diff options
| author | Chris Robinson <[email protected]> | 2018-01-07 05:32:07 -0800 |
|---|---|---|
| committer | Chris Robinson <[email protected]> | 2018-01-07 05:32:07 -0800 |
| commit | 4cc1c646466737ba411aa23ce4a6116936ada8c2 (patch) | |
| tree | 796fc698eb910630ac5f398fe38f26aef2cd456c /OpenAL32/Include/alu.h | |
| parent | 0e1fd34c89d8f09f68c2c243ceccd0dab4f7c6c0 (diff) | |
Replace the sinc4 resampler with cubic
Turns out the C version of the cubic resampler is just slightly faster than
even the SSE3 version of the FIR4 resampler. This is likely due to not using a
64KB random-access lookup table along with unaligned loads, both offseting the
gains from SSE.
Diffstat (limited to 'OpenAL32/Include/alu.h')
| -rw-r--r-- | OpenAL32/Include/alu.h | 4 |
1 files changed, 0 insertions, 4 deletions
diff --git a/OpenAL32/Include/alu.h b/OpenAL32/Include/alu.h index 625da0dc..c427df0c 100644 --- a/OpenAL32/Include/alu.h +++ b/OpenAL32/Include/alu.h @@ -396,10 +396,6 @@ inline ALfloat lerp(ALfloat val1, ALfloat val2, ALfloat mu) { return val1 + (val2-val1)*mu; } -inline ALfloat resample_fir4(ALfloat val0, ALfloat val1, ALfloat val2, ALfloat val3, const ALfloat *restrict filter) -{ - return filter[0]*val0 + filter[1]*val1 + filter[2]*val2 + filter[3]*val3; -} enum HrtfRequestMode { |