mirror of
https://gitlab.com/libeigen/eigen.git
synced 2026-04-10 11:34:33 +08:00
376 lines
12 KiB
Plaintext
376 lines
12 KiB
Plaintext
|
/*
|
|||
|
|
* $Id: compiler.dox,v 1.24 2005/03/09 12:05:19 opetzold Exp $
|
|||
|
|
*/
|
|||
|
|
|
|||
|
|
/**
|
|||
|
|
\page compiler Compiler Support
|
|||
|
|
|
|||
|
|
<p>Contents:</p>
|
|||
|
|
- \ref requirements
|
|||
|
|
- \ref gcc
|
|||
|
|
- \ref kcc
|
|||
|
|
- \ref pgCC
|
|||
|
|
- \ref intel
|
|||
|
|
- \ref vc71
|
|||
|
|
|
|||
|
|
\section requirements General compiler Requirements
|
|||
|
|
|
|||
|
|
This library is designed for portability - no compiler specific extensions
|
|||
|
|
are used. Nevertheless, there are a few requirements: (These are all a part
|
|||
|
|
of the C++ standard.)
|
|||
|
|
|
|||
|
|
- Support for the <tt>mutable</tt> keyword is required. This is used by the
|
|||
|
|
CommaInitializer only.
|
|||
|
|
|
|||
|
|
- The <tt>typename</tt> keyword is used exhaustively here.
|
|||
|
|
|
|||
|
|
- The namespace concept is required. The tvmet library is itself is a
|
|||
|
|
namespace. To avoid collisions of operators, there is also an element_wise
|
|||
|
|
namespace within tvmet.
|
|||
|
|
|
|||
|
|
- Partial specialization is needed for the extrema functions min and max
|
|||
|
|
to distinguish between vectors and matrices. This allows tvmet to return
|
|||
|
|
an object with a specific behavior. (The location of an extremum in a
|
|||
|
|
matrix has a (row, column) position whereas a vector extremum has only a
|
|||
|
|
single index for its position).
|
|||
|
|
|
|||
|
|
\section gcc The GNU Compiler Collection
|
|||
|
|
|
|||
|
|
The <a href=http://gcc.gnu.org>GNU compiler</a> collection is mainly used for
|
|||
|
|
developing this library. Moreover, it does compile the library the fastest.
|
|||
|
|
|
|||
|
|
\subsection gcc2953 GNU C++ Compiler v2.95.3
|
|||
|
|
|
|||
|
|
Gcc v2.95.3 is the last official release of the version 2 series from gnu.org.
|
|||
|
|
Since this compiler features the \ref requirements it does work, but only
|
|||
|
|
partial.
|
|||
|
|
|
|||
|
|
There are certain difficulties - see \ref ambiguous_overload (also, please
|
|||
|
|
read about \ref gcc296). Furthermore, there are problems with functions and
|
|||
|
|
operators declared in the namespace <code>element_wise</code> - the
|
|||
|
|
compiler doesn't seem to find them--even though the compiler does know
|
|||
|
|
about namespace tvmet. It appears to be a problem with nested namespaces and
|
|||
|
|
the compiler's ability to perform function/operator lookup, especially during
|
|||
|
|
regression tests: <code> matrix /= matrix </code> compiles inside a single
|
|||
|
|
file but not at the regression tests--which is a contradiction in terms.
|
|||
|
|
|
|||
|
|
Porting to gcc v2.95.3 requires a lot of knowledge and effort--unfortunately,
|
|||
|
|
I don't have enough of either. The examples do compile and the regression
|
|||
|
|
tests build partially.
|
|||
|
|
|
|||
|
|
Matrix and vector operators are working, but don't expect too much.
|
|||
|
|
|
|||
|
|
\subsection gcc296 GNU C++ Compiler v2.96 (Rh7.x, MD8.x)
|
|||
|
|
|
|||
|
|
This compiler isn't an official release of the GNU Compiler group but shipped
|
|||
|
|
by <a href=http://www.redhat.com>Red Hat</a> and Co.
|
|||
|
|
|
|||
|
|
Blitz++ is using a hasFastAccess() flag to perform a check for the use of
|
|||
|
|
_bz_meta_vecAssign::fastAssign (without bounds checking) or
|
|||
|
|
_bz_meta_vecAssign::assign (with bounds checking). This
|
|||
|
|
isn't really necessary for operations on blitz::TinyVector, since it's
|
|||
|
|
always true. Nevertheless, it is important for the produced asm code using
|
|||
|
|
the gcc-c++-2.96-0.48mdk. Generally the code for Blitz++ using the gcc-2.96
|
|||
|
|
is better than tvmet because of this (tested!).
