Menu
▾
▴
basilisk-cvs — This list receives all CVS commit messages.
You can subscribe to this list here.
| 2001 |
Jan
(23) |
Feb
(28) |
Mar
(27) |
Apr
(12) |
May
(16) |
Jun
(43) |
Jul
(96) |
Aug
(4) |
Sep
(2) |
Oct
(8) |
Nov
|
Dec
|
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2002 |
Jan
(35) |
Feb
(13) |
Mar
(37) |
Apr
(18) |
May
(30) |
Jun
(7) |
Jul
(7) |
Aug
|
Sep
(39) |
Oct
(34) |
Nov
(11) |
Dec
(8) |
| 2003 |
Jan
(11) |
Feb
(2) |
Mar
(68) |
Apr
(15) |
May
(16) |
Jun
(9) |
Jul
(4) |
Aug
(22) |
Sep
(56) |
Oct
(58) |
Nov
(88) |
Dec
(71) |
| 2004 |
Jan
(137) |
Feb
(39) |
Mar
|
Apr
(27) |
May
(89) |
Jun
(78) |
Jul
(28) |
Aug
|
Sep
(1) |
Oct
(2) |
Nov
(98) |
Dec
(69) |
| 2005 |
Jan
(57) |
Feb
(21) |
Mar
(76) |
Apr
(12) |
May
(28) |
Jun
(89) |
Jul
(53) |
Aug
(7) |
Sep
(5) |
Oct
(3) |
Nov
(69) |
Dec
(39) |
| 2006 |
Jan
(57) |
Feb
(19) |
Mar
(19) |
Apr
(45) |
May
(85) |
Jun
|
Jul
(75) |
Aug
(1) |
Sep
|
Oct
(1) |
Nov
|
Dec
|
| 2007 |
Jan
(54) |
Feb
(5) |
Mar
|
Apr
|
May
|
Jun
(31) |
Jul
(19) |
Aug
(1) |
Sep
|
Oct
|
Nov
(7) |
Dec
(13) |
| 2008 |
Jan
(63) |
Feb
(15) |
Mar
|
Apr
|
May
|
Jun
(8) |
Jul
(3) |
Aug
|
Sep
(1) |
Oct
(1) |
Nov
(1) |
Dec
(4) |
| 2009 |
Jan
(1) |
Feb
(10) |
Mar
(6) |
Apr
(6) |
May
|
Jun
|
Jul
(16) |
Aug
(59) |
Sep
(6) |
Oct
(5) |
Nov
(9) |
Dec
|
| 2010 |
Jan
|
Feb
(9) |
Mar
(4) |
Apr
(3) |
May
(1) |
Jun
|
Jul
(7) |
Aug
(6) |
Sep
(3) |
Oct
(11) |
Nov
(1) |
Dec
(4) |
| 2011 |
Jan
|
Feb
|
Mar
(4) |
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
(39) |
| 2012 |
Jan
(21) |
Feb
(3) |
Mar
(10) |
Apr
(16) |
May
|
Jun
(14) |
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
|
From: <cv...@ce...> - 2006-07-09 12:19:54
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/cpu/ppc by gbeauche Modified Files: ppc-dyngen-ops.cpp Log Message: Some minor optimizations: xchg (unused), movdqa in sse2 code. |
|
From: <cv...@ce...> - 2006-07-09 12:15:55
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/cpu/jit by gbeauche Modified Files: basic-dyngen-ops.cpp basic-dyngen.cpp basic-dyngen.hpp dyngen-exec.h Log Message: Remove use of global register A0 (now aliased to T0). This makes it possible to cache the CPU context pointer to a register and thus rendering generated code CPU context independent. Not useful to SheepShaver, but it is for another project for threads emulation on plain x86-32. Note: AltiVec performance may drop a little on x86 but this will be restored (and even improved) in the future. |
|
From: <cv...@ce...> - 2006-07-09 12:15:54
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/cpu/ppc by gbeauche Modified Files: ppc-dyngen-ops.cpp ppc-dyngen.cpp ppc-dyngen.hpp ppc-translate.cpp Log Message: Remove use of global register A0 (now aliased to T0). This makes it possible to cache the CPU context pointer to a register and thus rendering generated code CPU context independent. Not useful to SheepShaver, but it is for another project for threads emulation on plain x86-32. Note: AltiVec performance may drop a little on x86 but this will be restored (and even improved) in the future. |
|
From: <cv...@ce...> - 2006-07-09 12:15:54
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu by gbeauche Modified Files: sheepshaver_glue.cpp Log Message: Remove use of global register A0 (now aliased to T0). This makes it possible to cache the CPU context pointer to a register and thus rendering generated code CPU context independent. Not useful to SheepShaver, but it is for another project for threads emulation on plain x86-32. Note: AltiVec performance may drop a little on x86 but this will be restored (and even improved) in the future. |
