diff --git a/vp8/common/blockd.h b/vp8/common/blockd.h
index 82c55a9e9dff80a76e3c3100f32e8b0e7ab13b88..d8df42b4831830fbe104a339d52fedb62c1ecd9a 100644
--- a/vp8/common/blockd.h
+++ b/vp8/common/blockd.h
@@ -287,10 +287,6 @@ typedef struct macroblockd
      */
     DECLARE_ALIGNED(32, unsigned char, y_buf[22*32]);
 #endif
-
-#if CONFIG_RUNTIME_CPU_DETECT
-    struct VP8_COMMON_RTCD  *rtcd;
-#endif
 } MACROBLOCKD;
 
 
diff --git a/vp8/common/rtcd_defs.sh b/vp8/common/rtcd_defs.sh
index e18ca97da6c4f2fac4a6f9ae38fc0bccd0f3e67f..13fe8ecdd7ec7b1a13a3cbb06011ace6aea785c2 100644
--- a/vp8/common/rtcd_defs.sh
+++ b/vp8/common/rtcd_defs.sh
@@ -481,6 +481,13 @@ vp8_refining_search_sad_sse3=vp8_refining_search_sadx4
 prototype int vp8_diamond_search_sad "struct macroblock *x, struct block *b, struct blockd *d, union int_mv *ref_mv, union int_mv *best_mv, int search_param, int sad_per_bit, int *num00, struct variance_vtable *fn_ptr, int *mvcost[2], union int_mv *center_mv"
 vp8_diamond_search_sad_sse3=vp8_diamond_search_sadx4
 
+#
+# Alt-ref Noise Reduction (ARNR)
+#
+if [ "$CONFIG_REALTIME_ONLY" != "yes" ]; then
+    prototype void vp8_temporal_filter_apply "unsigned char *frame1, unsigned int stride, unsigned char *frame2, unsigned int block_size, int strength, int filter_weight, unsigned int *accumulator, unsigned short *count"
+    specialize vp8_temporal_filter_apply sse2
+fi
 
 # End of encoder only functions
 fi
diff --git a/vp8/decoder/decodframe.c b/vp8/decoder/decodframe.c
index ed0e3250d50190758cb1ac7044d8d21e2c30e8b1..7ba573123f2d4a2cf027edff5cfa80ca1fc71c3b 100644
--- a/vp8/decoder/decodframe.c
+++ b/vp8/decoder/decodframe.c
@@ -93,11 +93,6 @@ void mb_init_dequantizer(VP8D_COMP *pbi, MACROBLOCKD *xd)
     }
 }
 
-#if CONFIG_RUNTIME_CPU_DETECT
-#define RTCD_VTABLE(x) (&(pbi)->common.rtcd.x)
-#else
-#define RTCD_VTABLE(x) NULL
-#endif
 
 static void decode_macroblock(VP8D_COMP *pbi, MACROBLOCKD *xd,
                               unsigned int mb_idx)
diff --git a/vp8/decoder/threading.c b/vp8/decoder/threading.c
index bb77340136aa924ed07147c0d36851a635fb2f53..c2b15cf1810f88dd9d06643e7302768e31935665 100644
--- a/vp8/decoder/threading.c
+++ b/vp8/decoder/threading.c
@@ -30,12 +30,6 @@
 
 extern void mb_init_dequantizer(VP8D_COMP *pbi, MACROBLOCKD *xd);
 
-#if CONFIG_RUNTIME_CPU_DETECT
-#define RTCD_VTABLE(x) (&(pbi)->common.rtcd.x)
-#else
-#define RTCD_VTABLE(x) NULL
-#endif
-
 static void setup_decoding_thread_data(VP8D_COMP *pbi, MACROBLOCKD *xd, MB_ROW_DEC *mbrd, int count)
 {
     VP8_COMMON *const pc = & pbi->common;
@@ -44,9 +38,6 @@ static void setup_decoding_thread_data(VP8D_COMP *pbi, MACROBLOCKD *xd, MB_ROW_D
     for (i = 0; i < count; i++)
     {
         MACROBLOCKD *mbd = &mbrd[i].mbd;
-#if CONFIG_RUNTIME_CPU_DETECT
-        mbd->rtcd = xd->rtcd;
-#endif
         mbd->subpixel_predict        = xd->subpixel_predict;
         mbd->subpixel_predict8x4     = xd->subpixel_predict8x4;
         mbd->subpixel_predict8x8     = xd->subpixel_predict8x8;
diff --git a/vp8/encoder/encodeframe.c b/vp8/encoder/encodeframe.c
index 2392f0220801b13d3c561ead1204ab18983ff833..8fb05843e7c8d82b428e87502d70fe34be8a8f7b 100644
--- a/vp8/encoder/encodeframe.c
+++ b/vp8/encoder/encodeframe.c
@@ -29,13 +29,6 @@
 #include "vp8/common/invtrans.h"
 #include "vpx_ports/vpx_timer.h"
 
