summaryrefslogtreecommitdiffstats
path: root/Alc/mixer_sse.c
Commit message (Expand)AuthorAgeFilesLines
* Remove unnecessary ifdefsChris Robinson2014-05-041-2/+0
* Always use the current gains when mixingChris Robinson2014-05-041-7/+8
* Make sure all gain steps are applied with the SSE and Neon mixersChris Robinson2014-05-031-12/+13
* Use _mm_set_ps() to set an __m128 instead of {}Chris Robinson2014-04-261-2/+2
* Remove the click removal buffers for auxiliary effect slotsChris Robinson2014-03-231-1/+1
* Add gain stepping to the send mixersChris Robinson2014-03-231-23/+52
* Remove the now-unneeded click removal buffers for the deviceChris Robinson2014-03-231-1/+1
* Step mixing gains per-sample for non-HRTF mixingChris Robinson2014-03-231-15/+41
* Store the HrtfState directly in the DirectParamsChris Robinson2014-03-231-2/+2
* Use a union to combine HRTF and non-HRTF mixer paramsChris Robinson2014-03-191-1/+1
* Revert "Apply HRTF coefficient stepping separately"Chris Robinson2014-02-231-7/+53
* Apply HRTF coefficient stepping separatelyChris Robinson2013-11-101-53/+7
* Use a macro for the silence thresholdChris Robinson2013-10-061-2/+2
* Don't store the effect slot in SendParamsChris Robinson2013-10-061-16/+15
* Use a separate value for the maximum buffer channelsChris Robinson2013-07-231-2/+2
* Work around some problems with KDevelop's parserChris Robinson2013-06-181-0/+7
* Use C99's inline instead of __inlineChris Robinson2013-05-281-9/+9
* Use restrict instead of RESTRICTChris Robinson2013-05-221-13/+13
* Avoid an underflow in the SSE mixers if BufferSize is less than 4Chris Robinson2012-12-241-2/+2
* Constify the direct and send parameters given to the mixerChris Robinson2012-10-151-3/+3
* Remove the unused Device parameterChris Robinson2012-10-141-3/+1
* Store the output buffers in the DirectParams structChris Robinson2012-10-141-3/+4
* Remove the now-unused Source parameter from the DryMix methodsChris Robinson2012-10-141-2/+1
* Combine multiple loops into oneChris Robinson2012-09-241-34/+19
* Avoid mixing silence to outputChris Robinson2012-09-241-1/+11
* Remove SSE resamplers. They aren't gaining us much this way.Chris Robinson2012-09-241-92/+0
* Fix matrix multiply used by the SSE cubic resamplerChris Robinson2012-09-181-63/+22
* Explicitly give the wet buffer 1 channelChris Robinson2012-09-161-4/+4
* Check the proper value for setting WetPendingClicksChris Robinson2012-09-161-1/+1
* Avoid building redundant mixersChris Robinson2012-09-161-7/+5
* Implement an SSE MixSend methodChris Robinson2012-09-161-0/+29
* Implement an SSE cubic resamplerChris Robinson2012-09-141-0/+86
* Implement an SSE linear resamplerChris Robinson2012-09-141-0/+47
* Minor cleanups for variable declarationsChris Robinson2012-09-111-6/+3
* Use a non-interleaved DryBufferChris Robinson2012-09-111-26/+15
* Do the filtering separately from the mixingChris Robinson2012-09-111-17/+5
* Update HRTF codeChris Robinson2012-09-111-23/+86
* Use the right method to clear a __m128 to 0Chris Robinson2012-09-091-2/+2
* Use SSE to do 4 samples at once (non-HRTF direct mix), instead of to apply a ...Chris Robinson2012-09-091-22/+43
* Implement MixDirect_SSE separately from the C and Neon versionsChris Robinson2012-09-091-0/+45
* Separate the resampling and mixing stepsChris Robinson2012-09-081-8/+0
* Minor cleanups for mixer_incChris Robinson2012-08-291-6/+6
* Add an SSE-enhanced path for applying the mixer matrixChris Robinson2012-08-291-0/+15
* Apply HRTF mixer coefficients with stepping using SSEChris Robinson2012-08-151-2/+32
* Make sure the working coefficients are aligned for the SSE mixerChris Robinson2012-08-151-5/+1
* Move mixers into separate source filesChris Robinson2012-08-151-0/+48