i want to make some performance measurement, but ippSetCpuFeatures seems not to work on my machine
i get always a ippStsFeatureNotSupported
even if i use
IppGetCpuFeatures
to request the feature mask and pass the unmodified mask to
ippSetCpuFeatures
PX_FM (3) is the only value which works for ippSetCpuFeatures
Any ideas?
Ralf
Hey,
This is probably an obvious question..
I have an operation I'd like to optimize with intel.
currently the input and output are 8 bit matrices, and I'd like the output to be the subtraction of those 2 matrices.
It seems obvious to me that the output would have to be at least 16 bit..
what is the ipp function to do it? I'm looking around the ippmSub but can't seem to find it.
Thanks,
Alon
dear all：
it ruining in docker container,the issue can be reproduced
kernel：
CentOS release 6.5 (Final) 2.6.32-431.el6.x86_64 #1 SMP Fri Nov 22 03:15:09 UTC 2013 x86_64 x86_64 x86_64 GNU/Linux
vendor_id : GenuineIntel
cpu family : 6
model : 62
model name : Intel(R) Xeon(R) CPU E5-2650 v2 @ 2.60GHz
stepping : 4
cpu MHz : 2599.825
cache size : 20480 KB
physical id : 0
siblings : 16
core id : 6
cpu cores : 8
apicid : 13
initial apicid : 13
fpu : yes
fpu_exception : yes
cpuid level : 13
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm ida arat xsaveopt pln pts dts tpr_shadow vnmi flexpriority ept vpid fsgsbase smep erms
bogomips : 5199.65
clflush size : 64
cache_alignment : 64
address sizes : 46 bits physical, 48 bits virtual
painc messages
The program being debugged has been started already.
Start it from the beginning? (y or n) y
Starting program: /export/servers/nginx/sbin/nginx
[Thread debugging using libthread_db enabled]
init sucess
[New Thread 0x7ffff7fa5700 (LWP 7301)]
[New Thread 0x7ffff1699700 (LWP 7302)]
[New Thread 0x7ffff1298700 (LWP 7303)]
[New Thread 0x7ffff0e97700 (LWP 7304)]
[New Thread 0x7ffff0a96700 (LWP 7305)]
[New Thread 0x7ffff0695700 (LWP 7306)]
*** glibc detected *** /export/servers/nginx/sbin/nginx: double free or corruption (!prev): 0x0000000000923f80 ***
======= Backtrace: =========
/lib64/libc.so.6(+0x75e66)[0x7ffff5623e66]
/lib64/libc.so.6(+0x789b3)[0x7ffff56269b3]
/usr/lib/libGraphicsMagick.so.3(+0x133a7c)[0x7ffff70f5a7c]
/usr/lib/libGraphicsMagick.so.3(+0x13bbeb)[0x7ffff70fdbeb]
/opt/intel/composer_xe_2013_sp1.2.144/ipp/../compiler/lib/intel64/libiomp5.so(__kmp_invoke_microtask+0x93)[0x7ffff511c233]
======= Memory map: ========
00400000-00509000 r-xp 00000000 fd:04 918887 /export/servers/nginx/sbin/nginx
00708000-0071a000 rw-p 00108000 fd:04 918887 /export/servers/nginx/sbin/nginx
0071a000-00968000 rw-p 00000000 00:00 0 [heap]
7fffd4000000-7fffd4021000 rw-p 00000000 00:00 0
7fffd4021000-7fffd8000000 ---p 00000000 00:00 0
7fffdc000000-7fffdc021000 rw-p 00000000 00:00 0
7fffdc021000-7fffe0000000 ---p 00000000 00:00 0
7fffe0000000-7fffe0021000 rw-p 00000000 00:00 0
