| Commit message (Expand) | Author | Age | Files | Lines |
* | avutil/tx_template: Use more unsigned ints to avoid undefined overflows | Michael Niedermayer | 2022-12-25 | 1 | -2/+2 |
* | lavu/tx: zero-out imaginary of last coefficient in forward RDFTs | Lynne | 2022-12-03 | 1 | -1/+1 |
* | avutil/tx: Use unsigned in ff_tx_fft_sr_combine() to avoid undefined behavior | Michael Niedermayer | 2022-11-28 | 1 | -1/+1 |
* | lavu/tx: add DCT-III implementation | Lynne | 2022-11-24 | 1 | -2/+70 |
* | lavu/tx: add DCT-II implementation | Lynne | 2022-11-24 | 1 | -0/+108 |
* | lavu/tx: fix last coefficient scaling for R2C transforms | Lynne | 2022-11-24 | 1 | -1/+1 |
* | lavu/tx: generalize PFA FFTs | Lynne | 2022-11-24 | 1 | -56/+161 |
* | lavu/tx: refactor to explicitly track and convert lookup table order | Lynne | 2022-11-24 | 1 | -27/+22 |
* | lavu/tx: allow codelets to specify a minimum number of matching factors | Lynne | 2022-11-24 | 1 | -0/+18 |
* | lavu/tx: support output stride in naive transforms | Lynne | 2022-11-24 | 1 | -2/+6 |
* | lavu/tx: add fft_inplace_small transforms | Lynne | 2022-11-24 | 1 | -3/+31 |
* | lavu/tx: support out-of-place transforms in fft_inplace | Lynne | 2022-11-24 | 1 | -6/+7 |
* | lavu/tx: make C ptwo transforms in+out of place | Lynne | 2022-11-24 | 1 | -56/+61 |
* | lavu/tx: add naive_small FFT | Lynne | 2022-11-24 | 1 | -2/+61 |
* | lavu/tx: list all odd-length FFT factors as regular codelets | Lynne | 2022-11-24 | 1 | -0/+88 |
* | lavu/tx: generalize single-factor transforms | Lynne | 2022-11-24 | 1 | -23/+23 |
* | lavu/tx: make prime factor transforms truly in-place | Lynne | 2022-11-24 | 1 | -52/+56 |
* | avutil/tx_template: Move function pointers to const memory | Andreas Rheinhardt | 2022-10-28 | 1 | -21/+26 |
* | avutil/tx_template: Avoid code duplication | Andreas Rheinhardt | 2022-10-28 | 1 | -49/+27 |
* | avutil/tx_template: Don't waste space for inexistent factors | Andreas Rheinhardt | 2022-10-28 | 1 | -2/+7 |
* | x86/tx_float: add 15xN PFA FFT AVX SIMD | Lynne | 2022-09-23 | 1 | -26/+33 |
* | lavu/tx: do not steal lookup tables of subcontexts in the iMDCT | Lynne | 2022-09-23 | 1 | -7/+6 |
* | lavu/tx: remove av_cold from table definitions | Lynne | 2022-09-11 | 1 | -3/+3 |
* | lavu/tx: rotate 3 & 15-point exptabs | Lynne | 2022-09-10 | 1 | -5/+5 |
* | lavu/tx: generalize MDCTs | Lynne | 2022-09-10 | 1 | -29/+46 |
* | lavu/tx: add the inplace flag to PFA FFTs | Lynne | 2022-09-10 | 1 | -1/+1 |
* | lavu/tx: optimize and simplify inverse MDCTs | Lynne | 2022-08-16 | 1 | -13/+37 |
* | lavu/tx: add an RDFT implementation | Lynne | 2022-01-26 | 1 | -0/+130 |
* | lavu/tx: rewrite internal code as a tree-based codelet constructor | Lynne | 2022-01-26 | 1 | -543/+864 |
* | checkasm: add av_tx FFT SIMD testing code | Lynne | 2021-04-24 | 1 | -9/+9 |
* | lavu/tx: add full-sized iMDCT transform flag | Lynne | 2021-04-24 | 1 | -1/+28 |
* | lavu/tx: add a 9-point FFT and (i)MDCT | Lynne | 2021-04-24 | 1 | -1/+143 |
* | lavu/tx: add a 7-point FFT and (i)MDCT | Lynne | 2021-04-24 | 1 | -10/+116 |
* | lavu/tx: refactor power-of-two FFT | Lynne | 2021-04-24 | 1 | -86/+78 |
* | lavu/tx: do not invert permutes on MDCTs | Lynne | 2021-02-27 | 1 | -1/+1 |
* | lavu/tx: invert permutation lookups | Lynne | 2021-02-27 | 1 | -2/+2 |
* | lavu/tx: require output argument to match input for inplace transforms | Lynne | 2021-02-26 | 1 | -1/+0 |
* | lavu/tx: support in-place FFT transforms | Lynne | 2021-02-21 | 1 | -3/+33 |
* | avutil/tx: use ENOSYS instead of ENOTSUP | James Almer | 2021-01-13 | 1 | -1/+1 |
* | lavu: support arbitrary-point FFTs and all even (i)MDCT transforms | Lynne | 2021-01-13 | 1 | -6/+95 |
* | lavu/tx: add 2-point FFT transform | Lynne | 2020-03-23 | 1 | -10/+18 |
* | lavu/tx: improve 3-point fixed precision | Lynne | 2020-02-14 | 1 | -5/+18 |
* | lavu/tx: slightly optimize fft15 | Lynne | 2020-02-13 | 1 | -2/+2 |
* | lavu/tx: undef the correct macro | Lynne | 2020-02-13 | 1 | -1/+1 |
* | lavu/tx: implement 32 bit fixed point FFT and MDCT | Lynne | 2020-02-13 | 1 | -82/+57 |
* | lavu/tx: add support for double precision FFT and MDCT | Lynne | 2019-08-02 | 1 | -0/+643 |