<div dir="ltr"><br><div class="gmail_extra"><br><br><div class="gmail_quote">On Thu, Feb 21, 2013 at 5:26 PM, ykzhao <span dir="ltr"><<a href="mailto:yakui.zhao@intel.com" target="_blank">yakui.zhao@intel.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div>On Thu, 2013-02-21 at 06:30 -0700, Ratin wrote:<br>
> awesome, would like to see the result from HQ scaling sometime in the<br>
> future. I am just using putSurface, don't want to go thru Proc<br>
> pipeline if I don't have to. Is the performance penalty identical in<br>
> both ways? Is there a way I can measure how much GPU processing (%<br>
> and such) is being utilized?<br>
<br>
</div>They are implemented in different ways and it is difficult to check the<br>
performance penalty. The putsurface is based on the 3D model while the<br>
proc pipeline is based on GPGPU model. (Intel_gpu_top may help to show<br>
the GPU utility, which can be downloaded from the<br>
<a href="http://cgit.freedesktop.org/xorg/app/intel-gpu-tools/" target="_blank">http://cgit.freedesktop.org/xorg/app/intel-gpu-tools/</a>).<br>
<br>
Will you please check whether it can meet with your requirement if you<br>
can use the proc VPP to do the upscaling conversion and then call the<br>
vaPutsurface to display it?<br>
<br>
Thanks.<br>
Yakui<br></blockquote><div><br></div><div>Hi Yakui, Thanks for your reply. I just started looking into this , the total number of filters available for me seems to be only two, not sure if thats normal or not. I am using HD4000 My lspci output shows the following: <br>
<br>d02788e046eb:/usr/local/bin# lspci<br>00:00.0 Host bridge: Intel Corporation 3rd Gen Core processor DRAM Controller (rev 09)<br>00:02.0 VGA compatible controller: Intel Corporation 3rd Gen Core processor Graphics Controller (rev 09)<br>
00:14.0 USB controller: Intel Corporation 7 Series/C210 Series Chipset Family USB xHCI Host Controller (rev 04)<br>00:16.0 Communication controller: Intel Corporation 7 Series/C210 Series Chipset Family MEI Controller #1 (rev 04)<br>
00:1a.0 USB controller: Intel Corporation 7 Series/C210 Series Chipset Family USB Enhanced Host Controller #2 (rev 04)<br>00:1c.0 PCI bridge: Intel Corporation 7 Series/C210 Series Chipset Family PCI Express Root Port 1 (rev c4)<br>
00:1c.3 PCI bridge: Intel Corporation 7 Series/C210 Series Chipset Family PCI Express Root Port 4 (rev c4)<br>00:1d.0 USB controller: Intel Corporation 7 Series/C210 Series Chipset Family USB Enhanced Host Controller #1 (rev 04)<br>
00:1f.0 ISA bridge: Intel Corporation HM76 Express Chipset LPC Controller (rev 04)<br>00:1f.2 IDE interface: Intel Corporation 7 Series Chipset Family 4-port SATA Controller [IDE mode] (rev 04)<br>00:1f.3 SMBus: Intel Corporation 7 Series/C210 Series Chipset Family SMBus Controller (rev 04)<br>
00:1f.5 IDE interface: Intel Corporation 7 Series Chipset Family 2-port SATA Controller [IDE mode] (rev 04)<br>01:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168B PCI Express Gigabit Ethernet controller (rev 07)<br>
02:00.0 Network controller: Intel Corporation Centrino Wireless-N 2200 (rev c4)<br><br>I will use more query code to know what are those two filters and will post the results here..<br><br></div><div>Thanks<br><br></div>