-#if CONFIG_RUNTIME_CPU_DETECT
-#define RTCD(x)     &cpi->common.rtcd.x
-#define IF_RTCD(x)  (x)
-#else
-#define RTCD(x)     NULL
-#define IF_RTCD(x)  NULL
-#endif
 extern void vp8_stuff_mb(VP8_COMP *cpi, MACROBLOCKD *x, TOKENEXTRA **t) ;
 extern void vp8_calc_ref_frame_costs(int *ref_frame_cost,
                                      int prob_intra,
@@ -1097,11 +1090,11 @@ int vp8cx_encode_intra_macro_block(VP8_COMP *cpi, MACROBLOCK *x, TOKENEXTRA **t,
     }
 
     if (x->e_mbd.mode_info_context->mbmi.mode == B_PRED)
-        vp8_encode_intra4x4mby(IF_RTCD(&cpi->rtcd), x);
+        vp8_encode_intra4x4mby(x);
     else
-        vp8_encode_intra16x16mby(IF_RTCD(&cpi->rtcd), x);
+        vp8_encode_intra16x16mby(x);
 
-    vp8_encode_intra16x16mbuv(IF_RTCD(&cpi->rtcd), x);
+    vp8_encode_intra16x16mbuv(x);
 
     sum_intra_stats(cpi, x);
     vp8_tokenize_mb(cpi, &x->e_mbd, t);
@@ -1239,15 +1232,15 @@ int vp8cx_encode_inter_macroblock
 
     if (xd->mode_info_context->mbmi.ref_frame == INTRA_FRAME)
     {
-        vp8_encode_intra16x16mbuv(IF_RTCD(&cpi->rtcd), x);
+        vp8_encode_intra16x16mbuv(x);
 
         if (xd->mode_info_context->mbmi.mode == B_PRED)
         {
-            vp8_encode_intra4x4mby(IF_RTCD(&cpi->rtcd), x);
+            vp8_encode_intra4x4mby(x);
         }
         else
         {
-            vp8_encode_intra16x16mby(IF_RTCD(&cpi->rtcd), x);
+            vp8_encode_intra16x16mby(x);
         }
 
         sum_intra_stats(cpi, x);
@@ -1269,7 +1262,7 @@ int vp8cx_encode_inter_macroblock
 
         if (!x->skip)
         {
-            vp8_encode_inter16x16(IF_RTCD(&cpi->rtcd), x);
+            vp8_encode_inter16x16(x);
 
             // Clear mb_skip_coeff if mb_no_coeff_skip is not set
             if (!cpi->common.mb_no_coeff_skip)
diff --git a/vp8/encoder/encodeintra.c b/vp8/encoder/encodeintra.c
index c457906f6b9b063ec801ff510bfd9b665e47318e..1f83d2a49d2026c4835a6e78ff88e4bbb4d5a333 100644
--- a/vp8/encoder/encodeintra.c
+++ b/vp8/encoder/encodeintra.c
@@ -18,12 +18,6 @@
 #include "encodeintra.h"
 
 
-#if CONFIG_RUNTIME_CPU_DETECT
-#define IF_RTCD(x) (x)
-#else
-#define IF_RTCD(x) NULL
-#endif
-
 int vp8_encode_intra(VP8_COMP *cpi, MACROBLOCK *x, int use_dc_pred)
 {
 
@@ -33,13 +27,11 @@ int vp8_encode_intra(VP8_COMP *cpi, MACROBLOCK *x, int use_dc_pred)
 
     if (use_dc_pred)
     {
-        const VP8_ENCODER_RTCD *rtcd = IF_RTCD(&cpi->rtcd);
-
         x->e_mbd.mode_info_context->mbmi.mode = DC_PRED;
         x->e_mbd.mode_info_context->mbmi.uv_mode = DC_PRED;
         x->e_mbd.mode_info_context->mbmi.ref_frame = INTRA_FRAME;
 
-        vp8_encode_intra16x16mby(rtcd, x);
+        vp8_encode_intra16x16mby(x);
 
         vp8_inverse_transform_mby(&x->e_mbd);
     }
@@ -48,7 +40,7 @@ int vp8_encode_intra(VP8_COMP *cpi, MACROBLOCK *x, int use_dc_pred)
         for (i = 0; i < 16; i++)
         {
             x->e_mbd.block[i].bmi.as_mode = B_DC_PRED;
-            vp8_encode_intra4x4block(IF_RTCD(&cpi->rtcd), x, i);
+            vp8_encode_intra4x4block(x, i);
         }
     }
 
@@ -57,8 +49,7 @@ int vp8_encode_intra(VP8_COMP *cpi, MACROBLOCK *x, int use_dc_pred)
     return intra_pred_var;
 }
 
-void vp8_encode_intra4x4block(const VP8_ENCODER_RTCD *rtcd,
-                              MACROBLOCK *x, int ib)
+void vp8_encode_intra4x4block(MACROBLOCK *x, int ib)
 {
     BLOCKD *b = &x->e_mbd.block[ib];
     BLOCK *be = &x->block[ib];
@@ -86,7 +77,7 @@ void vp8_encode_intra4x4block(const VP8_ENCODER_RTCD *rtcd,
     }
 }
 
