topic Where can I get more details regarding an issue fixed in IPP 7. in Intel® Integrated Performance Primitives

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

Emmanuel_W_ — Thu, 07 Apr 2011 17:22:29 GMT

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

Where can I get more details regarding an issue fixed in IPP 7.

Vladimir_Dudnik — Thu, 07 Apr 2011 18:04:03 GMT

Hello,

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

Regards,
Vladimir

Where can I get more details regarding an issue fixed in IPP 7.

Emmanuel_W_ — Thu, 07 Apr 2011 19:53:31 GMT

Great thanks, and I suspect that the less optimized code was also in IPP 6.1.

Where can I get more details regarding an issue fixed in IPP 7.

PaulF_IntelCorp — Fri, 08 Apr 2011 17:45:04 GMT

Yes, the optimization problems also existed in the 6.1 code.

Where can I get more details regarding an issue fixed in IPP 7.

Emmanuel_W_ — Tue, 19 Apr 2011 16:43:17 GMT

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.

Where can I get more details regarding an issue fixed in IPP 7.

Vladimir_Dudnik — Wed, 20 Apr 2011 13:46:50 GMT

Have you compared performance on IA32 vs Intel64 architectures?

Vladimir

Where can I get more details regarding an issue fixed in IPP 7.

Emmanuel_W_ — Wed, 20 Apr 2011 18:37:43 GMT

No I just tested the two versions on 64bits expecting to see an improvment (no 32 bits system on hands).

Emmanuel

Where can I get more details regarding an issue fixed in IPP 7.

Vladimir_Dudnik — Thu, 21 Apr 2011 10:29:47 GMT

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 6.1		IPP 7.0.2
	intel64	intel64	ia32
ippiReconstructLumaIntra8x8_H264High_32s16u_IP1R	2.56	0.385	0.574
ippiReconstructChroma422Inter4x4_H264High_32s16u_IP2R	0.897	0.158	0.19
ippiDecodeCAVLCCoeffs_H264_1u32s	0.528	0.467	0.445
ippiReconstructChroma422Intra4x4_H264High_32s16u_IP2R	0.14	0.079	0.061

Regards,
Vladimir

Where can I get more details regarding an issue fixed in IPP 7.

Emmanuel_W_ — Thu, 21 Apr 2011 17:47:44 GMT

Thanks Vladimir,

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

Emmanuel