Intel® Integrated Performance Primitives

size limitation with the MKL library


We are working with the Intel-MKL free evaluation library. (We also use Compaq Visual Fortran 6.6 as you recommend). The problem we want to solve is to calculate the pseudoinverse matrix by using the DGESVD routine (i . e. single value decomposition with the double precision option). However we have experience linking problem as the dimension of the matrix we must work is very high (200.000x 200.000).

Fast Magnitude Routine for IPP PCA 16bit FFT Result


Does anyone know a fast magnitude calculation routine to turn a Ipp16sc FFT result into a Ipp16s or Ipp32s vector with PCA IPP calls quickly? The method I have been using (with the ippsNorm_L2_16s32s function, with each sc point as a vector) is too slow, almost doubling my processing time.



Wiener Filtering Audio

To whom,

I have an audio signal that I want to try to denoise through a Wiener filter. I have the FFT of the signal, but I dont know how to compute the signal to noise ratio vector needed by the ippsFilterUpdateWiener function that I want to use. I am programming in C to a PCA, Armcore, processor.




i am trying to use interpolation in rotate or shear,
all work but for IPPI_SMOOTH_EDGE

has anyone else found similar problem with that kind of interpolation ..

example code .. :
#define WIDTH 10
#define HEIGHT
IppiSize roi = {WIDTH, HEIGHT);
IppiRect rect = {0, 0, WIDTH, HEIGHT};
Ipp8u *img, *res_img;

img = ippsMalloc_8u(WIDTH*HEIGHT);
res_img = ippsMalloc_8u(WIDTH*HEIGHT);

G.722.1 decoder and RTP Packetisation


I am having a spot of difficulty with the g.722.1 decoder sample source code.

We have an application which receives 722.1 rtp packets and it attempts to decode these into raw audio information to write to file. It seems as though I have mostly done things correctly however the final raw audio seems to be bad data. Silence followed by bursts of random noise.

MatchTemplate and IppiDemo


I'm currently evaluating IPP 4.1 and find the IppiDemo.exe invaluable for testing out various ippi functions. I'm developing some machine vision systems and need to implement patern recognition algorithms for it. Maybe ippiMatchTemplate* functionswould give a good head start for it?

I can't access MatchTemplate in IppiDemo program. What am I doing wrong since the Process_by->ippCV->Feature_Detection is never enabled. Is it implemented in this demo software?

Kim Portman

S’abonner à Intel® Integrated Performance Primitives