ports/openmpi
ports/openmpi
1
1
Форкнуть 0
Код Релизы Активность
10 268 коммитов 3 Ветки 0 Теги
Граф коммитов

800 Коммитов

Автор SHA1 Сообщение Дата
George Bosilca
163391d71a Cleanup the win32 stuff. Add some more definition for UNIX compatibility. There 
is still an issue with the OMPI_DECLSPEC but I will investigate it a little
bit later.

This commit was SVN r8614.
 2005-12-31 12:23:28 +00:00
Jeff Squyres
6770facf59 Remove "static inline" from a prototype of a function that isn't 
static inline.

This commit was SVN r8587.
 2005-12-22 05:34:36 +00:00
George Bosilca
b88f2a3c32 More protection around the atomic operations on Windows. Still ahve to find 
a way to detect them correctly without popping up a Windows error message box.

This commit was SVN r8586.
 2005-12-22 00:13:09 +00:00
George Bosilca
b6036d985b Updated version of the windows compatibility file. 
This commit was SVN r8585.
 2005-12-22 00:10:56 +00:00
Jeff Squyres
f1e8790bbe Add remaining OPAL error codes in opal_err2str() 
This commit was SVN r8573.
 2005-12-21 06:27:34 +00:00
Brian Barrett
3f6c409164 * Need to specify link order to make sure we grab the right mmap 
This commit was SVN r8556.
 2005-12-20 00:50:47 +00:00
Brian Barrett
08799e4a48 * Make the format of the --with-BTL options the same for all the BTLs 
* Make sure --without-BTL works for all BTLs
* Fix copy-n-paste error in aix timer configrue help string

This should go to the v1.0 branch

This commit was SVN r8554.
 2005-12-20 00:47:36 +00:00
Brian Barrett
f993b3a1f0 * 1, 0, they're all the same... 
This commit was SVN r8550.
 2005-12-19 22:01:56 +00:00
Brian Barrett
7801b9045f temporarily bring back the malloc_hooks code so that Galen and I can do 
some regression testing

This commit was SVN r8548.
 2005-12-19 21:08:51 +00:00
Brian Barrett
22d058e67c make windows component prefered over linux component. Cygwin provides a 
/proc/cpuinfo (which is weird), so the Linux component was getting selected
when on Windows...

This commit was SVN r8543.
 2005-12-19 06:55:01 +00:00
Brian Barrett
70f4c0f281 update WIN32 defines to __WINDOWS__ 
This commit was SVN r8542.
 2005-12-19 05:43:40 +00:00
Brian Barrett
aca7c97451 properly build when we don't have any ASM support (ie Windows w/ CL compiler) 
This commit was SVN r8541.
 2005-12-19 05:39:07 +00:00
Brian Barrett
a5af07cd6b fixes suggested by Ralf for supporting both Libtool 1 and 2 in Open MPI... 
This commit was SVN r8538.
 2005-12-19 03:10:23 +00:00
George Bosilca
4d1be7f4fe Add the win32 directory to the build system but only if we build on 
Windows.

This commit was SVN r8535.
 2005-12-17 22:09:23 +00:00
George Bosilca
958bba0f99 mca_base_param_find should be exported. 
This commit was SVN r8534.
 2005-12-17 22:08:02 +00:00
George Bosilca
08d33cfd52 Cleanups for the windows helpers. They will get included on the next commit. 
This commit was SVN r8533.
 2005-12-17 22:07:04 +00:00
Brian Barrett
5685144e3d * update darwin memory hooks code to recent changes in API 
This commit was SVN r8522.
 2005-12-16 02:01:38 +00:00
Brian Barrett
b42bb3d8e8 More memory hooks tweaks... Set a flag on callbacks if the allocation / 
deallocation came from the allocator (malloc, fee, etc) or somewhere
else (the user calling mmap/munmap, etc).  Going to be used by Galen
to determine if it is worth searching the allocations tree

Set flag if it is possible to intercept mmap (not always possible
due to a circular dependency between mmap, dlsym, and calloc)

This commit was SVN r8521.
 2005-12-16 01:12:45 +00:00
Brian Barrett
2a94f693f6 * make sure to actually add the ptmalloc2-specific library dependencies to 
LIBADD, so that libtool does it's magic propogation thing...

