ffmpeg roll of source to mar 9 version...

patched-ffmpeg-mt/libavcodec/sh4/qpel.c

 /*
  * This is optimized for sh, which have post increment addressing (*p++).
  * Some CPU may be index (p[n]) faster than post increment (*p++).
  *
  * copyright (c) 2001-2003 BERO <bero@geocities.co.jp>
  *
  * This file is part of FFmpeg.
  *
  * FFmpeg is free software; you can redistribute it and/or
  * modify it under the terms of the GNU Lesser General Public
  * License as published by the Free Software Foundation; either
  * version 2.1 of the License, or (at your option) any later version.
  *
  * FFmpeg is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  * Lesser General Public License for more details.
  *
  * You should have received a copy of the GNU Lesser General Public
  * License along with FFmpeg; if not, write to the Free Software
  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
 #define PIXOP2(OPNAME, OP) \
 \
 static inline void OPNAME ## _pixels4_l2_aligned(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, int src_stride1, int src_stride2, int h) \
 {\
         do {\
-                OP(LP(dst  ),rnd_avg32(LP(src1  ),LP(src2  )) ); \
+                OP(LP(dst  ),rnd_avg32(LPC(src1  ),LPC(src2  )) ); \
                 src1+=src_stride1; \
                 src2+=src_stride2; \
                 dst+=dst_stride; \
         } while(--h); \
 }\
 \
 static inline void OPNAME ## _pixels4_l2_aligned2(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, int src_stride1, int src_stride2, int h) \
 {\
         do {\
-                OP(LP(dst  ),rnd_avg32(AV_RN32(src1  ),LP(src2  )) ); \
+                OP(LP(dst  ),rnd_avg32(AV_RN32(src1  ),LPC(src2  )) ); \
                 src1+=src_stride1; \
                 src2+=src_stride2; \
                 dst+=dst_stride; \
         } while(--h); \
 }\
 \
 static inline void OPNAME ## _no_rnd_pixels16_l2_aligned2(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, int src_stride1, int src_stride2, int h) \
 {\
         do {\
-                OP(LP(dst  ),no_rnd_avg32(AV_RN32(src1  ),LP(src2  )) ); \
-                OP(LP(dst+4),no_rnd_avg32(AV_RN32(src1+4),LP(src2+4)) ); \
-                OP(LP(dst+8),no_rnd_avg32(AV_RN32(src1+8),LP(src2+8)) ); \
-                OP(LP(dst+12),no_rnd_avg32(AV_RN32(src1+12),LP(src2+12)) ); \
+                OP(LP(dst  ),no_rnd_avg32(AV_RN32(src1  ),LPC(src2  )) ); \
+                OP(LP(dst+4),no_rnd_avg32(AV_RN32(src1+4),LPC(src2+4)) ); \
+                OP(LP(dst+8),no_rnd_avg32(AV_RN32(src1+8),LPC(src2+8)) ); \
+                OP(LP(dst+12),no_rnd_avg32(AV_RN32(src1+12),LPC(src2+12)) ); \
                 src1+=src_stride1; \
                 src2+=src_stride2; \
                 dst+=dst_stride; \
         } while(--h); \
 }\
 \
 static inline void OPNAME ## _pixels16_l2_aligned2(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, int src_stride1, int src_stride2, int h) \
 {\
         do {\
-                OP(LP(dst  ),rnd_avg32(AV_RN32(src1  ),LP(src2  )) ); \
-                OP(LP(dst+4),rnd_avg32(AV_RN32(src1+4),LP(src2+4)) ); \
-                OP(LP(dst+8),rnd_avg32(AV_RN32(src1+8),LP(src2+8)) ); \
-                OP(LP(dst+12),rnd_avg32(AV_RN32(src1+12),LP(src2+12)) ); \
+                OP(LP(dst  ),rnd_avg32(AV_RN32(src1  ),LPC(src2  )) ); \
+                OP(LP(dst+4),rnd_avg32(AV_RN32(src1+4),LPC(src2+4)) ); \