|
From: <cv...@ce...> - 2006-07-06 00:07:50
|
Update of /home/cvs/cebix/SheepShaver/src/Unix by gbeauche Modified Files: configure.ac Log Message: Use -fno-align-functions to really disable function alignment (a value of 0 used the default alignment, e.g. 16 bytes on x86_64). This is purely cosmetics and only helps reading the resulting disassembly. |
|
From: <cv...@ce...> - 2006-07-06 00:04:36
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/cpu/ppc by gbeauche Modified Files: ppc-dyngen-ops.cpp ppc-dyngen.cpp Log Message: Remove obsolete vminfp & vmaxfp (too long sequences) |
|
From: <cv...@ce...> - 2006-07-06 00:01:08
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/cpu/ppc by gbeauche
Modified Files:
ppc-dyngen-ops.cpp
Log Message:
Add more micro asm optimisations to x86{,-64} (mulhw, mulhwu, slw, srw, cntlzw
and subf* series). Also now enable the optimzations on x86_64 by default.
|
|
From: <cv...@ce...> - 2006-07-06 00:01:08
|
Update of /home/cvs/cebix/SheepShaver/src/Unix by gbeauche
Modified Files:
sysdeps.h
Log Message:
Add more micro asm optimisations to x86{,-64} (mulhw, mulhwu, slw, srw, cntlzw
and subf* series). Also now enable the optimzations on x86_64 by default.
|
|
From: <cv...@ce...> - 2006-07-04 23:27:09
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/mathlib by gbeauche Modified Files: mathlib.cpp Log Message: cosmetics |
|
From: <cv...@ce...> - 2006-07-04 23:23:44
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/mathlib by gbeauche Modified Files: mathlib.hpp Log Message: Use extra precision (e.g. long double) for fma operations though this inhibits some underflow conditions. |
|
From: <cv...@ce...> - 2006-07-04 23:20:47
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/cpu/ppc by gbeauche Modified Files: ppc-execute.hpp Log Message: Fix fmadd et al. to set FPSCR[VXISI] only if any of the multiply operands is an inifinity (2.1.5 -- don't set based on the intermediate result) |
|
From: <cv...@ce...> - 2006-07-04 23:17:41
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/cpu/ppc by gbeauche Modified Files: ppc-execute.cpp Log Message: Fix frsp FPSCR[OX] condition |
|
From: <cv...@ce...> - 2006-07-04 10:41:51
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/cpu/ppc by gbeauche Modified Files: ppc-execute.cpp Log Message: Fix mtfsb0 & mtfsb1 (VEX's xlc_dbl_u32 + code review) |
|
From: <cv...@ce...> - 2006-07-04 08:58:42
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/cpu/ppc by gbeauche Modified Files: ppc-operations.hpp Log Message: remove dead code (fdivs was never used) |
|
From: <cv...@ce...> - 2006-07-04 08:54:56
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/cpu/ppc by gbeauche Modified Files: ppc-decode.cpp Log Message: Fix mismerge from kpx branch |
|
From: <cv...@ce...> - 2006-07-04 07:19:19
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/cpu/ppc by gbeauche
Modified Files:
ppc-cpu.hpp ppc-execute.cpp ppc-execute.hpp
Log Message:
Improve FPU emulation accurracy. However, PPC_ENABLE_FPU_EXCEPTIONS is still
set to 0 until generated code is optimized enough (current slow down factor
is 3x vs. previous core, expectations are about 50% slower FP code).