7fffe0021000-7fffe4000000 ---p 00000000 00:00 0
7fffe4000000-7fffe4021000 rw-p 00000000 00:00 0
7fffe4021000-7fffe8000000 ---p 00000000 00:00 0
7fffe8000000-7fffe8021000 rw-p 00000000 00:00 0
7fffe8021000-7fffec000000 ---p 00000000 00:00 0
7fffec000000-7fffec021000 rw-p 00000000 00:00 0
7fffec021000-7ffff0000000 ---p 00000000 00:00 0
7ffff0295000-7ffff0296000 ---p 00000000 00:00 0
7ffff0296000-7ffff0696000 rw-p 00000000 00:00 0
7ffff0696000-7ffff0697000 ---p 00000000 00:00 0
7ffff0697000-7ffff0a97000 rw-p 00000000 00:00 0
7ffff0a97000-7ffff0a98000 ---p 00000000 00:00 0
7ffff0a98000-7ffff0e98000 rw-p 00000000 00:00 0
7ffff0e98000-7ffff0e99000 ---p 00000000 00:00 0
7ffff0e99000-7ffff1299000 rw-p 00000000 00:00 0
7ffff1299000-7ffff129a000 ---p 00000000 00:00 0
7ffff129a000-7ffff329a000 rw-p 00000000 00:00 0
7ffff329a000-7ffff32a6000 r-xp 00000000 fd:04 524365 /lib64/libnss_files-2.12.so
7ffff32a6000-7ffff34a6000 ---p 0000c000 fd:04 524365 /lib64/libnss_files-2.12.so
7ffff34a6000-7ffff34a7000 r--p 0000c000 fd:04 524365 /lib64/libnss_files-2.12.so
7ffff34a7000-7ffff34a8000 rw-p 0000d000 fd:04 524365 /lib64/libnss_files-2.12.so
7ffff34a8000-7ffff34af000 r-xp 00000000 fd:04 524528 /lib64/librt-2.12.so
7ffff34af000-7ffff36ae000 ---p 00007000 fd:04 524528 /lib64/librt-2.12.so
7ffff36ae000-7ffff36af000 r--p 00006000 fd:04 524528 /lib64/librt-2.12.so
7ffff36af000-7ffff36b0000 rw-p 00007000 fd:04 524528 /lib64/librt-2.12.so
7ffff36b0000-7ffff36ef000 r-xp 00000000 fd:04 657779 /usr/lib64/libjpeg.so.62.0.0
7ffff36ef000-7ffff38ef000 ---p 0003f000 fd:04 657779 /usr/lib64/libjpeg.so.62.0.0
7ffff38ef000-7ffff38f0000 rw-p 0003f000 fd:04 657779 /usr/lib64/libjpeg.so.62.0.0
7ffff38f0000-7ffff3900000 rw-p 00000000 00:00 0
7ffff3900000-7ffff3952000 r-xp 00000000 fd:04 1323448 /opt/intel/composer_xe_2013_sp1.2.144/compiler/lib/intel64/libintlc.so.5
7ffff3952000-7ffff3b52000 ---p 00052000 fd:04 1323448 /opt/intel/composer_xe_2013_sp1.2.144/compiler/lib/intel64/libintlc.so.5
7ffff3b52000-7ffff3b55000 rw-p 00052000 fd:04 1323448 /opt/intel/composer_xe_2013_sp1.2.144/compiler/lib/intel64/libintlc.so.5
7ffff3b55000-7ffff3b56000 rw-p 00000000 00:00 0
7ffff3b56000-7ffff3b5b000 r-xp 00000000 fd:04 1323378 /opt/intel/composer_xe_2013_sp1.2.144/compiler/lib/intel64/libirng.so
7ffff3b5b000-7ffff3d5b000 ---p 00005000 fd:04 1323378 /opt/intel/composer_xe_2013_sp1.2.144/compiler/lib/intel64/libirng.so
7ffff3d5b000-7ffff3d5d000 rw-p 00005000 fd:04 1323378 /opt/intel/composer_xe_2013_sp1.2.144/compiler/lib/intel64/libirng.so
7ffff3d5d000-7ffff4721000 r-xp 00000000 fd:04 1323415 /opt/intel/composer_xe_2013_sp1.2.144/compiler/lib/intel64/libsvml.so
7ffff4721000-7ffff4921000 ---p 009c4000 fd:04 1323415 /opt/intel/composer_xe_2013_sp1.2.144/compiler/lib/intel64/libsvml.so
7ffff4921000-7ffff4958000 rw-p 009c4000 fd:04 1323415 /opt/intel/composer_xe_2013_sp1.2.144/compiler/lib/intel64/libsvml.so
