specific test cases. An item listed here does not imply that it necessarily applies to your application(s). If your situation does not match the specific test case you may not have experienced the error or problem associated with that update. It is not possible to describe the details of every issue and its specific test case in these tables.

Please post a message on the IPP user forum, http://software.intel.com/en-us/forums/intel-integrated-performance-primitives/, and reference this page and the "DPD" number associated with the item of interest, if you have questions regarding the information in these tables.

IPP v6.1 update 2 (18 Oct 2009)

IPP v6.1 update 1 (02 Jul 2009)

IPP v6.1 (25 Apr 2009)

Solution:
By default, the linker only includes, or extracts, those functions, or library members, that your application requests. In this case, it is perfectly acceptable to list ALL the IPP lib files in your link list. Using this approach can significantly simplify your build process bookkeeping. (Caution, a few rules do still apply.)

The IPP lib file link lists shown below should work for building your IPP application. This KB article is based on the v6.1.1 IPP library distribution, version 6.1 update 1 (v6.1.1.xxx).

The link lists below assume a Windows Visual Studio build environment. The basic idea also applies to Windows and Linux makefiles or scripted build environments. For the Linux OS and other operating system build environments you will need to change the extension of your lib filenames to match those for your environment.

- Static Link (thread-safe model):

ippacemerged.lib ippccemerged.lib ippchemerged.lib ippcvemerged.lib ippdcemerged.lib ippdiemerged.lib ippgenemerged.lib ippiemerged.lib ippjemerged.lib ippmemerged.lib ippremerged.lib ippscemerged.lib ippsemerged.lib ippsremerged.lib ippvcemerged.lib ippvmemerged.lib ippacmerged.lib ippccmerged.lib ippchmerged.lib ippcvmerged.lib ippdcmerged.lib ippdimerged.lib ippgenmerged.lib ippimerged.lib ippjmerged.lib ipprmerged.lib ippmmerged.lib ippscmerged.lib ippsmerged.lib ippsrmerged.lib ippvcmerged.lib ippvmmerged.lib ippcore.lib

Note: These library files are located in the lib subdirectory in your IPP install directory. The “thread-safe” model means these libraries are safe to use within a multi-threaded application, even though this version of the library is not multi-threaded.

- Static Link (multi-threaded model):

ippacemerged.lib ippccemerged.lib ippchemerged.lib ippcvemerged.lib ippdcemerged.lib ippdiemerged.lib ippgenemerged.lib ippiemerged.lib ippjemerged.lib ippmemerged.lib ippremerged.lib ippscemerged.lib ippsemerged.lib ippsremerged.lib ippvcemerged.lib ippvmemerged.lib ippacmerged_t.lib ippccmerged.lib ippchmerged_t.lib ippcvmerged_t.lib ippdcmerged_t.lib ippdimerged_t.lib ippgenmerged_t.lib ippimerged_t.lib ippjmerged_t.lib ippmmerged_t.lib ipprmerged_t.lib ippscmerged_t.lib ippsmerged_t.lib ippsrmerged_t.lib ippvcmerged_t.lib ippvmmerged_t.lib ippcore_t.lib libircmt.lib svml_dispmt.lib libmmt.lib libiomp5mt.lib

Note: library files in red are Intel Compiler support files and are needed if you are NOT using the Intel compiler to compile and link your application. The equivalent files on a Linux system are named libirc, libsvml, libimf, and libiomp5. these libraries are required to satisfy Intel compiler optimizations and OpenMP calls used by the IPP library, because the IPP libraries are created using the Intel compiler.

- Dynamic Link:

ippac.lib ippcc.lib ippch.lib ippcv.lib ippdc.lib ippdi.lib ippgen.lib ippi.lib ippj.lib ippm.lib ippr.lib ipps.lib ippsc.lib ippsr.lib ippvc.lib ippvm.lib ippcore.lib libiomp5md.lib

Note: libiomp5md.lib is the Intel OpenMP library file and is used by the IPP libraries to implement multi-threading. The equivalent file is named libiomp5 on a Linux system. These files are located in the stublib directory on a Windows system and in the sharedlib directory on a Linux system. You are not required to use OpenMP in your application when you include this library file, but it is required by some IPP library functions when mult-threading is enabled (the default case). To disable OpenMP threading, within the dynamic libraries, see the ippSetNumThread() function.

IPP Cryptography Library
The IPP cryptography library files are not included in the above lists, since they are not part of the standard product. If you are using the IPP cryptography library you will need to add those library files to your link list. The crypto files are named ippcp*.

About Link List Order
Thank you to my colleague Chao Yu who pointed out that the order of the link list is important for static libraries in a Linux environment, since many of the linkers used in this environment default to operating in a single-pass mode. In this case it is best to order the library files according to the following rule: *emerged.a first, followed by *merged.a and ending with ippcore.a. The lists above have been ordered to reflect that rule.

If you have problems with interdependencies between libraries causing link errors on a Linux system you may need to use the -( and -) options (or equivalent --start-group and --end-group options) with your Linux linker to force multi-pass behavior, at the expense of reduced linker performance.

Additionally, you can repeat the name of a library on the link list to resolve circular dependencies, without resorting to the -( and -) options; by listing a library file a second time after the archive that depends on that key library. The nm command can be used to list the object file names within a specific library archive so you can identify which library is needed to satisfy a missing dependency problem.

Additional Info
Obviously, you must also set your makefile or environment variables to point to the appropriate install directories. See the env and tools subdirectories for your IPP installation for more information or review the articles linked below.