+                OP(LP(dst+8),rnd_avg32(AV_RN32(src1+8),LPC(src2+8)) ); \
+                OP(LP(dst+12),rnd_avg32(AV_RN32(src1+12),LPC(src2+12)) ); \
                 src1+=src_stride1; \
                 src2+=src_stride2; \
                 dst+=dst_stride; \
         } while(--h); \
 }\
 \
 static inline void OPNAME ## _no_rnd_pixels8_l2_aligned2(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, int src_stride1, int src_stride2, int h) \
 {\
         do { /* onlye src2 aligned */\
-                OP(LP(dst  ),no_rnd_avg32(AV_RN32(src1  ),LP(src2  )) ); \
-                OP(LP(dst+4),no_rnd_avg32(AV_RN32(src1+4),LP(src2+4)) ); \
+                OP(LP(dst  ),no_rnd_avg32(AV_RN32(src1  ),LPC(src2  )) ); \
+                OP(LP(dst+4),no_rnd_avg32(AV_RN32(src1+4),LPC(src2+4)) ); \
                 src1+=src_stride1; \
                 src2+=src_stride2; \
                 dst+=dst_stride; \
         } while(--h); \
 }\
 \
 static inline void OPNAME ## _pixels8_l2_aligned2(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, int src_stride1, int src_stride2, int h) \
 {\
         do {\
-                OP(LP(dst  ),rnd_avg32(AV_RN32(src1  ),LP(src2  )) ); \
-                OP(LP(dst+4),rnd_avg32(AV_RN32(src1+4),LP(src2+4)) ); \
+                OP(LP(dst  ),rnd_avg32(AV_RN32(src1  ),LPC(src2  )) ); \
+                OP(LP(dst+4),rnd_avg32(AV_RN32(src1+4),LPC(src2+4)) ); \
                 src1+=src_stride1; \
                 src2+=src_stride2; \
                 dst+=dst_stride; \
         } while(--h); \
 }\
 \
 static inline void OPNAME ## _no_rnd_pixels8_l2_aligned(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, int src_stride1, int src_stride2, int h) \
 {\
         do {\
-                OP(LP(dst  ),no_rnd_avg32(LP(src1  ),LP(src2  )) ); \
-                OP(LP(dst+4),no_rnd_avg32(LP(src1+4),LP(src2+4)) ); \
+                OP(LP(dst  ),no_rnd_avg32(LPC(src1  ),LPC(src2  )) ); \
+                OP(LP(dst+4),no_rnd_avg32(LPC(src1+4),LPC(src2+4)) ); \
                 src1+=src_stride1; \
                 src2+=src_stride2; \
                 dst+=dst_stride; \
         } while(--h); \
 }\
 \
 static inline void OPNAME ## _pixels8_l2_aligned(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, int src_stride1, int src_stride2, int h) \
 {\
         do {\
-                OP(LP(dst  ),rnd_avg32(LP(src1  ),LP(src2  )) ); \
-                OP(LP(dst+4),rnd_avg32(LP(src1+4),LP(src2+4)) ); \
+                OP(LP(dst  ),rnd_avg32(LPC(src1  ),LPC(src2  )) ); \
+                OP(LP(dst+4),rnd_avg32(LPC(src1+4),LPC(src2+4)) ); \
                 src1+=src_stride1; \
                 src2+=src_stride2; \
                 dst+=dst_stride; \
         } while(--h); \
 }\
 \
 static inline void OPNAME ## _no_rnd_pixels16_l2_aligned(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, int src_stride1, int src_stride2, int h) \
 {\
         do {\
-                OP(LP(dst  ),no_rnd_avg32(LP(src1  ),LP(src2  )) ); \
-                OP(LP(dst+4),no_rnd_avg32(LP(src1+4),LP(src2+4)) ); \
-                OP(LP(dst+8),no_rnd_avg32(LP(src1+8),LP(src2+8)) ); \
-                OP(LP(dst+12),no_rnd_avg32(LP(src1+12),LP(src2+12)) ); \
+                OP(LP(dst  ),no_rnd_avg32(LPC(src1  ),LPC(src2  )) ); \
+                OP(LP(dst+4),no_rnd_avg32(LPC(src1+4),LPC(src2+4)) ); \
