| .. |
|
crc.c
|
static/const/#include/tab police on various files
|
2009-01-02 21:43:52 +00:00 |
|
decoder.c
|
Improve libdemac SATURATE slightly on ARMv4/5, move filter buffers and code out of IRAM for sizes that aren't near realtime and extend udiv32_arm reciprocal table.
|
2010-01-30 02:20:54 +00:00 |
|
decoder.h
|
Calculate watermark from bitrate and harddisk spinup time.
|
2009-01-10 21:10:56 +00:00 |
|
demac.h
|
Calculate watermark from bitrate and harddisk spinup time.
|
2009-01-10 21:10:56 +00:00 |
|
demac_config.h
|
Put back the insane buffer where it belongs on non-ARM, and simplify the selection.
|
2010-02-04 20:20:10 +00:00 |
|
entropy.c
|
Fix decoding of stereo frames with silence in only one channel. * Make the standalone decoder contain debugging information.
|
2008-12-21 23:49:02 +00:00 |
|
entropy.h
|
Get rid of unused return values, except the one from decode_chunk() which will be used in the dual core split.
|
2008-11-26 18:01:18 +00:00 |
|
filter.c
|
libdemac: Add x86/x86_64 MMX asm for the filters. Not relevant for target but speeds up decoding on x86/x86_64 sims. Average speedup ranges from 25% for -c2000 to 3 times for -c5000; on Intel Atom it's even 45% for -c2000 to 6 times for -c5000.
|
2010-02-15 01:27:04 +00:00 |
|
filter.h
|
Get rid of unused return values, except the one from decode_chunk() which will be used in the dual core split.
|
2008-11-26 18:01:18 +00:00 |
|
filter_16_11.c
|
Calculate watermark from bitrate and harddisk spinup time.
|
2009-01-10 21:10:56 +00:00 |
|
filter_32_10.c
|
Calculate watermark from bitrate and harddisk spinup time.
|
2009-01-10 21:10:56 +00:00 |
|
filter_64_11.c
|
Calculate watermark from bitrate and harddisk spinup time.
|
2009-01-10 21:10:56 +00:00 |
|
filter_256_13.c
|
Improve libdemac SATURATE slightly on ARMv4/5, move filter buffers and code out of IRAM for sizes that aren't near realtime and extend udiv32_arm reciprocal table.
|
2010-01-30 02:20:54 +00:00 |
|
filter_1280_15.c
|
Improve libdemac SATURATE slightly on ARMv4/5, move filter buffers and code out of IRAM for sizes that aren't near realtime and extend udiv32_arm reciprocal table.
|
2010-01-30 02:20:54 +00:00 |
|
parser.c
|
|
|
|
parser.h
|
Fix decoding of stereo frames with silence in only one channel. * Make the standalone decoder contain debugging information.
|
2008-12-21 23:49:02 +00:00 |
|
predictor-arm.S
|
Remove all tabs within codec path.
|
2010-02-22 19:44:05 +00:00 |
|
predictor-cf.S
|
Implement mono predictor in assembler for coldfire, yielding a ~6% speedup for mono -c1000. Apply ideas gained from it back to the stereo predictor, saving 4 instructions. No speed increase for stereo, probably due to cache aliasing effects. * 80-column police.
|
2008-12-02 02:26:04 +00:00 |
|
predictor.c
|
Assembler optimised mono predictor for ARM. Speedup for -c1000 mono is ~5% on PP, ~8% on Gigabeat S (less for higher compression levels). Also fix some overlooked comments in the stereo predictor.
|
2008-12-09 23:20:59 +00:00 |
|
predictor.h
|
Get rid of unused return values, except the one from decode_chunk() which will be used in the dual core split.
|
2008-11-26 18:01:18 +00:00 |
|
SOURCES
|
Move udiv32_arm.S into libdemac, as this divider is specialized for the APE codec and an optimized divider is already provided for general use in codeclib.
|
2010-02-04 05:49:37 +00:00 |
|
udiv32_arm-pre.S
|
Fix yellow: add newline at EOF in udiv32_arm-pre.S
|
2010-02-04 08:55:36 +00:00 |
|
udiv32_arm.S
|
Clarify comments in ARMv6 divider regarding special-case handling of large (high bit set) numerators.
|
2010-02-20 06:29:23 +00:00 |
|
vector_math16_armv5te.h
|
APE: Fused vector math for the filters on ARMv5te. Speedup on Cowon D2 is ~4% for -c2000..-c4000 (less for -c5000). Thanks to Frank Gevaerts for testing.
|
2010-02-10 23:23:17 +00:00 |
|
vector_math16_armv6.h
|
APE: Fused vector math for the filters on ARMv6. Speedup is ~2.5% for -c2000, ~7% for -c3000 and higher.
|
2010-02-08 21:59:24 +00:00 |
|
vector_math16_cf.h
|
APE codec: Speed up decoding of -c2000 and higher on ARMv4 and coldfire by fusing vector math for the filters. Speedup is roughly 3.5% for -c2000, 8% for -c3000 and 12% for -c4000. To be extended to other architectures.
|
2010-02-02 22:50:21 +00:00 |
|
vector_math16_mmx.h
|
libdemac: Add x86/x86_64 MMX asm for the filters. Not relevant for target but speeds up decoding on x86/x86_64 sims. Average speedup ranges from 25% for -c2000 to 3 times for -c5000; on Intel Atom it's even 45% for -c2000 to 6 times for -c5000.
|
2010-02-15 01:27:04 +00:00 |
|
vector_math32_armv4.h
|
APE codec: Speed up decoding of -c2000 and higher on ARMv4 and coldfire by fusing vector math for the filters. Speedup is roughly 3.5% for -c2000, 8% for -c3000 and 12% for -c4000. To be extended to other architectures.
|
2010-02-02 22:50:21 +00:00 |
|
vector_math_generic.h
|
Several tweaks and cleanups: * Use .rept instead of repeated macros for repeating blocks. * Use MUL (variant) instead of MLA (variant) in the first step of the ARM scalarproduct() if there's no loop. * Unroll ARM assembler functions to 32 where not already done, plus the generic scalarproduct().
|
2008-11-19 21:31:33 +00:00 |
398b37124e