Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Don't use al::vector where not needed | Chris Robinson | 2023-10-12 | 1 | -5/+3 |
| | |||||
* | Make and use a separate zconvolve method without scaling | Chris Robinson | 2023-10-11 | 1 | -3/+76 |
| | | | | | | When you're doing hundreds or thousands of separate zconvolve calls into the same buffer, it's more efficient to do the multiply once at the end instead of in each call. | ||||
* | Fix conversion warnings | Chris Robinson | 2023-10-10 | 1 | -19/+21 |
| | |||||
* | Fix array lookup index | Chris Robinson | 2023-10-10 | 1 | -2/+3 |
| | |||||
* | Use size_t and uint for non-negative values and indices | Chris Robinson | 2023-10-10 | 1 | -208/+208 |
| | |||||
* | Use an anonymous namespace instead of static functions | Chris Robinson | 2023-10-10 | 1 | -194/+202 |
| | |||||
* | Combine some VADD(VMUL(... to VMADD(... | Chris Robinson | 2023-10-10 | 1 | -43/+43 |
| | |||||
* | Use a bool instead of an int for 0/1 | Chris Robinson | 2023-10-09 | 1 | -25/+27 |
| | | | | Also update some comments. | ||||
* | Cleanup PFFFT | Chris Robinson | 2023-10-09 | 1 | -571/+604 |
| | | | | | | Make stylization more consistent. Remove SVMUL (they all simulated it with a LD_PS1 on the scalar). Avoid calling LD_PS1 on the same value in a loop. | ||||
* | Remove more type-punning from pffft | Chris Robinson | 2023-10-08 | 1 | -52/+63 |
| | |||||
* | Clean up some more type-punning in pffft | Chris Robinson | 2023-10-08 | 1 | -22/+42 |
| | |||||
* | Avoid some type-punning and clean up pffft a bit | Chris Robinson | 2023-10-08 | 1 | -161/+148 |
| | |||||
* | Update and clarify some comments | Chris Robinson | 2023-10-07 | 1 | -4/+4 |
| | |||||
* | Add a generic GCC vector extension fallback for pffft | Chris Robinson | 2023-10-06 | 1 | -13/+80 |
| | | | | Also combine multiple allocations into one. | ||||
* | Fix x86-64 MSVC check | Chris Robinson | 2023-10-06 | 1 | -1/+1 |
| | |||||
* | Include a copy of PFFFT | Chris Robinson | 2023-10-06 | 1 | -0/+2021 |
This is a notably faster FFT implementation for 32-bit float signals, provided under a 3-clause BSD license. |