7ffff4958000-7ffff4bd9000 r-xp 00000000 fd:04 1323461 /opt/intel/composer_xe_2013_sp1.2.144/compiler/lib/intel64/libimf.so
7ffff4bd9000-7ffff4dd8000 ---p 00281000 fd:04 1323461 /opt/intel/composer_xe_2013_sp1.2.144/compiler/lib/intel64/libimf.so
7ffff4dd8000-7ffff4e1b000 rw-p 00280000 fd:04 1323461 /opt/intel/composer_xe_2013_sp1.2.144/compiler/lib/intel64/libimf.so
7ffff4e1b000-7ffff4e8c000 r-xp 00000000 fd:04 524525 /lib64/libfreebl3.so
7ffff4e8c000-7ffff508b000 ---p 00071000 fd:04 524525 /lib64/libfreebl3.so
7ffff508b000-7ffff508d000 r--p 00070000 fd:04 524525 /lib64/libfreebl3.so
7ffff508d000-7ffff508e000 rw-p 00072000 fd:04 524525 /lib64/libfreebl3.so
7ffff508e000-7ffff5092000 rw-p 00000000 00:00 0
7ffff5092000-7ffff5177000 r-xp 00000000 fd:04 1323455 /opt/intel/composer_xe_2013_sp1.2.144/compiler/lib/intel64/libiomp5.so
7ffff5177000-7ffff5377000 ---p 000e5000 fd:04 1323455 /opt/intel/composer_xe_2013_sp1.2.144/compiler/lib/intel64/libiomp5.so
7ffff5377000-7ffff5382000 rw-p 000e5000 fd:04 1323455 /opt/intel/composer_xe_2013_sp1.2.144/compiler/lib/intel64/libiomp5.so
7ffff5382000-7ffff53aa000 rw-p 00000000 00:00 0
7ffff53aa000-7ffff53ac000 r-xp 00000000 fd:04 524519 /lib64/libdl-2.12.so
Program received signal SIGABRT, Aborted.
[Switching to Thread 0x7ffff0695700 (LWP 7306)]
0x00007ffff55e0625 in raise () from /lib64/libc.so.6
(gdb) bt
#0 0x00007ffff55e0625 in raise () from /lib64/libc.so.6
#1 0x00007ffff55e1e05 in abort () from /lib64/libc.so.6
#2 0x00007ffff561e537 in __libc_message () from /lib64/libc.so.6
#3 0x00007ffff5623e66 in malloc_printerr () from /lib64/libc.so.6
#4 0x00007ffff56269b3 in _int_free () from /lib64/libc.so.6
#5 0x00007ffff70f5a7c in DestroyEdge (polygon_info=0x1c32, mid=3.2252605360516574e-319, fill=7306, fill_rule=6, x=-1, y=0,
stroke_opacity=0x1) at magick/render.c:790
#6 GetPixelOpacity (polygon_info=0x1c32, mid=3.2252605360516574e-319, fill=7306, fill_rule=6, x=-1, y=0, stroke_opacity=0x1)
at magick/render.c:3180
#7 0x00007ffff70fdbeb in L_DrawPolygonPrimitive_3546__par_loop1_2_1200 () at magick/render.c:3594
#8 0x00007ffff511c233 in L_kmp_invoke_pass_parms ()
from /opt/intel/composer_xe_2013_sp1.2.144/ipp/../compiler/lib/intel64/libiomp5.so
#9 0x00007fffffff5098 in ?? ()
#10 0x00007fffffff5038 in ?? ()
#11 0x00007fffffff5090 in ?? ()
#12 0x00007fffffff5048 in ?? ()
#13 0x00007fffffff5078 in ?? ()
#14 0x00007fffffff5074 in ?? ()
#15 0x00007fffffff5028 in ?? ()
#16 0x00007fffffff5030 in ?? ()
#17 0x00007fffffff5010 in ?? ()
#18 0x00007fffffff5018 in ?? ()
#19 0x00007fffffffb688 in ?? ()
#20 0x00007ffff752403c in .2.23_2__kmpc_chunk_pack_.27 () from /usr/lib/libGraphicsMagick.so.3
I'm using a lowpass filter created with ippsFIRMRInit to upsample a signal by a user definable factor. The output of the filter is scaled roughly (not exactly) proportional to the upsample factor.
