diff vp8dsp.h @ 12194:80b142c2e9f7 libavcodec

Change function prototypes for width=8 inner and mbedge loopfilter functions so that it does both U and V planes at the same time. This will have speed advantages when using SSE2 (or higher) optimizations, since we can do both the U and V rows together in a single xmm register. This also renames filter16 to filter16y and filter8 to filter8uv so that it's more obvious what each function is used for.

--- a/vp8dsp.h	Mon Jul 19 20:53:58 2010 +0000
+++ b/vp8dsp.h	Mon Jul 19 21:18:04 2010 +0000
@@ -35,16 +35,24 @@
     void (*vp8_idct_dc_add)(uint8_t *dst, DCTELEM block[16], int stride);
 
     // loop filter applied to edges between macroblocks
-    void (*vp8_v_loop_filter16)(uint8_t *dst, int stride, int flim_E, int flim_I, int hev_thresh);
-    void (*vp8_h_loop_filter16)(uint8_t *dst, int stride, int flim_E, int flim_I, int hev_thresh);
-    void (*vp8_v_loop_filter8)(uint8_t *dst, int stride, int flim_E, int flim_I, int hev_thresh);
-    void (*vp8_h_loop_filter8)(uint8_t *dst, int stride, int flim_E, int flim_I, int hev_thresh);
+    void (*vp8_v_loop_filter16y)(uint8_t *dst, int stride,
+                                 int flim_E, int flim_I, int hev_thresh);
+    void (*vp8_h_loop_filter16y)(uint8_t *dst, int stride,
+                                 int flim_E, int flim_I, int hev_thresh);
+    void (*vp8_v_loop_filter8uv)(uint8_t *dstU, uint8_t *dstV, int stride,
+                                 int flim_E, int flim_I, int hev_thresh);
+    void (*vp8_h_loop_filter8uv)(uint8_t *dstU, uint8_t *dstV, int stride,
+                                 int flim_E, int flim_I, int hev_thresh);
 
     // loop filter applied to inner macroblock edges
-    void (*vp8_v_loop_filter16_inner)(uint8_t *dst, int stride, int flim_E, int flim_I, int hev_thresh);
-    void (*vp8_h_loop_filter16_inner)(uint8_t *dst, int stride, int flim_E, int flim_I, int hev_thresh);
-    void (*vp8_v_loop_filter8_inner)(uint8_t *dst, int stride, int flim_E, int flim_I, int hev_thresh);
-    void (*vp8_h_loop_filter8_inner)(uint8_t *dst, int stride, int flim_E, int flim_I, int hev_thresh);
+    void (*vp8_v_loop_filter16y_inner)(uint8_t *dst, int stride,
+                                       int flim_E, int flim_I, int hev_thresh);
+    void (*vp8_h_loop_filter16y_inner)(uint8_t *dst, int stride,
+                                       int flim_E, int flim_I, int hev_thresh);
+    void (*vp8_v_loop_filter8uv_inner)(uint8_t *dstU, uint8_t *dstV, int stride,
+                                       int flim_E, int flim_I, int hev_thresh);
+    void (*vp8_h_loop_filter8uv_inner)(uint8_t *dstU, uint8_t *dstV, int stride,
+                                       int flim_E, int flim_I, int hev_thresh);
 
     void (*vp8_v_loop_filter_simple)(uint8_t *dst, int stride, int flim);
     void (*vp8_h_loop_filter_simple)(uint8_t *dst, int stride, int flim);