31 Commits (d859bb1db0b082644881058a12653e3207855678)

Author SHA1 Message Date
Vitor Sessak 9263a05aab Mark "i" parameter of vector_clipf_sse() as early-clobber 15 years ago
Vitor Sessak 50e23ae9d3 Mark parameter src of vector_clipf() as const 15 years ago
Vitor Sessak 0a68cd876e SSE optimized vector_clipf(). 10% faster TwinVQ decoding. 15 years ago
Diego Biurrun 9be6f0d2f8 Do not check for both CONFIG_VC1_DECODER and CONFIG_WMV3_DECODER, 16 years ago
Diego Biurrun 99e5a9d1ea Do not redundantly check for both CONFIG_THEORA_DECODER and CONFIG_VP3_DECODER. 16 years ago
Carl Eugen Hoyos 36904c4c9f Icc 11.1 still does not align the stack pointer, disable some x264 functions. 16 years ago
Jason Garrett-Glaser 73b02e2460 SSE version of clear_blocks 16 years ago
David Conrad c21c835b8d avg_ pixel functions need to use (dst+pix+1)>>1 to average with existing 16 years ago
David Conrad 9bf0fdf378 VC1: extend MMX qpel MC to include MMX2 avg qpel 16 years ago
David Conrad 8013da7364 VC1: add and use avg_no_rnd chroma MC functions 16 years ago
David Conrad c374691b28 Rename put_no_rnd_h264_chroma* to reflect its usage in VC1 only 16 years ago
Stefano Sabatini 6b4343616c Rename FF_MM_MMXEXT to FF_MM_MMX2, for both clarity and consistency 16 years ago
Reimar Döffinger 0be9e73e38 Mark line_skip3 asm argument as output-only instead of using av_uninit. 16 years ago
Reimar Döffinger d7460a9cac Mark put_signed_pixels_clamped_mmx output operands as early-clobber because 16 years ago
Reimar Döffinger 531a3d2721 Use DECLARE_ASM_CONST for non-global ff_vector128 constant used via MANGLE 16 years ago
Alex Converse 3dd6531208 Rewrite put_signed_pixels_clamped_mmx() to eliminate mmx.h from dsputil_mmx.c. 16 years ago
Zuxy Meng ecb24904fe add SSE2 version of vp6_filter_diag 16 years ago
Sebastien Lucas 6af3c226c3 add MMX version of vp6_filter_diag 16 years ago
Aurelien Jacobs 5110b25e1e convert ff_pw_64 into an xmm_reg for future use in vp6 sse code 16 years ago
Diego Biurrun d3a4b4e09c Add check whether the compiler/assembler supports 10 or more operands. 16 years ago
Loren Merritt 3daa434a40 ff_add_hfyu_median_prediction_mmx2 16 years ago
David Conrad 137ae32760 Workaround for gcc 3.4 to align sh properly 16 years ago
Diego Biurrun 406792e7b0 cosmetics: Remove pointless period after copyright statement non-sentences. 16 years ago
Aurelien Jacobs 49fb20cb8a replace all occurrence of ENABLE_ by the corresponding CONFIG_, HAVE_ or ARCH_ 16 years ago
Aurelien Jacobs b250f9c66d Change semantic of CONFIG_*, HAVE_* and ARCH_*. 16 years ago
Diego Biurrun c47d146be8 Add missing 'void' keyword to parameterless function declarations. 16 years ago
Mathieu Velten 21ff7689da Use H264 MMX chroma functions to accelerate RV40 decoding. 16 years ago
Jason Garrett-Glaser 37fed10087 Add x264 SSE2 iDCT functions to H.264 decoder. 16 years ago
Carl Eugen Hoyos 2c67c65963 Fix h264 decoding on SSE2 cores with icc compilation. 16 years ago
Jason Garrett-Glaser c1fc70362f Fix compilation without optimization under 64-bit with x264 deblock asm enabled. 16 years ago
Diego Biurrun a6493a8fbd Rename libavcodec/i386/ --> libavcodec/x86/. 16 years ago
Diego Biurrun ebb160a0b0 Use ARCH_X86_32 instead of !ARCH_X86_64, it is more straightforward. 16 years ago
Jason Garrett-Glaser a22eff36f9 Port x264 deblocking code to libavcodec. 16 years ago
Michael Niedermayer ac22385931 H.264 idct functions that include the chroma, inter luma and intra16 luma loops 16 years ago
Aurelien Jacobs 5e6604490a avoid POSIX reserved _t suffix 16 years ago
Loren Merritt 5fecfb7d58 clear_block mmx 16 years ago
Diego Biurrun 9686df2be5 Delete unnecessary 'extern' keywords. 16 years ago
Dominik Mierzejewski 82d1605fe7 Remove duplicated MM_* macros for CPU capabilities from dsputil.h. 16 years ago
Diego Pettenò 782fc0c36f Rename template included sources from .h to _template.c. 16 years ago
Reimar Döffinger 31c4f07017 Use x86_reg type instead of long in float_to_int16 MMX/SSE functions. 16 years ago
David Conrad 0dba1995bc Cosmetics: reindent 16 years ago
David Conrad ca4a4ac1b3 Combine non-bitexact sections 16 years ago
David Conrad daa1ea049a VP3 loop filter is mmx2 not mmx 16 years ago
David Conrad 357f45d9bc MMX VP3 Loop Filter 16 years ago
Diego Pettenò be449fca79 Convert asm keyword into __asm__. 16 years ago
David Conrad 8cfd78ce8f Ensure MMX/SSE2 VP3 IDCT selection isn't disabled when only Theora is enabled 16 years ago
David Conrad ccd3ec82b8 MMX/SSE2 VP3 IDCT are bitexact now that the dequantization matrices are permutated correctly 16 years ago
David Conrad b4c3d83584 Use ff_vp3_idct_data in vp3dsp_mmx.c rather than duplicating it 16 years ago
David Conrad 21383da8c4 Let ff_pw_8 be used as an SSE constant 16 years ago
Loren Merritt ebceaa1cd5 gcc chokes on the 7 registers needed for float_to_int16_interleave6 (even inside HAVE_7REGS), so write it in yasm 16 years ago