x86: include x86inc.asm in x86util.asm

[ffmpeg] / libavcodec / x86 / vp56dsp.asm

diff --git a/libavcodec/x86/vp56dsp.asm b/libavcodec/x86/vp56dsp.asm
index 1b3165e54ae45282a8be5f6861cad97702579d52..f89ec7f43a9b15428c8e01313b52eb6824bda4bc 100644 (file)
--- a/libavcodec/x86/vp56dsp.asm
+++ b/libavcodec/x86/vp56dsp.asm
@@ -3,31 +3,31 @@
 ;* Copyright (C) 2009  Sebastien Lucas <sebastien.lucas@gmail.com>
 ;* Copyright (C) 2009  Zuxy Meng <zuxy.meng@gmail.com>
 ;*
-;* This file is part of FFmpeg.
+;* This file is part of Libav.
 ;*
-;* FFmpeg is free software; you can redistribute it and/or
+;* Libav is free software; you can redistribute it and/or
 ;* modify it under the terms of the GNU Lesser General Public
 ;* License as published by the Free Software Foundation; either
 ;* version 2.1 of the License, or (at your option) any later version.
 ;*
-;* FFmpeg is distributed in the hope that it will be useful,
+;* Libav is distributed in the hope that it will be useful,
 ;* but WITHOUT ANY WARRANTY; without even the implied warranty of
 ;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 ;* Lesser General Public License for more details.
 ;*
 ;* You should have received a copy of the GNU Lesser General Public
-;* License along with FFmpeg; if not, write to the Free Software
-;* 51, Inc., Foundation Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+;* License along with Libav; if not, write to the Free Software
+;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 ;******************************************************************************
 
-%include "x86inc.asm"
 %include "x86util.asm"
 
 cextern pw_64
 
 SECTION .text
 
-%macro DIAG4_MMX 6
+%macro DIAG4 6
+%if mmsize == 8
     movq          m0, [%1+%2]
     movq          m1, [%1+%3]
     movq          m3, m0
@@ -48,8 +48,8 @@ SECTION .text
     movq          m5, m2
     punpcklbw     m1, m7
     punpcklbw     m2, m7
-    punpcklbw     m4, m7
-    punpcklbw     m5, m7
+    punpckhbw     m4, m7
+    punpckhbw     m5, m7
     pmullw        m1, [rsp+8*13] ; src[x+8 ] * biweight [2]
     pmullw        m2, [rsp+8*14] ; src[x+16] * biweight [3]
     pmullw        m4, [rsp+8*13] ; src[x+8 ] * biweight [2]
@@ -64,9 +64,7 @@ SECTION .text
     psraw         m3, 7
     packuswb      m0, m3
     movq        [%6], m0
-%endmacro
-
-%macro DIAG4_SSE2 6
+%else ; mmsize == 16
     movq          m0, [%1+%2]
     movq          m1, [%1+%3]
     punpcklbw     m0, m7
@@ -86,25 +84,25 @@ SECTION .text
     psraw         m0, 7
     packuswb      m0, m0
     movq        [%6], m0
+%endif ; mmsize == 8/16
 %endmacro
 
-%macro SPLAT4REGS_MMX 0
+%macro SPLAT4REGS 0
+%if mmsize == 8
     movq         m5, m3
     punpcklwd    m3, m3
     movq         m4, m3
     punpckldq    m3, m3
     punpckhdq    m4, m4
     punpckhwd    m5, m5
-    movq         m6, m5
-    punpckhdq    m6, m6
+    movq         m2, m5
+    punpckhdq    m2, m2
     punpckldq    m5, m5
     movq [rsp+8*11], m3
     movq [rsp+8*12], m4
     movq [rsp+8*13], m5
-    movq [rsp+8*14], m6
-%endmacro
-
-%macro SPLAT4REGS_SSE2 0
+    movq [rsp+8*14], m2
+%else ; mmsize == 16
     pshuflw      m4, m3, 0x0
     pshuflw      m5, m3, 0x55
     pshuflw      m6, m3, 0xAA
@@ -113,21 +111,22 @@ SECTION .text
     punpcklqdq   m5, m5
     punpcklqdq   m6, m6
     punpcklqdq   m3, m3
+%endif ; mmsize == 8/16
 %endmacro
 
-%macro vp6_filter_diag4 2
+%macro vp6_filter_diag4 0
 ; void ff_vp6_filter_diag4_<opt>(uint8_t *dst, uint8_t *src, int stride,
 ;                                const int16_t h_weight[4], const int16_t v_weights[4])
-cglobal vp6_filter_diag4_%1, 5, 7, %2
+cglobal vp6_filter_diag4, 5, 7, 8
     mov          r5, rsp         ; backup stack pointer
     and         rsp, ~(mmsize-1) ; align stack
-%ifidn %1, sse2
+%if mmsize == 16
     sub         rsp, 8*11
 %else
     sub         rsp, 8*15
     movq         m6, [pw_64]
 %endif
-%ifdef ARCH_X86_64
+%if ARCH_X86_64
     movsxd       r2, r2d
 %endif
 
@@ -139,7 +138,7 @@ cglobal vp6_filter_diag4_%1, 5, 7, %2
 
     mov          r3, rsp
     mov          r6, 11
-.nextrow
+.nextrow:
     DIAG4        r1, -1, 0, 1, 2, r3
     add          r3, 8
     add          r1, r2
@@ -151,7 +150,7 @@ cglobal vp6_filter_diag4_%1, 5, 7, %2
 
     lea          r3, [rsp+8]
     mov          r6, 8
-.nextcol
+.nextcol:
     DIAG4        r3, -8, 0, 8, 16, r0
     add          r3, 8
     add          r0, r2
@@ -162,12 +161,10 @@ cglobal vp6_filter_diag4_%1, 5, 7, %2
     RET
 %endmacro
 
-INIT_MMX
-%define DIAG4      DIAG4_MMX
-%define SPLAT4REGS SPLAT4REGS_MMX
-vp6_filter_diag4 mmx,  0
+%if ARCH_X86_32
+INIT_MMX mmx
+vp6_filter_diag4
+%endif
 
-INIT_XMM
-%define DIAG4      DIAG4_SSE2
-%define SPLAT4REGS SPLAT4REGS_SSE2
-vp6_filter_diag4 sse2, 8
+INIT_XMM sse2
+vp6_filter_diag4