+                OP(LP(dst+8),no_rnd_avg32(LPC(src1+8),LPC(src2+8)) ); \
+                OP(LP(dst+12),no_rnd_avg32(LPC(src1+12),LPC(src2+12)) ); \
                 src1+=src_stride1; \
                 src2+=src_stride2; \
                 dst+=dst_stride; \
         } while(--h); \
 }\
 \
 static inline void OPNAME ## _pixels16_l2_aligned(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, int src_stride1, int src_stride2, int h) \
 {\
         do {\
-                OP(LP(dst  ),rnd_avg32(LP(src1  ),LP(src2  )) ); \
-                OP(LP(dst+4),rnd_avg32(LP(src1+4),LP(src2+4)) ); \
-                OP(LP(dst+8),rnd_avg32(LP(src1+8),LP(src2+8)) ); \
-                OP(LP(dst+12),rnd_avg32(LP(src1+12),LP(src2+12)) ); \
+                OP(LP(dst  ),rnd_avg32(LPC(src1  ),LPC(src2  )) ); \
+                OP(LP(dst+4),rnd_avg32(LPC(src1+4),LPC(src2+4)) ); \
+                OP(LP(dst+8),rnd_avg32(LPC(src1+8),LPC(src2+8)) ); \
+                OP(LP(dst+12),rnd_avg32(LPC(src1+12),LPC(src2+12)) ); \
                 src1+=src_stride1; \
                 src2+=src_stride2; \
                 dst+=dst_stride; \
         } while(--h); \
 }\
 \
 static inline void OPNAME ## _no_rnd_pixels16_l2_aligned1(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, int src_stride1, int src_stride2, int h) \
 { OPNAME ## _no_rnd_pixels16_l2_aligned2(dst,src2,src1,dst_stride,src_stride2,src_stride1,h); } \
 \
 static inline void OPNAME ## _pixels16_l2_aligned1(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, int src_stride1, int src_stride2, int h) \
 { OPNAME ## _pixels16_l2_aligned2(dst,src2,src1,dst_stride,src_stride2,src_stride1,h); } \
 \
 static inline void OPNAME ## _no_rnd_pixels8_l2_aligned1(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, int src_stride1, int src_stride2, int h) \
 { OPNAME ## _no_rnd_pixels8_l2_aligned2(dst,src2,src1,dst_stride,src_stride2,src_stride1,h); } \
 \
 static inline void OPNAME ## _pixels8_l2_aligned1(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, int dst_stride, int src_stride1, int src_stride2, int h) \
 { OPNAME ## _pixels8_l2_aligned2(dst,src2,src1,dst_stride,src_stride2,src_stride1,h); } \
 \
 static inline void OPNAME ## _pixels8_l4_aligned(uint8_t *dst, const uint8_t *src1, uint8_t *src2, uint8_t *src3, uint8_t *src4,int dst_stride, int src_stride1, int src_stride2,int src_stride3,int src_stride4, int h){\
         do { \
                 uint32_t a0,a1,a2,a3; \
-                UNPACK(a0,a1,LP(src1),LP(src2)); \
-                UNPACK(a2,a3,LP(src3),LP(src4)); \
+                UNPACK(a0,a1,LPC(src1),LPC(src2)); \
+                UNPACK(a2,a3,LPC(src3),LPC(src4)); \
                 OP(LP(dst),rnd_PACK(a0,a1,a2,a3)); \
-                UNPACK(a0,a1,LP(src1+4),LP(src2+4)); \
-                UNPACK(a2,a3,LP(src3+4),LP(src4+4)); \
+                UNPACK(a0,a1,LPC(src1+4),LPC(src2+4)); \
+                UNPACK(a2,a3,LPC(src3+4),LPC(src4+4)); \
                 OP(LP(dst+4),rnd_PACK(a0,a1,a2,a3)); \
                 src1+=src_stride1;\
                 src2+=src_stride2;\
                 src3+=src_stride3;\
                 src4+=src_stride4;\
                 dst+=dst_stride;\
         } while(--h); \
 } \
 \
 static inline void OPNAME ## _no_rnd_pixels8_l4_aligned(uint8_t *dst, const uint8_t *src1, uint8_t *src2, uint8_t *src3, uint8_t *src4,int dst_stride, int src_stride1, int src_stride2,int src_stride3,int src_stride4, int h){\