-void vp8_encode_intra4x4mby(const VP8_ENCODER_RTCD *rtcd, MACROBLOCK *mb)
+void vp8_encode_intra4x4mby(MACROBLOCK *mb)
 {
     int i;
 
@@ -94,11 +85,11 @@ void vp8_encode_intra4x4mby(const VP8_ENCODER_RTCD *rtcd, MACROBLOCK *mb)
     vp8_intra_prediction_down_copy(x);
 
     for (i = 0; i < 16; i++)
-        vp8_encode_intra4x4block(rtcd, mb, i);
+        vp8_encode_intra4x4block(mb, i);
     return;
 }
 
-void vp8_encode_intra16x16mby(const VP8_ENCODER_RTCD *rtcd, MACROBLOCK *x)
+void vp8_encode_intra16x16mby(MACROBLOCK *x)
 {
     BLOCK *b = &x->block[0];
     MACROBLOCKD *xd = &x->e_mbd;
@@ -113,10 +104,10 @@ void vp8_encode_intra16x16mby(const VP8_ENCODER_RTCD *rtcd, MACROBLOCK *x)
     vp8_quantize_mby(x);
 
     if (x->optimize)
-        vp8_optimize_mby(x, rtcd);
+        vp8_optimize_mby(x);
 }
 
-void vp8_encode_intra16x16mbuv(const VP8_ENCODER_RTCD *rtcd, MACROBLOCK *x)
+void vp8_encode_intra16x16mbuv(MACROBLOCK *x)
 {
     MACROBLOCKD *xd = &x->e_mbd;
 
@@ -131,5 +122,5 @@ void vp8_encode_intra16x16mbuv(const VP8_ENCODER_RTCD *rtcd, MACROBLOCK *x)
     vp8_quantize_mbuv(x);
 
     if (x->optimize)
-        vp8_optimize_mbuv(x, rtcd);
+        vp8_optimize_mbuv(x);
 }
diff --git a/vp8/encoder/encodeintra.h b/vp8/encoder/encodeintra.h
index 9c1fa56842507dda7ddffc50b33f977508555c44..be2141f2c633b9564eae243fe20ada34393146f4 100644
--- a/vp8/encoder/encodeintra.h
+++ b/vp8/encoder/encodeintra.h
@@ -14,9 +14,8 @@
 #include "onyx_int.h"
 
 int vp8_encode_intra(VP8_COMP *cpi, MACROBLOCK *x, int use_dc_pred);
-void vp8_encode_intra16x16mby(const VP8_ENCODER_RTCD *, MACROBLOCK *x);
-void vp8_encode_intra16x16mbuv(const VP8_ENCODER_RTCD *, MACROBLOCK *x);
-void vp8_encode_intra4x4mby(const VP8_ENCODER_RTCD *, MACROBLOCK *mb);
-void vp8_encode_intra4x4block(const VP8_ENCODER_RTCD *rtcd,
-                              MACROBLOCK *x, int ib);
+void vp8_encode_intra16x16mby(MACROBLOCK *x);
+void vp8_encode_intra16x16mbuv(MACROBLOCK *x);
+void vp8_encode_intra4x4mby(MACROBLOCK *mb);
+void vp8_encode_intra4x4block(MACROBLOCK *x, int ib);
 #endif
diff --git a/vp8/encoder/encodemb.c b/vp8/encoder/encodemb.c
index 8e139400b333c7f702193c81e026fba861edba54..f89e4f7a4d593bfddb70e379658e38e1fdd0f7fa 100644
--- a/vp8/encoder/encodemb.c
+++ b/vp8/encoder/encodemb.c
@@ -19,11 +19,6 @@
 #include "vpx_mem/vpx_mem.h"
 #include "rdopt.h"
 
-#if CONFIG_RUNTIME_CPU_DETECT
-#define IF_RTCD(x) (x)
-#else
-#define IF_RTCD(x) NULL
-#endif
 void vp8_subtract_b_c(BLOCK *be, BLOCKD *bd, int pitch)
 {
     unsigned char *src_ptr = (*(be->base_src) + be->src);
@@ -98,7 +93,7 @@ void vp8_subtract_mby_c(short *diff, unsigned char *src, int src_stride,
     }
 }
 
-static void vp8_subtract_mb(const VP8_ENCODER_RTCD *rtcd, MACROBLOCK *x)
+static void vp8_subtract_mb(MACROBLOCK *x)
 {
     BLOCK *b = &x->block[0];
 
@@ -227,8 +222,7 @@ static const int plane_rd_mult[4]=
 };
 
 static void optimize_b(MACROBLOCK *mb, int ib, int type,
-                       ENTROPY_CONTEXT *a, ENTROPY_CONTEXT *l,
-                       const VP8_ENCODER_RTCD *rtcd)
+                       ENTROPY_CONTEXT *a, ENTROPY_CONTEXT *l)
 {
     BLOCK *b;
     BLOCKD *d;
@@ -509,7 +503,7 @@ static void check_reset_2nd_coeffs(MACROBLOCKD *x, int type,
     }
 }
 
