diff options
| author | James Almer <jamrial@gmail.com> | 2014-09-24 19:53:07 -0300 |
|---|---|---|
| committer | James Almer <jamrial@gmail.com> | 2014-09-24 21:52:13 -0300 |
| commit | 4f4f08e6f00f9949c27e2f76bb7f732e6d16871e (patch) | |
| tree | 1c277162e923ff1ea8f001890c8ce33b65f821de /libavcodec/x86/idctdsp.asm | |
| parent | c99a8828148949430608c3866e671a599a5805ba (diff) | |
x86/idctdsp: port {put,add}_pixels_clamped to yasm
Also add sse2 versions for both.
put_pixels_clamped port and sse2 version originally written by Timothy Gu.
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
Diffstat (limited to 'libavcodec/x86/idctdsp.asm')
| -rw-r--r-- | libavcodec/x86/idctdsp.asm | 103 |
1 files changed, 103 insertions, 0 deletions
diff --git a/libavcodec/x86/idctdsp.asm b/libavcodec/x86/idctdsp.asm index c3f37c4910..0aa73459e2 100644 --- a/libavcodec/x86/idctdsp.asm +++ b/libavcodec/x86/idctdsp.asm @@ -78,3 +78,106 @@ INIT_MMX mmx PUT_SIGNED_PIXELS_CLAMPED 0 INIT_XMM sse2 PUT_SIGNED_PIXELS_CLAMPED 3 + +;-------------------------------------------------------------------------- +; void ff_put_pixels_clamped(const int16_t *block, uint8_t *pixels, +; ptrdiff_t line_size); +;-------------------------------------------------------------------------- +; %1 = block offset +%macro PUT_PIXELS_CLAMPED_HALF 1 + mova m0, [blockq+mmsize*0+%1] + mova m1, [blockq+mmsize*2+%1] +%if mmsize == 8 + mova m2, [blockq+mmsize*4+%1] + mova m3, [blockq+mmsize*6+%1] +%endif + packuswb m0, [blockq+mmsize*1+%1] + packuswb m1, [blockq+mmsize*3+%1] +%if mmsize == 8 + packuswb m2, [blockq+mmsize*5+%1] + packuswb m3, [blockq+mmsize*7+%1] + movq [pixelsq], m0 + movq [lsizeq+pixelsq], m1 + movq [2*lsizeq+pixelsq], m2 + movq [lsize3q+pixelsq], m3 +%else + movq [pixelsq], m0 + movhps [lsizeq+pixelsq], m0 + movq [2*lsizeq+pixelsq], m1 + movhps [lsize3q+pixelsq], m1 +%endif +%endmacro + +%macro PUT_PIXELS_CLAMPED 0 +cglobal put_pixels_clamped, 3, 4, 2, block, pixels, lsize, lsize3 + lea lsize3q, [lsizeq*3] + PUT_PIXELS_CLAMPED_HALF 0 + lea pixelsq, [pixelsq+lsizeq*4] + PUT_PIXELS_CLAMPED_HALF 64 + RET +%endmacro + +INIT_MMX mmx +PUT_PIXELS_CLAMPED +INIT_XMM sse2 +PUT_PIXELS_CLAMPED + +;-------------------------------------------------------------------------- +; void ff_add_pixels_clamped(const int16_t *block, uint8_t *pixels, +; ptrdiff_t line_size); +;-------------------------------------------------------------------------- +; %1 = block offset +%macro ADD_PIXELS_CLAMPED 1 + mova m0, [blockq+mmsize*0+%1] + mova m1, [blockq+mmsize*1+%1] +%if mmsize == 8 + mova m5, [blockq+mmsize*2+%1] + mova m6, [blockq+mmsize*3+%1] +%endif + movq m2, [pixelsq] + movq m3, [pixelsq+lsizeq] +%if mmsize == 8 + mova m7, m2 + punpcklbw m2, m4 + punpckhbw m7, m4 + paddsw m0, m2 + paddsw m1, m7 + mova m7, m3 + punpcklbw m3, m4 + punpckhbw m7, m4 + paddsw m5, m3 + paddsw m6, m7 +%else + punpcklbw m2, m4 + punpcklbw m3, m4 + paddsw m0, m2 + paddsw m1, m3 +%endif + packuswb m0, m1 +%if mmsize == 8 + packuswb m5, m6 + movq [pixelsq], m0 + movq [pixelsq+lsizeq], m5 +%else + movq [pixelsq], m0 + movhps [pixelsq+lsizeq], m0 +%endif +%endmacro + +%macro ADD_PIXELS_CLAMPED 0 +cglobal add_pixels_clamped, 3, 3, 5, block, pixels, lsize + pxor m4, m4 + ADD_PIXELS_CLAMPED 0 + lea pixelsq, [pixelsq+lsizeq*2] + ADD_PIXELS_CLAMPED 32 + lea pixelsq, [pixelsq+lsizeq*2] + ADD_PIXELS_CLAMPED 64 + lea pixelsq, [pixelsq+lsizeq*2] + ADD_PIXELS_CLAMPED 96 + RET +%endmacro + +INIT_MMX mmx +ADD_PIXELS_CLAMPED +INIT_XMM sse2 +ADD_PIXELS_CLAMPED |