|
|||
|
|
|
|||
|
|
I got into trouble with stl_relops.h where miscellaneous operators are defined. A
|
|||
|
|
simple define of __SGI_STL_INTERNAL_RELOPS in the config header doesn't solve
|
|||
|
|
the problem, only the commented out header version, see \ref
|
|||
|
|
ambiguous_overload. Because of this problem, the regression tests don't
|
|||
|
|
compile with this version. Projects with do not use the relational
|
|||
|
|
operators are not affected.
|
|||
|
|
|
|||
|
|
It seems that the inlining performed by this compiler collection isn't very
|
|||
|
|
smart. I got a lot of warnings: can't inline call to ... So, it would be
|
|||
|
|
best to use the \ref gcc30x and later compilers.
|
|||
|
|
|
|||
|
|
\subsection gcc30x GNU C++ Compiler v3.0.x
|
|||
|
|
|
|||
|
|
These compiler produce better code than the \ref gcc296! Even the problems
|
|||
|
|
with blitz++ fastAssign have vanished. And this compiler conforms to the
|
|||
|
|
standard. The regression tests does compile and run successfully.
|
|||
|
|
|
|||
|
|
Due to the nature of ET and MT there is a need for a high level of inlining.
|
|||
|
|
The v3.0.x seems to do this well as compared to the v2.9x compilers which
|
|||
|
|
produce inline warnings.
|
|||
|
|
|
|||
|
|
This compiler works great with the
|
|||
|
|
<a href=http://www.stlport.org">STLPort-4.5.3</a>
|
|||
|
|
implementation of the STL/C++ Library, Tiny Vector and Matrix template library
|
|||
|
|
and <a href=http://cppunit.sourceforge.net>cpp-unit</a>.
|
|||
|
|
|
|||
|
|
\subsection gcc31x GNU C++ Compiler v3.1
|
|||
|
|
|
|||
|
|
%tvmet does compile with this new GNU C++ compiler. The produced code looks
|
|||
|
|
as good as the code created by \ref gcc30x. (Does anyone have time to make
|
|||
|
|
a benchmark?)
|
|||
|
|
|
|||
|
|
The primary goal is conformance to the standard ISO/IEC 14882:1998.
|
|||
|
|
|
|||
|
|
\subsection gcc32x GNU C++ Compiler v3.2.x
|
|||
|
|
|
|||
|
|
The once again changed Application Binary Interface (ABI) doesn't affect
|
|||
|
|
tvmet since it isn't a binary library--it's only compiled templates inside
|
|||
|
|
the client code.
|
|||
|
|
|
|||
|
|
There are some problems with the GNU C++ compiler collection on the
|
|||
|
|
regression test due to some bugs (IMO), \sa \ref regressiontest_failed.
|
|||
|
|
|
|||
|
|
\subsection gcc33x GNU C++ Compiler v3.3
|
|||
|
|
|
|||
|
|
Tested and works fine. Only some warnings on failed inlining which doesn't
|
|||
|
|
concern tvmet directly.