Is this expected behavior? If so, how do you determine the correction factor to make the upsampled data look like the original signal?
There's a "doNormal" option for ippsFIRGenLowpass, but there's nothing in the documentation that explains what it does. I tried setting it to both true and false, with no noticeable difference in the output.
Hello Guys,
I am implementing the JPEG encoding, As part of this I am done with implementation and it's working fine. But, I need to update the encoding part in the progress meter.
could anyone suggest me which API, I need to use to get the progress of the encoder.
Regards,
sathish.
Hello All,
I upgraded the Intel IPP 8.0 libraries to 8.2 . In 8.2 i didnt found ippj.lib file. So, I am getting linker errors for the methods avaliable in ippj.lib file.
In the ippj.h file mentioned that so many methods are deprecated. So, how to build my project now.
Regards,
sathish.
Hello All,
we purchased the Intel Parallel Studio XE 2015 Update 1 Composer Edition for C++ Windows License. While installation I am not getting the Options page to select the deprecated domains. Actually, we are using the Image Compression domains in our code.
could any one suggest in this regard.
Regards,
sathish.
I've been implementing tiled resizing using TBB with IPP resizing functions. All works well with the TBB tiled resizing sample code using the newer resizing API in IPP 8.2 update 1 (.e.g. ResizeFilterInit, ResizeFilter). I can divide the image vertically into groups of scan lines and the results are bytewise identical however many scan lines I use as the TBB grain size.
My problem concerns resizing YUV422. As far as I can tell newer resizing APIs for YUV422 so far only exist for nearest neighbour and linear interpolation. I'd like to use Supersampling, Lanczos or possibly cubic interpolation (often with antialiasing) for better quality.
My options seem to be:
For Lanczos and cubic ResizeYCbCr422
For supersampling ResizeYUV422 (which is deprecated).
However I'm finding ResizeYCbCr gives different results when than image is tiled too finely - the individual slices end up getting vertically stretched or squashed slightly and the output image contains noticeable visual artifacts. The rule of thumb seems to be that the image can't be divided by more than the power of two that divides both the source and destination height or horizontally by half the highest power of two that divides the source and destination width. The same problem happens if not using TBB for tiling.
ResizeYUV422 with supersampling doesn't seem to allow any vertical tiling without changing the results.
Will Intel be implementing YUV422 resizing support for supersampling and Lanczos any time soon so that I can move to the new resizing APIs which will hopefully allow seamless tiling? If not are there any workarounds?
I doubt that it would be worthwhile in performance terms to upsample from YUV422 to YUV444, resize in YUV444 and then subsample back to YUV422. I also couldn't find any appropriate upsampling or downsampling primitives in IPP from a brief inspection. It sounds like taking the simple mean of two pixels for subsampling doesn't give good results with edges in images.
Thanks for any advice or suggestions,
When will support for the SHA-3 algorithms be added to the crypto libraries for hashing functions?
Hello All,
Actually, I have implmented the JPEG encoding using Intel IPP libs . Its working for the small images and its not working for the large images. I understood that the problem is with , I am providing the whole Pixel data at a time. But , the large images having the size 15000X15000, 85000X85000 in these cases it will not allocate memory and so its failing .
Now, I am thinking that I need provide the pixel data row by row. But, How to provide the data row by row and how to write the data to output file row by row.
could anyone help me in this regard.
Regards,
sathish
My IPP is ver.7.0, and it supports SOF3, but not SOF7, SOF11, SOF15.
The four markers above indicate lossless-compressed JPEG, is it all right?
How about the last version?
I had registered the trial version of parallel studio 2015 Update 2 composer edition for windows and downloaded the related crypto package. After installing the composer studio ,when i tried to install the crypto it is telling please install IPP of the same version and then install the crypto and installation doesn't proceed thereafter.
Packages douwnloaded: w_ccompxe_2015.2.179
Crypto pacakge: w_ccompxe_crypto_ipp_8.2.1.148
The crypto installation is very much needed since use checksum methods and we want to profile the performance of MD5 in never version.