-static void optimize_mb(MACROBLOCK *x, const VP8_ENCODER_RTCD *rtcd)
+static void optimize_mb(MACROBLOCK *x)
 {
     int b;
     int type;
@@ -532,27 +526,27 @@ static void optimize_mb(MACROBLOCK *x, const VP8_ENCODER_RTCD *rtcd)
     for (b = 0; b < 16; b++)
     {
         optimize_b(x, b, type,
-            ta + vp8_block2above[b], tl + vp8_block2left[b], rtcd);
+            ta + vp8_block2above[b], tl + vp8_block2left[b]);
     }
 
     for (b = 16; b < 24; b++)
     {
         optimize_b(x, b, PLANE_TYPE_UV,
-            ta + vp8_block2above[b], tl + vp8_block2left[b], rtcd);
+            ta + vp8_block2above[b], tl + vp8_block2left[b]);
     }
 
     if (has_2nd_order)
     {
         b=24;
         optimize_b(x, b, PLANE_TYPE_Y2,
-            ta + vp8_block2above[b], tl + vp8_block2left[b], rtcd);
+            ta + vp8_block2above[b], tl + vp8_block2left[b]);
         check_reset_2nd_coeffs(&x->e_mbd, PLANE_TYPE_Y2,
             ta + vp8_block2above[b], tl + vp8_block2left[b]);
     }
 }
 
 
-void vp8_optimize_mby(MACROBLOCK *x, const VP8_ENCODER_RTCD *rtcd)
+void vp8_optimize_mby(MACROBLOCK *x)
 {
     int b;
     int type;
@@ -581,7 +575,7 @@ void vp8_optimize_mby(MACROBLOCK *x, const VP8_ENCODER_RTCD *rtcd)
     for (b = 0; b < 16; b++)
     {
         optimize_b(x, b, type,
-            ta + vp8_block2above[b], tl + vp8_block2left[b], rtcd);
+            ta + vp8_block2above[b], tl + vp8_block2left[b]);
     }
 
 
@@ -589,13 +583,13 @@ void vp8_optimize_mby(MACROBLOCK *x, const VP8_ENCODER_RTCD *rtcd)
     {
         b=24;
         optimize_b(x, b, PLANE_TYPE_Y2,
-            ta + vp8_block2above[b], tl + vp8_block2left[b], rtcd);
+            ta + vp8_block2above[b], tl + vp8_block2left[b]);
         check_reset_2nd_coeffs(&x->e_mbd, PLANE_TYPE_Y2,
             ta + vp8_block2above[b], tl + vp8_block2left[b]);
     }
 }
 
-void vp8_optimize_mbuv(MACROBLOCK *x, const VP8_ENCODER_RTCD *rtcd)
+void vp8_optimize_mbuv(MACROBLOCK *x)
 {
     int b;
     ENTROPY_CONTEXT_PLANES t_above, t_left;
@@ -617,26 +611,26 @@ void vp8_optimize_mbuv(MACROBLOCK *x, const VP8_ENCODER_RTCD *rtcd)
     for (b = 16; b < 24; b++)
     {
         optimize_b(x, b, PLANE_TYPE_UV,
-            ta + vp8_block2above[b], tl + vp8_block2left[b], rtcd);
+            ta + vp8_block2above[b], tl + vp8_block2left[b]);
     }
 }
 
-void vp8_encode_inter16x16(const VP8_ENCODER_RTCD *rtcd, MACROBLOCK *x)
+void vp8_encode_inter16x16(MACROBLOCK *x)
 {
     vp8_build_inter_predictors_mb(&x->e_mbd);
 
-    vp8_subtract_mb(rtcd, x);
+    vp8_subtract_mb(x);
 
     transform_mb(x);
 
     vp8_quantize_mb(x);
 
     if (x->optimize)
-        optimize_mb(x, rtcd);
+        optimize_mb(x);
 }
 
 /* this funciton is used by first pass only */
-void vp8_encode_inter16x16y(const VP8_ENCODER_RTCD *rtcd, MACROBLOCK *x)
+void vp8_encode_inter16x16y(MACROBLOCK *x)
 {
     BLOCK *b = &x->block[0];
 
diff --git a/vp8/encoder/encodemb.h b/vp8/encoder/encodemb.h
index df3ac2f6fcdd4968138fb616754abc5621a90f95..6badf7d901aa86a9e76d7cca332d5e6725e8ac6d 100644
--- a/vp8/encoder/encodemb.h
+++ b/vp8/encoder/encodemb.h
@@ -13,15 +13,14 @@
 #define __INC_ENCODEMB_H
 
