lavfi: add an NVIDIA NPP-based scaling filter

Changelog

@@ -52,6 +52,7 @@ version <next>:
 - G.723.1 muxer and encoder
 - compressed SWF
 - VAAPI-accelerated format conversion and scaling
+- libnpp/CUDA-accelerated format conversion and scaling
 
 
 version 11:

configure

@@ -195,6 +195,7 @@ External library support:
   --enable-libkvazaar      enable HEVC encoding via libkvazaar [no]
   --enable-libmfx          enable HW acceleration through libmfx
   --enable-libmp3lame      enable MP3 encoding via libmp3lame [no]
+  --enable-libnpp          enable NVIDIA Performance Primitives-based code [no]
   --enable-libopencore-amrnb enable AMR-NB de/encoding via libopencore-amrnb [no]
   --enable-libopencore-amrwb enable AMR-WB decoding via libopencore-amrwb [no]
   --enable-libopencv       enable video filtering via libopencv [no]
@@ -1222,6 +1223,7 @@ EXTERNAL_LIBRARY_LIST="
     libkvazaar
     libmfx
     libmp3lame
+    libnpp
     libopencore_amrnb
     libopencore_amrwb
     libopencv
@@ -2359,6 +2361,7 @@ interlace_filter_deps="gpl"
 ocv_filter_deps="libopencv"
 resample_filter_deps="avresample"
 scale_filter_deps="swscale"
+scale_npp_filter_deps="cuda libnpp"
 scale_vaapi_filter_deps="vaapi VAProcPipelineParameterBuffer"
 
 # examples
@@ -4024,6 +4027,7 @@ die_license_disabled gpl x11grab
 die_license_disabled nonfree cuda
 die_license_disabled nonfree libfaac
 die_license_disabled nonfree libfdk_aac
+die_license_disabled nonfree libnpp
 die_license_disabled nonfree nvenc
 die_license_disabled nonfree openssl
 
@@ -4520,6 +4524,7 @@ enabled libilbc           && require libilbc ilbc.h WebRtcIlbcfix_InitDecode -li
 enabled libkvazaar        && require_pkg_config "kvazaar >= 0.8.1" kvazaar.h kvz_api_get
 enabled libmfx            && require_pkg_config libmfx "mfx/mfxvideo.h" MFXInit
 enabled libmp3lame        && require "libmp3lame >= 3.98.3" lame/lame.h lame_set_VBR_quality -lmp3lame
+enabled libnpp            && require libnpp npp.h nppGetLibVersion -lnppi -lnppc
 enabled libopencore_amrnb && require libopencore_amrnb opencore-amrnb/interf_dec.h Decoder_Interface_init -lopencore-amrnb
 enabled libopencore_amrwb && require libopencore_amrwb opencore-amrwb/dec_if.h D_IF_init -lopencore-amrwb
 enabled libopencv         && require_pkg_config opencv opencv/cv.h cvCreateImageHeader

doc/filters.texi

@@ -2181,6 +2181,44 @@ scale="trunc(3/2*iw/hsub)*hsub:trunc(3/2*ih/vsub)*vsub"
 scale=w='min(500\, iw*3/2):h=-1'
 @end example
 
+@section scale_npp
+
+Use the NVIDIA Performance Primitives (libnpp) to perform scaling and/or pixel
+format conversion on CUDA video frames. Setting the output width and height
+works in the same way as for the @var{scale} filter.
+
+The following additional options are accepted:
+@table @option
+@item format
+The pixel format of the output CUDA frames. If set to the string "same" (the
+default), the input format will be kept. Note that automatic format negotiation
+and conversion is not yet supported for hardware frames
+
+@item interp_algo
+The interpolation algorithm used for resizing. One of the following:
+@table @option
+@item nn
+Nearest neighbour.
+
+@item linear
+@item cubic
+@item cubic2p_bspline
+2-parameter cubic (B=1, C=0)
+
+@item cubic2p_catmullrom
+2-parameter cubic (B=0, C=1/2)
+
+@item cubic2p_b05c03
+2-parameter cubic (B=1/2, C=3/10)
+
+@item super
+Supersampling
+
+@item lanczos
+@end table
+
+@end table
+
 @section select
 Select frames to pass in output.
 

libavfilter/Makefile

@@ -71,6 +71,7 @@ OBJS-$(CONFIG_OVERLAY_FILTER)                += vf_overlay.o
 OBJS-$(CONFIG_PAD_FILTER)                    += vf_pad.o
 OBJS-$(CONFIG_PIXDESCTEST_FILTER)            += vf_pixdesctest.o
 OBJS-$(CONFIG_SCALE_FILTER)                  += vf_scale.o
+OBJS-$(CONFIG_SCALE_NPP_FILTER)              += vf_scale_npp.o
 OBJS-$(CONFIG_SCALE_VAAPI_FILTER)            += vf_scale_vaapi.o
 OBJS-$(CONFIG_SELECT_FILTER)                 += vf_select.o
 OBJS-$(CONFIG_SETDAR_FILTER)                 += vf_aspect.o

libavfilter/allfilters.c

@@ -97,6 +97,7 @@ void avfilter_register_all(void)
     REGISTER_FILTER(PAD,            pad,            vf);
     REGISTER_FILTER(PIXDESCTEST,    pixdesctest,    vf);
     REGISTER_FILTER(SCALE,          scale,          vf);
+    REGISTER_FILTER(SCALE_NPP,      scale_npp,      vf);
     REGISTER_FILTER(SCALE_VAAPI,    scale_vaapi,    vf);
     REGISTER_FILTER(SELECT,         select,         vf);
     REGISTER_FILTER(SETDAR,         setdar,         vf);

libavfilter/version.h

@@ -30,7 +30,7 @@
 #include "libavutil/version.h"
 
 #define LIBAVFILTER_VERSION_MAJOR  6
-#define LIBAVFILTER_VERSION_MINOR  3
+#define LIBAVFILTER_VERSION_MINOR  4
 #define LIBAVFILTER_VERSION_MICRO  0
 
 #define LIBAVFILTER_VERSION_INT AV_VERSION_INT(LIBAVFILTER_VERSION_MAJOR, \