| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| |
|
|
|
|
|
|
|
| |
This uses the following vectorisation:
for (i = 0; i < blocksize; i++) {
ang[i] = mag[i] - copysignf(fmaxf(ang[i], 0.f), mag[i]);
mag[i] = mag[i] - copysignf(fminf(ang[i], 0.f), mag[i]);
}
|
| |
|
|
| |
... for a difference between pointers.
|
| |\
| |
| |
| |
| |
| |
| | |
* commit '3956a5e0ea46ed7e27ca888fe11c47986ad99261':
aarch64: NEON vorbis_inverse_coupling
Merged-by: Michael Niedermayer <michaelni@gmx.at>
|
| | |
| |
| |
| |
| | |
From the ARMv7 NEON version. 16 times faster as the C version, overall
more than 12% faster vorbis decoding on Apple's A7.
|
| |\ \
| |/
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
* commit 'ce378f0dd0c4e5350b3280e6b3e8d6b46fe4b0a3':
fate: Use wmv2 IDCT for wmv2 tests
vorbisdsp: change block_size type from int to intptr_t.
Conflicts:
tests/fate-run.sh
tests/fate/vcodec.mak
Merged-by: Michael Niedermayer <michaelni@gmx.at>
|
| | |
| |
| |
| | |
This saves one instruction in the x86-64 assembly.
|
| |/
|
|
|
|
|
|
|
|
|
| |
* commit 'fef906c77c09940a2fdad155b2adc05080e17eda':
Move vorbis_inverse_coupling from dsputil to vorbisdspcontext.
Conflicts:
libavcodec/dsputil.c
libavcodec/x86/dsputil_mmx.c
Merged-by: Michael Niedermayer <michaelni@gmx.at>
|
|
|
Conveniently (together with Justin's earlier patches), this makes
our vorbis decoder entirely independent of dsputil.
|
