FFmpeg

Commit Graph

Author	SHA1	Message	Date
James Almer	edff061fb0	x86/swr: add ff_float_to_int32_a_avx2 13797 decicycles in ff_float_to_int32_a_sse2, 32768 runs, 0 skips 8603 decicycles in ff_float_to_int32_a_avx2, 32766 runs, 2 skips Reviewed-by: Christophe Gisquet <christophe.gisquet@gmail.com> Signed-off-by: James Almer <jamrial@gmail.com>	10 years ago
James Almer	b385c4c6a3	x86/swr: replace sse4 instructions in pack_6ch with sse ones There's no benefit from using blendps here except on CPUs with AVX, where it's faster than shufps according to Intel's documentation. As such, rename the sse4 functions to sse/sse2 and use shufps instead. Reviewed-by: Michael Niedermayer <michaelni@gmx.at> Signed-off-by: James Almer <jamrial@gmail.com>	10 years ago
James Almer	9937362c54	x86/swr: use lavu helper macros to check CPU extensions Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
James Almer	8279a15284	x86/swr: split audioconvert and rematrix DSP into separate files Also rename resample_x86_dsp.c to resample_init.c Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
James Almer	857cd1f33b	swr: initialize only the necessary resample dsp functions Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
James Almer	b5f0eac068	swr: rename swresample_dsp init functions to swri_resample_dsp The swresample_ prefix is not for internal functions Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
James Almer	c45b7f0d80	x86/swr: add ff_resample_{common, linear}_int16_xop Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
James Almer	1a69224f44	x86/swr: add ff_resample_{common, linear}_float_fma Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
James Almer	dd2c9034b1	x86/swr: convert resample_{common, linear}_double_sse2 to yasm Signed-off-by: James Almer <jamrial@gmail.com> 312531 -> 311528 dezicycles Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
Ronald S. Bultje	847bb638c0	swr: convert resample_common/linear_int16_mmx2/sse2 to yasm. Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
Ronald S. Bultje	faa1471ffc	swr: rewrite resample_common/linear_float_sse/avx in yasm. Linear interpolation goes from 63 (llvm) or 58 (gcc) to 48 (yasm) cycles/sample on 64bit, or from 66 (llvm/gcc) to 52 (yasm) cycles/ sample on 32bit. Bon-linear goes from 43 (llvm) or 38 (gcc) to 32 (yasm) cycles/sample on 64bit, or from 46 (llvm) or 44 (gcc) to 38 (yasm) cycles/sample on 32bit (all testing on OSX 10.9.2, llvm 5.1 and gcc 4.8/9). Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
Ronald S. Bultje	083cd3d1f7	swr: compile mmx2 s16p functions only on x86-32. Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
James Almer	7f4dfbd080	swr: add prototypes for resample dsp functions Should fix compilation failures with MSVC and any other compiler without inline asm support. Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
Ronald S. Bultje	ada8f9c046	swr: remove obsolete function prototypes. Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
Ronald S. Bultje	7128a35f8c	swr: split out DSP functions. DSP bits of swri_resample go into their own mini-DSP functions; DSP init goes from a per-call branch in multiple_resample to a proper DSP init routine; x86 bits go into x86/; swri_resample() moves out of resample_template.c into resample.c because it's independent of DSP code or sample type; multiple_resample() is simplified. Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
James Almer	a9bf713d35	swresample: add swri_resample_float_avx Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
Matt Oliver	1898c2f49d	inline asm: fix arrays as named constraints. Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
James Almer	4cdea92976	swresample/resample: add missing xmm clobbers Might fix fate-swr on ICL Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
James Almer	cdac3ab59f	swresample: add swri_resample_double_sse2 Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
James Almer	63dbba655e	swresample/resample: sse float linear interpolation About two times faster Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
James Almer	fa25c4c400	swresample/resample: mmx2/sse2 int16 linear interpolation About three times faster Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
James Almer	32291ba6ea	swresample: add swri_resample_float_sse At least two times faster than the C version. Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
Matt Oliver	8236747511	Automatically change MANGLE() into named inline asm operands when direct symbol reference in inline asm are not supported. This is part of the patch-set for intel C inline asm on windows support Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
James Almer	7c8bf09edd	swresample: change COMMON_CORE_INT16 asm from SSSE3 to SSE2 pshuf+paddd is slightly faster than phaddd. The real gain is in pre-ssse3 processors like AMD K8 and K10, which get a big boost in performance compared to the mmxext version Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
Martin Storsjö	3dd04cbcf7	swresample: Add arm&x86 clobber tests Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
Reimar Döffinger	cbeaf67888	Avoid using empty macro arguments. These are not supported by all compilers (gcc 2.95 but also older SPARC compilers, see gcc bug #33304 for example), and there is no real need for them. One use of this feature remains in libavdevice/v4l2.c which can't be replaced quite as easily. Signed-off-by: Reimar Döffinger <Reimar.Doeffinger@gmx.de>	11 years ago
Ronald S. Bultje	ad75d2b590	x86: Fix compilation with nasm on PPC & OS/2 Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	11 years ago
Michael Niedermayer	ca2818b881	swresample/x86/audio_convert: add emms to CONV Might fix Ticket1874 Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	12 years ago
Michael Niedermayer	4cfc92081d	swr: add native_simd_one Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	12 years ago
Michael Niedermayer	31a797eb28	swr: add av_cold to init/free functions Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	12 years ago
Carl Eugen Hoyos	a26789cf9f	Fix compilation with yasm-0.6.2.	12 years ago
Carl Eugen Hoyos	52be5428c0	Add some missing _EXTERNAL suffixes to yasm source files.	12 years ago
Michael Niedermayer	68712ce820	swr/x86: 16bit integer mix functions need SSE2 not SSE Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	c88e60af76	swr/x86: 10l, missed some SSE2 instructions in code marked as SSE. Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Clément Bœsch	ca612a27ae	swr: fix make checkheaders.	13 years ago
Clément Bœsch	022cbb6791	swr: small align cosmetic.	13 years ago
Clément Bœsch	3491c2a909	swr: use __asm__ instead of __asm. For consistency only.	13 years ago
Michael Niedermayer	4ccf6e3971	swr: MMX2 & SSSE3 int16 resample core about 4 times faster Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	5f8f6243ef	swr: fix 10l use of uninitialized data Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	728f86edfc	swr: mix_2_1_int16_mmx/sse Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	d504266cef	swr: mix_1_1_int16_sse Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	cbeeaf2593	swr: mix_1_1 int16 MMX Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	52afa43691	swr: mix_2_1_float SSE/AVX Based-on code by Justin Ruggles Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	beb0cd6acf	swr: SIMD rematrixing and SSE/AVX mix_1_1 float Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	a927641e7a	libswresample-simd: Add ff_pack_6ch_float_to_int32_a_avx and ff_pack_6ch_float_to_int32_a_sse4 Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	ca986a06ad	libswresample-simd: add ff_pack_6ch_int32_to_float_a_avx and ff_pack_6ch_int32_to_float_a_sse4 Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	c4047ad9e0	libswresample: make NOP_N macro less picky on its parameters Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	57bc91c710	libswresample: Change FLOAT_TO_INT32_N to need 1 register less same speed on sandy bridge Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	ecfdd125f1	libswresample-simd: rename 6ch pack to what it is Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	429b964e25	libswresample-simd: make the converter registers parameters Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago

1 2

75 Commits (cb58c771ade66afcc623250e1c7ac8191381d991)