Intel® Integrated Performance Primitives
Community support and discussions relating to developing high-performance vision, signal, security, and storage applications.
Announcements
This community is designed for sharing of public information. Please do not share Intel or third-party confidential information here.
6624 Discussions

Where can I get more details regarding an issue fixed in IPP 7.02

Emmanuel_W_
New Contributor I
175 Views
Hi,

The following item is mentionned in the list of issue fixed in IPP 7 update 2.

DPD200137548 H.264 Decompression on x64 is significantly slower compared to x32.

It sounds like a serious issue but there is no detail about the fix or situation in which the problem happen.

-Is this a sample fix, a library fix or both ?
-Is this an issue in IPP 6.1 or was this a bug introduced in IPP 7 ?
-Is this an issue with any H.264 stream or only specific profiles ?

Thanks
0 Kudos
8 Replies
Vladimir_Dudnik
Employee
175 Views
Hello,

this issue was related to the level of optimization for primitive functions. No H.264 sample code changes involved.

Regards,
Vladimir
Emmanuel_W_
New Contributor I
175 Views
Great thanks, and I suspect that the less optimized code was also in IPP 6.1.

PaulF_IntelCorp
Employee
175 Views
Yes, the optimization problems also existed in the 6.1 code.
Emmanuel_W_
New Contributor I
175 Views
I have run several tests using sample version 6.1 and IPP 6.1 vs 7.02 and can't find any difference in term of speed.
Vladimir_Dudnik
Employee
175 Views
Have you compared performance on IA32 vs Intel64 architectures?

Vladimir
Emmanuel_W_
New Contributor I
175 Views
No I just tested the two versions on 64bits expecting to see an improvment (no 32 bits system on hands).

Emmanuel
Vladimir_Dudnik
Employee
175 Views

Hi Emmanuel,

a lot of factors may affect performance comparison. But for this particular issue we have a confirmation that it was fixed from customer who has intially reported about it. Below are performance data on IPP functions

IPP 6.1IPP 7.0.2
intel64intel64ia32
ippiReconstructLumaIntra8x8_H264High_32s16u_IP1R2.560.3850.574
ippiReconstructChroma422Inter4x4_H264High_32s16u_IP2R0.8970.1580.19
ippiDecodeCAVLCCoeffs_H264_1u32s0.5280.4670.445
ippiReconstructChroma422Intra4x4_H264High_32s16u_IP2R0.140.0790.061


Regards,
Vladimir
Emmanuel_W_
New Contributor I
175 Views
Thanks Vladimir,

I didn't use 8x8 transform or 422 sampling in my tests so that makes sence ;)

Emmanuel
Reply