The main benefit is exception bits are accurate. All glibc test-fenv,
test-arith{,f}, test-double, test-float pass on ppc, and mostly on x86_64
with gcc 4.0.1. Yes, this is also compiler dependent.
FIXME: find a real Mac application that depends on precise FPSCR bits... I
think I don't want to care optimizing yet until someone shows me a real world
application.
|
|
From: <cv...@ce...> - 2006-07-04 07:19:19
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/mathlib by gbeauche
Modified Files:
ieeefp.hpp
Log Message:
Improve FPU emulation accurracy. However, PPC_ENABLE_FPU_EXCEPTIONS is still
set to 0 until generated code is optimized enough (current slow down factor
is 3x vs. previous core, expectations are about 50% slower FP code).
The main benefit is exception bits are accurate. All glibc test-fenv,
test-arith{,f}, test-double, test-float pass on ppc, and mostly on x86_64
with gcc 4.0.1. Yes, this is also compiler dependent.
FIXME: find a real Mac application that depends on precise FPSCR bits... I
think I don't want to care optimizing yet until someone shows me a real world
application.
|
|
From: <cv...@ce...> - 2006-07-04 07:06:20
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/mathlib by gbeauche Modified Files: mathlib.hpp Added Files: mathlib-ppc.hpp Log Message: Fix fnmadds & fnmsubs emulation + try to provide optimized fma routines for better precision |
|
From: <cv...@ce...> - 2006-07-04 07:06:20
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/cpu/ppc by gbeauche Modified Files: ppc-decode.cpp ppc-operations.hpp Log Message: Fix fnmadds & fnmsubs emulation + try to provide optimized fma routines for better precision |
|
From: <cv...@ce...> - 2006-07-04 06:59:30
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/mathlib by gbeauche Added Files: mathlib-x86_64.hpp Log Message: Use lrint() for fctiw on x86-64. This is because some glibc use AMD optimized math library where floor(), ceil() et al. don't set the inexact flag correctly |
|
From: <cv...@ce...> - 2006-07-04 06:58:27
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/cpu/ppc by gbeauche Modified Files: ppc-cpu.hpp ppc-decode.cpp ppc-execute.cpp ppc-operations.hpp Log Message: Fix fctiw emulation (VEX's jm-ppc-test -f, handle current rounding mode) |
|
From: <cv...@ce...> - 2006-07-04 06:58:26
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/mathlib by gbeauche Modified Files: mathlib-i386.hpp mathlib.cpp mathlib.hpp Log Message: Fix fctiw emulation (VEX's jm-ppc-test -f, handle current rounding mode) |
|
From: <cv...@ce...> - 2006-07-04 04:47:06
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/cpu/ppc by gbeauche Modified Files: ppc-operations.hpp ppc-translate.cpp Log Message: Fix vminfp & vmaxfp emulation (VEX's jm-ppc-test -a, triggered nan bugs) |
|
From: <cv...@ce...> - 2006-07-04 04:37:17
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/cpu/ppc by gbeauche Modified Files: ppc-operations.hpp Log Message: Fix vctsxs & vctuxs emulation (VEX's jm-ppc-test -a, triggered inf/nan bugs) |
|
From: <cv...@ce...> - 2006-07-04 04:37:16
|
Update of /home/cvs/cebix/SheepShaver/src/kpx_cpu/src/mathlib by gbeauche Modified Files: ieeefp.hpp mathlib.cpp mathlib.hpp Log Message: Fix vctsxs & vctuxs emulation (VEX's jm-ppc-test -a, triggered inf/nan bugs) |
