[XviD-devel] mmx transfer8x8/16x16 optimization, setedges, etc.

[peter ross]

at the request of alban, ive assembled two new functions. i say  assembled 
because it basically involved  copying and pasting that "skals" chap's code.
xvid currently has a transfer8x8_copy_[c,mmx] function, which copy an 8x8 
block from one buffer to another. this function is limited by the assumption 
that both buffers have the same stride. the new functions, 
transfer8x8copy_[c,mmx] and transfer8x8copy_[c,mmx] provide stride arguments 
for both destination and source buffers.

NOW, on this machine (p3,800mhz) the new 8x8copy function is *1* cycle 
slower than current 8x8_copy function. so i reckon we can replace it with 
the new one (rather than maintaining two pieces of near identical code). any 
opinions?

speedwise, the mmx8x8 copy is ~25% faster than the c/memcpy version. the 
mmx16x16 copy is ~75% faster than the c/memcpy version.
alban this should speed up your ouput_mb function a little. AND, the 
16x16copy can now replace the four 8x8copy's used to copy not-coded mbs (in 
decoder_pframe function). please perform some tests alban and post the 
results. Note: *I* will commit this code in a day-or-so. btw, the 16x16 
could also be sse2'd.

alban and i were the possibility of "on-the-fly" set_edges for decoding. why 
bother? well, there's two reasons.
1. potential for added decoding speed. i suspect that the edges are rarely 
used, so by not calling image_setedges we might save some time.
2. support for mode-1 direct rending. in this mode, xvid uses the VIDEO-RAM 
as it's internal reference-frame buffer. the problem is doing so is that 
VIDEo-RAM has no room for edges (hence the need for on-the-fly).

also, i've been sitting on ircnet#xvid a little bit lately. syskin & mf 
asked that you, the dev team, drop by some time for a chin wag (that's slang 
for CHAT).

-- pete

;----


void transfer8x8copy_c(uint8_t * dst,
			const uint8_t * src,
			const uint32_t dst_stride,
			const uint32_t src_stride)
{
    int j;

    for (j = 0; j < 8; j++)
    {
        memcpy(dst, src, 8);
        dst += dst_stride;
        src += src_stride;
    }
}

void transfer16x16copy_c(uint8_t * dst,
			const uint8_t * src,
			const uint32_t dst_stride,
			const uint32_t src_stride)
{
    int j;

    for (j = 0; j < 16; j++)
    {
        memcpy(dst, src, 16);
        dst += dst_stride;
        src += src_stride;
    }
}


cglobal	transfer8x8copy_mmx
;===========================================================================
;
; void transfer8x8copy_mmx(uint8_t * const dst,
;			const uint8_t * const src,
;			const uint32_t dst_stride,
;			const uint32_t src_stride);
;
;
;===========================================================================

%macro COPY_8x8_MMX	0
  movq mm0, [eax]
  movq mm1, [eax+ebx]
  movq [ecx], mm0
  lea eax,[eax+2*ebx]
  movq [ecx+edx], mm1
  lea ecx,[ecx+2*edx]
%endmacro

align 16
transfer8x8copy_mmx:
  push ebx
  mov ecx, [esp+4+ 4] ; Dst
  mov eax, [esp+4+ 8] ; Src
  mov edx, [esp+4+12] ; dst-stride
  mov ebx, [esp+4+16] ; src-stride

  COPY_8x8_MMX
  COPY_8x8_MMX
  COPY_8x8_MMX
  COPY_8x8_MMX

  pop ebx
  ret



cglobal	transfer16x16copy_mmx
;===========================================================================
;
; void transfer16x16copy_mmx(uint8_t * const dst,
;			const uint8_t * const src,
;			const uint32_t dst_stride,
;			const uint32_t src_stride);
;
;
;===========================================================================

%macro COPY_16x16_MMX	0
  movq mm0, [eax]
  movq mm1, [eax + 8]
  movq mm2, [eax+ebx]
  movq mm3, [eax+ebx + 8]
  movq [ecx], mm0
  lea eax,[eax+2*ebx]
  movq [ecx + 8], mm1
  movq [ecx+edx], mm2
  movq [ecx+edx+8], mm3
  lea ecx,[ecx+2*edx]
%endmacro

align 16
transfer16x16copy_mmx:
  push ebx
  mov ecx, [esp+4+ 4] ; Dst
  mov eax, [esp+4+ 8] ; Src
  mov edx, [esp+4+12] ; dst-stride
  mov ebx, [esp+4+16] ; src-stride

  COPY_16x16_MMX
  COPY_16x16_MMX
  COPY_16x16_MMX
  COPY_16x16_MMX

  COPY_16x16_MMX
  COPY_16x16_MMX
  COPY_16x16_MMX
  COPY_16x16_MMX

  pop ebx
  ret

;---




_________________________________________________________________
Chat with friends online, try MSN Messenger: http://messenger.msn.com