idct_dc for VC-1/WMV3 decoder; ~11% faster decoding overall.

Includes mmx2 asm for the various functions.
Note that the actual idct still does not have an x86 SIMD implemtation.
For wmv3 files using regular idct, the decoder just falls back to simple_idct,
since simple_idct_dc doesn't exist (yet).

Originally committed as revision 19204 to svn://svn.ffmpeg.org/ffmpeg/trunk

1 files changed, 203 insertions, 0 deletions

diff --git a/libavcodec/x86/vc1dsp_mmx.c b/libavcodec/x86/vc1dsp_mmx.c
index 2c98b37b97..3071d02808 100644
--- a/libavcodec/x86/vc1dsp_mmx.c
+++ b/libavcodec/x86/vc1dsp_mmx.c
@@ -494,6 +494,204 @@ DECLARE_FUNCTION(3, 1)
 DECLARE_FUNCTION(3, 2)
 DECLARE_FUNCTION(3, 3)
 
+static void vc1_inv_trans_4x4_dc_mmx2(uint8_t *dest, int linesize, DCTELEM *block)
+{
+    int dc = block[0];
+    dc = (17 * dc +  4) >> 3;
+    dc = (17 * dc + 64) >> 7;
+    __asm__ volatile(
+        "movd          %0, %%mm0 \n\t"
+        "pshufw $0, %%mm0, %%mm0 \n\t"
+        "pxor       %%mm1, %%mm1 \n\t"
+        "psubw      %%mm0, %%mm1 \n\t"
+        "packuswb   %%mm0, %%mm0 \n\t"
+        "packuswb   %%mm1, %%mm1 \n\t"
+        ::"r"(dc)
+    );
+    __asm__ volatile(
+        "movd          %0, %%mm2 \n\t"
+        "movd          %1, %%mm3 \n\t"
+        "movd          %2, %%mm4 \n\t"
+        "movd          %3, %%mm5 \n\t"
+        "paddusb    %%mm0, %%mm2 \n\t"
+        "paddusb    %%mm0, %%mm3 \n\t"
+        "paddusb    %%mm0, %%mm4 \n\t"
+        "paddusb    %%mm0, %%mm5 \n\t"
+        "psubusb    %%mm1, %%mm2 \n\t"
+        "psubusb    %%mm1, %%mm3 \n\t"
+        "psubusb    %%mm1, %%mm4 \n\t"
+        "psubusb    %%mm1, %%mm5 \n\t"
+        "movd       %%mm2, %0    \n\t"
+        "movd       %%mm3, %1    \n\t"
+        "movd       %%mm4, %2    \n\t"
+        "movd       %%mm5, %3    \n\t"
+        :"+m"(*(uint32_t*)(dest+0*linesize)),
+         "+m"(*(uint32_t*)(dest+1*linesize)),
+         "+m"(*(uint32_t*)(dest+2*linesize)),
+         "+m"(*(uint32_t*)(dest+3*linesize))
+    );
+}
+
+static void vc1_inv_trans_4x8_dc_mmx2(uint8_t *dest, int linesize, DCTELEM *block)
+{
+    int dc = block[0];
+    dc = (17 * dc +  4) >> 3;
+    dc = (12 * dc + 64) >> 7;
+    __asm__ volatile(
+        "movd          %0, %%mm0 \n\t"
+        "pshufw $0, %%mm0, %%mm0 \n\t"
+        "pxor       %%mm1, %%mm1 \n\t"
+        "psubw      %%mm0, %%mm1 \n\t"
+        "packuswb   %%mm0, %%mm0 \n\t"
+        "packuswb   %%mm1, %%mm1 \n\t"
+        ::"r"(dc)
+    );
+    __asm__ volatile(
+        "movd          %0, %%mm2 \n\t"
+        "movd          %1, %%mm3 \n\t"
+        "movd          %2, %%mm4 \n\t"
+        "movd          %3, %%mm5 \n\t"
+        "paddusb    %%mm0, %%mm2 \n\t"
+        "paddusb    %%mm0, %%mm3 \n\t"
+        "paddusb    %%mm0, %%mm4 \n\t"
+        "paddusb    %%mm0, %%mm5 \n\t"