Hi,
We were currently using the intel IPP 7.1 but still using the depreciated method ResizeCenter.
We were evaluating the intel IPP 8.2.1 and want to replace the resizecenter method with Resize<Interpolation>
my Q's here are
1) can we achieve same display as ResizeCenter using new method Resize<Interpolation> or do we have any change when i compare pixel by pixel for the resized images. This is needed to ensure that check correctness and we have already unit testers to check the output pixel by pixel.
2) I had also seen options for border interpolation which is not present in the old method resizecenter.
3) Also we have been using the multi threaded version of static library in my project.. Now i have read somewhere that this multi threaded libraries are depreciated in 8.2.1 and kept under a folder in threaded folder. Does it mean that no new processor optimizations went into those multi threaded library version. Will it be any change in performance if we still link to newer version of multi threaded libraries compared to single threaded library.
4) Also please tell me the difference between the ippresizeCenter,ippiResizeSqrPixle and ippiresize methods in terms of abilities and usage.
Thanks & Regards,
Muralidhar
Hi all,
I use IPP 7.1 to process uncompressed images from IP-cam.
So, I have to init my custom DLL, call IPP functions via my own functions inside my DLL and, finally, shut down my DLL.
And of course I have to call IPP functions in accordance with IP-cam FPS. If IP-cam gives me 25 FPS, I have to call IPP-functions 25 times per second.
Everything was fine, when I used dynamic-linkage DLL (as I know, they are multithreaded, so I use ippSetNumThreads(1) to avoid problems in OpenMP).
But when I tried static linkage, I got huge CPU load. ippStaticInit() call doesn't change anything.
Have I make any additional settings to make CPU load with static and dynamic linkage equal?
Best Regards,
Roman
Hi,
How to handle unhandled, just thrown, H264 bad bitstream exceptions?
Where is the documentation about IPP exception handling, an a general IPP exceptions?
Details:
From time to time, it is inevitable to get a bad inbound h264 stream.
As per IPP's H264 code, some of the H264 bitstream parameters cause uncatched and thrown exceptions.
It will be nice, if not necessary, to provide more info about these exceptions, as well as a piece of advise how to handle that.
At this point, this is a major show stopper, since many developers got applications with H264 decoder in the field that simply crash because of it, causing unnecessary blame towards the quality of the IPP's H264 decoder.
Please answer me on these questions.
Vladimir Pavlovic
Senior Software Engineer
Hello Everyone,
I am doing the JPEG encoding using Intel IPP libs. Everything is looking fine but I am encoding the 70000X70000 image , the output JPEG file is showing 4464X4464 . I ecoded the 50000X50000 image and the output JPEG file is showing correctly as 50000X50000 . I am not sure why 70000X70000 file convrted to 4464X4464. Is there any limitation for JPEG encoding?.
could anyone comment.
Regards,
sathish
We're currently using IPP 8.0 for one of our software products. A new developer recently came on board with us and I want to buy him a copy of IPP 8.0 (or maybe 8.1). I've been scouring the Intel IPP web site but can't seem to find any way to purchase anything but the new IPP 8.2 stuff (which I don't want). Is there any way to buy more copies of the old stand alone IPP 8.0 or 8.1 products?
The function "ippiTranspose" is deprecated. Any other existing function can do the job?
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*.
So where are these files ?
i need to to use bignumber but it is impossible because i do not have IPP Cryptography Library ? i precise I bought the product !
thanks for your help
Hi everyone,
Recently I tried to replace the stock zlib with IPP zlib 7.0.6 on 64-bit Linux in order to boost the performance of a project using HBase 0.99.2. However I observed slowdown in compression performance by about 30%. I measure the time that "deflate" function takes (inside Hadoop native library), and indeed it's slower than stock zlib and the slowdown happens almost all inside "deflate" calls.
I wrote a couple of test programs separately which invoke zlib. In those cases, IPP shows good amount of improvement over stock one. It seems the slowdown only happens when it's used with HBase.
I don't know what could cause IPP zlib to be slower than the stock one. Has anyone some ideas? Thanks.
