summaryrefslogtreecommitdiff
path: root/apps/codecs/libwmapro (follow)
Commit message (Collapse)AuthorAge
* Using icode attribute for S5L870x is faster on some codecs. Speed up for mpc ↵Andree Buschmann2010-11-02
| | | | | | is ~3%, for aac ~1%. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@28453 a1c6a512-1295-4272-9138-f99709370657
* Another minor ARM speedup for libwmapro. Drop lsb of multiplication result ↵Andree Buschmann2010-08-05
| | | | | | in fixmul31(). The difference to current implementation is +/-1 in the output signal. Same routines are used for other codecs and in the codec lib as well. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27728 a1c6a512-1295-4272-9138-f99709370657
* Minor of libwmapro on ARM. Swap operands for fixmul31, is 1% faster.Andree Buschmann2010-08-05
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27727 a1c6a512-1295-4272-9138-f99709370657
* Remove the comment about Coldfire asm. The current code (using fixmul16 ↵Mohamed Tarek2010-08-05
| | | | | | macros) is fast enough; even faster than an equivalent CF asm version, as pointed out by Nils Wallménius. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27724 a1c6a512-1295-4272-9138-f99709370657
* libwmapro: remove coldfire fixmul24 as it is both incorrect and unused, fix ↵Nils Wallménius2010-08-05
| | | | | | fixmul 31 comment. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27715 a1c6a512-1295-4272-9138-f99709370657
* update wmapro's README.Mohamed Tarek2010-08-05
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27710 a1c6a512-1295-4272-9138-f99709370657
* Fix reds. Mohamed Tarek2010-08-05
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27707 a1c6a512-1295-4272-9138-f99709370657
* oops ! shouldn't have removed mdct_tables.Mohamed Tarek2010-08-05
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27706 a1c6a512-1295-4272-9138-f99709370657
* Drop the the mdct files from libwmapro since they are no longer needed.Mohamed Tarek2010-08-05
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27705 a1c6a512-1295-4272-9138-f99709370657
* Increase wmapro decoder output sample depth to 24 bits, makes the mean error ↵Mohamed Tarek2010-08-04
| | | | | | between our output and the original floating point decoder ~5e-8. (FS#11498 by Buschel) git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27703 a1c6a512-1295-4272-9138-f99709370657
* Fix red by removing sine_512 from iram (2KB). minor slowdown for PP5024 ↵Mohamed Tarek2010-08-04
| | | | | | (~0.05MHz) on a 320kbps sample, and ~0.03MHz slowdown for Coldfire on a 55kbps sample. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27702 a1c6a512-1295-4272-9138-f99709370657
* Use codeclib's mdct in wmapro. Input coeffs to the transform needed to be ↵Mohamed Tarek2010-08-04
| | | | | | scaled down first by (log2(frame_size) - 3). Increases decoding speed by 1.3MHz on PP5022 and saves ~32KB that were previously needed by the mdct tables. (FS#11511 by Buschel and myself) git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27701 a1c6a512-1295-4272-9138-f99709370657
* Fix the sample count in wma pro.Mohamed Tarek2010-08-03
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27687 a1c6a512-1295-4272-9138-f99709370657
* Use higher precision for libwmapro's quant_tab[].Andree Buschmann2010-08-01
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27662 a1c6a512-1295-4272-9138-f99709370657
* Housekeeping for libwmapro. Define some multiple used constants, use more ↵Andree Buschmann2010-07-31
| | | | | | precise value for cos(pi/4). git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27644 a1c6a512-1295-4272-9138-f99709370657
* libwmapro: fix comment for coldfire fixmul31.Nils Wallménius2010-07-30
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27626 a1c6a512-1295-4272-9138-f99709370657
* Maintenance and minor speedup of libwmapro. Comment unused arrays, fix ↵Andree Buschmann2010-07-29
| | | | | | comment, remove tabs and introduce WMAPRO_FRACT to wma.h to remove magic numbers. Swap operands of fixmul16-call for minor speedup on ARM (+1%). git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27617 a1c6a512-1295-4272-9138-f99709370657