+        "psubusb    %%mm1, %%mm2 \n\t"
+        "psubusb    %%mm1, %%mm3 \n\t"
+        "psubusb    %%mm1, %%mm4 \n\t"
+        "psubusb    %%mm1, %%mm5 \n\t"
+        "movd       %%mm2, %0    \n\t"
+        "movd       %%mm3, %1    \n\t"
+        "movd       %%mm4, %2    \n\t"
+        "movd       %%mm5, %3    \n\t"
+        :"+m"(*(uint32_t*)(dest+0*linesize)),
+         "+m"(*(uint32_t*)(dest+1*linesize)),
+         "+m"(*(uint32_t*)(dest+2*linesize)),
+         "+m"(*(uint32_t*)(dest+3*linesize))
+    );
+    dest += 4*linesize;
+    __asm__ volatile(
+        "movd          %0, %%mm2 \n\t"
+        "movd          %1, %%mm3 \n\t"
+        "movd          %2, %%mm4 \n\t"
+        "movd          %3, %%mm5 \n\t"
+        "paddusb    %%mm0, %%mm2 \n\t"
+        "paddusb    %%mm0, %%mm3 \n\t"
+        "paddusb    %%mm0, %%mm4 \n\t"
+        "paddusb    %%mm0, %%mm5 \n\t"
+        "psubusb    %%mm1, %%mm2 \n\t"
+        "psubusb    %%mm1, %%mm3 \n\t"
+        "psubusb    %%mm1, %%mm4 \n\t"
+        "psubusb    %%mm1, %%mm5 \n\t"
+        "movd       %%mm2, %0    \n\t"
+        "movd       %%mm3, %1    \n\t"
+        "movd       %%mm4, %2    \n\t"
+        "movd       %%mm5, %3    \n\t"
+        :"+m"(*(uint32_t*)(dest+0*linesize)),
+         "+m"(*(uint32_t*)(dest+1*linesize)),
+         "+m"(*(uint32_t*)(dest+2*linesize)),
+         "+m"(*(uint32_t*)(dest+3*linesize))
+    );
+}
+
+static void vc1_inv_trans_8x4_dc_mmx2(uint8_t *dest, int linesize, DCTELEM *block)
+{
+    int dc = block[0];
+    dc = ( 3 * dc +  1) >> 1;
+    dc = (17 * dc + 64) >> 7;
+    __asm__ volatile(
+        "movd          %0, %%mm0 \n\t"
+        "pshufw $0, %%mm0, %%mm0 \n\t"
+        "pxor       %%mm1, %%mm1 \n\t"
+        "psubw      %%mm0, %%mm1 \n\t"
+        "packuswb   %%mm0, %%mm0 \n\t"
+        "packuswb   %%mm1, %%mm1 \n\t"
+        ::"r"(dc)
+    );
+    __asm__ volatile(
+        "movq          %0, %%mm2 \n\t"
+        "movq          %1, %%mm3 \n\t"
+        "movq          %2, %%mm4 \n\t"
+        "movq          %3, %%mm5 \n\t"
+        "paddusb    %%mm0, %%mm2 \n\t"
+        "paddusb    %%mm0, %%mm3 \n\t"
+        "paddusb    %%mm0, %%mm4 \n\t"
+        "paddusb    %%mm0, %%mm5 \n\t"
+        "psubusb    %%mm1, %%mm2 \n\t"
+        "psubusb    %%mm1, %%mm3 \n\t"
+        "psubusb    %%mm1, %%mm4 \n\t"
+        "psubusb    %%mm1, %%mm5 \n\t"
+        "movq       %%mm2, %0    \n\t"
+        "movq       %%mm3, %1    \n\t"
+        "movq       %%mm4, %2    \n\t"
+        "movq       %%mm5, %3    \n\t"
+        :"+m"(*(uint32_t*)(dest+0*linesize)),
+         "+m"(*(uint32_t*)(dest+1*linesize)),
+         "+m"(*(uint32_t*)(dest+2*linesize)),
+         "+m"(*(uint32_t*)(dest+3*linesize))
+    );
+}
+
+static void vc1_inv_trans_8x8_dc_mmx2(uint8_t *dest, int linesize, DCTELEM *block)
