len0rd/rockbox
1
0
Fork 1
mirror of https://github.com/Rockbox/rockbox.git synced 2025-11-20 02:22:43 -05:00
Code Issues Projects Releases Packages Wiki Activity Actions

Submit FS#11365. Speed up mp3 decoding on ARM processors. It is faster to use the C-implementation of dct32 compiled with -O1 as the asm implementation of dct32 compiled with -O2. Configuration for Coldfire processors is untouched. In the new configuration the stack of the COP decoding thread needs to be increased on dualcore targets. Speed is increasing by up to 0.9 MHz (-O2 against -O1 using eabi).

Browse source 
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@26746 a1c6a512-1295-4272-9138-f99709370657
This commit is contained in:
Andree Buschmann 2010-06-10 19:02:27 +00:00
parent 2c9f4fad72
commit 00e01e82cb
4 changed files with 15 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

13
apps/codecs/libmad/libmad.make
View file

@ -11,7 +11,18 @@
# (one for codec, one for mpegplayer)
# so a little trickery is necessary
MADFLAGS = $(CODECFLAGS) -UDEBUG -DNDEBUG -O2 -I$(APPSDIR)/codecs/libmad -DHAVE_LIMITS_H
# Extract optimization level ('-O') from compile flags. Will be set later.
MADFLAGS = $(filter-out -O%,$(CODECFLAGS)) -I$(APPSDIR)/codecs/libmad
MADFLAGS += -UDEBUG -DNDEBUG -DHAVE_LIMITS_H
# libmad is faster on ARM-targets with -O1 than -O2
ifeq ($(CPU),arm)
MADFLAGS += -O1
else
MADFLAGS += -O2
endif
# MPEGplayer
MPEGMADFLAGS = $(MADFLAGS) -DMPEGPLAYER
# libmad