avcodec/h264: sse2 and avx 4:2:2 idct add8 10-bit functions

Yorkfield:
 - sse2:
   - complex: 4.13x faster (1514 vs. 367 cycles)
   - simple:  4.38x faster (1836 vs. 419 cycles)

Skylake:
 - sse2:
   - complex: 3.61x faster ( 936 vs. 260 cycles)
   - simple:  3.97x faster (1126 vs. 284 cycles)
 - avx (versus sse2):
   - complex: 1.07x faster (260 vs. 244 cycles)
   - simple:  1.03x faster (284 vs. 274 cycles)

libavcodec/x86/h264_idct_10bit.asm

@@ -350,6 +350,59 @@ INIT_XMM avx
 IDCT_ADD8
 %endif
 
+;-----------------------------------------------------------------------------
+; void ff_h264_idct_add8_422_10(pixel **dst, const int *block_offset,
+;                               int16_t *block, int stride,
+;                               const uint8_t nnzc[6*8])
+;-----------------------------------------------------------------------------
+%assign last_block 44
+
+%macro IDCT_ADD8_422 0
+
+cglobal h264_idct_add8_422_10, 5, 8, 7
+    movsxdifnidn r3, r3d
+%if ARCH_X86_64
+    mov      r7, r0
+%endif
+
+    add      r2, 1024
+    mov      r0, [r0]
+    ADD16_OP_INTRA 16, 4+ 6*8
+    ADD16_OP_INTRA 18, 4+ 7*8
+    ADD16_OP_INTRA 24, 4+ 8*8 ; i+4
+    ADD16_OP_INTRA 26, 4+ 9*8 ; i+4
+    add      r2, 1024-128*4
+
+%if ARCH_X86_64
+    mov      r0, [r7+gprsize]
+%else
+    mov      r0, r0m
+    mov      r0, [r0+gprsize]
+%endif
+
+    ADD16_OP_INTRA 32, 4+11*8
+    ADD16_OP_INTRA 34, 4+12*8
+    ADD16_OP_INTRA 40, 4+13*8 ; i+4
+    ADD16_OP_INTRA 42, 4+14*8 ; i+4
+REP_RET
+    AC 16
+    AC 18
+    AC 24 ; i+4
+    AC 26 ; i+4
+    AC 32
+    AC 34
+    AC 40 ; i+4
+    AC 42 ; i+4
+
+%endmacro
+
+INIT_XMM sse2
+IDCT_ADD8_422
+%if HAVE_AVX_EXTERNAL
+INIT_XMM avx
+IDCT_ADD8_422
+%endif
+
 ;-----------------------------------------------------------------------------
 ; void ff_h264_idct8_add_10(pixel *dst, int16_t *block, int stride)
 ;-----------------------------------------------------------------------------

libavcodec/x86/h264dsp_init.c

@@ -80,6 +80,9 @@ IDCT_ADD_REP_FUNC2(, 8, 10, avx)
 
 IDCT_ADD_REP_FUNC2(, 8_422, 8, mmx)
 
+IDCT_ADD_REP_FUNC2(, 8_422, 10, sse2)
+IDCT_ADD_REP_FUNC2(, 8_422, 10, avx)
+
 void ff_h264_luma_dc_dequant_idct_mmx(int16_t *output, int16_t *input, int qmul);
 void ff_h264_luma_dc_dequant_idct_sse2(int16_t *output, int16_t *input, int qmul);
 
@@ -319,8 +322,11 @@ av_cold void ff_h264dsp_init_x86(H264DSPContext *c, const int bit_depth,
             c->h264_idct8_dc_add = ff_h264_idct8_dc_add_10_sse2;
 
             c->h264_idct_add16 = ff_h264_idct_add16_10_sse2;
-            if (chroma_format_idc <= 1)
+            if (chroma_format_idc <= 1) {
                 c->h264_idct_add8 = ff_h264_idct_add8_10_sse2;
+            } else {
+                c->h264_idct_add8 = ff_h264_idct_add8_422_10_sse2;
+            }
             c->h264_idct_add16intra = ff_h264_idct_add16intra_10_sse2;
 #if HAVE_ALIGNED_STACK
             c->h264_idct8_add  = ff_h264_idct8_add_10_sse2;
@@ -359,8 +365,11 @@ av_cold void ff_h264dsp_init_x86(H264DSPContext *c, const int bit_depth,
             c->h264_idct8_dc_add = ff_h264_idct8_dc_add_10_avx;
 
             c->h264_idct_add16 = ff_h264_idct_add16_10_avx;
-            if (chroma_format_idc <= 1)
+            if (chroma_format_idc <= 1) {
                 c->h264_idct_add8 = ff_h264_idct_add8_10_avx;
+            } else {
+                c->h264_idct_add8 = ff_h264_idct_add8_422_10_avx;
+            }
             c->h264_idct_add16intra = ff_h264_idct_add16intra_10_avx;
 #if HAVE_ALIGNED_STACK
             c->h264_idct8_add  = ff_h264_idct8_add_10_avx;