+{
+    int dc = block[0];
+    dc = (3 * dc +  1) >> 1;
+    dc = (3 * dc + 16) >> 5;
+    __asm__ volatile(
+        "movd          %0, %%mm0 \n\t"
+        "pshufw $0, %%mm0, %%mm0 \n\t"
+        "pxor       %%mm1, %%mm1 \n\t"
+        "psubw      %%mm0, %%mm1 \n\t"
+        "packuswb   %%mm0, %%mm0 \n\t"
+        "packuswb   %%mm1, %%mm1 \n\t"
+        ::"r"(dc)
+    );
+    __asm__ volatile(
+        "movq          %0, %%mm2 \n\t"
+        "movq          %1, %%mm3 \n\t"
+        "movq          %2, %%mm4 \n\t"
+        "movq          %3, %%mm5 \n\t"
+        "paddusb    %%mm0, %%mm2 \n\t"
+        "paddusb    %%mm0, %%mm3 \n\t"
+        "paddusb    %%mm0, %%mm4 \n\t"
+        "paddusb    %%mm0, %%mm5 \n\t"
+        "psubusb    %%mm1, %%mm2 \n\t"
+        "psubusb    %%mm1, %%mm3 \n\t"
+        "psubusb    %%mm1, %%mm4 \n\t"
+        "psubusb    %%mm1, %%mm5 \n\t"
+        "movq       %%mm2, %0    \n\t"
+        "movq       %%mm3, %1    \n\t"
+        "movq       %%mm4, %2    \n\t"
+        "movq       %%mm5, %3    \n\t"
+        :"+m"(*(uint32_t*)(dest+0*linesize)),
+         "+m"(*(uint32_t*)(dest+1*linesize)),
+         "+m"(*(uint32_t*)(dest+2*linesize)),
+         "+m"(*(uint32_t*)(dest+3*linesize))
+    );
+    dest += 4*linesize;
+    __asm__ volatile(
+        "movq          %0, %%mm2 \n\t"
+        "movq          %1, %%mm3 \n\t"
+        "movq          %2, %%mm4 \n\t"
+        "movq          %3, %%mm5 \n\t"
+        "paddusb    %%mm0, %%mm2 \n\t"
+        "paddusb    %%mm0, %%mm3 \n\t"
+        "paddusb    %%mm0, %%mm4 \n\t"
+        "paddusb    %%mm0, %%mm5 \n\t"
+        "psubusb    %%mm1, %%mm2 \n\t"
+        "psubusb    %%mm1, %%mm3 \n\t"
+        "psubusb    %%mm1, %%mm4 \n\t"
+        "psubusb    %%mm1, %%mm5 \n\t"
+        "movq       %%mm2, %0    \n\t"
+        "movq       %%mm3, %1    \n\t"
+        "movq       %%mm4, %2    \n\t"
+        "movq       %%mm5, %3    \n\t"
+        :"+m"(*(uint32_t*)(dest+0*linesize)),
+         "+m"(*(uint32_t*)(dest+1*linesize)),
+         "+m"(*(uint32_t*)(dest+2*linesize)),
+         "+m"(*(uint32_t*)(dest+3*linesize))
+    );
+}
+
 void ff_vc1dsp_init_mmx(DSPContext* dsp, AVCodecContext *avctx) {
     mm_flags = mm_support();
 
@@ -537,5 +735,10 @@ void ff_vc1dsp_init_mmx(DSPContext* dsp, AVCodecContext *avctx) {
         dsp->avg_vc1_mspel_pixels_tab[ 7] = avg_vc1_mspel_mc31_mmx2;
         dsp->avg_vc1_mspel_pixels_tab[11] = avg_vc1_mspel_mc32_mmx2;
         dsp->avg_vc1_mspel_pixels_tab[15] = avg_vc1_mspel_mc33_mmx2;
+
+        dsp->vc1_inv_trans_8x8_dc = vc1_inv_trans_8x8_dc_mmx2;
+        dsp->vc1_inv_trans_4x8_dc = vc1_inv_trans_4x8_dc_mmx2;
+        dsp->vc1_inv_trans_8x4_dc = vc1_inv_trans_8x4_dc_mmx2;
+        dsp->vc1_inv_trans_4x4_dc = vc1_inv_trans_4x4_dc_mmx2;
     }
 }