lavu/tx: support in-place FFT transforms

This commit adds support for in-place FFT transforms. Since our
internal transforms were all in-place anyway, this only changes
the permutation on the input.

Unfortunately, research papers were of no help here. All focused
on dry hardware implementations, where permutes are free, or on
software implementations where binary bloat is of no concern so
storing dozen times the transforms for each permutation and version
is not considered bad practice.
Still, for a pure C implementation, it's only around 28% slower
than the multi-megabyte FFTW3 in unaligned mode.

Unlike a closed permutation like with PFA, split-radix FFT bit-reversals
contain multiple NOPs, multiple simple swaps, and a few chained swaps,
so regular single-loop single-state permute loops were not possible.
Instead, we filter out parts of the input indices which are redundant.
This allows for a single branch, and with some clever AVX512 asm,
could possibly be SIMD'd without refactoring.

The inplace_idx array is guaranteed to never be larger than the
revtab array, and in practice only requires around log2(len) entries.

The power-of-two MDCTs can be done in-place as well. And it's
possible to eliminate a copy in the compound MDCTs too, however
it'll be slower than doing them out of place, and we'd need to dirty
the input array.

1 files changed, 3 insertions, 0 deletions

diff --git a/doc/APIchanges b/doc/APIchanges
index c353d2d281..33be750af2 100644
--- a/doc/APIchanges
+++ b/doc/APIchanges
@@ -15,6 +15,9 @@ libavutil:     2017-10-21
 
 API changes, most recent first:
 
+2021-02-21 - xxxxxxxxxx - lavu 56.66.100 - tx.h
+  Add enum AVTXFlags and AVTXFlags.AV_TX_INPLACE
+
 2021-02-14 - xxxxxxxxxx - lavd 58.12.100 - avdevice.h
   Deprecated avdevice_capabilities_create() and
   avdevice_capabilities_free().