diff --git a/libavcodec/dsputil.c b/libavcodec/dsputil.c
index b78e172cae..d98015dfbc 100644
--- a/libavcodec/dsputil.c
+++ b/libavcodec/dsputil.c
@@ -2689,17 +2689,29 @@ av_cold void ff_dsputil_init(DSPContext* c, AVCodecContext *avctx)
     c->shrink[2]= ff_shrink44;
     c->shrink[3]= ff_shrink88;
 
+#define hpel_funcs(prefix, idx, num) \
+    c->prefix ## _pixels_tab idx [0] = prefix ## _pixels ## num ## _8_c; \
+    c->prefix ## _pixels_tab idx [1] = prefix ## _pixels ## num ## _x2_8_c; \
+    c->prefix ## _pixels_tab idx [2] = prefix ## _pixels ## num ## _y2_8_c; \
+    c->prefix ## _pixels_tab idx [3] = prefix ## _pixels ## num ## _xy2_8_c
+
+    hpel_funcs(put, [0], 16);
+    hpel_funcs(put, [1],  8);
+    hpel_funcs(put, [2],  4);
+    hpel_funcs(put, [3],  2);
+    hpel_funcs(put_no_rnd, [0], 16);
+    hpel_funcs(put_no_rnd, [1],  8);
+    hpel_funcs(avg, [0], 16);
+    hpel_funcs(avg, [1],  8);
+    hpel_funcs(avg, [2],  4);
+    hpel_funcs(avg, [3],  2);
+    hpel_funcs(avg_no_rnd,[0], 16);
+
 #undef FUNC
 #undef FUNCC
 #define FUNC(f, depth) f ## _ ## depth
 #define FUNCC(f, depth) f ## _ ## depth ## _c
 
-#define dspfunc1(PFX, IDX, NUM, depth)\
-    c->PFX ## _pixels_tab[IDX][0] = FUNCC(PFX ## _pixels ## NUM        , depth);\
-    c->PFX ## _pixels_tab[IDX][1] = FUNCC(PFX ## _pixels ## NUM ## _x2 , depth);\
-    c->PFX ## _pixels_tab[IDX][2] = FUNCC(PFX ## _pixels ## NUM ## _y2 , depth);\
-    c->PFX ## _pixels_tab[IDX][3] = FUNCC(PFX ## _pixels ## NUM ## _xy2, depth)
-
 #define dspfunc2(PFX, IDX, NUM, depth)\
     c->PFX ## _pixels_tab[IDX][ 0] = FUNCC(PFX ## NUM ## _mc00, depth);\
     c->PFX ## _pixels_tab[IDX][ 1] = FUNCC(PFX ## NUM ## _mc10, depth);\
@@ -2718,7 +2730,6 @@ av_cold void ff_dsputil_init(DSPContext* c, AVCodecContext *avctx)
     c->PFX ## _pixels_tab[IDX][14] = FUNCC(PFX ## NUM ## _mc23, depth);\
     c->PFX ## _pixels_tab[IDX][15] = FUNCC(PFX ## NUM ## _mc33, depth)
 
-
 #define BIT_DEPTH_FUNCS(depth, dct)\
     c->get_pixels                    = FUNCC(get_pixels   ## dct   , depth);\
     c->draw_edges                    = FUNCC(draw_edges            , depth);\
@@ -2733,18 +2744,6 @@ av_cold void ff_dsputil_init(DSPContext* c, AVCodecContext *avctx)
     c->avg_h264_chroma_pixels_tab[0] = FUNCC(avg_h264_chroma_mc8   , depth);\
     c->avg_h264_chroma_pixels_tab[1] = FUNCC(avg_h264_chroma_mc4   , depth);\
     c->avg_h264_chroma_pixels_tab[2] = FUNCC(avg_h264_chroma_mc2   , depth);\
-\
-    dspfunc1(put       , 0, 16, depth);\
-    dspfunc1(put       , 1,  8, depth);\
-    dspfunc1(put       , 2,  4, depth);\
-    dspfunc1(put       , 3,  2, depth);\
-    dspfunc1(put_no_rnd, 0, 16, depth);\
-    dspfunc1(put_no_rnd, 1,  8, depth);\
-    dspfunc1(avg       , 0, 16, depth);\
-    dspfunc1(avg       , 1,  8, depth);\
-    dspfunc1(avg       , 2,  4, depth);\
-    dspfunc1(avg       , 3,  2, depth);\
-    dspfunc1(avg_no_rnd, 0, 16, depth);\
 \
     dspfunc2(put_h264_qpel, 0, 16, depth);\
     dspfunc2(put_h264_qpel, 1,  8, depth);\
diff --git a/libavcodec/dsputil_template.c b/libavcodec/dsputil_template.c
index 28ff0e5f09..2de0e65465 100644
--- a/libavcodec/dsputil_template.c
+++ b/libavcodec/dsputil_template.c
@@ -197,15 +197,7 @@ DCTELEM_FUNCS(int16_t, _16)
 DCTELEM_FUNCS(dctcoef, _32)
 #endif
 
