X-Git-Url: https://git.sesse.net/?a=blobdiff_plain;f=libavcodec%2Fx86%2Fh264_idct_10bit.asm;h=9fd05abb2b7349c737e52d37bacebdcfe0e23bd2;hb=591cf8aa0ee9e09aac29861f4229616df7604172;hp=4f7491dbf5df4ef33267a3841b7e8d23477f6e59;hpb=7c282d0c758dc5e9593312da1c191cdf76de0303;p=ffmpeg

diff --git a/libavcodec/x86/h264_idct_10bit.asm b/libavcodec/x86/h264_idct_10bit.asm
index 4f7491dbf5d..9fd05abb2b7 100644
--- a/libavcodec/x86/h264_idct_10bit.asm
+++ b/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)
 ;-----------------------------------------------------------------------------