[FFmpeg-devel] [PATCH] Port x264 SSE2 deblocking code to H.264 decoder

[Loren Merritt]

On Wed, 17 Dec 2008, Michael Niedermayer wrote:

>> @@ -275,10 +274,10 @@
>>
>>  %ifdef ARCH_X86_64
>>  ;-----------------------------------------------------------------------------
>> -; void x264_deblock_v_luma_sse2( uint8_t *pix, int stride, int alpha, int beta, int8_t *tc0 )
>> +; void h264_v_loop_filter_luma_sse2( uint8_t *pix, int stride, int alpha, int beta, int8_t *tc0 )
>>  ;-----------------------------------------------------------------------------
>>  INIT_XMM
>> -cglobal x264_deblock_v_luma_sse2
>> +cglobal h264_v_loop_filter_luma_sse2
>>      movd    m8, [r4] ; tc0
>>      lea     r4, [r1*3]
>>      dec     r2d        ; alpha-1
>
> would it be possible to use some kind of macro to give these functions
> differnt prefixes so the .asm files could be identical?

Like this? then it'll be ff_x264_deblock_v_luma_sse2

--Loren Merritt
-------------- next part --------------
diff --git a/libavcodec/i386/dsputil_yasm.asm b/libavcodec/i386/dsputil_yasm.asm
index 2d7d465..974491f 100644
--- a/libavcodec/i386/dsputil_yasm.asm
+++ b/libavcodec/i386/dsputil_yasm.asm
@@ -38,7 +38,7 @@ section .text align=16
 
 %macro FLOAT_TO_INT16_INTERLEAVE6 1
 ; void ff_float_to_int16_interleave6_sse(int16_t *dst, const float **src, int len)
-cglobal ff_float_to_int16_interleave6_%1, 2,7,0, dst, src, src1, src2, src3, src4, src5
+cglobal float_to_int16_interleave6_%1, 2,7,0, dst, src, src1, src2, src3, src4, src5
 %ifdef ARCH_X86_64
     %define lend r10d
     mov     lend, r2d
diff --git a/libavcodec/i386/fft_mmx.asm b/libavcodec/i386/fft_mmx.asm
index c0a9bd5..3971867 100644
--- a/libavcodec/i386/fft_mmx.asm
+++ b/libavcodec/i386/fft_mmx.asm
@@ -451,7 +451,7 @@ dispatch_tab%3%2: pointer list_of_fft
 
 ; On x86_32, this function does the register saving and restoring for all of fft.
 ; The others pass args in registers and don't spill anything.
-cglobal ff_fft_dispatch%3%2, 2,5,0, z, nbits
+cglobal fft_dispatch%3%2, 2,5,0, z, nbits
     lea r2, [dispatch_tab%3%2 GLOBAL]
     mov r2, [r2 + (nbitsq-2)*gprsize]
     call r2
diff --git a/libavcodec/i386/x86inc.asm b/libavcodec/i386/x86inc.asm
index 54c4679..3729b5b 100644
--- a/libavcodec/i386/x86inc.asm
+++ b/libavcodec/i386/x86inc.asm
@@ -370,20 +370,14 @@ DECLARE_REG 6, ebp, ebp, bp, null, [esp + stack_offset + 28]
 
 ; Symbol prefix for C linkage
 %macro cglobal 1-2+
+    %xdefine %1 ff_%1
+    %ifdef PREFIX
+        %xdefine %1 _ %+ %1
+    %endif
     %ifidn __OUTPUT_FORMAT__,elf
-        %ifdef PREFIX
-            global _%1:function hidden
-            %define %1 _%1
-        %else
-            global %1:function hidden
-        %endif
+        global %1:function hidden
     %else
-        %ifdef PREFIX
-            global _%1
-            %define %1 _%1
-        %else
-            global %1
-        %endif
+        global %1
     %endif
     align function_align
     %1: