Commit 21e077fc authored by Yogender Gupta's avatar Yogender Gupta Committed by Timo Rothenpieler

avfilter/thumbnail_cuda: add cuda thumbnail filter

Signed-off-by: 's avatarTimo Rothenpieler <timo@rothenpieler.org>
parent 183fd30e
......@@ -48,6 +48,8 @@ version <next>:
- convolve video filter
- VP9 tile threading support
- KMS screen grabber
- CUDA thumbnail filter
version 3.3:
- CrystalHD decoder moved to new decode API
......
......@@ -2759,6 +2759,7 @@ vaapi_encode_deps="vaapi"
hwupload_cuda_filter_deps="cuda"
scale_npp_filter_deps="cuda libnpp"
scale_cuda_filter_deps="cuda_sdk"
thumbnail_cuda_filter_deps="cuda_sdk"
nvenc_deps="cuda"
nvenc_deps_any="dlopen LoadLibrary"
......
......@@ -315,6 +315,7 @@ OBJS-$(CONFIG_TBLEND_FILTER) += vf_blend.o framesync.o
OBJS-$(CONFIG_TELECINE_FILTER) += vf_telecine.o
OBJS-$(CONFIG_THRESHOLD_FILTER) += vf_threshold.o framesync.o
OBJS-$(CONFIG_THUMBNAIL_FILTER) += vf_thumbnail.o
OBJS-$(CONFIG_THUMBNAIL_CUDA_FILTER) += vf_thumbnail_cuda.o vf_thumbnail_cuda.ptx.o
OBJS-$(CONFIG_TILE_FILTER) += vf_tile.o
OBJS-$(CONFIG_TINTERLACE_FILTER) += vf_tinterlace.o
OBJS-$(CONFIG_TLUT2_FILTER) += vf_lut2.o framesync.o
......
......@@ -326,6 +326,7 @@ static void register_all(void)
REGISTER_FILTER(TELECINE, telecine, vf);
REGISTER_FILTER(THRESHOLD, threshold, vf);
REGISTER_FILTER(THUMBNAIL, thumbnail, vf);
REGISTER_FILTER(THUMBNAIL_CUDA, thumbnail_cuda, vf);
REGISTER_FILTER(TILE, tile, vf);
REGISTER_FILTER(TINTERLACE, tinterlace, vf);
REGISTER_FILTER(TLUT2, tlut2, vf);
......
......@@ -30,7 +30,7 @@
#include "libavutil/version.h"
#define LIBAVFILTER_VERSION_MAJOR 6
#define LIBAVFILTER_VERSION_MINOR 105
#define LIBAVFILTER_VERSION_MINOR 106
#define LIBAVFILTER_VERSION_MICRO 100
#define LIBAVFILTER_VERSION_INT AV_VERSION_INT(LIBAVFILTER_VERSION_MAJOR, \
......
This diff is collapsed.
/*
* Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*/
extern "C" {
texture<unsigned char, 2> uchar_tex;
texture<uchar2, 2> uchar2_tex;
texture<unsigned short, 2> ushort_tex;
texture<ushort2, 2> ushort2_tex;
__global__ void Thumbnail_uchar(int *histogram, int src_width, int src_height)
{
int x = blockIdx.x * blockDim.x + threadIdx.x;
int y = blockIdx.y * blockDim.y + threadIdx.y;
if (y < src_height && x < src_width)
{
unsigned char pixel = tex2D(uchar_tex, x, y);
atomicAdd(&histogram[pixel], 1);
}
}
__global__ void Thumbnail_uchar2(int *histogram, int src_width, int src_height)
{
int x = blockIdx.x * blockDim.x + threadIdx.x;
int y = blockIdx.y * blockDim.y + threadIdx.y;
if (y < src_height && x < src_width)
{
uchar2 pixel = tex2D(uchar2_tex, x, y);
atomicAdd(&histogram[pixel.x], 1);
atomicAdd(&histogram[256 + pixel.y], 1);
}
}
__global__ void Thumbnail_ushort(int *histogram, int src_width, int src_height)
{
int x = blockIdx.x * blockDim.x + threadIdx.x;
int y = blockIdx.y * blockDim.y + threadIdx.y;
if (y < src_height && x < src_width)
{
unsigned short pixel = (tex2D(ushort_tex, x, y) + 128) >> 8;
atomicAdd(&histogram[pixel], 1);
}
}
__global__ void Thumbnail_ushort2(int *histogram, int src_width, int src_height)
{
int x = blockIdx.x * blockDim.x + threadIdx.x;
int y = blockIdx.y * blockDim.y + threadIdx.y;
if (y < src_height && x < src_width)
{
ushort2 pixel = tex2D(ushort2_tex, x, y);
atomicAdd(&histogram[(pixel.x + 128) >> 8], 1);
atomicAdd(&histogram[256 + (pixel.y + 128) >> 8], 1);
}
}
}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment