Revision 1.13 - (view) (annotate) - [select for diffs]
2006-01-16T21:31:08Z (18 years, 5 months ago) by gbeauche
Branch: MAIN
CVS Tags: nigel-build-19
Changes since 1.12: +0 -7 lines
Diff to previous 1.12

JIT generated code is not guaranteed to be leaf, e.g. there could be a call
to a generic instruction handler (untranslated code). This caused problems
on MacOS X for Intel where the unaligned stack conditions turned out to be
more visible. Performance loss is really neglectable and this is the right
fix now anyway.

Happy New Year!

Revision 1.11 - (view) (annotate) - [select for diffs]
2004-11-08T21:10:46Z (19 years, 8 months ago) by gbeauche
Branch: MAIN
Changes since 1.10: +3 -2 lines
Diff to previous 1.10

Merge BSF simulation on P4 from Amithlon. Use 33-bit memory addressing model.

revive and fix almost two-year old port to x86_64

Revision 1.9 - (view) (annotate) - [select for diffs]
2004-01-12T15:29:30Z (20 years, 6 months ago) by cebix
Branch: MAIN
CVS Tags: nigel-build-15, nigel-build-16
Changes since 1.8: +2 -2 lines
Diff to previous 1.8

Happy New Year! :)

Implement lazy icache range invalidation. Disable for now until it shows
a real benefit over only 2%

Revision 1.7 - (view) (annotate) - [select for diffs]
2003-03-21T19:12:44Z (21 years, 3 months ago) by gbeauche
Branch: MAIN
CVS Tags: nigel-build-12, nigel-build-13
Changes since 1.6: +6 -0 lines
Diff to previous 1.6

Remove some dead code. Start implementation of optimized calls to interpretive
fallbacks for untranslatable instruction handlers. Disabled for now since
call_m_01() is not correctly imeplemented yet.

Workaround change in flags handling for BSF instruction on Pentium 4.
i.e. currently disable translation of ADDX/SUBX/B<CHG,CLR,SET,TST> instructions
in that case. That is to say, better (much?) slower than inaccurate. :-(

Revision 1.5 - (view) (annotate) - [select for diffs]
2002-10-03T16:13:46Z (21 years, 9 months ago) by gbeauche
Branch: MAIN
Changes since 1.4: +25 -0 lines
Diff to previous 1.4

JIT add copyright notices just to notify people that's real derivative
work from GPL code (UAE-JIT). Additions and improvements are from B2
developers.

Turn on block inlining so that people could test this feature and report
if they do gain something or renders JIT less stable.

Revision 1.3 - (view) (annotate) - [select for diffs]
2002-10-02T15:55:10Z (21 years, 9 months ago) by gbeauche
Branch: MAIN
Changes since 1.2: +5 -10 lines
Diff to previous 1.2

- Remove dead code in readcpu.cpp concerning CONST_JUMP control flow.
- Replace unused fl_compiled with fl_const_jump
- Implement block inlining enabled with USE_INLINING && USE_CHECKSUM_INFO.
  However, this is currently disabled as it doesn't give much and exhibits
  even more a cache/code generation problem with FPU JIT compiled code.
- Actual checksum values are now integral part of a blockinfo regardless
  of USE_CHECKSUM_INFO is set or not. Reduce number of elements in that
  structure and speeds up a little calculation of checksum of chained blocks.
- Don't care about show_checksum() for now.

- Rewrite blockinfo allocator et al. Use a template class so that this
  can work with other types related to blockinfos.
- Add new method to compute checksums. This should permit code inlining
  and follow-ups of const_jumps without breaking the lazy cache invalidator.
  aka. chain infos for checksuming. TODO: Incomplete support thus disabled.

Revision 1.1 - (view) (annotate) - [select for diffs]
2002-09-17T16:04:06Z (21 years, 9 months ago) by gbeauche
Branch: MAIN

Import JIT compiler