         do { \
                 uint32_t a0,a1,a2,a3; \
-                UNPACK(a0,a1,LP(src1),LP(src2)); \
-                UNPACK(a2,a3,LP(src3),LP(src4)); \
+                UNPACK(a0,a1,LPC(src1),LPC(src2)); \
+                UNPACK(a2,a3,LPC(src3),LPC(src4)); \
                 OP(LP(dst),no_rnd_PACK(a0,a1,a2,a3)); \
-                UNPACK(a0,a1,LP(src1+4),LP(src2+4)); \
-                UNPACK(a2,a3,LP(src3+4),LP(src4+4)); \
+                UNPACK(a0,a1,LPC(src1+4),LPC(src2+4)); \
+                UNPACK(a2,a3,LPC(src3+4),LPC(src4+4)); \
                 OP(LP(dst+4),no_rnd_PACK(a0,a1,a2,a3)); \
                 src1+=src_stride1;\
                 src2+=src_stride2;\
                 src3+=src_stride3;\
                 src4+=src_stride4;\
                 dst+=dst_stride;\
         } while(--h); \
 } \
 \
 static inline void OPNAME ## _pixels8_l4_aligned0(uint8_t *dst, const uint8_t *src1, uint8_t *src2, uint8_t *src3, uint8_t *src4,int dst_stride, int src_stride1, int src_stride2,int src_stride3,int src_stride4, int h){\
         do { \
                 uint32_t a0,a1,a2,a3; /* src1 only not aligned */\
-                UNPACK(a0,a1,AV_RN32(src1),LP(src2)); \
-                UNPACK(a2,a3,LP(src3),LP(src4)); \
+                UNPACK(a0,a1,AV_RN32(src1),LPC(src2)); \
+                UNPACK(a2,a3,LPC(src3),LPC(src4)); \
                 OP(LP(dst),rnd_PACK(a0,a1,a2,a3)); \
-                UNPACK(a0,a1,AV_RN32(src1+4),LP(src2+4)); \
-                UNPACK(a2,a3,LP(src3+4),LP(src4+4)); \
+                UNPACK(a0,a1,AV_RN32(src1+4),LPC(src2+4)); \
+                UNPACK(a2,a3,LPC(src3+4),LPC(src4+4)); \
                 OP(LP(dst+4),rnd_PACK(a0,a1,a2,a3)); \
                 src1+=src_stride1;\
                 src2+=src_stride2;\
                 src3+=src_stride3;\
                 src4+=src_stride4;\
                 dst+=dst_stride;\
         } while(--h); \
 } \
 \
 static inline void OPNAME ## _no_rnd_pixels8_l4_aligned0(uint8_t *dst, const uint8_t *src1, uint8_t *src2, uint8_t *src3, uint8_t *src4,int dst_stride, int src_stride1, int src_stride2,int src_stride3,int src_stride4, int h){\
         do { \
                 uint32_t a0,a1,a2,a3; \
-                UNPACK(a0,a1,AV_RN32(src1),LP(src2)); \
-                UNPACK(a2,a3,LP(src3),LP(src4)); \
+                UNPACK(a0,a1,AV_RN32(src1),LPC(src2)); \
+                UNPACK(a2,a3,LPC(src3),LPC(src4)); \
                 OP(LP(dst),no_rnd_PACK(a0,a1,a2,a3)); \
-                UNPACK(a0,a1,AV_RN32(src1+4),LP(src2+4)); \
-                UNPACK(a2,a3,LP(src3+4),LP(src4+4)); \
+                UNPACK(a0,a1,AV_RN32(src1+4),LPC(src2+4)); \
+                UNPACK(a2,a3,LPC(src3+4),LPC(src4+4)); \
                 OP(LP(dst+4),no_rnd_PACK(a0,a1,a2,a3)); \
                 src1+=src_stride1;\
                 src2+=src_stride2;\
                 src3+=src_stride3;\
                 src4+=src_stride4;\
                 dst+=dst_stride;\
         } while(--h); \
 } \
 \
 static inline void OPNAME ## _pixels16_l4_aligned(uint8_t *dst, const uint8_t *src1, uint8_t *src2, uint8_t *src3, uint8_t *src4,int dst_stride, int src_stride1, int src_stride2,int src_stride3,int src_stride4, int h){\
         do { \
                 uint32_t a0,a1,a2,a3; \
-                UNPACK(a0,a1,LP(src1),LP(src2)); \