Using Intel® IPP Threaded Static Libraries
Building a Windows* Application Using Intel® IPP
Compiling and Linking with Microsoft* Visual C++* and Intel® C++ Compiler
Error LNK2001: Unresolved External Symbol _ipp*
How to Build an Intel IPP Application
Intel® IPP - Intel® IPP Linkage Models - Quick Reference Guide
Intel® IPP- Library Dependencies by Domain
Intel® IPP - Threading / OpenMP* FAQ

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.

• Release Notes
  • Intel® Integrated Performance Primitives for Windows* Release Notes (PDF)
  • Intel® Integrated Performance Primitives for Linux* Release Notes (PDF)
  • Cryptography for Intel® Integrated Performance Primitives for Windows* Release Notes (HTML)
  • Cryptography for Intel® Integrated Performance Primitives for Linux* Release Notes (HTML)


• Intel® Integrated Performance Primitives Reference Manual
  • Volume 1: Signal Processing
    (HTML) (PDF) (CHM)
  • Volume 2: Image and Video Processing
    (HTML) (PDF) (CHM)
  • Volume 3: Small Matrices and Realistic Rendering
    (HTML) (PDF) (CHM)
  • Volume 4: Cryptography
    (HTML) (PDF) (CHM)


• User's Guides
  • Intel® Integrated Performance Primitives for Windows* OS on IA-32 Architecture User’s Guide
    (HTML) (PDF)
  • Intel® Integrated Performance Primitives for Windows* OS on Intel® 64 Architecture User’s Guide
    (HTML) (PDF)
  • Intel® Integrated Performance Primitives for Windows* OS on IA-64 Architecture User’s Guide
    (PDF)
  • Intel® Integrated Performance Primitives for Linux* OS on IA-32 Architecture User’s Guide
    (PDF)

-------------------------------------------------------------------------------------------------------------------------------------------------
ippGetCpuFeatures is a function in IPP to get information about the features of the processor used in your computer system. This function is declared in the ippcore.h file

If it returns ippCPUID_AVXX(mask value 256) - Intel® Advanced Vector Extensions(Intel AVX) instruction set is supported.

If it returns ippAVX_ENABLEDBYOS(mask value 512)- The operating system supports Intel® AVX.

--------------------------------------------------------------------------------------------------------------------------------------------------
ippGetCpuType is a function in IPP to detect the processor type used in your computer system. This function also declared in ippcore.h.

If it returns ippCpuAVX - Processor supports Intel® Advanced Vector Extensions instruction Set.

 -------------------------------------------------------------------------------------------------------------------------------------------------

Intel® IPP uses codes optimized for various central processing units (CPUs). Dispatching refers to detection of your CPU and selecting the Intel® IPP binary that corresponds to the hardware that you are using.  

New "e9" code for Intel 64(EM64T), it means specific IPP functions are optimized for processors that support Intel® Advanced Vector Extensions instruction set. In IPP 6.1, more than sixty five functions including FFT, filtering, geometric transform functions, some of the functions in signal processing, image processing, speech processing, spiral and realistic rendering have been optimized for AVX.  

For more information refer to Intel® Integrated Performance Primitives for Windows* OS on Intel® 64 Architecture ‘User's Guide'

In IPP 6.1, functionality for the RSA signature scheme defined in version1.5 of the PKCS#1 standard ([PKCS 1.2.1])

New PKCS V1.5 Encryption Scheme Functions in IPP

RSAEncrypt_PKCSv15	Carries out the encryption using the v1.5 version of the PKCS#1 standard
RSADecrypt_PKCSv15	Carries out the decryption using the v1.5 version of the PKCS#1 standard

PKCS V1.5 Signature Scheme Functions in IPP

RSASSASign_MD5_PKCSv15	Generates a signature using the v1.5 version of the RSA scheme with the MD5 message digest
RSASSASign_SHA1_PKCSv15	Generates a signature using the v1.5 version of the RSA scheme with the SHA-1 message digest
RSASSASign_SHA224_PKCSv15	Generates a signature using the v1.5 version of the RSA scheme with the SHA-224 message digest
RSASSASign_SHA256_PKCSv15	Generates a signature using the v1.5 version of the RSA scheme with the SHA-256 message digest
RSASSASign_SHA384_PKCSv15	Generates a signature using the v1.5 version of the RSA scheme with the SHA-384 message digest
RSASSASign_SHA512_PKCSv15	Generates a signature using the v1.5 version of the RSA scheme with the SHA-512 message digest
RSASSAVerify_MD5_PKCSv15	Verifies a signature using the v1.5 version of the RSA scheme with the MD5 message digest
RSASSAVerify_SHA1_PKCSv15	Verifies a signature using the v1.5 version of the RSA scheme with the SHA-1 message digest
RSASSAVerify_SHA224_PKCSv15	Verifies a signature using the v1.5 version of the RSA scheme with the SHA-224 message digest
RSASSAVerify_SHA256_PKCSv15	Verifies a signature using the v1.5 version of the RSA scheme with the SHA-256 message digest
RSASSAVerify_SHA384_PKCSv15	Verifies a signature using the v1.5 version of the RSA scheme with the SHA-384 message digest
RSASSAVerify_SHA512_PKCSv15	Verifies a signature using the v1.5 version of the RSA scheme with the SHA-512 message digest

More information about usage of these functions, refer to IPP Documentation- Volume 4: Cryptography [PDF 2.2MB]

How to get access to Intel® IPP Cryptography Libraries - http://software.intel.com/en-us/articles/download-ipp-cryptography-libraries/