vo_opengl: implement compute shader based EWA kernel

This performs almost 50% faster on my machine (!!), from 4650μs down to
about 3176μs for ewa_lanczossharp.

It's possible we could use a similar approach to speed up the separable
scalers, although with vastly simpler code. For separable scalers we'd
also have the additional huge benefit of only needing padding in one
direction, so we could potentially use a big 256x1 kernel or something
to essentially compute an entire row at once.

1 files changed, 3 insertions, 0 deletions

diff --git a/video/out/opengl/video_shaders.h b/video/out/opengl/video_shaders.h
index e0594f28f3..597027ca6b 100644
--- a/video/out/opengl/video_shaders.h
+++ b/video/out/opengl/video_shaders.h
@@ -32,6 +32,9 @@ void pass_sample_separated_gen(struct gl_shader_cache *sc, struct scaler *scaler
                                int d_x, int d_y);
 void pass_sample_polar(struct gl_shader_cache *sc, struct scaler *scaler,
                        int components, int glsl_version);
+void pass_compute_polar(struct gl_shader_cache *sc, struct scaler *scaler,
+                        int components, int bw, int bh, float ratiox,
+                        float ratioy);
 void pass_sample_bicubic_fast(struct gl_shader_cache *sc);
 void pass_sample_oversample(struct gl_shader_cache *sc, struct scaler *scaler,
                             int w, int h);