This commit was SVN r8508.
 2005-12-15 18:11:51 +00:00
Jeff Squyres
6bc6178e8d Make the comment explain much more fully what is going on (in typical 
Jeff-length).  Also change it such that we also have a lt_dlhandle
type -- even in the case of --disable-dlopen.  Specifically, even in
the case of --disable-dlopen, we still have shell functions that use
an lt_dlhandle parameter, so we need that type, even if <ltdl.h> isn't
used.

This commit was SVN r8507.
 2005-12-15 17:47:54 +00:00
Brian Barrett
e574fd7fbe - update some svn ignores 
- don't fail to configure if threads aren't found, since
  we don't have thread support on windows
- rather than setting the asm file name to none in asm-data,
  special case windows w/ CL in the ompi_config_asm macros.
  Otherwise, there were some warnings during make dist and
  configure that didn't need to be there.

This commit was SVN r8502.
 2005-12-15 04:19:16 +00:00
Brian Barrett
e8cca1710f couple of changes to make Open MPI compile under Cygwin with gcc: 
- add the right asm format
  - add checks for some constants / fields that cygwin
    doesn't have in the stacktrace code
  - fix for slightly more verbose libtool 2 betas that
    have multiple lines for link output

This commit was SVN r8501.
 2005-12-15 00:51:28 +00:00
Brian Barrett
01e7191c3e * use our memory barriers instead of ptmalloc2's, since it only does the 
right thing with gcc on x86.

This commit was SVN r8490.
 2005-12-13 16:04:48 +00:00
Rainer Keller
e59291ebd3 - As I got a conflict for doing the same thing due to problems on SX, 
decided check in...
   Protect also stdio.h

This commit was SVN r8486.
 2005-12-13 08:05:41 +00:00
George Bosilca
c9c9a6df61 A line for WINDOWS asm support ... yes none at the moment. Most of the 
functions we generate from assembler are available on windows.

This commit was SVN r8485.
 2005-12-13 06:18:39 +00:00
George Bosilca
cf09491da5 Remove all useless header as well as those generating name conflicts (io.h). 
This commit was SVN r8484.
 2005-12-13 06:17:15 +00:00
George Bosilca
af39262a66 I hope I get it right this time. We detect at configure time if the current 
Windows installation provide the 32 and 64 bits atomic operations and compile
only the relevant part. For 64 bits there is a problem, but I already put a
big comment about it in the configure file ...

This commit was SVN r8480.
 2005-12-13 06:08:45 +00:00
George Bosilca
30648c55ff First version of the paffinity for Windows. We detect correctly if the 
functions are available in the .h file as well as the kernel32.dll but
we generate empty functions.

This commit was SVN r8478.
 2005-12-13 06:04:41 +00:00
George Bosilca
3e03a5f702 A better comment I hope ... 
This commit was SVN r8477.
 2005-12-12 23:39:40 +00:00
George Bosilca
ed234c910f The compare and set return an int (always). 
This commit was SVN r8476.
 2005-12-12 23:17:04 +00:00
George Bosilca
39e8d4ce02 Protect the function definition not the typedef. 
This commit was SVN r8475.
 2005-12-12 22:33:02 +00:00
George Bosilca
6f3ac068a6 Use Windows functions ... Microsoft complain about a bunch of POSIX functions as being 
deprecated. They offer the _ version as not deprecated, so let's use what they provide.