-                UNPACK(a2,a3,LP(src3),LP(src4)); \
+                UNPACK(a0,a1,LPC(src1),LPC(src2)); \
+                UNPACK(a2,a3,LPC(src3),LPC(src4)); \
                 OP(LP(dst),rnd_PACK(a0,a1,a2,a3)); \
-                UNPACK(a0,a1,LP(src1+4),LP(src2+4)); \
-                UNPACK(a2,a3,LP(src3+4),LP(src4+4)); \
+                UNPACK(a0,a1,LPC(src1+4),LPC(src2+4)); \
+                UNPACK(a2,a3,LPC(src3+4),LPC(src4+4)); \
                 OP(LP(dst+8),rnd_PACK(a0,a1,a2,a3)); \
-                UNPACK(a0,a1,LP(src1+8),LP(src2+8)); \
-                UNPACK(a2,a3,LP(src3+8),LP(src4+8)); \
+                UNPACK(a0,a1,LPC(src1+8),LPC(src2+8)); \
+                UNPACK(a2,a3,LPC(src3+8),LPC(src4+8)); \
                 OP(LP(dst+8),rnd_PACK(a0,a1,a2,a3)); \
-                UNPACK(a0,a1,LP(src1+12),LP(src2+12)); \
-                UNPACK(a2,a3,LP(src3+12),LP(src4+12)); \
+                UNPACK(a0,a1,LPC(src1+12),LPC(src2+12)); \
+                UNPACK(a2,a3,LPC(src3+12),LPC(src4+12)); \
                 OP(LP(dst+12),rnd_PACK(a0,a1,a2,a3)); \
                 src1+=src_stride1;\
                 src2+=src_stride2;\
                 src3+=src_stride3;\
                 src4+=src_stride4;\
                 dst+=dst_stride;\
         } while(--h); \
 } \
 \
 static inline void OPNAME ## _no_rnd_pixels16_l4_aligned(uint8_t *dst, const uint8_t *src1, uint8_t *src2, uint8_t *src3, uint8_t *src4,int dst_stride, int src_stride1, int src_stride2,int src_stride3,int src_stride4, int h){\
         do { \
                 uint32_t a0,a1,a2,a3; \
-                UNPACK(a0,a1,LP(src1),LP(src2)); \
-                UNPACK(a2,a3,LP(src3),LP(src4)); \
+                UNPACK(a0,a1,LPC(src1),LPC(src2)); \
+                UNPACK(a2,a3,LPC(src3),LPC(src4)); \
                 OP(LP(dst),no_rnd_PACK(a0,a1,a2,a3)); \
-                UNPACK(a0,a1,LP(src1+4),LP(src2+4)); \
-                UNPACK(a2,a3,LP(src3+4),LP(src4+4)); \
+                UNPACK(a0,a1,LPC(src1+4),LPC(src2+4)); \
+                UNPACK(a2,a3,LPC(src3+4),LPC(src4+4)); \
                 OP(LP(dst+4),no_rnd_PACK(a0,a1,a2,a3)); \
-                UNPACK(a0,a1,LP(src1+8),LP(src2+8)); \
-                UNPACK(a2,a3,LP(src3+8),LP(src4+8)); \
+                UNPACK(a0,a1,LPC(src1+8),LPC(src2+8)); \
+                UNPACK(a2,a3,LPC(src3+8),LPC(src4+8)); \
                 OP(LP(dst+8),no_rnd_PACK(a0,a1,a2,a3)); \
-                UNPACK(a0,a1,LP(src1+12),LP(src2+12)); \
-                UNPACK(a2,a3,LP(src3+12),LP(src4+12)); \
+                UNPACK(a0,a1,LPC(src1+12),LPC(src2+12)); \
+                UNPACK(a2,a3,LPC(src3+12),LPC(src4+12)); \
                 OP(LP(dst+12),no_rnd_PACK(a0,a1,a2,a3)); \
                 src1+=src_stride1;\
                 src2+=src_stride2;\
                 src3+=src_stride3;\
                 src4+=src_stride4;\
                 dst+=dst_stride;\
         } while(--h); \
 } \
 \
 static inline void OPNAME ## _pixels16_l4_aligned0(uint8_t *dst, const uint8_t *src1, uint8_t *src2, uint8_t *src3, uint8_t *src4,int dst_stride, int src_stride1, int src_stride2,int src_stride3,int src_stride4, int h){\
         do { /* src1 is unaligned */\
                 uint32_t a0,a1,a2,a3; \
-                UNPACK(a0,a1,AV_RN32(src1),LP(src2)); \
-                UNPACK(a2,a3,LP(src3),LP(src4)); \
+                UNPACK(a0,a1,AV_RN32(src1),LPC(src2)); \
