rockbox/apps/codecs/demac/libdemac/vector_math16_armv5te.h, branch master My Rockbox tree Add codecs to librbcodec. 2012-04-25T20:13:20+00:00 Sean Bartell wingedtachikoma@gmail.com 2011-06-26T01:32:25+00:00 f40bfc9267b13b54e6379dfe7539447662879d24 Change-Id: Id7f4717d51ed02d67cb9f9cb3c0ada4a81843f97 Reviewed-on: http://gerrit.rockbox.org/137 Reviewed-by: Nils Wallménius <nils@rockbox.org> Tested-by: Nils Wallménius <nils@rockbox.org> 
Change-Id: Id7f4717d51ed02d67cb9f9cb3c0ada4a81843f97
Reviewed-on: http://gerrit.rockbox.org/137
Reviewed-by: Nils Wallménius <nils@rockbox.org>
Tested-by: Nils Wallménius <nils@rockbox.org>
Correction to clobber lists of several codec's inline assembly. 2010-05-29T15:00:10+00:00 Andree Buschmann AndreeBuschmann@t-online.de 2010-05-29T15:00:10+00:00 68054481958397a2ef348cbb19333b5c188adec9 git-svn-id: svn://svn.rockbox.org/rockbox/trunk@26376 a1c6a512-1295-4272-9138-f99709370657 
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@26376 a1c6a512-1295-4272-9138-f99709370657
Get rid of .rept in inline asm() blocks where possible. Using .rept causes gcc to wrongly estimate the size of the asm(), leading to (potential) compilation problems. This is necessary for the upcoming restructuring, and should fix ARMv6+ sim builds as well. No functional change. 2010-03-03T20:52:02+00:00 Jens Arnold amiconn@rockbox.org 2010-03-03T20:52:02+00:00 0030ae28b551df94defe25c04c1859ba508e632e git-svn-id: svn://svn.rockbox.org/rockbox/trunk@25004 a1c6a512-1295-4272-9138-f99709370657 
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@25004 a1c6a512-1295-4272-9138-f99709370657
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. 2010-02-10T23:23:17+00:00 Jens Arnold amiconn@rockbox.org 2010-02-10T23:23:17+00:00 0a291fff12c27ba6b46521ecaf126bdb4726c24e git-svn-id: svn://svn.rockbox.org/rockbox/trunk@24590 a1c6a512-1295-4272-9138-f99709370657 
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@24590 a1c6a512-1295-4272-9138-f99709370657
Resurrect the ARM7 16-bit packed vector addition/subtraction for ARMv5, giving a nice speedup for the higher compression levels (tested on Cowon D2). 2008-11-28T23:50:22+00:00 Jens Arnold amiconn@rockbox.org 2008-11-28T23:50:22+00:00 88270f7622891810bafc9404fc5dc6a7496f3f10 git-svn-id: svn://svn.rockbox.org/rockbox/trunk@19260 a1c6a512-1295-4272-9138-f99709370657 
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@19260 a1c6a512-1295-4272-9138-f99709370657
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(). 2008-11-19T21:31:33+00:00 Jens Arnold amiconn@rockbox.org 2008-11-19T21:31:33+00:00 2a5053f58c1a33334776cc90264c67dde815cef3 git-svn-id: svn://svn.rockbox.org/rockbox/trunk@19144 a1c6a512-1295-4272-9138-f99709370657 
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@19144 a1c6a512-1295-4272-9138-f99709370657
Avoid unnecessary register copies on ARMv5. 2008-11-16T10:12:38+00:00 Jens Arnold amiconn@rockbox.org 2008-11-16T10:12:38+00:00 5ba11af85595ff5bfa84bfb45151e59ce02e6309 git-svn-id: svn://svn.rockbox.org/rockbox/trunk@19112 a1c6a512-1295-4272-9138-f99709370657 
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@19112 a1c6a512-1295-4272-9138-f99709370657
Add preliminary ARMv5te optimisations (verified working, but can probably be sped up further), and fix a comment in the ARMv6 code. 2008-10-03T09:33:36+00:00 Jens Arnold amiconn@rockbox.org 2008-10-03T09:33:36+00:00 46bf6bd49301cdfe254253725b7a104b32da1061 git-svn-id: svn://svn.rockbox.org/rockbox/trunk@18693 a1c6a512-1295-4272-9138-f99709370657 
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@18693 a1c6a512-1295-4272-9138-f99709370657