summaryrefslogtreecommitdiff
path: root/libswresample/x86
Commit message (Collapse)AuthorAge
...
* swr/x86: 16bit integer mix functions need SSE2 not SSEMichael Niedermayer2012-07-07
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr/x86: 10l, missed some SSE2 instructions in code marked as SSE.Michael Niedermayer2012-07-05
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: fix make checkheaders.Clément Bœsch2012-06-30
|
* swr: small align cosmetic.Clément Bœsch2012-06-30
|
* swr: use __asm__ instead of __asm.Clément Bœsch2012-06-30
| | | | For consistency only.
* swr: MMX2 & SSSE3 int16 resample coreMichael Niedermayer2012-06-28
| | | | | | about 4 times faster Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: fix 10l use of uninitialized dataMichael Niedermayer2012-06-13
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: mix_2_1_int16_mmx/sseMichael Niedermayer2012-06-12
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: mix_1_1_int16_sseMichael Niedermayer2012-06-12
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: mix_1_1 int16 MMXMichael Niedermayer2012-06-12
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: mix_2_1_float SSE/AVXMichael Niedermayer2012-06-12
| | | | | Based-on code by Justin Ruggles Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: SIMD rematrixing and SSE/AVX mix_1_1 floatMichael Niedermayer2012-06-12
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* libswresample-simd: Add ff_pack_6ch_float_to_int32_a_avx and ↵Michael Niedermayer2012-05-13
| | | | | | ff_pack_6ch_float_to_int32_a_sse4 Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* libswresample-simd: add ff_pack_6ch_int32_to_float_a_avx and ↵Michael Niedermayer2012-05-13
| | | | | | ff_pack_6ch_int32_to_float_a_sse4 Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* libswresample: make NOP_N macro less picky on its parametersMichael Niedermayer2012-05-13
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* libswresample: Change FLOAT_TO_INT32_N to need 1 register lessMichael Niedermayer2012-05-13
| | | | | | same speed on sandy bridge Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* libswresample-simd: rename 6ch pack to what it isMichael Niedermayer2012-05-13
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* libswresample-simd: make the converter registers parametersMichael Niedermayer2012-05-13
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* libswresample: cosmeticsMichael Niedermayer2012-05-13
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* libswresample: unaligned AVX/SSE4 float and int32 6ch packMichael Niedermayer2012-05-13
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* libswresample: Implement MMX, SSE4 and AVX 6ch float and int32 packing function.Justin Ruggles2012-05-13
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr-x86-simd: add ff_unpack_2ch_int16_to_int16/int32/float_a_ssse3Michael Niedermayer2012-05-06
| | | | | | more than 10% faster (tested on sandybridge) Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr-x86-simd: stereo unpack S16/S32/FLT-> S16/S32/FLT SSE/SSE2 (16 new SIMD ↵Michael Niedermayer2012-05-06
| | | | | | functions) Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr-x86-simd: create prototypes with macros, this is simpler.Michael Niedermayer2012-05-06
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr-x86-SIMD: 3 instructions less for stereo planar->packed s32/flt->s16Michael Niedermayer2012-05-06
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: replace the remaining 2 audio convert SIMD macros by the new onesMichael Niedermayer2012-05-05
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: fix internal asm labelsMichael Niedermayer2012-05-05
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: fix PACK_2CH register countMichael Niedermayer2012-05-05
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: replace planar->planar/packed->packed FLT<->S16/S32 SIMD by new macrosMichael Niedermayer2012-05-05
| | | | | | this simplifies the code Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: implement stereo S16/S32/FLT->S16/S32/FLT planar->packed in SSE/SSE2Michael Niedermayer2012-05-05
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: change simd len argument to be in samples instead of dst bytes.Michael Niedermayer2012-05-05
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: add ff_int32_to_float_a_avxMichael Niedermayer2012-05-03
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: int32_to_int16_mmx/sseMichael Niedermayer2012-04-29
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: float_to_int16_sse2()Michael Niedermayer2012-04-29
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: float_to_int32_sse2()Michael Niedermayer2012-04-29
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: add int16_to_float_sse2()Michael Niedermayer2012-04-28
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: add int32_to_float_sse2Michael Niedermayer2012-04-28
| | | | | | could be done for sse/3dnow too if someone wants Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: int16->int32: use the old index negate trick to avoid 2 addsMichael Niedermayer2012-04-28
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: more correct cglobal parameters to int16->int32Michael Niedermayer2012-04-28
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: seperate functions for aligned & unalignedMichael Niedermayer2012-04-28
| | | | | | If someone has an idea on how to do this cleaner, its welcome Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: add int16_to_int32_mmx/sseMichael Niedermayer2012-04-28
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-16 08:33:06 +0000