FFmpeg

Commit Graph

Author	SHA1	Message	Date
Derek Buitenhuis	206895708e	x86inc: Remove our FMA4 support This is so we can sync to x264's version of FMA4 support. This partialy reverts commit `79687079a9`. Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>	11 years ago
Derek Buitenhuis	15748773bf	avresample/x86: Switch operand order for mulps With the forthcoming VEX instruction emulation, mulps must have only the third operand point to memory, as this is what vmulps expects. Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>	11 years ago
Diego Biurrun	3ac7fa81b2	Consistently use "cpu_flags" as variable/parameter name for CPU flags	11 years ago
Diego Biurrun	b6649ab503	cosmetics: Remove unnecessary extern keywords from function declarations	12 years ago
Justin Ruggles	a6a3164b13	x86: lavr: add SSE2/AVX dither_int_to_float()	12 years ago
Justin Ruggles	1fb8f6a44f	x86: lavr: add SSE2 quantize() for dithering	12 years ago
Justin Ruggles	95d01c3f1c	x86: lavr: use the x86inc.asm automatic stack alignment in mixing functions CC:libav-stable@libav.org	12 years ago
Ronald S. Bultje	7a9e65acee	x86: lavr: fix stack allocation for 7 and 8 channel downmixing on x86-32 Fixes crashes on Win32 and stack overruns on x86-32 in general.	12 years ago
Diego Biurrun	2b479bcab0	build: Drop AVX assembly ifdefs An assembler able to cope with AVX instructions is now required.	12 years ago
Diego Biurrun	4b60fac419	x86: PALIGNR: port to cpuflags	12 years ago
Diego Biurrun	352e18b766	x86: avresample: Add missing colons to assembly labels YASM accepts labels without colons, but NASM issues warnings.	12 years ago
Diego Biurrun	04581c8c77	x86: yasm: Use complete source path for macro helper %includes This is more consistent with the way we handle C #includes and it simplifies the build system.	12 years ago
Diego Biurrun	6860b4081d	x86: include x86inc.asm in x86util.asm This is necessary to allow refactoring some x86util macros with cpuflags.	12 years ago
Justin Ruggles	10e645e9cb	lavr: handle clipping in the float to s32 conversion We cannot clip to INT_MAX because that value cannot be exactly represented by a float value and ends up overflowing during conversion anyway. We need to use a slightly smaller float value, which ends up with slightly inaccurate results for samples which clip or nearly clip, but it is close enough. Using doubles as intermediates in the conversion would be more accurate, but it takes about twice as much time. Signed-off-by: Luca Barbato <lu_zero@gentoo.org>	12 years ago
Diego Biurrun	e0c6cce447	x86: Replace checks for CPU extensions and flags by convenience macros This separates code relying on inline from that relying on external assembly and fixes instances where the coalesced check was incorrect.	12 years ago
Diego Biurrun	17337f54c0	x86: Split inline and external assembly #ifdefs	12 years ago
Diego Biurrun	a886b279a0	x86: cosmetics: Comment some #endifs for better readability	12 years ago
Justin Ruggles	06e751a40f	lavr: x86: optimized 6-channel flt to fltp conversion	12 years ago
Justin Ruggles	e07c9705c8	lavr: x86: optimized 2-channel flt to fltp conversion	12 years ago
Justin Ruggles	5245c9f3ad	lavr: x86: optimized 6-channel flt to s16p conversion	12 years ago
Justin Ruggles	31d0d7181d	lavr: x86: optimized 2-channel flt to s16p conversion	12 years ago
Justin Ruggles	6092dafb5a	lavr: x86: optimized 6-channel s16 to fltp conversion	12 years ago