|
|||
|
|
|
|||
|
|
Anyway, here the code from <tt>examples/ray.cc</tt> on gcc 3.3.3 using
|
|||
|
|
<tt>-O2 -DTVMET_OPTIMIZE</tt>
|
|||
|
|
|
|||
|
|
\par Assembler (IA-32 Intel<65> Architecture):
|
|||
|
|
\code
|
|||
|
|
movl 16(%ebp), %edx
|
|||
|
|
movl 12(%ebp), %ebx
|
|||
|
|
movl 8(%ebp), %esi
|
|||
|
|
fldl 8(%edx)
|
|||
|
|
fldl 16(%edx)
|
|||
|
|
fmull 16(%ebx)
|
|||
|
|
fxch %st(1)
|
|||
|
|
movl %ebx, -24(%ebp)
|
|||
|
|
fmull 8(%ebx)
|
|||
|
|
movl %edx, -32(%ebp)
|
|||
|
|
fldl (%edx)
|
|||
|
|
fmull (%ebx)
|
|||
|
|
fxch %st(1)
|
|||
|
|
movl %edx, -60(%ebp)
|
|||
|
|
movl %edx, -12(%ebp)
|
|||
|
|
faddp %st, %st(2)
|
|||
|
|
faddp %st, %st(1)
|
|||
|
|
fadd %st(0), %st
|
|||
|
|
fstpl -56(%ebp)
|
|||
|
|
movl -56(%ebp), %ecx
|
|||
|
|
movl -52(%ebp), %eax
|
|||
|
|
movl %ecx, -20(%ebp)
|
|||
|
|
movl %eax, -16(%ebp)
|
|||
|
|
movl %ecx, -40(%ebp)
|
|||
|
|
movl %eax, -36(%ebp)
|
|||
|
|
movl %ecx, -68(%ebp)
|
|||
|
|
movl %eax, -64(%ebp)
|
|||
|
|
fldl (%edx)
|
|||
|
|
fmull -20(%ebp)
|
|||
|
|
fsubrl (%ebx)
|
|||
|
|
fstpl (%esi)
|
|||
|
|
fldl 8(%edx)
|
|||
|
|
fmull -20(%ebp)
|
|||
|
|
fsubrl 8(%ebx)
|
|||
|
|
fstpl 8(%esi)
|
|||
|
|
fldl 16(%edx)
|
|||
|
|
fmull -20(%ebp)
|
|||
|
|
fsubrl 16(%ebx)
|
|||
|
|
fstpl 16(%esi)
|
|||
|
|
addl $64, %esp
|
|||
|
|
popl %ebx
|
|||
|
|
popl %esi
|
|||
|
|
popl %ebp
|
|||
|
|
ret
|
|||
|
|
\endcode
|
|||
|
|
|
|||
|
|
\subsection gcc34x GNU C++ Compiler v3.4.x
|
|||
|
|
|
|||
|
|
The compiler 3.4.3 works fine, starting with tvmet release 1.7.1. The problem is
|
|||
|
|
the correct syntax for the CommaInitializer template declaration and
|
|||
|
|
implementation.
|
|||
|
|
|
|||
|
|
There is no assembler output for our <tt>examples/ray.cc</tt>, since I don't
|
|||
|
|
have this compiler yet (yes, I need to update my linux system ;-)
|
|||
|
|
|
|||
|
|
|
|||
|
|
\section kcc Kai C++
|
|||
|
|
|
|||
|
|
This has not been tested. Unfortunately Kai's compiler is no longer shipped
|
|||
|
|
-- one should use the Intel compiler instead
|
|||
|
|
(see <a href=http://www.kai.com>here</a>).
|
|||
|
|
|
|||
|
|
If you have used it successfully including regression and/or benchmark tests,
|
|||
|
|
please give me an answer.
|
|||
|
|
|
|||
|
|
\section pgCC Portland Group Compiler Technology
|
|||
|
|
|
|||
|
|
\subsection pgCC32 Portland Group C++ 3.2
|
|||
|
|
|
|||
|
|
The <a href=http://www.pgroup.com>Portland Group</a> C++ compiler is shipped
|
|||
|
|
with the RogueWave Standard C++ Library which provides conformance to the
|
|||
|
|
standard. Unfortunately, the <cname> C library wrapper headers and the C++
|
|||
|
|
overloads of the math functions are not provided on all platforms, see
|
|||
|
|
<http://www.cug.com/roundup>. The download evaluation version 3.2-4 for
|
|||
|
|
Linux is affected for example. At first glance, it does compile with pgCC
|
|||
|
|
since it has has the great <a href=http://www.edg.com>EDG</a> front-end.
|
|||
|
|
|
|||
|
|
Maybe there is a solution with other standard library implementations like
|
|||
|
|
<a href=http://www.stlport.org>STLPort</a> (On a quick try the STL Port
|
|||
|
|
doesn't recognize the pgCC). If you know more about this, please let me know.
|
|||
|
|
|
|||
|
|
Anyway, the code produced is very poor even if I use high inlining levels
|
|||
|
|
like the command line option -Minline=levels:100 which increases the compile
|
|||
|
|
time dramatically! The benchmark tests have not been done. Unfortunately,
|
|||
|
|
my trial period has expired. I haven't any idea if this compiler will pass
|
|||
|
|
the regression tests.