This commit was SVN r8470.
 2005-12-12 22:04:30 +00:00
George Bosilca
c107d02eee Miss this one on the last commit. 
This commit was SVN r8469.
 2005-12-12 22:02:42 +00:00
George Bosilca
bd0ee62e62 Protect headers and use __WINDOWS__ for Windows code. 
This commit was SVN r8468.
 2005-12-12 22:01:51 +00:00
George Bosilca
8c71f578da The real timer in Windows is a long long. 
This commit was SVN r8467.
 2005-12-12 21:52:53 +00:00
George Bosilca
6e5aeab0b5 Remove the dependance to ltdl.h for all the the places where we dont't really need it. Read 
the comment for more informations.

This commit was SVN r8466.
 2005-12-12 21:51:20 +00:00
George Bosilca
1f342275a0 Support the atomic.h and timer.h header files. 
This commit was SVN r8462.
 2005-12-12 19:52:13 +00:00
Brian Barrett
d8d67b618f don't intercept mmap if we have to use dlsym to get at the real mmap. dlsym 
may call calloc(large number), which causes ptmalloc2 to call mmap, which
causes us to try to dlsym for mmap, which leads to looping badness.

This commit was SVN r8461.
 2005-12-12 19:38:42 +00:00
George Bosilca
436ef18ec2 Adding high performance timers for windows (the same as for Linux we use the counters from 
the processor).

This commit was SVN r8458.
 2005-12-12 17:27:48 +00:00
Brian Barrett
6c4ac2299c fix typo in release hooks if calling for every malloc/free 
This commit was SVN r8431.
 2005-12-10 05:06:52 +00:00
George Bosilca
699653f733 Typo correction. 
This commit was SVN r8427.
 2005-12-09 05:17:27 +00:00
Brian Barrett
0348d02875 * need to expose posix_memalign so that the one in our ptmalloc2 is used 
instead of the one in libc.  Thanks to Gleb Natapov for tracking this
  down.

This commit was SVN r8418.
 2005-12-08 18:06:52 +00:00
George Bosilca
d145902b17 Move all win32 related files in opal, and modify all the Makefiles.am to 
include the change.

This commit was SVN r8412.
 2005-12-08 06:17:15 +00:00
Brian Barrett
364ca3f075 - Add configure-time switch (--enable-ptmalloc2-opt-sbrk) to control when 
the ptmalloc2 memory hooks component triggers callbacks for memory
  allocation / deallocation.  If enabled (the default) it is only when
  memory is actually obtained from or released to the OS (so little
  malloc calls only trigger callbacks if sbrk is called).  If disabled,
  callbacks are triggered every time malloc/free/etc. is called
* It turns out that syscall and mmap aren't good friends due to the return
  type of mmap and some old legacy issues with syscall functions that
  take more than 5 parameters.  For now, default to either loading
  the symbol from glibc using dlsym or using the __m{un,}map functions.
  Thanks to George for finding this.
* Fix some dumb typos in the mmap / munmap catching code

This commit was SVN r8410.
 2005-12-08 04:47:03 +00:00
George Bosilca
f636243309 Look like opal is a better place for windows related stuff. 
This commit was SVN r8405.
 2005-12-08 00:07:40 +00:00
Brian Barrett
aa28207fdc don't include gas assembler hints 
This commit was SVN r8400.
 2005-12-07 18:18:36 +00:00
Jeff Squyres
b04f6bf71b Fix a segv; it's possible to have an empty string parameter (""), such 
that opal_argv_split() will return an empty array.  So test for that
case before trying to iterate through the array.

This commit was SVN r8396.
 2005-12-06 20:06:40 +00:00
George Bosilca
1fe691c1f5 powerpc-apple-darwin8-gcc-4.0.0 catch 2 warnings about uninitialized usage. Reading the code I have to agree with it, 
even if it's highly improbable that it could happens in real life. But we never know ...

This commit was SVN r8393.
 2005-12-06 18:44:52 +00:00
George Bosilca
9efd0e0813 Include the memoryhooks.h after the standard include files to insure that all expected types are 
correctly defined (like size_t).

This commit was SVN r8383.
 2005-12-06 05:55:36 +00:00
George Bosilca
23c618ab51 Allow a VPATH build to find the include files. 
This commit was SVN r8382.
 2005-12-06 05:26:36 +00:00