path: root/apps/codecs/demac/libdemac/vector_math16_armv6.h
AgeCommit message (Expand)AuthorFilesLines
2012-04-25Add codecs to librbcodec.Sean Bartell1-490/+0
2010-05-29Correction to clobber lists of several codec's inline assembly.Andree Buschmann1-3/+3
2010-03-03Get rid of .rept in inline asm() blocks where possible. Using .rept causes gc...Jens Arnold1-17/+17
2010-02-08APE: Fused vector math for the filters on ARMv6. Speedup is ~2.5% for -c2000,...Jens Arnold1-147/+348
2008-11-24Tweak the ARMv6 filter assembly a bit further.Jens Arnold1-27/+22
2008-11-19Several tweaks and cleanups: * Use .rept instead of repeated macros for repea...Jens Arnold1-57/+54
2008-10-07Another minor improvement: better pipelining and one less register used in ve...Jens Arnold1-14/+16
2008-10-07APE: Further ARMv6 filter optimisations: Save 4 'ror's per round by utilising...Jens Arnold1-81/+66
2008-10-03Further speedup for ARMv6 by better pipelining in scalarproduct().Jens Arnold1-27/+53
2008-10-03Fix static noise on armv6.Jens Arnold1-4/+3
2008-10-03Add preliminary ARMv5te optimisations (verified working, but can probably be ...Jens Arnold1-3/+1
2008-10-03Add armv6 specific asm code for the APE filters, speeding up -c2000..-c5000 a...Jens Arnold1-0/+287