 #include "onyx_int.h"
-struct VP8_ENCODER_RTCD;
-void vp8_encode_inter16x16(const struct VP8_ENCODER_RTCD *rtcd, MACROBLOCK *x);
+void vp8_encode_inter16x16(MACROBLOCK *x);
 
 void vp8_build_dcblock(MACROBLOCK *b);
 void vp8_transform_mb(MACROBLOCK *mb);
 void vp8_transform_mbuv(MACROBLOCK *x);
 void vp8_transform_intra_mby(MACROBLOCK *x);
 
-void vp8_optimize_mby(MACROBLOCK *x, const struct VP8_ENCODER_RTCD *rtcd);
-void vp8_optimize_mbuv(MACROBLOCK *x, const struct VP8_ENCODER_RTCD *rtcd);
-void vp8_encode_inter16x16y(const struct VP8_ENCODER_RTCD *rtcd, MACROBLOCK *x);
+void vp8_optimize_mby(MACROBLOCK *x);
+void vp8_optimize_mbuv(MACROBLOCK *x);
+void vp8_encode_inter16x16y(MACROBLOCK *x);
 #endif
diff --git a/vp8/encoder/ethreading.c b/vp8/encoder/ethreading.c
index 9dfb426c7bdfd6d06687ca3259a7f1d2a576fd65..bb6b2846c87c9e2c975f8f2728520c035e54a5a5 100644
--- a/vp8/encoder/ethreading.c
+++ b/vp8/encoder/ethreading.c
@@ -425,9 +425,6 @@ void vp8cx_init_mbrthread_data(VP8_COMP *cpi,
         mbd->subpixel_predict8x4     = xd->subpixel_predict8x4;
         mbd->subpixel_predict8x8     = xd->subpixel_predict8x8;
         mbd->subpixel_predict16x16   = xd->subpixel_predict16x16;
-#if CONFIG_RUNTIME_CPU_DETECT
-        mbd->rtcd                   = xd->rtcd;
-#endif
         mb->gf_active_ptr            = x->gf_active_ptr;
 
         vpx_memset(mbr_ei[i].segment_counts, 0, sizeof(mbr_ei[i].segment_counts));
diff --git a/vp8/encoder/firstpass.c b/vp8/encoder/firstpass.c
index 09f184c6b5314c8ff5b30983c1e994a1bae25b7e..6e5532c01059978eadae8aadc72a891c456cef64 100644
--- a/vp8/encoder/firstpass.c
+++ b/vp8/encoder/firstpass.c
@@ -31,12 +31,6 @@
 
 //#define OUTPUT_FPF 1
 
-#if CONFIG_RUNTIME_CPU_DETECT
-#define IF_RTCD(x) (x)
-#else
-#define IF_RTCD(x) NULL
-#endif
-
 extern void vp8_build_block_offsets(MACROBLOCK *x);
 extern void vp8_setup_block_ptrs(MACROBLOCK *x);
 extern void vp8cx_frame_init_quantizer(VP8_COMP *cpi);
@@ -674,7 +668,7 @@ void vp8_first_pass(VP8_COMP *cpi)
                     d->bmi.mv.as_mv.col <<= 3;
                     this_error = motion_error;
                     vp8_set_mbmode_and_mvs(x, NEWMV, &d->bmi.mv);
-                    vp8_encode_inter16x16y(IF_RTCD(&cpi->rtcd), x);
+                    vp8_encode_inter16x16y(x);
                     sum_mvr += d->bmi.mv.as_mv.row;
                     sum_mvr_abs += abs(d->bmi.mv.as_mv.row);
                     sum_mvc += d->bmi.mv.as_mv.col;
diff --git a/vp8/encoder/generic/csystemdependent.c b/vp8/encoder/generic/csystemdependent.c
index 1d6acca149786c36805185029588c59cd7cd4191..673a8050d08e92297fc2a93fe6600b0719a3e049 100644
--- a/vp8/encoder/generic/csystemdependent.c
+++ b/vp8/encoder/generic/csystemdependent.c
@@ -24,12 +24,6 @@ extern void vp8_yv12_copy_partial_frame(YV12_BUFFER_CONFIG *src_ybc,
 
 void vp8_cmachine_specific_config(VP8_COMP *cpi)
 {
-#if CONFIG_RUNTIME_CPU_DETECT
-#if !(CONFIG_REALTIME_ONLY)
-    cpi->rtcd.temporal.apply                 = vp8_temporal_filter_apply_c;
-#endif
-#endif
-
     // Pure C:
     vp8_yv12_copy_partial_frame_ptr = vp8_yv12_copy_partial_frame;
 
diff --git a/vp8/encoder/onyx_if.c b/vp8/encoder/onyx_if.c
index b02d378e03d5153e6ff54875172edfb02d8d5ed1..b03b33953a242f86ae53ec71bc8fd38dae9c09f8 100644
--- a/vp8/encoder/onyx_if.c
+++ b/vp8/encoder/onyx_if.c
@@ -31,7 +31,6 @@
 #include "vp8/common/swapyv12buffer.h"
 #include "vp8/common/threading.h"
 #include "vpx_ports/vpx_timer.h"
-#include "temporal_filter.h"
 #if ARCH_ARM
 #include "vpx_ports/arm.h"
 #endif
@@ -43,14 +42,6 @@
 #include <stdio.h>
 #include <limits.h>
 
