Primitivas Intel® Integrated Performance

Intel® IPP 2018 Update 1 is now available

Intel® IPP 2018 Update 1 is now available. Intel(R) IPP 2018 release added new functions to support the LZ4 data compression, introduced the standalone cryptography packages, and added the optimization code for the GraphicsMagick source.  Intel IPP 2018 Update 1 added new Platform-Aware APIs, and extended optimization for Intel® AVX-512 and Intel® SSE4.2 instruction set.

Check Intel® IPP 2018 Update 1 release notes to learn more information.
 

Which is the fastest way to use the IPPS FFT ?

Hi,

i've been recently porting a convolution library that uses Apple's vDSP to IPP to make it cross-platform capable. 

In general, i made it work, the results seem fine, but i somewhat stunned that it is significantly slower than vDSP on the same machine (compared over various different blocksizes).

The platform i'm currently working on is OSX El Capitan, with clang as a compiler, on an Intel i7 (broadwell) processor.

I'm currently the using real-valued in-place FFT. Using ippInit() or not doesn't seem to change anything.

Mismatch in output of ippiResizeLinear<mod> from older resize API ippiResize<mod> and also from legacy ippiresizeSqrPixel<mod>

Hi,

Initially I was using older version of IPP resize API (ippiResize_16u_C1R)  with linear interpolation and BorderType Const. Since the IPP9.0 ResizeLinear with takes only two type of BorderType parameter (ippBorderInMem & ippBorderRepl), so I used src image with margin and border value zero and called ippiResizeLinear_16u_C1R with border type ippBorderInMem. But output of ippiResizeLinear_16u_C1R API is different from that resize API in older version.

Linking problem on x86_64 Android with static libraries

Hi

I am getting a linker error when I try to build a shared library with static linking of the Android IPP libraries for x86_64 (intel64):

Android/Sdk/ndk-bundle/build//../toolchains/x86_64-4.9/prebuilt/windows-x86_64/lib/gcc/x86_64-linux-android/4.9.x/../../../../x86_

64-linux-android/bin\ld: error: libipps.a(pscosm7l9as_y8.o): requires dynamic R_X86_64_PC32 reloc against 'y8_ownsCosOne_m7y8' w

hich may overflow at runtime; recompile with -fPIC

 

Same build for x86 (32-bit) works just fine.

 

IPP 9.0.3 and 2018.Initial Cause Crashes

I found that IPP 9.0.3 and 2018.Initial causes blue screen on machine of  Skylake CPUs + x299 chipset. If IPP is used in x64 kernel mode, the blue screen happens when calculating sha256. If it is used in x64 user mode, it causes blue screen as well in some machines. Has the issue been fixed? (I couldn't get a chance to try 2018.1 though).

ippiDilateBorder_16u_C1R performance regression in 2018

Hello,

The latest community version of IPP has a 4x performance regression in the ippiDilateBorder_16u_C1R function for largish neighborhoods.  A sized 221x221 neighborhood in our use case seems to be affected (with an image size of 7002x8998), though I'm sure it's measurable for smaller neighboorhoods as well.  I've seen this regression in Windows, haven't tested it in Linux, yet.  This is while using a Haswell CPU.  I'm not sure how much it matters, but the neighborhood is defined as 1 for all values.

Assine o Primitivas Intel® Integrated Performance