Enable SSE4 version of apply temporal filter

Evaluating on 5 midres clips with 4 bitrates over 30 frames on speed 1
auto_alt_ref=1, there is a speed up of 1.660%.

BUG=webm:1591

Change-Id: Idbda58548679e6f7b8fc0d7f6144f7be057ef690

diff --git a/vp9/encoder/vp9_temporal_filter.c b/vp9/encoder/vp9_temporal_filter.c
index bc8619bbe321d8176b7fab5080876924e37024be..04b589ac3514667b478185d120b3a01a46bf0ca7 100644 (file)
--- a/vp9/encoder/vp9_temporal_filter.c
+++ b/vp9/encoder/vp9_temporal_filter.c
@@ -776,7 +776,7 @@ void vp9_temporal_filter_iterate_row_c(VP9_COMP *cpi, ThreadData *td,
               count + (BLK_PELS << 1));
         } else {
           // Apply the filter (YUV)
-          vp9_apply_temporal_filter_c(
+          vp9_apply_temporal_filter(
               f->y_buffer + mb_y_offset, f->y_stride, predictor, BW,
               f->u_buffer + mb_uv_offset, f->v_buffer + mb_uv_offset,
               f->uv_stride, predictor + BLK_PELS, predictor + (BLK_PELS << 1),
@@ -787,7 +787,7 @@ void vp9_temporal_filter_iterate_row_c(VP9_COMP *cpi, ThreadData *td,
         }
 #else
         // Apply the filter (YUV)
-        vp9_apply_temporal_filter_c(
+        vp9_apply_temporal_filter(
             f->y_buffer + mb_y_offset, f->y_stride, predictor, BW,
             f->u_buffer + mb_uv_offset, f->v_buffer + mb_uv_offset,
             f->uv_stride, predictor + BLK_PELS, predictor + (BLK_PELS << 1),