-#if CONFIG_RUNTIME_CPU_DETECT
-#define IF_RTCD(x) (x)
-#define RTCD(x) &cpi->common.rtcd.x
-#else
-#define IF_RTCD(x) NULL
-#define RTCD(x) NULL
-#endif
-
 extern void vp8cx_pick_filter_level_fast(YV12_BUFFER_CONFIG *sd, VP8_COMP *cpi);
 extern void vp8cx_set_alt_lf_level(VP8_COMP *cpi, int filt_val);
 extern void vp8cx_pick_filter_level(YV12_BUFFER_CONFIG *sd, VP8_COMP *cpi);
diff --git a/vp8/encoder/onyx_int.h b/vp8/encoder/onyx_int.h
index f91e6df14d2da2633dbb61c5cce7b7933a10cbd9..6920fc316f9823c0213b310078b55eec608cd6cd 100644
--- a/vp8/encoder/onyx_int.h
+++ b/vp8/encoder/onyx_int.h
@@ -26,7 +26,6 @@
 #include "vpx_ports/mem.h"
 #include "vpx/internal/vpx_codec_internal.h"
 #include "mcomp.h"
-#include "temporal_filter.h"
 #include "vp8/common/findnearmv.h"
 #include "lookahead.h"
 
@@ -220,12 +219,6 @@ typedef struct
     void *ptr1;
 } LPFTHREAD_DATA;
 
-
-typedef struct VP8_ENCODER_RTCD
-{
-    vp8_temporal_rtcd_vtable_t  temporal;
-} VP8_ENCODER_RTCD;
-
 enum
 {
     BLOCK_16X8,
@@ -609,9 +602,6 @@ typedef struct VP8_COMP
         double est_max_qcorrection_factor;
     } twopass;
 
-#if CONFIG_RUNTIME_CPU_DETECT
-    VP8_ENCODER_RTCD            rtcd;
-#endif
 #if VP8_TEMPORAL_ALT_REF
     YV12_BUFFER_CONFIG alt_ref_buffer;
     YV12_BUFFER_CONFIG *frames[MAX_LAG_BUFFERS];
diff --git a/vp8/encoder/pickinter.c b/vp8/encoder/pickinter.c
index 4f69a5a899e86d1d0c0b0fa309f765007e092aa6..732701126fa434df1c17c6ba5ad09c9512e106fe 100644
--- a/vp8/encoder/pickinter.c
+++ b/vp8/encoder/pickinter.c
@@ -25,12 +25,6 @@
 #include "rdopt.h"
 #include "vpx_mem/vpx_mem.h"
 
-#if CONFIG_RUNTIME_CPU_DETECT
-#define IF_RTCD(x) (x)
-#else
-#define IF_RTCD(x)  NULL
-#endif
-
 extern int VP8_UVSSE(MACROBLOCK *x);
 
 #ifdef SPEEDSTATS
@@ -131,7 +125,6 @@ static int get_prediction_error(BLOCK *be, BLOCKD *b)
 }
 
 static int pick_intra4x4block(
-    const VP8_ENCODER_RTCD *rtcd,
     MACROBLOCK *x,
     int ib,
     B_PREDICTION_MODE *best_mode,
@@ -169,14 +162,13 @@ static int pick_intra4x4block(
     }
 
     b->bmi.as_mode = (B_PREDICTION_MODE)(*best_mode);
-    vp8_encode_intra4x4block(rtcd, x, ib);
+    vp8_encode_intra4x4block(x, ib);
     return best_rd;
 }
 
 
 static int pick_intra4x4mby_modes
 (
-    const VP8_ENCODER_RTCD *rtcd,
     MACROBLOCK *mb,
     int *Rate,
     int *best_dist
@@ -210,7 +202,7 @@ static int pick_intra4x4mby_modes
         }
 
 
-        pick_intra4x4block(rtcd, mb, i, &best_mode, bmode_costs, &r, &d);
+        pick_intra4x4block(mb, i, &best_mode, bmode_costs, &r, &d);
 
         cost += r;
         distortion += d;
@@ -664,7 +656,7 @@ void vp8_pick_inter_mode(VP8_COMP *cpi, MACROBLOCK *x, int recon_yoffset,
         case B_PRED:
             /* Pass best so far to pick_intra4x4mby_modes to use as breakout */
             distortion2 = best_sse;
-            pick_intra4x4mby_modes(IF_RTCD(&cpi->rtcd), x, &rate, &distortion2);
+            pick_intra4x4mby_modes(x, &rate, &distortion2);
 
             if (distortion2 == INT_MAX)
             {
@@ -1084,7 +1076,7 @@ void vp8_pick_intra_mode(VP8_COMP *cpi, MACROBLOCK *x, int *rate_)
     }
     x->e_mbd.mode_info_context->mbmi.mode = best_mode;
 
-    error4x4 = pick_intra4x4mby_modes(IF_RTCD(&cpi->rtcd), x, &rate,
+    error4x4 = pick_intra4x4mby_modes(x, &rate,
                                       &best_sse);
     if (error4x4 < error16x16)
     {
diff --git a/vp8/encoder/picklpf.c b/vp8/encoder/picklpf.c
index 09e45bea646ba4f97f5d3fa83ae0699c18acd72f..441514d9168b4460811566f3c08071aa7fc2c27e 100644
--- a/vp8/encoder/picklpf.c
+++ b/vp8/encoder/picklpf.c
@@ -23,12 +23,6 @@
 
 extern int vp8_calc_ss_err(YV12_BUFFER_CONFIG *source, YV12_BUFFER_CONFIG *dest);
 
-#if CONFIG_RUNTIME_CPU_DETECT
-#define IF_RTCD(x) (x)
-#else
-#define IF_RTCD(x) NULL
-#endif
-
 extern void (*vp8_yv12_copy_partial_frame_ptr)(YV12_BUFFER_CONFIG *src_ybc,
                                                YV12_BUFFER_CONFIG *dst_ybc);
 
diff --git a/vp8/encoder/rdopt.c b/vp8/encoder/rdopt.c
index 786138f3ff33b3f1ebe1587ac154c92020f58847..76c764844369d3b1ff3a0ce4ce8204bc4862770a 100644
--- a/vp8/encoder/rdopt.c
+++ b/vp8/encoder/rdopt.c
@@ -34,13 +34,6 @@
 #include "vpx_mem/vpx_mem.h"
 #include "vp8/common/systemdependent.h"
 
-#if CONFIG_RUNTIME_CPU_DETECT
-#define IF_RTCD(x)  (x)
-#else
-#define IF_RTCD(x)  NULL
-#endif
-
-
 extern void vp8_update_zbin_extra(VP8_COMP *cpi, MACROBLOCK *x);
 
 #define MAXF(a,b)            (((a) > (b)) ? (a) : (b))
diff --git a/vp8/encoder/temporal_filter.c b/vp8/encoder/temporal_filter.c
index 62a7ec3aeea5cfe26c160025c01ffe9df1d2e8ed..57caccf24a1e83b9e071fb71c3388319e2943876 100644
--- a/vp8/encoder/temporal_filter.c
+++ b/vp8/encoder/temporal_filter.c
@@ -332,7 +332,7 @@ static void vp8_temporal_filter_iterate_c
                          predictor);
 
                     // Apply the filter (YUV)
-                    TEMPORAL_INVOKE(&cpi->rtcd.temporal, apply)
+                    vp8_temporal_filter_apply
                         (f->y_buffer + mb_y_offset,
                          f->y_stride,
                          predictor,
@@ -342,7 +342,7 @@ static void vp8_temporal_filter_iterate_c
                          accumulator,
                          count);
 
-                    TEMPORAL_INVOKE(&cpi->rtcd.temporal, apply)
+                    vp8_temporal_filter_apply
                         (f->u_buffer + mb_uv_offset,
                          f->uv_stride,
                          predictor + 256,
@@ -352,7 +352,7 @@ static void vp8_temporal_filter_iterate_c
                          accumulator + 256,
                          count + 256);
 
