Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Remove the sinc8 resampler option | Chris Robinson | 2017-02-19 | 1 | -77/+4 |
| | | | | | Perf shows less than 1 percent CPU difference from the higher quality bsinc resampler, but uses almost twice as much memory (a 128KB lookup table). | ||||
* | Put BsincState in a generic union | Chris Robinson | 2017-02-13 | 1 | -9/+9 |
| | |||||
* | Use ALsizei and ALint for sizes and offsets with resamplers and filters | Chris Robinson | 2017-01-16 | 1 | -15/+15 |
| | |||||
* | Add some more 'restrict' keywords | Chris Robinson | 2016-10-06 | 1 | -6/+9 |
| | |||||
* | Fix placement of alignas - fixes Mac OS X build | rdb | 2016-05-03 | 1 | -6/+6 |
| | |||||
* | Implement a band-limited sinc resampler | Chris Robinson | 2015-11-05 | 1 | -3/+3 |
| | | | | | | | | This is essentially a 12-point sinc resampler, unless it's resampling to a rate higher than the output, at which point it will vary between 12 and 24 points and do anti-aliasing to avoid/reduce frequencies going over nyquist. Code provided by Christopher Fitzgerald. | ||||
* | Use the correct position in the SSE resamplers for left-over processing | Chris Robinson | 2015-10-25 | 1 | -5/+8 |
| | |||||
* | Fix the SSE4.1 resamplers | Chris Robinson | 2015-10-24 | 1 | -20/+20 |
| | | | | | Apparently the given _mm_extract_epi32 index obeys memory order, rather than component order. | ||||
* | Use the correct array indices for SSE register components | Chris Robinson | 2015-10-17 | 1 | -25/+25 |
| | | | | | | SSE uses reverse ordering, such that component 0 is the last in memory. _mm_load_* and _mm_loadu_*, and the corresponding stores, do not change the memory ordering. | ||||
* | Replace the sinc6 resampler with sinc8, and make SSE versions | Chris Robinson | 2015-10-11 | 1 | -0/+72 |
| | |||||
* | Slightly improve the FIR4 SSE resamplers | Chris Robinson | 2015-10-11 | 1 | -4/+3 |
| | |||||
* | Implement a 6-point sinc-lanczos filter | Chris Robinson | 2015-09-29 | 1 | -4/+4 |
| | |||||
* | Replace the cubic resampler with a 4-point sinc/lanczos filter | Chris Robinson | 2015-09-27 | 1 | -6/+6 |
| | |||||
* | Constify some variables | Chris Robinson | 2014-12-16 | 1 | -12/+12 |
| | |||||
* | Multiply samples with the cubic coeffs before transposing | Chris Robinson | 2014-12-15 | 1 | -6/+7 |
| | | | | This avoids having to transpose the cubic coefficients. | ||||
* | Load samples with _mm_loadu_ps in the cubic SSE resamplers | Chris Robinson | 2014-12-15 | 1 | -4/+5 |
| | |||||
* | Add SSE2 and SSE4.1 cubic resamplers | Chris Robinson | 2014-12-15 | 1 | -0/+66 |
| | |||||
* | Update COPYING to the latest ↵ | François Cami | 2014-08-18 | 1 | -2/+2 |
| | | | | https://www.gnu.org/licenses/old-licenses/lgpl-2.0.txt to fix the FSF' address Fix the FSF' address in the source | ||||
* | Update a couple sources with the proper author | Chris Robinson | 2014-06-06 | 1 | -1/+1 |
| | |||||
* | Move InitiatePositionArrays to mixer_defs.h | Chris Robinson | 2014-06-06 | 1 | -23/+2 |
| | |||||
* | Add SSE2 and SSE4.1 linear resamplers | Timothy Arceri | 2014-06-06 | 1 | -0/+103 |
Currently the only way SSE 4.1 is detected is by using __get_cpuid, i.e. with GCC. Windows' IsProcessorFeaturePresent does not report SSE4.1 capabilities. |