../
|
mathlib.hpp
|
1.11
(17 years ago)
by gbeauche:
Add throw() specs for Linux glibc platforms
|
mathlib-i386.cpp
|
1.1
(18 years ago)
by gbeauche:
Extend internal math library from GNU libc to accomodate older systems
with glibc 2.2.X or simply no C99 capable C library. Fix vrfiz instruction
to really truncate on float values.
|
mathlib-i386.hpp
|
1.2
(17 years ago)
by gbeauche:
Fix fctiw emulation (VEX's jm-ppc-test -f, handle current rounding mode)
|
mathlib-ppc.hpp
|
1.1
(17 years ago)
by gbeauche:
Fix fnmadds & fnmsubs emulation + try to provide optimized fma routines for
better precision
|
ieeefp.hpp
|
1.8
(17 years ago)
by gbeauche:
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.
|
ieeefp-mips.hpp
|
1.1
(18 years ago)
by gbeauche:
Some compilers don't permit the use of C99 extensions from C++. This is the
case for MIPSPro (IRIX) for fegetround(), isinf() et al., though they are
available in the math library.
|
mathlib-x86_64.hpp
|
1.1
(17 years ago)
by gbeauche:
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
|
mathlib.cpp
|
1.6
(17 years ago)
by gbeauche:
cosmetics
|
ieeefp-i386.cpp
|
1.5
(18 years ago)
by gbeauche:
dos2unix
|
ieeefp.cpp
|
1.3
(18 years ago)
by gbeauche:
dos2unix
|
ieeefp-i386.hpp
|
1.5
(18 years ago)
by gbeauche:
dos2unix
|
0 directories and
11 files shown