-                    TEMPORAL_INVOKE(&cpi->rtcd.temporal, apply)
+                    vp8_temporal_filter_apply
                         (f->v_buffer + mb_uv_offset,
                          f->uv_stride,
                          predictor + 320,
diff --git a/vp8/encoder/temporal_filter.h b/vp8/encoder/temporal_filter.h
deleted file mode 100644
index 740037a856676226421ba94a46f86afd52858195..0000000000000000000000000000000000000000
--- a/vp8/encoder/temporal_filter.h
+++ /dev/null
@@ -1,48 +0,0 @@
-/*
- *  Copyright (c) 2010 The WebM project authors. All Rights Reserved.
- *
- *  Use of this source code is governed by a BSD-style license
- *  that can be found in the LICENSE file in the root of the source
- *  tree. An additional intellectual property rights grant can be found
- *  in the file PATENTS.  All contributing project authors may
- *  be found in the AUTHORS file in the root of the source tree.
- */
-
-
-#ifndef __INC_VP8_TEMPORAL_FILTER_H
-#define __INC_VP8_TEMPORAL_FILTER_H
-
-#define prototype_apply(sym)\
-    void (sym) \
-    ( \
-     unsigned char *frame1, \
-     unsigned int stride, \
-     unsigned char *frame2, \
-     unsigned int block_size, \
-     int strength, \
-     int filter_weight, \
-     unsigned int *accumulator, \
-     unsigned short *count \
-    )
-
-#if ARCH_X86 || ARCH_X86_64
-#include "x86/temporal_filter_x86.h"
-#endif
-
-#ifndef vp8_temporal_filter_apply
-#define vp8_temporal_filter_apply vp8_temporal_filter_apply_c
-#endif
-extern prototype_apply(vp8_temporal_filter_apply);
-
-typedef struct
-{
-    prototype_apply(*apply);
-} vp8_temporal_rtcd_vtable_t;
-
-#if CONFIG_RUNTIME_CPU_DETECT
-#define TEMPORAL_INVOKE(ctx,fn) (ctx)->fn
-#else
-#define TEMPORAL_INVOKE(ctx,fn) vp8_temporal_filter_##fn
-#endif
-
-#endif // __INC_VP8_TEMPORAL_FILTER_H
diff --git a/vp8/encoder/x86/temporal_filter_x86.h b/vp8/encoder/x86/temporal_filter_x86.h
deleted file mode 100644
index 2daa1401828b5be21f329b385cecc09a74e593cb..0000000000000000000000000000000000000000
--- a/vp8/encoder/x86/temporal_filter_x86.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- *  Copyright (c) 2010 The WebM project authors. All Rights Reserved.
- *
- *  Use of this source code is governed by a BSD-style license
- *  that can be found in the LICENSE file in the root of the source
- *  tree. An additional intellectual property rights grant can be found
- *  in the file PATENTS.  All contributing project authors may
- *  be found in the AUTHORS file in the root of the source tree.
- */
-
-
-#ifndef __INC_VP8_TEMPORAL_FILTER_X86_H
-#define __INC_VP8_TEMPORAL_FILTER_X86_H
-
-#if HAVE_SSE2
-extern prototype_apply(vp8_temporal_filter_apply_sse2);
-
-#if !CONFIG_RUNTIME_CPU_DETECT
-
-#undef  vp8_temporal_filter_apply
-#define vp8_temporal_filter_apply vp8_temporal_filter_apply_sse2
-
-#endif
-
-#endif
-
-#endif // __INC_VP8_TEMPORAL_FILTER_X86_H
diff --git a/vp8/encoder/x86/x86_csystemdependent.c b/vp8/encoder/x86/x86_csystemdependent.c
index 4d27d5cf79e1a4f17e93bc70fc88264480ea6a78..8aa2e1fa38188c51fab7d4cb4513d361b2ca2224 100644
--- a/vp8/encoder/x86/x86_csystemdependent.c
+++ b/vp8/encoder/x86/x86_csystemdependent.c
@@ -114,26 +114,4 @@ void vp8_subtract_b_sse2(BLOCK *be, BLOCKD *bd, int pitch)
 
 void vp8_arch_x86_encoder_init(VP8_COMP *cpi)
 {
-#if CONFIG_RUNTIME_CPU_DETECT
-    int flags = x86_simd_caps();
-
-    /* Note:
-     *
-     * This platform can be built without runtime CPU detection as well. If
-     * you modify any of the function mappings present in this file, be sure
-     * to also update them in static mapings (<arch>/filename_<arch>.h)
-     */
-
-    /* Override default functions with fastest ones for this CPU. */
-#if HAVE_SSE2
-    if (flags & HAS_SSE2)
-    {
-#if !(CONFIG_REALTIME_ONLY)
-        cpi->rtcd.temporal.apply                 = vp8_temporal_filter_apply_sse2;
-#endif
-
-    }
-#endif
-
-#endif
 }
diff --git a/vp8/vp8cx.mk b/vp8/vp8cx.mk
index 8de4066e319869fbf13c0eebb0445001713a0f72..0d7120aed9b55af19040e06dbbbfb75832452301 100644
--- a/vp8/vp8cx.mk
+++ b/vp8/vp8cx.mk
@@ -84,7 +84,6 @@ VP8_CX_SRCS-yes += encoder/variance_c.c
 VP8_CX_SRCS-$(CONFIG_INTERNAL_STATS) += common/postproc.h
 VP8_CX_SRCS-$(CONFIG_INTERNAL_STATS) += common/postproc.c
 VP8_CX_SRCS-yes += encoder/temporal_filter.c
-VP8_CX_SRCS-yes += encoder/temporal_filter.h
 VP8_CX_SRCS-$(CONFIG_MULTI_RES_ENCODING) += encoder/mr_dissim.c
 VP8_CX_SRCS-$(CONFIG_MULTI_RES_ENCODING) += encoder/mr_dissim.h
 
@@ -93,7 +92,6 @@ VP8_CX_SRCS_REMOVE-yes += encoder/firstpass.c
 VP8_CX_SRCS_REMOVE-yes += encoder/temporal_filter.c
 endif
 
-VP8_CX_SRCS-$(ARCH_X86)$(ARCH_X86_64) += encoder/x86/temporal_filter_x86.h
 VP8_CX_SRCS-$(ARCH_X86)$(ARCH_X86_64) += encoder/x86/x86_csystemdependent.c
 VP8_CX_SRCS-$(HAVE_MMX) += encoder/x86/variance_mmx.c
 VP8_CX_SRCS-$(HAVE_MMX) += encoder/x86/variance_impl_mmx.asm