PUT_NO_RND_PIXELS8_X2
-; void ff_put_no_rnd_pixels8_x2_exact(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
-%macro PUT_NO_RND_PIXELS8_X2_EXACT 0
-cglobal put_no_rnd_pixels8_x2_exact, 4,5
- lea r4, [r2*3]
- pcmpeqb m6, m6
-.loop:
- mova m0, [r1]
- mova m2, [r1+r2]
- mova m1, [r1+1]
- mova m3, [r1+r2+1]
- pxor m0, m6
- pxor m2, m6
- pxor m1, m6
- pxor m3, m6
- PAVGB m0, m1
- PAVGB m2, m3
- pxor m0, m6
- pxor m2, m6
- mova [r0], m0
- mova [r0+r2], m2
- mova m0, [r1+r2*2]
- mova m1, [r1+r2*2+1]
- mova m2, [r1+r4]
- mova m3, [r1+r4+1]
- pxor m0, m6
- pxor m1, m6
- pxor m2, m6
- pxor m3, m6
- PAVGB m0, m1
- PAVGB m2, m3
- pxor m0, m6
- pxor m2, m6
- mova [r0+r2*2], m0
- mova [r0+r4], m2
- lea r1, [r1+r2*4]
- lea r0, [r0+r2*4]
- sub r3d, 4
- jg .loop
- REP_RET
-%endmacro
-
-INIT_MMX mmxext
-PUT_NO_RND_PIXELS8_X2_EXACT
-INIT_MMX 3dnow
-PUT_NO_RND_PIXELS8_X2_EXACT
-
-
; void ff_put_pixels8_y2(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
%macro PUT_PIXELS8_Y2 0
%if cpuflag(sse2)
PUT_NO_RND_PIXELS8_Y2
-; void ff_put_no_rnd_pixels8_y2_exact(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
-%macro PUT_NO_RND_PIXELS8_Y2_EXACT 0
-cglobal put_no_rnd_pixels8_y2_exact, 4,5
- lea r4, [r2*3]
- mova m0, [r1]
- pcmpeqb m6, m6
- add r1, r2
- pxor m0, m6
-.loop:
- mova m1, [r1]
- mova m2, [r1+r2]
- pxor m1, m6
- pxor m2, m6
- PAVGB m0, m1
- PAVGB m1, m2
- pxor m0, m6
- pxor m1, m6
- mova [r0], m0
- mova [r0+r2], m1
- mova m1, [r1+r2*2]
- mova m0, [r1+r4]
- pxor m1, m6
- pxor m0, m6
- PAVGB m2, m1
- PAVGB m1, m0
- pxor m2, m6
- pxor m1, m6
- mova [r0+r2*2], m2
- mova [r0+r4], m1
- lea r1, [r1+r2*4]
- lea r0, [r0+r2*4]
- sub r3d, 4
- jg .loop
- REP_RET
-%endmacro
-
-INIT_MMX mmxext
-PUT_NO_RND_PIXELS8_Y2_EXACT
-INIT_MMX 3dnow
-PUT_NO_RND_PIXELS8_Y2_EXACT
-
-
; void ff_avg_pixels8(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
%macro AVG_PIXELS8 0
cglobal avg_pixels8, 4,5