<div>Ratin<br></div><div><br><br>On Tue, Feb 19, 2013 at 7:24 PM, Xiang, Haihao<br>
> <<a href="mailto:haihao.xiang@intel.com" target="_blank">haihao.xiang@intel.com</a>> wrote:<br>
><br>
><br>
> > I am using Intel_driver from the staging branch, on a Gen 3<br>
> HD4000. So<br>
> > there other algorithms like bi-cubic is not supported?<br>
><br>
><br>
> You can select another scaling method other than the default<br>
> method via<br>
> the flag to vaPutSurface() or the filter_flag in<br>
> VAProcPipelineParameterBuffer.<br>
><br>
> /* Scaling flags for vaPutSurface() */<br>
> #define VA_FILTER_SCALING_DEFAULT 0x00000000<br>
> #define VA_FILTER_SCALING_FAST 0x00000100<br>
> #define VA_FILTER_SCALING_HQ 0x00000200<br>
> #define VA_FILTER_SCALING_NL_ANAMORPHIC 0x00000300<br>
> #define VA_FILTER_SCALING_MASK 0x00000f00<br>
><br>
> In VAProcPipelineParameterBuffer:<br>
><br>
> * - Scaling: \c VA_FILTER_SCALING_DEFAULT, \c<br>
> VA_FILTER_SCALING_FAST,<br>
> * \c VA_FILTER_SCALING_HQ, \c<br>
> VA_FILTER_SCALING_NL_ANAMORPHIC.<br>
> */<br>
> unsigned int filter_flags;<br>
><br>
> For Inter driver, Currently only<br>
> VA_FILTER_SCALING_NL_ANAMORPHIC and<br>
> VA_FILTER_SCALING_DEFAULT/VA_FILTER_SCALING_FAST are<br>
> supported. We<br>
> will add the support for VA_FILTER_SCALING_HQ.<br>
><br>
> Thanks<br>
> Haihao<br>
><br>
> ><br>
> ><br>
> ><br>
> > On Mon, Feb 18, 2013 at 12:11 AM, Xiang, Haihao<br>
> > <<a href="mailto:haihao.xiang@intel.com" target="_blank">haihao.xiang@intel.com</a>> wrote:<br>
> > On Fri, 2013-02-15 at 16:18 -0800, Ratin wrote:<br>
> > > I am decoding a 720 P video stream from a camera<br>
> to 1080 P<br>
> > surfaces<br>
> > > and displaying them on the screen. I am seeing<br>
> noticable<br>
> > noise and<br>
> > > pulsating which is directly related to the I frame<br>
> interval<br>
> > > (aparently), the lowest I-frame interval I can<br>
> specify for<br>
> > the camera<br>
> > > is 1 second and selecting that in addition to<br>
> bitrate of<br>
> > 8192 kbps<br>
> > > makes is slightly better but still a lot of noise.<br>
> A<br>
> > software<br>
> > > decoded/scaled video looks all smooth.<br>
> > ><br>
> > ><br>
> > > What I am wondering is what's the default scaling<br>
> algorithm<br>
> > being used<br>
> > > in vaapi/intel driver and how do I specify better<br>
> scaling<br>
> > algorithms<br>
> > > like bi-cubic etc.and possibly specify the<br>
> strength of<br>
> > deblocking<br>
> > > filter level as well, and what can I do to reduce<br>
> the<br>
> > pulsating ?<br>
> ><br>
> ><br>
> > Which driver are you using ? For Intel, it is<br>
> bilinear.<br>
> ><br>
> > ><br>
> > ><br>
> > ><br>
> > ><br>
> > > Any input would be much appreciated.<br>
> > ><br>
> > ><br>
> > > Thanks<br>
> > ><br>
> > ><br>
> > > Ratin<br>
> > ><br>
> > ><br>
> ><br>
> > > _______________________________________________<br>
> > > Libva mailing list<br>
> > > <a href="mailto:Libva@lists.freedesktop.org" target="_blank">Libva@lists.freedesktop.org</a><br>
> > ><br>
> <a href="http://lists.freedesktop.org/mailman/listinfo/libva" target="_blank">http://lists.freedesktop.org/mailman/listinfo/libva</a><br>
> ><br>
> ><br>
> ><br>
> ><br>
><br>
><br>
><br>
><br>
><br>
<br>
<br>
</div></div><br></div></div>