Merge remote-tracking branch 'qatar/master'

[ffmpeg] / libavcodec / x86 / h264_qpel_8bit.asm

diff --git a/libavcodec/x86/h264_qpel_8bit.asm b/libavcodec/x86/h264_qpel_8bit.asm
index 2d287ba443688bb9ac3f5ed67aa165110b3e5020..3039f172068789ff0998b35f592a05ca12ae4238 100644 (file)
--- a/libavcodec/x86/h264_qpel_8bit.asm
+++ b/libavcodec/x86/h264_qpel_8bit.asm
@@ -860,3 +860,172 @@ INIT_XMM ssse3
 QPEL16_H_LOWPASS_L2_OP put
 QPEL16_H_LOWPASS_L2_OP avg
 %endif
+
+; void pixels4_l2_mmxext(uint8_t *dst, uint8_t *src1, uint8_t *src2, int dstStride, int src1Stride, int h)
+%macro PIXELS4_L2 1
+%define OP op_%1h
+cglobal %1_pixels4_l2, 6,6
+    movsxdifnidn r3, r3d
+    movsxdifnidn r4, r4d
+    test        r5d, 1
+    je        .loop
+    movd         m0, [r1]
+    movd         m1, [r2]
+    add          r1, r4
+    add          r2, 4
+    pavgb        m0, m1
+    OP           m0, [r0], m3
+    add          r0, r3
+    dec         r5d
+.loop:
+    mova         m0, [r1]
+    mova         m1, [r1+r4]
+    lea          r1, [r1+2*r4]
+    pavgb        m0, [r2]
+    pavgb        m1, [r2+4]
+    OP           m0, [r0], m3
+    OP           m1, [r0+r3], m3
+    lea          r0, [r0+2*r3]
+    mova         m0, [r1]
+    mova         m1, [r1+r4]
+    lea          r1, [r1+2*r4]
+    pavgb        m0, [r2+8]
+    pavgb        m1, [r2+12]
+    OP           m0, [r0], m3
+    OP           m1, [r0+r3], m3
+    lea          r0, [r0+2*r3]
+    add          r2, 16
+    sub         r5d, 4
+    jne       .loop
+    REP_RET
+%endmacro
+
+INIT_MMX mmxext
+PIXELS4_L2 put
+PIXELS4_L2 avg
+
+; void pixels8_l2_mmxext(uint8_t *dst, uint8_t *src1, uint8_t *src2, int dstStride, int src1Stride, int h)
+%macro PIXELS8_L2 1
+%define OP op_%1
+cglobal %1_pixels8_l2, 6,6
+    movsxdifnidn r3, r3d
+    movsxdifnidn r4, r4d
+    test        r5d, 1
+    je        .loop
+    mova         m0, [r1]
+    mova         m1, [r2]
+    add          r1, r4
+    add          r2, 8
+    pavgb        m0, m1
+    OP           m0, [r0]
+    add          r0, r3
+    dec         r5d
+.loop:
+    mova         m0, [r1]
+    mova         m1, [r1+r4]
+    lea          r1, [r1+2*r4]
+    pavgb        m0, [r2]
+    pavgb        m1, [r2+8]
+    OP           m0, [r0]
+    OP           m1, [r0+r3]
+    lea          r0, [r0+2*r3]
+    mova         m0, [r1]
+    mova         m1, [r1+r4]
+    lea          r1, [r1+2*r4]
+    pavgb        m0, [r2+16]
+    pavgb        m1, [r2+24]
+    OP           m0, [r0]
+    OP           m1, [r0+r3]
+    lea          r0, [r0+2*r3]
+    add          r2, 32
+    sub         r5d, 4
+    jne       .loop
+    REP_RET
+%endmacro
+
+INIT_MMX mmxext
+PIXELS8_L2 put
+PIXELS8_L2 avg
+
+; void pixels16_l2_mmxext(uint8_t *dst, uint8_t *src1, uint8_t *src2, int dstStride, int src1Stride, int h)
+%macro PIXELS16_L2 1
+%define OP op_%1
+cglobal %1_pixels16_l2, 6,6
+    movsxdifnidn r3, r3d
+    movsxdifnidn r4, r4d
+    test        r5d, 1
+    je        .loop
+    mova         m0, [r1]
+    mova         m1, [r1+8]
+    pavgb        m0, [r2]
+    pavgb        m1, [r2+8]
+    add          r1, r4
+    add          r2, 16
+    OP           m0, [r0]
+    OP           m1, [r0+8]
+    add          r0, r3
+    dec         r5d
+.loop:
+    mova         m0, [r1]
+    mova         m1, [r1+8]
+    add          r1, r4
+    pavgb        m0, [r2]
+    pavgb        m1, [r2+8]
+    OP           m0, [r0]
+    OP           m1, [r0+8]
+    add          r0, r3
+    mova         m0, [r1]
+    mova         m1, [r1+8]
+    add          r1, r4
+    pavgb        m0, [r2+16]
+    pavgb        m1, [r2+24]
+    OP           m0, [r0]
+    OP           m1, [r0+8]
+    add          r0, r3
+    add          r2, 32
+    sub         r5d, 2
+    jne       .loop
+    REP_RET
+%endmacro
+
+INIT_MMX mmxext
+PIXELS16_L2 put
+PIXELS16_L2 avg
+
+INIT_MMX mmxext
+; void pixels(uint8_t *block, const uint8_t *pixels, int line_size, int h)
+%macro PIXELS48 2
+%if %2 == 4
+%define OP movh
+%else
+%define OP mova
+%endif
+cglobal %1_pixels%2, 4,5
+    movsxdifnidn r2, r2d
+    lea          r4, [r2*3]
+.loop:
+    OP           m0, [r1]
+    OP           m1, [r1+r2]
+    OP           m2, [r1+r2*2]
+    OP           m3, [r1+r4]
+    lea          r1, [r1+r2*4]
+%ifidn %1, avg
+    pavgb        m0, [r0]
+    pavgb        m1, [r0+r2]
+    pavgb        m2, [r0+r2*2]
+    pavgb        m3, [r0+r4]
+%endif
+    OP         [r0], m0
+    OP      [r0+r2], m1
+    OP    [r0+r2*2], m2
+    OP      [r0+r4], m3
+    sub         r3d, 4
+    lea          r0, [r0+r2*4]
+    jne       .loop
+    RET
+%endmacro
+
+PIXELS48 put, 4
+PIXELS48 avg, 4
+PIXELS48 put, 8
+PIXELS48 avg, 8