diff options
| author | Diego Biurrun <diego@biurrun.de> | 2013-01-29 19:28:07 +0100 |
|---|---|---|
| committer | Diego Biurrun <diego@biurrun.de> | 2013-01-31 11:19:23 +0100 |
| commit | 52acd79165e70799871a2feeb02b4fdc0d38a956 (patch) | |
| tree | 3747787efefbbf6924b87e9fdbe0f860197b9fe7 /libavcodec | |
| parent | 197252f1c58b1d53f97c10201990a471dd46d31c (diff) | |
| download | ffmpeg-52acd79165e70799871a2feeb02b4fdc0d38a956.tar.gz | |
x86: hpel: Move {avg,put}_pixels16_sse2 to hpeldsp
Diffstat (limited to 'libavcodec')
| -rw-r--r-- | libavcodec/x86/dsputil.asm | 43 | ||||
| -rw-r--r-- | libavcodec/x86/hpeldsp.asm | 43 |
2 files changed, 43 insertions, 43 deletions
diff --git a/libavcodec/x86/dsputil.asm b/libavcodec/x86/dsputil.asm index 351376d743..8002779a2e 100644 --- a/libavcodec/x86/dsputil.asm +++ b/libavcodec/x86/dsputil.asm @@ -648,46 +648,3 @@ BSWAP32_BUF INIT_XMM ssse3 BSWAP32_BUF - -INIT_XMM sse2 -; void put_pixels16_sse2(uint8_t *block, const uint8_t *pixels, int line_size, int h) -cglobal put_pixels16, 4,5,4 - movsxdifnidn r2, r2d - lea r4, [r2*3] -.loop: - movu m0, [r1] - movu m1, [r1+r2] - movu m2, [r1+r2*2] - movu m3, [r1+r4] - lea r1, [r1+r2*4] - mova [r0], m0 - mova [r0+r2], m1 - mova [r0+r2*2], m2 - mova [r0+r4], m3 - sub r3d, 4 - lea r0, [r0+r2*4] - jnz .loop - REP_RET - -; void avg_pixels16_sse2(uint8_t *block, const uint8_t *pixels, int line_size, int h) -cglobal avg_pixels16, 4,5,4 - movsxdifnidn r2, r2d - lea r4, [r2*3] -.loop: - movu m0, [r1] - movu m1, [r1+r2] - movu m2, [r1+r2*2] - movu m3, [r1+r4] - lea r1, [r1+r2*4] - pavgb m0, [r0] - pavgb m1, [r0+r2] - pavgb m2, [r0+r2*2] - pavgb m3, [r0+r4] - mova [r0], m0 - mova [r0+r2], m1 - mova [r0+r2*2], m2 - mova [r0+r4], m3 - sub r3d, 4 - lea r0, [r0+r2*4] - jnz .loop - REP_RET diff --git a/libavcodec/x86/hpeldsp.asm b/libavcodec/x86/hpeldsp.asm index ee5d56293e..920ae67630 100644 --- a/libavcodec/x86/hpeldsp.asm +++ b/libavcodec/x86/hpeldsp.asm @@ -463,3 +463,46 @@ INIT_MMX mmxext AVG_PIXELS8_XY2 INIT_MMX 3dnow AVG_PIXELS8_XY2 + +INIT_XMM sse2 +; void put_pixels16_sse2(uint8_t *block, const uint8_t *pixels, int line_size, int h) +cglobal put_pixels16, 4,5,4 + movsxdifnidn r2, r2d + lea r4, [r2*3] +.loop: + movu m0, [r1] + movu m1, [r1+r2] + movu m2, [r1+r2*2] + movu m3, [r1+r4] + lea r1, [r1+r2*4] + mova [r0], m0 + mova [r0+r2], m1 + mova [r0+r2*2], m2 + mova [r0+r4], m3 + sub r3d, 4 + lea r0, [r0+r2*4] + jnz .loop + REP_RET + +; void avg_pixels16_sse2(uint8_t *block, const uint8_t *pixels, int line_size, int h) +cglobal avg_pixels16, 4,5,4 + movsxdifnidn r2, r2d + lea r4, [r2*3] +.loop: + movu m0, [r1] + movu m1, [r1+r2] + movu m2, [r1+r2*2] + movu m3, [r1+r4] + lea r1, [r1+r2*4] + pavgb m0, [r0] + pavgb m1, [r0+r2] + pavgb m2, [r0+r2*2] + pavgb m3, [r0+r4] + mova [r0], m0 + mova [r0+r2], m1 + mova [r0+r2*2], m2 + mova [r0+r4], m3 + sub r3d, 4 + lea r0, [r0+r2*4] + jnz .loop + REP_RET |