diff options
author | Mark Thompson <sw@jkqxz.net> | 2017-09-10 21:53:36 +0100 |
---|---|---|
committer | Mark Thompson <sw@jkqxz.net> | 2017-11-22 23:18:02 +0000 |
commit | 9204b2deea85c834ba3d5fa2b0e92b86c24f45ae (patch) | |
tree | efb5937de9aad668bf07beccd5caebb55360ab3d /libavfilter/opencl | |
parent | 59d6529333c4550701401d59d67b60454b164b1f (diff) | |
download | ffmpeg-9204b2deea85c834ba3d5fa2b0e92b86c24f45ae.tar.gz |
lavfi: Add OpenCL overlay filter
Input and output formats must be the same, the overlay format must be
the same as the input except possibly with an additional alpha component.
Diffstat (limited to 'libavfilter/opencl')
-rw-r--r-- | libavfilter/opencl/overlay.cl | 104 |
1 files changed, 104 insertions, 0 deletions
diff --git a/libavfilter/opencl/overlay.cl b/libavfilter/opencl/overlay.cl new file mode 100644 index 0000000000..8c783d0edc --- /dev/null +++ b/libavfilter/opencl/overlay.cl @@ -0,0 +1,104 @@ +/* + * This file is part of FFmpeg. + * + * FFmpeg is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * FFmpeg is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with FFmpeg; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ + +__kernel void overlay_no_alpha(__write_only image2d_t dst, + __read_only image2d_t main, + __read_only image2d_t overlay, + int x_position, + int y_position) +{ + const sampler_t sampler = (CLK_NORMALIZED_COORDS_FALSE | + CLK_FILTER_NEAREST); + + int2 overlay_size = get_image_dim(overlay); + int2 loc = (int2)(get_global_id(0), get_global_id(1)); + + if (loc.x < x_position || + loc.y < y_position || + loc.x >= overlay_size.x + x_position || + loc.y >= overlay_size.y + y_position) { + float4 val = read_imagef(main, sampler, loc); + write_imagef(dst, loc, val); + } else { + int2 loc_overlay = (int2)(x_position, y_position); + float4 val = read_imagef(overlay, sampler, loc - loc_overlay); + write_imagef(dst, loc, val); + } +} + +__kernel void overlay_internal_alpha(__write_only image2d_t dst, + __read_only image2d_t main, + __read_only image2d_t overlay, + int x_position, + int y_position) +{ + const sampler_t sampler = (CLK_NORMALIZED_COORDS_FALSE | + CLK_FILTER_NEAREST); + + int2 overlay_size = get_image_dim(overlay); + int2 loc = (int2)(get_global_id(0), get_global_id(1)); + + if (loc.x < x_position || + loc.y < y_position || + loc.x >= overlay_size.x + x_position || + loc.y >= overlay_size.y + y_position) { + float4 val = read_imagef(main, sampler, loc); + write_imagef(dst, loc, val); + } else { + int2 loc_overlay = (int2)(x_position, y_position); + float4 in_main = read_imagef(main, sampler, loc); + float4 in_overlay = read_imagef(overlay, sampler, loc - loc_overlay); + float4 val = in_overlay * in_overlay.w + in_main * (1.0f - in_overlay.w); + write_imagef(dst, loc, val); + } +} + +__kernel void overlay_external_alpha(__write_only image2d_t dst, + __read_only image2d_t main, + __read_only image2d_t overlay, + __read_only image2d_t alpha, + int x_position, + int y_position, + int alpha_adj_x, + int alpha_adj_y) +{ + const sampler_t sampler = (CLK_NORMALIZED_COORDS_FALSE | + CLK_FILTER_NEAREST); + + int2 overlay_size = get_image_dim(overlay); + int2 loc = (int2)(get_global_id(0), get_global_id(1)); + + if (loc.x < x_position || + loc.y < y_position || + loc.x >= overlay_size.x + x_position || + loc.y >= overlay_size.y + y_position) { + float4 val = read_imagef(main, sampler, loc); + write_imagef(dst, loc, val); + } else { + int2 loc_overlay = (int2)(x_position, y_position); + float4 in_main = read_imagef(main, sampler, loc); + float4 in_overlay = read_imagef(overlay, sampler, loc - loc_overlay); + + int2 loc_alpha = (int2)(loc.x * alpha_adj_x, + loc.y * alpha_adj_y) - loc_overlay; + float4 in_alpha = read_imagef(alpha, sampler, loc_alpha); + + float4 val = in_overlay * in_alpha.x + in_main * (1.0f - in_alpha.x); + write_imagef(dst, loc, val); + } +} |