From 197252f1c58b1d53f97c10201990a471dd46d31c Mon Sep 17 00:00:00 2001 From: Diego Biurrun Date: Thu, 31 Jan 2013 00:50:51 +0100 Subject: [PATCH 1/2] configure: Add a comment indicating why uclibc is checked before glibc --- configure | 1 + 1 file changed, 1 insertion(+) diff --git a/configure b/configure index c41a396f3e..ebeea83edf 100755 --- a/configure +++ b/configure @@ -3035,6 +3035,7 @@ esac # determine libc flavour +# uclibc defines __GLIBC__, so it needs to be checked before glibc. if check_cpp_condition features.h "defined __UCLIBC__"; then libc_type=uclibc add_cppflags -D_POSIX_C_SOURCE=200112 -D_XOPEN_SOURCE=600 From 52acd79165e70799871a2feeb02b4fdc0d38a956 Mon Sep 17 00:00:00 2001 From: Diego Biurrun Date: Tue, 29 Jan 2013 19:28:07 +0100 Subject: [PATCH 2/2] x86: hpel: Move {avg,put}_pixels16_sse2 to hpeldsp --- libavcodec/x86/dsputil.asm | 43 -------------------------------------- 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