Changes between Version 32 and Version 33 of QtBackLog


Ignore:
Timestamp:
Nov 14, 2009 12:24:41 PM (14 years ago)
Author:
zecke@selfish.org
Comment:

Mention individual commits

Legend:

Unmodified
Added
Removed
Modified
  • QtBackLog

    v32 v33  
    22
    33=== Qt problems ===
    4 ||Description||Branch||Created on||Landed in||Landed Date||
    5 ||~~ARM optimized qdrawhelper is only enabled for RCVT (symbian)~~ A pure armv4/C implementation was used giving a significant improvement too. The ARMv4 memfill implementation gave about a 1fps improvement. What is left is ARM neon code for the porter duff operations|| || || || ||
    6 ||The C version comp_func_SourceOver was improved giving a 10fps improvement on the test case.||[http://qt.gitorious.org/~zecke/qt/zeckes-qt/commits/merge/arm-asm-changes arm-asm-changes]||09.11.2009|| || ||
    7 ||ARMv6 should be auto detected. Currently arm/armv6 can be passed as -embedded options. The benefit of ARMv6 in src/corelib is the use of atomic load and exchange, instead of the old "swap" extension. `__ARCH_ARM_6__` should be used to detect it. The first part of ARM detection was done||[http://qt.gitorious.org/~zecke/qt/zeckes-qt/commits/merge/arm-asm-changes arm-asm-changes]||9.11.2009|| || ||
    8 ||Enabled pld (preload) in qdrawhelper for ARMv5te and upwards -- For GNU CC the arm revision is detected automatically and this gave a 1fps improvement.||[http://qt.gitorious.org/~zecke/qt/zeckes-qt/commits/merge/arm-asm-changes arm-asm-tweaks]||9.11.2009|| || ||
     4||Description||Branch/Commit||Created on||Landed in||Landed Date||
     5||What is left is ARM neon code for the porter duff operations.|| || || ||
     6||~~ARM optimized qdrawhelper is only enabled for RCVT (symbian)~~ A pure armv4/C implementation was used giving a significant improvement too. The ARMv4 memfill implementation gave about a 1fps improvement. ||[http://qt.gitorious.org/~zecke/qt/zeckes-qt/commit/c51c85dd3aa4a920f363e315ef4512f1d97401b3 memfill] ||9.11.09|| || ||
     7||The C version comp_func_SourceOver was improved giving a 10fps improvement on the test case.||[http://qt.gitorious.org/~zecke/qt/zeckes-qt/commit/a69e152dcc704eff6b7e409ad1ed43f732e6be9c a69e1] [http://qt.gitorious.org/~zecke/qt/zeckes-qt/commit/7f379c05ea9e6b60c081af2c18a84ec290af2df4 7f379c]||09.11.2009|| || ||
     8||ARMv6 should be auto detected. Currently arm/armv6 can be passed as -embedded options. The benefit of ARMv6 in src/corelib is the use of atomic load and exchange, instead of the old "swap" extension. `__ARCH_ARM_6__` should be used to detect it. The first part of ARM detection was done||[http://qt.gitorious.org/~zecke/qt/zeckes-qt/commit/50b67cf1f47d2caa5b876175129ff8943cba616a 50b67]||9.11.2009|| || ||
     9||Enabled pld (preload) in qdrawhelper for ARMv5te and upwards -- For GNU CC the arm revision is detected automatically and this gave a 1fps improvement.||[http://qt.gitorious.org/~zecke/qt/zeckes-qt/commit/b2d17d7c4ecd31cba36ef79909e2e819217a0971 b2d17d]||9.11.2009|| || ||
    910||Optimize scrolling of Windowsurfaces. Either optimize memcpy/memmove or consider using a tile based window surface|| || || || ||
    1011||QImageReader deserves some optimatations. E.g. decode to the QImage provided to the decoder, do not parse every gif when trying to determine the size.||[http://qt.gitorious.org/~zecke/qt/zeckes-qt/commits/merge/qimagehandler-changes image-changes]|| || || ||