|
|||
|
|
|
|||
|
|
\subsection pgCC51 Portland Group C++ 5.1
|
|||
|
|
|
|||
|
|
The <a href=http://www.pgroup.com>Portland Group</a> C++ compiler is shipped
|
|||
|
|
with the <a href=http://www.stlport.org>STLport</a> Standard C++ Library, cool!
|
|||
|
|
|
|||
|
|
The code produced isn't very compact compared with the intel or gnu compiler.
|
|||
|
|
Anyway it works, but the compiler time increases dramatically
|
|||
|
|
even on higher inline levels.
|
|||
|
|
|
|||
|
|
|
|||
|
|
\section intel Intel Compiler
|
|||
|
|
|
|||
|
|
\subsection icc5 Intel Compiler v5.0.1
|
|||
|
|
|
|||
|
|
This compiler complains even more than gcc-3.0.x regarding template
|
|||
|
|
specifiers (e.g. correct spaces for template arguments to std::complex are
|
|||
|
|
needed even when not instanced).
|
|||
|
|
|
|||
|
|
The produced code looks good but, I haven't done a benchmark to compare it
|
|||
|
|
with the gcc-3.0.x since the compile time increases for the benchmark test
|
|||
|
|
dramatically.
|
|||
|
|
|
|||
|
|
I have not run any regression tests due to the compile time needed by my
|
|||
|
|
AMD K6/400 Linux box ...
|
|||
|
|
|
|||
|
|
\subsection icc6 Intel Compiler v6.0.x
|
|||
|
|
|
|||
|
|
Should work, but I haven't tested it.
|
|||
|
|
|
|||
|
|
\subsection icc7 Intel Compiler v7.x
|
|||
|
|
|
|||
|
|
This compiler is well supported by tvmet and passes the regression tests
|
|||
|
|
without any failure - as opposed to the GNU C++ compiler collection.
|
|||
|
|
|
|||
|
|
\subsection icc8 Intel Compiler v8.x
|
|||
|
|
|
|||
|
|
No regression tests are done - reports are welcome. I'm not expecting
|
|||
|
|
problems. Anyway, this versions uses pure macros for IEEE math isnan and
|
|||
|
|
isinf. This prevents overwriting with tvmet's functions. Therefore
|
|||
|
|
this functions are disabled after tvmet release 1.4.1. The code produced
|
|||
|
|
is even on <tt>examples/ray.cc</tt> more compact than the \ref gcc33x.
|
|||
|
|
|
|||
|
|
Anyway, here the code from <tt>examples/ray.cc</tt> using
|
|||
|
|
<tt>-O2 -DTVMET_OPTIMIZE</tt>
|
|||
|
|
|
|||
|
|
\par Assembler (IA-32 Intel<65> Architecture):
|
|||
|
|
\code
|
|||
|
|
movl 4(%esp), %ecx
|
|||
|
|
movl 8(%esp), %edx
|
|||
|
|
movl 12(%esp), %eax
|
|||
|
|
fldl (%edx)
|
|||
|
|
fmull (%eax)
|
|||
|
|
fldl 8(%edx)
|
|||
|
|
fmull 8(%eax)
|
|||
|
|
fldl 16(%edx)
|
|||
|
|
fmull 16(%eax)
|
|||
|
|
faddp %st, %st(1)
|
|||
|
|
faddp %st, %st(1)
|
|||
|
|
fldl (%eax)
|
|||
|
|
fxch %st(1)
|
|||
|
|
fadd %st(0), %st
|
|||
|
|
fmul %st, %st(1)
|
|||
|
|
fxch %st(1)
|
|||
|
|
fsubrl (%edx)
|
|||
|
|
fstpl (%ecx)
|
|||
|
|
fldl 8(%eax)
|
|||
|
|
fmul %st(1), %st
|
|||
|
|
fsubrl 8(%edx)
|
|||
|
|
fstpl 8(%ecx)
|
|||
|
|
fldl 16(%eax)
|
|||
|
|
fmulp %st, %st(1)
|
|||
|
|
fsubrl 16(%edx)
|
|||
|
|
fstpl 16(%ecx)
|
|||
|
|
ret
|
|||
|
|
\endcode
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
\section vc71 Microsoft Visual C++ v7.1
|
|||
|
|
|
|||
|
|
\htmlonly
|
|||
|
|
<script language="JavaScript">
|
|||
|
|
var m_name="blbounnejapny";
|
|||
|
|
var m_domain="hotmail.com";
|
|||
|
|
var m_text='<a href="mailto:'+m_name+'@'+m_domain+'?subject=tvmet and Microsoft VC++">';
|
|||
|
|
m_text+='Robi Carnecky</a>';
|
|||
|
|
document.write(m_text);
|
|||
|
|
</script>
|
|||
|
|
\endhtmlonly
|
|||
|
|
\latexonly
|
|||
|
|
Robi Carnecky <blbounnejapny@hotmail.com>
|
|||
|
|
\endlatexonly
|
|||
|
|
has reported the success on tvmet using Visual C++ v7.1. At this
|
|||
|
|
release of tvmet there are some warnings left - the work is on
|
|||
|
|
progress.
|
|||
|
|
|
|||
|
|
The <a href="http://msdn.microsoft.com/visualc/vctoolkit2003/">Microsoft Visual C++ Toolkit 2003</a>
|
|||
|
|
and Visual C++ prior 7.1 do not compile - you will get an undefined
|
|||
|
|
internal error unfortunally.
|
|||
|
|
|
|||
|
|
Anyway, here the code from <tt>examples/ray.cc</tt>:
|
|||
|
|
|
|||
|
|
\par Assembler (IA-32 Intel<65> Architecture, no SSE2):
|
|||
|
|
\code
|
|||
|
|
push ebp
|
|||
|
|
mov ebp, esp
|
|||
|
|
and esp, -8 ; fffffff8H
|
|||
|
|
sub esp, 28 ; 0000001cH
|
|||
|
|
mov eax, DWORD PTR _ray$[ebp]
|
|||
|
|
mov ecx, DWORD PTR _surfaceNormal$[ebp]
|
|||
|
|
fld QWORD PTR [eax+16]
|
|||
|
|
fmul QWORD PTR [ecx+16]
|
|||
|
|
push ebx
|
|||
|
|
fld QWORD PTR [eax+8]
|
|||
|
|
push esi
|
|||
|
|
fmul QWORD PTR [ecx+8]
|
|||
|
|
push edi
|
|||
|
|
mov edi, DWORD PTR $T35206[esp+52]
|
|||
|
|
faddp ST(1), ST(0)
|
|||
|
|
mov DWORD PTR $T35027[esp+60], edi
|
|||
|
|
fld QWORD PTR [eax]
|
|||
|
|
pop edi
|
|||
|
|
fmul QWORD PTR [ecx]
|
|||
|
|
faddp ST(1), ST(0)
|
|||
|
|
fadd ST(0), ST(0)
|
|||
|
|
fstp QWORD PTR $T35206[esp+36]
|
|||
|
|
mov esi, DWORD PTR $T35206[esp+40]
|
|||
|
|
mov edx, DWORD PTR $T35206[esp+36]
|
|||
|
|
mov ebx, DWORD PTR $T35265[esp+40]
|
|||
|
|
mov DWORD PTR $T35027[esp+44], edx
|
|||
|
|
mov edx, DWORD PTR _reflection$[ebp]
|
|||
|
|
mov DWORD PTR $T35027[esp+48], esi
|
|||
|
|
fld QWORD PTR $T35027[esp+44]
|
|||
|
|
fmul QWORD PTR [ecx]
|
|||
|
|
pop esi
|
|||
|
|
mov DWORD PTR $T35027[esp+36], ebx
|
|||
|
|
pop ebx
|
|||
|
|
fsubr QWORD PTR [eax]
|
|||
|
|
fstp QWORD PTR [edx]
|
|||
|
|
fld QWORD PTR $T35027[esp+36]
|
|||
|
|
fmul QWORD PTR [ecx+8]
|
|||
|
|
fsubr QWORD PTR [eax+8]
|
|||
|
|
fstp QWORD PTR [edx+8]
|
|||
|
|
fld QWORD PTR $T35027[esp+36]
|
|||
|
|
fmul QWORD PTR [ecx+16]
|
|||
|
|
fsubr QWORD PTR [eax+16]
|
|||
|
|
fstp QWORD PTR [edx+16]
|
|||
|
|
mov esp, ebp
|
|||
|
|
pop ebp
|
|||
|
|
\endcode
|
|||
|
|
|
|||
|
|
\sa \ref regressiontest_failed
|
|||
|
|
\sa \ref install_win
|
|||
|
|
*/
|
|||
|
|
|
|||
|
|
|
|||
|
|
// Local Variables:
|
|||
|
|
// mode:c++
|
|||
|
|
// End:
|