SSE2 optimizations for vp8_build_intra_predictors_mby{,_s}()

Ronald recently sent me this patch that he did in April.
> From: Ronald S. Bultje <rbultje@google.com>
> Date: Thu, 28 Apr 2011 17:30:15 -0700
> Subject: [PATCH] SSE2 optimizations for
> vp8_build_intra_predictors_mby{,_s}().
HD decode tests have shown a performance boost up to 1.5%,
depending on material.
Patch set 3: Fixed encoder crash.

Change-Id: Ie1fd1fa3dc750eec1a7a20bfa2decc079dcf48c8

1 files changed, 66 insertions, 0 deletions

diff --git a/vp8/common/x86/recon_wrapper_sse2.c b/vp8/common/x86/recon_wrapper_sse2.c
index fcc75a901..44221cd0b 100644
--- a/vp8/common/x86/recon_wrapper_sse2.c
+++ b/vp8/common/x86/recon_wrapper_sse2.c
@@ -94,3 +94,69 @@ void vp8_build_intra_predictors_mbuv_s_ssse3(MACROBLOCKD *x)
                                         vp8_intra_pred_uv_tm_ssse3,
                                         vp8_intra_pred_uv_ho_ssse3);
 }
+
+extern build_intra_predictors_mbuv_prototype(vp8_intra_pred_y_dc_sse2);
+extern build_intra_predictors_mbuv_prototype(vp8_intra_pred_y_dctop_sse2);
+extern build_intra_predictors_mbuv_prototype(vp8_intra_pred_y_dcleft_sse2);
+extern build_intra_predictors_mbuv_prototype(vp8_intra_pred_y_dc128_sse2);
+extern build_intra_predictors_mbuv_prototype(vp8_intra_pred_y_ho_sse2);
+extern build_intra_predictors_mbuv_prototype(vp8_intra_pred_y_ve_sse2);
+extern build_intra_predictors_mbuv_prototype(vp8_intra_pred_y_tm_sse2);
+extern build_intra_predictors_mbuv_prototype(vp8_intra_pred_y_tm_ssse3);
+
+static void vp8_build_intra_predictors_mby_x86(MACROBLOCKD *x,
+                                               unsigned char *dst_y,
+                                               int dst_stride,
+                                               build_intra_predictors_mbuv_fn_t tm_func)
+{
+    int mode = x->mode_info_context->mbmi.mode;
+    build_intra_predictors_mbuv_fn_t fn;
+    int src_stride = x->dst.y_stride;
+    switch (mode) {
+        case  V_PRED: fn = vp8_intra_pred_y_ve_sse2; break;
+        case  H_PRED: fn = vp8_intra_pred_y_ho_sse2; break;
+        case TM_PRED: fn = tm_func; break;
+        case DC_PRED:
+            if (x->up_available) {
+                if (x->left_available) {
+                    fn = vp8_intra_pred_y_dc_sse2; break;
+                } else {
+                    fn = vp8_intra_pred_y_dctop_sse2; break;
+                }
+            } else if (x->left_available) {
+                fn = vp8_intra_pred_y_dcleft_sse2; break;
+            } else {
+                fn = vp8_intra_pred_y_dc128_sse2; break;
+            }
+            break;
+        default: return;
+    }
+
+    fn(dst_y, dst_stride, x->dst.y_buffer, src_stride);
+    return;
+}
+
+void vp8_build_intra_predictors_mby_sse2(MACROBLOCKD *x)
+{
+    vp8_build_intra_predictors_mby_x86(x, x->predictor, 16,
+                                       vp8_intra_pred_y_tm_sse2);
+}
+
+void vp8_build_intra_predictors_mby_ssse3(MACROBLOCKD *x)
+{
+    vp8_build_intra_predictors_mby_x86(x, x->predictor, 16,
+                                       vp8_intra_pred_y_tm_ssse3);
+}
+
+void vp8_build_intra_predictors_mby_s_sse2(MACROBLOCKD *x)
+{
+    vp8_build_intra_predictors_mby_x86(x, x->dst.y_buffer, x->dst.y_stride,
+                                       vp8_intra_pred_y_tm_sse2);
+}
+
+void vp8_build_intra_predictors_mby_s_ssse3(MACROBLOCKD *x)
+{
+    vp8_build_intra_predictors_mby_x86(x, x->dst.y_buffer, x->dst.y_stride,
+                                       vp8_intra_pred_y_tm_ssse3);
+
+}