+                UNPACK(a2,a3,LPC(src3),LPC(src4)); \
                 OP(LP(dst),rnd_PACK(a0,a1,a2,a3)); \
-                UNPACK(a0,a1,AV_RN32(src1+4),LP(src2+4)); \
-                UNPACK(a2,a3,LP(src3+4),LP(src4+4)); \
+                UNPACK(a0,a1,AV_RN32(src1+4),LPC(src2+4)); \
+                UNPACK(a2,a3,LPC(src3+4),LPC(src4+4)); \
                 OP(LP(dst+8),rnd_PACK(a0,a1,a2,a3)); \
-                UNPACK(a0,a1,AV_RN32(src1+8),LP(src2+8)); \
-                UNPACK(a2,a3,LP(src3+8),LP(src4+8)); \
+                UNPACK(a0,a1,AV_RN32(src1+8),LPC(src2+8)); \
+                UNPACK(a2,a3,LPC(src3+8),LPC(src4+8)); \
                 OP(LP(dst+8),rnd_PACK(a0,a1,a2,a3)); \
-                UNPACK(a0,a1,AV_RN32(src1+12),LP(src2+12)); \
-                UNPACK(a2,a3,LP(src3+12),LP(src4+12)); \
+                UNPACK(a0,a1,AV_RN32(src1+12),LPC(src2+12)); \
+                UNPACK(a2,a3,LPC(src3+12),LPC(src4+12)); \
                 OP(LP(dst+12),rnd_PACK(a0,a1,a2,a3)); \
                 src1+=src_stride1;\
                 src2+=src_stride2;\
                 src3+=src_stride3;\
                 src4+=src_stride4;\
                 dst+=dst_stride;\
         } while(--h); \
 } \
 \
 static inline void OPNAME ## _no_rnd_pixels16_l4_aligned0(uint8_t *dst, const uint8_t *src1, uint8_t *src2, uint8_t *src3, uint8_t *src4,int dst_stride, int src_stride1, int src_stride2,int src_stride3,int src_stride4, int h){\
         do { \
                 uint32_t a0,a1,a2,a3; \
-                UNPACK(a0,a1,AV_RN32(src1),LP(src2)); \
-                UNPACK(a2,a3,LP(src3),LP(src4)); \
+                UNPACK(a0,a1,AV_RN32(src1),LPC(src2)); \
+                UNPACK(a2,a3,LPC(src3),LPC(src4)); \
                 OP(LP(dst),no_rnd_PACK(a0,a1,a2,a3)); \
-                UNPACK(a0,a1,AV_RN32(src1+4),LP(src2+4)); \
-                UNPACK(a2,a3,LP(src3+4),LP(src4+4)); \
+                UNPACK(a0,a1,AV_RN32(src1+4),LPC(src2+4)); \
+                UNPACK(a2,a3,LPC(src3+4),LPC(src4+4)); \
                 OP(LP(dst+4),no_rnd_PACK(a0,a1,a2,a3)); \
-                UNPACK(a0,a1,AV_RN32(src1+8),LP(src2+8)); \
-                UNPACK(a2,a3,LP(src3+8),LP(src4+8)); \
+                UNPACK(a0,a1,AV_RN32(src1+8),LPC(src2+8)); \
+                UNPACK(a2,a3,LPC(src3+8),LPC(src4+8)); \
                 OP(LP(dst+8),no_rnd_PACK(a0,a1,a2,a3)); \
-                UNPACK(a0,a1,AV_RN32(src1+12),LP(src2+12)); \
-                UNPACK(a2,a3,LP(src3+12),LP(src4+12)); \
+                UNPACK(a0,a1,AV_RN32(src1+12),LPC(src2+12)); \
+                UNPACK(a2,a3,LPC(src3+12),LPC(src4+12)); \
                 OP(LP(dst+12),no_rnd_PACK(a0,a1,a2,a3)); \
                 src1+=src_stride1;\
                 src2+=src_stride2;\
                 src3+=src_stride3;\
                 src4+=src_stride4;\
                 dst+=dst_stride;\
         } while(--h); \
 } \
 \
 
@@ skipping 1085 matching lines @@
     wmv2_mspel8_h_lowpass(halfH, src-stride, 8, stride, 11);
     wmv2_mspel8_v_lowpass(halfV, src+1, 8, stride, 8);
     wmv2_mspel8_v_lowpass(halfHV, halfH+8, 8, 8, 8);
     put_pixels8_l2_aligned(dst, halfV, halfHV, stride, 8, 8, 8);
 }
 static void put_mspel8_mc22_sh4(uint8_t *dst, uint8_t *src, int stride){
     uint8_t halfH[88];
     wmv2_mspel8_h_lowpass(halfH, src-stride, 8, stride, 11);
     wmv2_mspel8_v_lowpass(dst, halfH+8, stride, 8, 8);
 }