Justin Ruggles	91851a7b37	lavr: x86: optimized 2-channel s16 to fltp conversion	12 years ago
Justin Ruggles	205ace8843	lavr: x86: optimized 6-channel s16 to s16p conversion	12 years ago
Justin Ruggles	8eeffa8ada	lavr: x86: optimized 2-channel s16 to s16p conversion	12 years ago
Justin Ruggles	b66e20d2aa	lavr: x86: optimized 2-channel fltp to flt conversion	12 years ago
Justin Ruggles	d5b4e50c47	lavr: x86: optimized 6-channel fltp to s16 conversion	12 years ago
Justin Ruggles	a58a013980	lavr: x86: optimized 2-channel fltp to s16 conversion	12 years ago
Justin Ruggles	90cc27f813	lavr: x86: optimized 6-channel s16p to flt conversion	12 years ago
Justin Ruggles	46f929adad	lavr: x86: optimized 2-channel s16p to flt conversion	12 years ago
Justin Ruggles	13df7d2d40	lavr: x86: optimized 6-channel s16p to s16 conversion	12 years ago
Justin Ruggles	c0e12535aa	lavr: x86: optimized 2-channel s16p to s16 conversion	12 years ago
Mans Rullgard	a3df4781f4	x86: add colons after labels nasm prints a warning if the colon is missing. Signed-off-by: Mans Rullgard <mans@mansr.com>	12 years ago
Justin Ruggles	e9da9a3111	lavr: x86: improve non-SSE4 version of S16_TO_S32_SX macro Removes a false dependency on existing contents of the 2nd dst register, giving better performance for OOE.	12 years ago
Justin Ruggles	2f096bb10e	lavr: add x86-optimized mixing functions Adds optimized functions for mixing 3 through 8 input channels to 1 and 2 output channels in fltp or s16p format with flt coeffs.	12 years ago
Ronald S. Bultje	30b45d9c38	x86inc: automatically insert vzeroupper for YMM functions.	12 years ago
Justin Ruggles	0dadf9d1e9	lavr: x86: add missing vzeroupper in ff_mix_1_to_2_fltp_flt()	12 years ago
Justin Ruggles	acd9948e74	lavr: x86: fix ff_conv_fltp_to_flt_6ch function prototypes Changed to match the number of parameters in conv_func_interleave(), which is how they are called. The change isn't strictly necessary because the 4th parameter is not used, but the code is clearer if they match.	13 years ago
Justin Ruggles	14a34d90ad	lavr: x86: merge some branches	13 years ago
Justin Ruggles	4e4dd71730	lavr: Add x86-optimized function for flt to s32 conversion	13 years ago
Justin Ruggles	6c63cbfe7a	lavr: Add x86-optimized function for flt to s16 conversion	13 years ago
Justin Ruggles	97ce1ba867	lavr: Add x86-optimized functions for s32 to flt conversion	13 years ago
Justin Ruggles	5904f25b9f	lavr: Add x86-optimized functions for s32 to s16 conversion	13 years ago
Justin Ruggles	d721f67d0a	lavr: Add x86-optimized functions for s16 to flt conversion	13 years ago
Justin Ruggles	1168e29df1	lavr: Add x86-optimized function for s16 to s32 conversion	13 years ago
Justin Ruggles	f61ce90caa	lavr: add x86-optimized functions for mixing 1-to-2 s16p with flt coeffs	13 years ago
Justin Ruggles	29f7490c46	lavr: add x86-optimized functions for mixing 1-to-2 fltp with flt coeffs	13 years ago
Justin Ruggles	b75726cb79	lavr: add x86-optimized function for mixing 2 to 1 s16p with q8 coeffs	13 years ago
Justin Ruggles	c140fb2cbc	lavr: add x86-optimized functions for mixing 2 to 1 s16p with float coeffs	13 years ago
Justin Ruggles	5cc6d5244d	lavr: replace the SSE version of ff_conv_fltp_to_flt_6ch() with SSE4 and AVX The current SSE version is slower than the MMX version on Athlon64 and Sandy Bridge, but the SSE4 and AVX versions are faster on Sandy Bridge.	13 years ago

1 2

53 Commits (66499f34b56fc6a9fdef25543bd9d576fc787895)