-#define PIXOP2(OPNAME, OP) \
-static void FUNCC(OPNAME ## _pixels2)(uint8_t *block, const uint8_t *pixels, int line_size, int h){\
-    int i;\
-    for(i=0; i<h; i++){\
-        OP(*((pixel2*)(block  )), AV_RN2P(pixels  ));\
-        pixels+=line_size;\
-        block +=line_size;\
-    }\
-}\
+#define PIXOP3(OPNAME, OP) \
 static void FUNCC(OPNAME ## _pixels4)(uint8_t *block, const uint8_t *pixels, int line_size, int h){\
     int i;\
     for(i=0; i<h; i++){\
@@ -227,20 +219,6 @@ static inline void FUNCC(OPNAME ## _no_rnd_pixels8)(uint8_t *block, const uint8_
     FUNCC(OPNAME ## _pixels8)(block, pixels, line_size, h);\
 }\
 \
-static inline void FUNC(OPNAME ## _no_rnd_pixels8_l2)(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, \
-                                                int src_stride1, int src_stride2, int h){\
-    int i;\
-    for(i=0; i<h; i++){\
-        pixel4 a,b;\
-        a= AV_RN4P(&src1[i*src_stride1  ]);\
-        b= AV_RN4P(&src2[i*src_stride2  ]);\
-        OP(*((pixel4*)&dst[i*dst_stride  ]), no_rnd_avg_pixel4(a, b));\
-        a= AV_RN4P(&src1[i*src_stride1+4*sizeof(pixel)]);\
-        b= AV_RN4P(&src2[i*src_stride2+4*sizeof(pixel)]);\
-        OP(*((pixel4*)&dst[i*dst_stride+4*sizeof(pixel)]), no_rnd_avg_pixel4(a, b));\
-    }\
-}\
-\
 static inline void FUNC(OPNAME ## _pixels8_l2)(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, \
                                                 int src_stride1, int src_stride2, int h){\
     int i;\
@@ -283,6 +261,36 @@ static inline void FUNC(OPNAME ## _pixels16_l2)(uint8_t *dst, const uint8_t *src
     FUNC(OPNAME ## _pixels8_l2)(dst+8*sizeof(pixel), src1+8*sizeof(pixel), src2+8*sizeof(pixel), dst_stride, src_stride1, src_stride2, h);\
 }\
 \
+CALL_2X_PIXELS(FUNCC(OPNAME ## _pixels16)    , FUNCC(OPNAME ## _pixels8)    , 8*sizeof(pixel))
+
+#define PIXOP4(OPNAME, OP) \
+static void FUNCC(OPNAME ## _pixels2)(uint8_t *block, const uint8_t *pixels, int line_size, int h){\
+    int i;\
+    for(i=0; i<h; i++){\
+        OP(*((pixel2*)(block  )), AV_RN2P(pixels  ));\
+        pixels+=line_size;\
+        block +=line_size;\
+    }\
+}\
+PIXOP3(OPNAME, OP)
+
+#define PIXOP2(OPNAME, OP) \
+PIXOP4(OPNAME, OP)\
+\
+static inline void FUNC(OPNAME ## _no_rnd_pixels8_l2)(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, \
+                                                int src_stride1, int src_stride2, int h){\
+    int i;\
+    for(i=0; i<h; i++){\
+        pixel4 a,b;\
+        a= AV_RN4P(&src1[i*src_stride1  ]);\
+        b= AV_RN4P(&src2[i*src_stride2  ]);\
+        OP(*((pixel4*)&dst[i*dst_stride  ]), no_rnd_avg_pixel4(a, b));\
+        a= AV_RN4P(&src1[i*src_stride1+4*sizeof(pixel)]);\
+        b= AV_RN4P(&src2[i*src_stride2+4*sizeof(pixel)]);\
+        OP(*((pixel4*)&dst[i*dst_stride+4*sizeof(pixel)]), no_rnd_avg_pixel4(a, b));\
+    }\
+}\
+\
 static inline void FUNC(OPNAME ## _no_rnd_pixels16_l2)(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, \
                                                 int src_stride1, int src_stride2, int h){\
     FUNC(OPNAME ## _no_rnd_pixels8_l2)(dst  , src1  , src2  , dst_stride, src_stride1, src_stride2, h);\
@@ -562,7 +570,6 @@ static inline void FUNCC(OPNAME ## _no_rnd_pixels8_xy2)(uint8_t *block, const ui
     }\
 }\
 \
-CALL_2X_PIXELS(FUNCC(OPNAME ## _pixels16)    , FUNCC(OPNAME ## _pixels8)    , 8*sizeof(pixel))\
 CALL_2X_PIXELS(FUNCC(OPNAME ## _pixels16_x2) , FUNCC(OPNAME ## _pixels8_x2) , 8*sizeof(pixel))\
 CALL_2X_PIXELS(FUNCC(OPNAME ## _pixels16_y2) , FUNCC(OPNAME ## _pixels8_y2) , 8*sizeof(pixel))\
 CALL_2X_PIXELS(FUNCC(OPNAME ## _pixels16_xy2), FUNCC(OPNAME ## _pixels8_xy2), 8*sizeof(pixel))\
@@ -573,15 +580,16 @@ CALL_2X_PIXELS(FUNCC(OPNAME ## _no_rnd_pixels16_xy2), FUNCC(OPNAME ## _no_rnd_pi
 
 #define op_avg(a, b) a = rnd_avg_pixel4(a, b)
 #define op_put(a, b) a = b
-
+#if BIT_DEPTH == 8
 PIXOP2(avg, op_avg)
 PIXOP2(put, op_put)
+#else
+PIXOP3(avg, op_avg)
+PIXOP4(put, op_put)
+#endif
 #undef op_avg
 #undef op_put
 
-#define put_no_rnd_pixels8_c  put_pixels8_c
-#define put_no_rnd_pixels16_c put_pixels16_c
-
 #define H264_CHROMA_MC(OPNAME, OP)\
 static void FUNCC(OPNAME ## h264_chroma_mc2)(uint8_t *_dst/*align 8*/, uint8_t *_src/*align 1*/, int stride, int h, int x, int y){\
     pixel *dst = (pixel*)_dst;\