X-Git-Url: https://git.sesse.net/?a=blobdiff_plain;f=libswscale%2Fx86%2Fswscale_template.c;h=97d8cae6134a9eaa6fef82d0ad1af167a035606e;hb=20aec597d05f1930dbd4e4c5ab8ee837dea5b5f3;hp=7c304706798eb23297252e2a71e51ab2ddc083de;hpb=94346ab593f3fc0822f11d3e3f378f9944ad2d40;p=ffmpeg

diff --git a/libswscale/x86/swscale_template.c b/libswscale/x86/swscale_template.c
index 7c304706798..97d8cae6134 100644
--- a/libswscale/x86/swscale_template.c
+++ b/libswscale/x86/swscale_template.c
@@ -38,88 +38,6 @@
 #endif
 #define MOVNTQ(a,b)  REAL_MOVNTQ(a,b)
 
-#if !COMPILE_TEMPLATE_MMXEXT
-static av_always_inline void
-dither_8to16(const uint8_t *srcDither, int rot)
-{
-    if (rot) {
-        __asm__ volatile("pxor      %%mm0, %%mm0\n\t"
-                         "movq       (%0), %%mm3\n\t"
-                         "movq      %%mm3, %%mm4\n\t"
-                         "psrlq       $24, %%mm3\n\t"
-                         "psllq       $40, %%mm4\n\t"
-                         "por       %%mm4, %%mm3\n\t"
-                         "movq      %%mm3, %%mm4\n\t"
-                         "punpcklbw %%mm0, %%mm3\n\t"
-                         "punpckhbw %%mm0, %%mm4\n\t"
-                         :: "r"(srcDither)
-                         );
-    } else {
-        __asm__ volatile("pxor      %%mm0, %%mm0\n\t"
-                         "movq       (%0), %%mm3\n\t"
-                         "movq      %%mm3, %%mm4\n\t"
-                         "punpcklbw %%mm0, %%mm3\n\t"
-                         "punpckhbw %%mm0, %%mm4\n\t"
-                         :: "r"(srcDither)
-                         );
-    }
-}
-#endif
-
-static void RENAME(yuv2yuvX)(const int16_t *filter, int filterSize,
-                           const int16_t **src, uint8_t *dest, int dstW,
-                           const uint8_t *dither, int offset)
-{
-    dither_8to16(dither, offset);
-    filterSize--;
-    __asm__ volatile(
-        "movd %0, %%mm1\n\t"
-        "punpcklwd %%mm1, %%mm1\n\t"
-        "punpckldq %%mm1, %%mm1\n\t"
-        "psllw        $3, %%mm1\n\t"
-        "paddw     %%mm1, %%mm3\n\t"
-        "paddw     %%mm1, %%mm4\n\t"
-        "psraw        $4, %%mm3\n\t"
-        "psraw        $4, %%mm4\n\t"
-        ::"m"(filterSize)
-     );
-
-    __asm__ volatile(\
-        "movq    %%mm3, %%mm6\n\t"
-        "movq    %%mm4, %%mm7\n\t"
-        "movl %3, %%ecx\n\t"
-        "mov                                 %0, %%"FF_REG_d"       \n\t"\
-        "mov                        (%%"FF_REG_d"), %%"FF_REG_S"    \n\t"\
-        ".p2align                             4                     \n\t" /* FIXME Unroll? */\
-        "1:                                                         \n\t"\
-        "movq                      8(%%"FF_REG_d"), %%mm0           \n\t" /* filterCoeff */\
-        "movq                (%%"FF_REG_S", %%"FF_REG_c", 2), %%mm2 \n\t" /* srcData */\
-        "movq               8(%%"FF_REG_S", %%"FF_REG_c", 2), %%mm5 \n\t" /* srcData */\
-        "add                                $16, %%"FF_REG_d"       \n\t"\
-        "mov                        (%%"FF_REG_d"), %%"FF_REG_S"    \n\t"\
-        "test                         %%"FF_REG_S", %%"FF_REG_S"    \n\t"\
-        "pmulhw                           %%mm0, %%mm2      \n\t"\
-        "pmulhw                           %%mm0, %%mm5      \n\t"\
-        "paddw                            %%mm2, %%mm3      \n\t"\
-        "paddw                            %%mm5, %%mm4      \n\t"\
-        " jnz                                1b             \n\t"\
-        "psraw                               $3, %%mm3      \n\t"\
-        "psraw                               $3, %%mm4      \n\t"\
-        "packuswb                         %%mm4, %%mm3      \n\t"
-        MOVNTQ2 "                         %%mm3, (%1, %%"FF_REG_c")\n\t"
-        "add                          $8, %%"FF_REG_c"      \n\t"\
-        "cmp                          %2, %%"FF_REG_c"      \n\t"\
-        "movq    %%mm6, %%mm3\n\t"
-        "movq    %%mm7, %%mm4\n\t"
-        "mov                                 %0, %%"FF_REG_d"     \n\t"\
-        "mov                        (%%"FF_REG_d"), %%"FF_REG_S"  \n\t"\
-        "jb                                  1b                   \n\t"\
-        :: "g" (filter),
-           "r" (dest-offset), "g" ((x86_reg)(dstW+offset)), "m" (offset)
-        : "%"FF_REG_d, "%"FF_REG_S, "%"FF_REG_c
-    );
-}
-
 #define YSCALEYUV2PACKEDX_UV \
     __asm__ volatile(\
         "xor                %%"FF_REG_a", %%"FF_REG_a"  \n\t"\
@@ -1499,8 +1417,8 @@ static av_cold void RENAME(sws_init_swscale)(SwsContext *c)
     enum AVPixelFormat dstFormat = c->dstFormat;
 
     c->use_mmx_vfilter= 0;
-    if (!is16BPS(dstFormat) && !isNBPS(dstFormat) && dstFormat != AV_PIX_FMT_NV12
-        && dstFormat != AV_PIX_FMT_NV21 && dstFormat != AV_PIX_FMT_GRAYF32BE && dstFormat != AV_PIX_FMT_GRAYF32LE
+    if (!is16BPS(dstFormat) && !isNBPS(dstFormat) && !isSemiPlanarYUV(dstFormat)
+        && dstFormat != AV_PIX_FMT_GRAYF32BE && dstFormat != AV_PIX_FMT_GRAYF32LE
         && !(c->flags & SWS_BITEXACT)) {
             if (c->flags & SWS_ACCURATE_RND) {
                 if (!(c->flags & SWS_FULL_CHR_H_INT)) {
@@ -1517,7 +1435,6 @@ static av_cold void RENAME(sws_init_swscale)(SwsContext *c)
                 }
             } else {
                 c->use_mmx_vfilter= 1;
-                c->yuv2planeX = RENAME(yuv2yuvX    );
                 if (!(c->flags & SWS_FULL_CHR_H_INT)) {
                     switch (c->dstFormat) {
                     case AV_PIX_FMT_RGB32:   c->yuv2packedX = RENAME(yuv2rgb32_X);   break;