-extern void rgb24tobgr32(const uint8_t *src, uint8_t *dst, long src_size);
-extern void rgb32tobgr24(const uint8_t *src, uint8_t *dst, long src_size);
-extern void rgb16tobgr32(const uint8_t *src, uint8_t *dst, long src_size);
-extern void rgb16tobgr24(const uint8_t *src, uint8_t *dst, long src_size);
-extern void rgb16tobgr16(const uint8_t *src, uint8_t *dst, long src_size);
-extern void rgb16tobgr15(const uint8_t *src, uint8_t *dst, long src_size);
-extern void rgb15tobgr32(const uint8_t *src, uint8_t *dst, long src_size);
-extern void rgb15tobgr24(const uint8_t *src, uint8_t *dst, long src_size);
-extern void rgb15tobgr16(const uint8_t *src, uint8_t *dst, long src_size);
-extern void rgb15tobgr15(const uint8_t *src, uint8_t *dst, long src_size);
-extern void rgb8tobgr8(const uint8_t *src, uint8_t *dst, long src_size);
-
-
-extern void palette8torgb32(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette);
-extern void palette8tobgr32(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette);
-extern void palette8torgb24(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette);
-extern void palette8tobgr24(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette);
-extern void palette8torgb16(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette);
-extern void palette8tobgr16(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette);
-extern void palette8torgb15(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette);
-extern void palette8tobgr15(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette);
+void rgb24to32 (const uint8_t *src, uint8_t *dst, long src_size);
+void rgb32to24 (const uint8_t *src, uint8_t *dst, long src_size);
+void rgb16tobgr32(const uint8_t *src, uint8_t *dst, long src_size);
+void rgb16to24 (const uint8_t *src, uint8_t *dst, long src_size);
+void rgb16tobgr16(const uint8_t *src, uint8_t *dst, long src_size);
+void rgb16tobgr15(const uint8_t *src, uint8_t *dst, long src_size);
+void rgb15tobgr32(const uint8_t *src, uint8_t *dst, long src_size);
+void rgb15to24 (const uint8_t *src, uint8_t *dst, long src_size);
+void rgb15tobgr16(const uint8_t *src, uint8_t *dst, long src_size);
+void rgb15tobgr15(const uint8_t *src, uint8_t *dst, long src_size);
+void bgr8torgb8 (const uint8_t *src, uint8_t *dst, long src_size);
+
+void shuffle_bytes_0321(const uint8_t *src, uint8_t *dst, long src_size);
+void shuffle_bytes_1230(const uint8_t *src, uint8_t *dst, long src_size);
+void shuffle_bytes_2103(const uint8_t *src, uint8_t *dst, long src_size);
+void shuffle_bytes_3012(const uint8_t *src, uint8_t *dst, long src_size);
+void shuffle_bytes_3210(const uint8_t *src, uint8_t *dst, long src_size);
+
+void palette8topacked32(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette);
+void palette8topacked24(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette);
+void palette8torgb16(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette);
+void palette8tobgr16(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette);
+void palette8torgb15(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette);
+void palette8tobgr15(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette);