Speeds up decoding of the 64 kbps test file by 2.59 MHz and the
128 kbps test file by 4.31 MHz on H300 (cf). Decoding the same
files on c200 is sped up by 0.33 MHz and 0.55 MHz respectively.
Change-Id: I0f9f9ef6a7293581cf45e3201b33c65504c95c81
The recent merge of upstream changed the fft to use C_MUL which
wasn't implemented in asm for coldfire.
Speeds up decoding 64 kbps test file by 2.68 MHz and 128 kbps
test file by 2.80 MHz on H300.
Change-Id: I8b61fc0f9568d6350431e311a12e44fe4f60f72e
Sync to commit bb4b6885a139644cf3ac14e7deda9f633ec2d93c
This brings in a bunch of optimizations to decode speed
and memory usage. Allocations are switched from using
the pseudostack to using the real stack. Enabled hacks
to reduce stack usage.
This should fix crashes on sansa clip, although some
files will not play due to failing allocations in the
codec buffer.
Speeds up decoding of the following test files:
H300 (cf) C200 (arm7tdmi) ipod classic (arm9e)
16 kbps (silk) 14.28 MHz 4.00 MHz 2.61 MHz
64 kbps (celt) 4.09 MHz 8.08 MHz 6.24 MHz
128 kbps (celt) 1.93 MHz 8.83 MHz 6.53 MHz
Change-Id: I851733a8a5824b61feb363a173091bc7e6629b58
Sync opus codec to upstream commit
02fed471a4568852d6618e041c4f2af0d7730ee2 (August 30 2013)
This brings in a lot of optimizations but also makes the diff
between our codec and the upstream much smaller as most of our
optimizations have been upstreamed or supeceded.
Speedups across the board for CELT mode files:
64kbps 128kbps
H300 9.82MHz 15.48MHz
c200 4.86MHz 9.63MHz
fuze v1 10.32MHz 15.92MHz
For the silk mode test file (16kbps) arm targets get a speedup
of about 2MHz while the H300 is 7.8MHz slower, likely because it's
now using the pseudostack more rather than the real stack which
is in iram. Patches to get around that are upcomming.
Change-Id: Ifecf963e461c51ac42e09dac1e91bc4bc3b12fa3
Speeds up decoding of 128k opus files by 1.2MHz on AMSv2. Rounding
error is 1 bit due to KissFFT using a 15 bit shift instead of a 16 bit shift.
Also, change an LDMIA in the armv4 code to LDM as the pointer should not
increment.
Change-Id: I626a207c6a056a1984e33cfe89415c35d0caed93
Reviewed-on: http://gerrit.rockbox.org/377
Reviewed-by: Michael Giacomelli <giac2000@hotmail.com>
Tested-by: Michael Giacomelli <giac2000@hotmail.com>
avoids complicated index calculations in the loops.
saves 0.3MHz decoding a 64kbps test file on h300 (cf) and
0.2MHz on c200 (pp)
Change-Id: I1918912d9a4502f89980c6bb270ec2ef10a07010
Signed-off-by: Nils Wallménius <nils@rockbox.org>
speeds up decoding of a 64kbps test_file by 1.5MHz on c200 (pp)
and 1.9MHz on fuzev1 (amsv1)
Change-Id: I1db460b634eba608c3e00541d96fc93d5a05710b
Signed-off-by: Nils Wallménius <nils@rockbox.org>
speeds up decoding of a 64kbps test file by 0.5Hz on h300 (cf)
0.9MHz on c200 (pp) and 0.2MHz on fuzev1 (amsv1)
Change-Id: Ib537c2393fa6dca0b61e4e9f80eef5e688c2c2bd
Signed-off-by: Nils Wallménius <nils@rockbox.org>
Unroll overlap add loop by four and use memcpy for copying
instead of loops.
Change-Id: I17114626a395d5972130251d892f851bc86e3a6a
Signed-off-by: Nils Wallménius <nils@rockbox.org>
Replace complicated macro doing three 16*16 muls and add an inline
asm implementation for arm, speeds up decoding a 64kbps test file
by 0.5MHz on c200 (pp) and gives slightly better precision.
Change-Id: I6fc5b83c210f01bffdc38aec54cc5a8b646d8169
Signed-off-by: Nils Wallménius <nils@rockbox.org>
Hoist load of coefficients out of the loop.
Speeds up decoding of a 64kbps test file by 0.6MHz on h300 (cf)
0.2MHz on c200 (pp) and 0.1MHz on fuzev1 (amsv1)
Signed-off-by: Nils Wallménius <nils@rockbox.org>
Change-Id: I4be0059fc2a77748575f5fc9378f7f348d64f1c4
Skip expensive multiply-accumulate loop when gains are 0 and
just copy using memcpy if soure and destination are not the same
Speeds up decoding of a 64kbps test file by 6MHz on h300 (cf)
7MHz on c200 (pp) and 6MHz on fuzev1 (amsv1)
Change-Id: Ibbc9ddfd45a9ac661467b1327b8c67761924fb8b
Signed-off-by: Nils Wallménius <nils@rockbox.org>
Reorder operands to take advantage of the early termination of
multiplications. Saves 2.5MHz decoding a 64kbps opus test file
on c200 (pp).
Change-Id: I470266dc870ab183ece3b23426d41e2a64342a71
Speeds up decoding of 64kbps test file by 6.3MHz on h300 (cf)
and 1.2MHz on c200 (pp).
Signed-off-by: Nils Wallménius <nils@rockbox.org>
Change-Id: I08c2c332153abcbef9447c81986777fd2fcc73fe
speeds up decoding of 64kbps test file by 19MHz on h300 (cf)
and 2.5MHz on c200 (pp)
Change-Id: Idacd2f8962c20c518055d586daeec6b932b7ded2
Signed-off-by: Nils Wallménius <nils@rockbox.org>
Remove downsampling code from deemphasis loop as we don't use
it and remove multiplications that are not relevant when
not using custom modes. Saves 1.4MHz on h300 (cf), 4.3MHz on
c200 (pp) and 4.6 on fuzev1 (amsv1).
Change-Id: Iab3f1d737a656a563aaa351d50db987a9cff2287
Saves about 30MHz on h300 (cf) and 1.5MHz on c200 (pp) decoding a
64kbps test file. Stack usage is still below 70%.
Change-Id: Ib13df9011adb4eef4bb91a52e5a32741c8bf8988
Speeds up decoding of a 64kbps opus test file by 34MHz on h300 (cf),
24MHz on c200 (pp) and 13MHz on fuzev1 (amsv1)
Change-Id: I0dce6b3bfe6c81d0a722dfebb13891b9a428c6ba
Synchronised with opus repo on github (https://github.com/freqmod/rockbox-opus)
Status:
* Seeking ported from speex, but fails on some cases (e.g. seek to granule 0)
* ReplayGain parsing needs to be reworked, we do vorbis-style replaygain now.
http://wiki.xiph.org/OggOpus#Comment_Header explicitly forbids these in
favour of R128_TRACK_GAIN tag.
* No optimisation yet, source files still nearly identical to opus upstream
* Multi-stream opus files may not be parsed correctly
Change-Id: Ia66f1027dc1d288083e3c57b2816700078376f9a
Reviewed-on: http://gerrit.rockbox.org/300
Reviewed-by: Bertrik Sikken <bertrik@sikken.nl>
Tested-by: Bertrik Sikken <bertrik@sikken.nl>
