Computación en paralelo

H264 Decoder Problem

Hellow, I have trouble with H264 Decoder.

I decoded H.264 HD(1920x1080) and SD(720x480) mutually.

For changin decoding parameter(resolution etc) dynamically, I used UMC::H264VideoDecoder.Init .

But keep to change  in 3 minute, access violation happen in UMC::H264VideoDecoder !!

Access violation happen in RefreshCABACBits (umc_h264_bitstream_inlines.h line 313.

I think access violation cause by the function's paramter two (m_pMagicBits) is NULL.

How can I fix that's ?

Install trouble - "error occured during the installation of assembly component"

Hi all,

I'm trying to install Vtune Amplifier XE 2013 Update 16 on Windows 7 Enterprise x64 and running into an error.

[[{"fid":"317312","view_mode":"default","fields":{"format":"default","field_file_image_alt_text[und][0][value]":"","field_file_image_title_text[und][0][value]":"","field_tags[und]":""},"type":"media","attributes":{"height":166,"width":435,"class":"media-element file-default"}}]]

How to get peak performnace in FFT


I want to get peak performance using batch FFT. I am giving sample code below that i have written. I have compiled on host using command icc -mkl fftcheck.cpp -o fftchecknew -L/opt/intel/mkl/lib/intel64. Also i have set some environment variables mentioned below.


export  MIC_KMP_AFFINITY=scatter,granularity=fine



./fftchecknew 512 1024 1024.

[OMP Target] Difference in mapping of global arrays (malloc vs static)

There are 2 ways to have a global array: Use a pointer and malloc, or just define it as an array:

#omp declare target
int gArray[10];
int* gVals /*somewhere later:*/ = malloc(10*sizeof(int));
#omp end declare target

I though, these where equivalent in handling but just discovered a huge difference: When I map them to a target, only the gVals will be actually mapped. If I want the values of gArray on my device I have to use "target update". Is this a bug in the current icc or is this covered in the spec? I could not find anything specific to this.

What/where is DAPL provider ?

DAPL providers ucm, scm are frequently mentioned, but what is

Could someone point me to a description of the use case for the DAPL provider

I am currently using the Intel MPI Library 4.1 for Linux with Mellanox OFED 2.1; shm:dapl and shm:ofa both seem to work, but with shm:dapl I get warning messages about not being able to find Mellanox DAPL does have this file. This file does not appear in DAPL 2.0.41 either:

dss_solver gives non-stable solve

Hi there,

I am using the mkl_dss.f77 to solve large sparse non-linear equations by iteratively calling the dss_solver. I just spotted that although I set the same initial values, I could not obtain a same result for every time. And I found this is due to the dss_solver gives results with slightly difference every time and the difference adds up in the iteration process which leads to a non-stable solve for the large sparse non-linear equations.

How can I make the mkl_dss solver to have repetitive accuracy? Anyone could give me some advice on this subject? 

Suscribirse a Computación en paralelo