* Make codeclib_misc.h include the asm headers to simplify inclusion magic.Nils Wallménius2010-07-29
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27615 a1c6a512-1295-4272-9138-f99709370657
* libmwapro: use codeclib asm macros for XNPROD31, speeds up decoding of a ↵Nils Wallménius2010-07-29
| | | | | | 55kbps wma pro file by 40% on h300. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27612 a1c6a512-1295-4272-9138-f99709370657
* libwmapro: coldfire asm for vector_fixmul_scalar, 1% speedupNils Wallménius2010-07-28
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27607 a1c6a512-1295-4272-9138-f99709370657
* Refactor asm macros in libwmapro's vector_fixmul_() functions. No change to ↵Andree Buschmann2010-07-28
| | | | | | output samples. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27604 a1c6a512-1295-4272-9138-f99709370657
* Add ARM assembler to libwmapro vector_fixmul_scalar(). Speeds up decoding by ↵Andree Buschmann2010-07-28
| | | | | | 1% on PP5022. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27603 a1c6a512-1295-4272-9138-f99709370657
* Refinement of initial lowmem handling for libwmapro (r27593). Set maximum ↵Andree Buschmann2010-07-28
| | | | | | supported channels to 2 instead of 8 for low memory targets. This solution saves more RAM than the former solution and does avoid possible NULLPTR access. As add-on remove tabs. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27602 a1c6a512-1295-4272-9138-f99709370657
* Correct the scaling of the coeffs to 17bits.Mohamed Tarek2010-07-28
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27599 a1c6a512-1295-4272-9138-f99709370657
* Submit next part of FS#11498. Unroll loop for minor speedup of libwmapro on ↵Andree Buschmann2010-07-28
| | | | | | ARM (1%). git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27595 a1c6a512-1295-4272-9138-f99709370657
* Enable wmapro compilation for lowmem targets by excluding multichannel ↵Mohamed Tarek2010-07-28
| | | | | | buffers for them. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27593 a1c6a512-1295-4272-9138-f99709370657
* libwmapro: build with -O2 for coldfire, 5% speedup.Nils Wallménius2010-07-27
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27586 a1c6a512-1295-4272-9138-f99709370657
* libwmapro: tiny tweak fo coldfire fixmul24 for a very slight speedup.Nils Wallménius2010-07-27
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27585 a1c6a512-1295-4272-9138-f99709370657
* libwmapro: slightly shorter and faster inline asm fixed point multiplication ↵Nils Wallménius2010-07-26
| | | | | | routines, speedup is ~0.5%. Also don't lie to gcc about which vars are changed by the asm. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27584 a1c6a512-1295-4272-9138-f99709370657
* Modify the wma pro decoder to produce non-interleaved samples, and work ↵Mohamed Tarek2010-07-26
| | | | | | | | | directly on the buffers in WMAProDecCtx instead to avoid the redundant copying of the output data. ~10% speedup (-2MHz) on pp502x and ~1.5% speedup (-3.8Mhz) on mcf2049. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27583 a1c6a512-1295-4272-9138-f99709370657
* Submit part of FS#11498. Major speedup for WMA Professional on ARM and ↵Andree Buschmann2010-07-26
| | | | | | Coldfire CPUs. Introduce asm routines for multiplications, move arrays with major impact on decoding speed to IRAM. Speeds up decoding by 25% on PP5022 and 34% on mcf5249. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27582 a1c6a512-1295-4272-9138-f99709370657
* libwmapro: coldfire asm for vector_fixmul_window, gives a speedup of ~13%, ↵Nils Wallménius2010-07-26
| | | | | | drop the add_bias argument for the vector_fixmul_window function, since it was always 0 git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27573 a1c6a512-1295-4272-9138-f99709370657
* Increase the size of quant table in libwmapro to accomodate more values for ↵Mohamed Tarek2010-07-17
| | | | | | exp. Fixes wma pro failure on test files in download.rockbox.org/test_files. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27460 a1c6a512-1295-4272-9138-f99709370657
* libwmapro no longer needs libm in the sim; update the makefile and ↵Mohamed Tarek2010-07-17
| | | | | | README.rockbox. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27456 a1c6a512-1295-4272-9138-f99709370657
* libwmapro : remove dead/unneeded code from wma.[ch]Mohamed Tarek2010-07-17
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27455 a1c6a512-1295-4272-9138-f99709370657
* libwmapro : Rename all FIXED occurrances to int32_t and remove types.hMohamed Tarek2010-07-17
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27454 a1c6a512-1295-4272-9138-f99709370657
* More cleaning for libwmapro; use codeclib's bitstream functions and drop ↵Mohamed Tarek2010-07-17
| | | | | | those from the libwmapro. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27453 a1c6a512-1295-4272-9138-f99709370657
* Initial cleanup for libwmapro.Mohamed Tarek2010-07-15
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27425 a1c6a512-1295-4272-9138-f99709370657
* wmapro: silence some warnings related to function prototypes unused in rockboxRafaël Carré2010-07-14
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27421 a1c6a512-1295-4272-9138-f99709370657
* wmapro: don't force little endiannessRafaël Carré2010-07-14
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27420 a1c6a512-1295-4272-9138-f99709370657
* Add WMA Pro to the main build. WMA Pro now plays on target and decodes in ↵Mohamed Tarek2010-07-14
| | | | | | 151% realtime in a 320kbps sample on a sansa e200. Lots of cleanup still need to be done, and optimisations should start soon too. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27417 a1c6a512-1295-4272-9138-f99709370657
* Remove the floating point code from wmaprodec.c and change variable names ↵Mohamed Tarek2010-07-14
| | | | | | accordingly. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27416 a1c6a512-1295-4272-9138-f99709370657
* Complete the conversion of WMA Pro to fixed point. Floating point code is ↵Mohamed Tarek2010-07-12
| | | | | | still there for better history and to have a returning point in svn should something go wrong. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27402 a1c6a512-1295-4272-9138-f99709370657
* Rename/change SIMVER to APP_TYPE in the Makefiles.Thomas Martitz2010-07-10
| | | | | | | SIMVER was really only used to detect a simulator build. With APP_TYPE you can now differentiate between simulator, application, checkwps and database builds. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27372 a1c6a512-1295-4272-9138-f99709370657
* wmapro codec sim build needs to link with libmRafaël Carré2010-07-07
| | | | | | Override generic rule in libwmapro/*.make git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27336 a1c6a512-1295-4272-9138-f99709370657
* Partial conversion of the wmapro decoder to fixed point arithmetic. ↵Mohamed Tarek2010-07-05
| | | | | | | | | Currently inverse quantization & rescaling, imdct and windowing are all in fixed point. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27302 a1c6a512-1295-4272-9138-f99709370657
* Add a patch file in libwmapro to make it easier to add the library and the ↵Mohamed Tarek2010-06-21
| | | | | | decoder to the main build and modify README.rockbox accordingly. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27012 a1c6a512-1295-4272-9138-f99709370657
* Remove the stubbed main() from wmaprodec.c since it's useless now and remove ↵Mohamed Tarek2010-06-21
| | | | | | Makefile for the same reason. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27010 a1c6a512-1295-4272-9138-f99709370657
* Wrote apps/codecs/wmapro.c and modified libwmapro to make the codec work in ↵Mohamed Tarek2010-06-21
| | | | | | | | | | the sim. Neither libwmapro nor wmapro.c have been added to the main build yet, codecs.make should be edited to compile both with rockbox. current status of the decoder : - Plays and seeks in the sim - Still in floating point git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27006 a1c6a512-1295-4272-9138-f99709370657
* Fix ffmpeg revision number in libwmapro/README.rockboxMohamed Tarek2010-05-09
| | | | git-svn-id: svn://svn.rockbox.org/rockbox/trunk@25923 a1c6a512-1295-4272-9138-f99709370657
generated by cgit v1.1 at 2026-04-26 12:52:35 +0000