question on simple_3_encode_vmem_async

hi Intel-giant,

OS: Ubuntu 12.04

       mediasdk-tutorials-0.0.3

       MediaServerStudioEssentials2015R6

Platform:  i5-4570S

I got questions as reading simple_encode_vmem_async.cpp

Q1. Is this parameter (AsyncDepth) platform-dependent ??  2 cores or 4 cores or else ?? Or did you mean it's better for all platform?? May I know how did you proof to result in good performance ??  

    // - AsyncDepth represents the number of tasks that can be submitted, before synchronizing is required
    // - The choice of AsyncDepth = 4 is quite arbitrary but has proven to result in good performance
    mfxEncParams.AsyncDepth = 4;

Q2. according to  the following, why the suggested frame number will be changed??

    // Query number of required surfaces for encoder
    mfxFrameAllocRequest EncRequest;
    ...
    sts = mfxENC.QueryIOSurf(&mfxEncParams, &EncRequest);
    ...

    EncRequest.NumFrameSuggested = EncRequest.NumFrameSuggested + mfxEncParams.AsyncDepth;   ==> why AsyncDepth was added ??

Thanks in advance...    QQa