1
1
Граф коммитов

2013 Коммитов

Автор SHA1 Сообщение Дата
Jeff Squyres
a0abf45372 Ensure to return the right status -- strip the exit status out of the
return code from waitpid().  For example, in some cases, when gcc
fails to compile the app for some reason, it returns an error status
of 1, which is a return code of 256.  If we return 256 from main(),
only the lower 8 bits are returned which results in a 0 return status
from the wrapper compiler (doh!).  So be sure that we properly strip
out the correct return status from the underlying compiler and return
only those 8 bits through main().

This commit was SVN r2175.
2004-08-17 03:02:01 +00:00
Jeff Squyres
bd7d7e3eb5 - Minor fixes to code base to make it in ompi code style
- Ensure to always make the mpiCC sym link when we're on
  case-sensitive filesystems (fix Makefile.am logic)

This commit was SVN r2174.
2004-08-17 02:34:17 +00:00
Rich Graham
9b07ea2585 fix fifo memory allocation to use the correct lengths. Add an interface
function (used in testing) to check for fifo size.

This commit was SVN r2173.
2004-08-16 23:37:07 +00:00
Tim Woodall
442c9e03b5 provide pml implementation - will need to update for romio
This commit was SVN r2172.
2004-08-16 23:10:25 +00:00
Rich Graham
30f1b87165 add to the circular buffer unit test
This commit was SVN r2171.
2004-08-16 23:07:10 +00:00
Rich Graham
f75b88faa5 fix a bug, so that the fifo size is rounded up to a power of 2.
Add some support code to determine nearest power of 2.

This commit was SVN r2170.
2004-08-16 23:06:33 +00:00
Ralph Castain
2db94bb016 Checkpoint the registry. Now have several of the basic functions operating - can define segments, get index of dictionaries, etc - all the basic elements required to build get/put. Will continue tonight.
This commit was SVN r2169.
2004-08-16 21:36:50 +00:00
Ralph Castain
c11d3896f0 Fix the proxy component to default to using the seed daemon as its replica.
This commit was SVN r2168.
2004-08-16 20:21:39 +00:00
Tim Woodall
9c9037ef2b added support for querying oob contact info and setting
contact info for seed daemon 

This commit was SVN r2167.
2004-08-16 19:39:54 +00:00
Tim Woodall
bd8af9ecdf return correct status
This commit was SVN r2166.
2004-08-16 19:09:03 +00:00
Weikuan Yu
8b45b6e3a4 Add an additional type MCA_PTL_HDR_TYPE_FIN for last fragment notification
This commit was SVN r2165.
2004-08-16 18:37:34 +00:00
Ralph Castain
60a5428e43 Update the registry - restore the gpr_replica.c file into the make system, update functionality.
This commit was SVN r2164.
2004-08-16 16:20:47 +00:00
Weikuan Yu
61b4bc71a5 check in some cleanup
This commit was SVN r2163.
2004-08-16 15:48:22 +00:00
David Daniel
3dae1199a6 Removing explicit reference to stdint.h (breaks Solaris compile)
This commit was SVN r2162.
2004-08-16 03:53:17 +00:00
Jeff Squyres
0d093b40a0 Ensure to output using the selected component
This commit was SVN r2161.
2004-08-16 03:25:31 +00:00
Jeff Squyres
2d1976b403 Remove silly ordering issue that sometimes caused a seg fault. Duh.
This commit was SVN r2160.
2004-08-16 03:08:01 +00:00
Jeff Squyres
292baf897e Now that gpr is apparently ready for prime-time, remove the hacks that
made it [somewhat] compile and fully integrate it into the build
process:
- add configure.params to gpr/proxy and gpr/replica
- bring gpr/proxy/Makefile.am and gpr/replica/Makefile.am up-to-date
- uncomment gpr sections from ompi_info
- took the liberty of changing a member variable from "delete" to
  "delete_fn" in gpr.h ("delete" is a keyword in C++, and gpr.h is
  included in ompi_info, which is written in C++)

This commit was SVN r2159.
2004-08-16 02:59:38 +00:00
Ralph Castain
0d7c16f400 Update the registry with some functionality and an early draft of the unit test.
I could use some help from one of you MCA gurus - if you run the test, you'll see that I cannot get the gpr components to be recognized. I'm not sure of the reason - I would appreciate any help you can provide to get the gpr components "registered".

This commit was SVN r2158.
2004-08-16 02:08:48 +00:00
David Daniel
a1688d5b9f more atomic.h changes
This commit was SVN r2157.
2004-08-16 01:13:25 +00:00
David Daniel
bfc4b52b8b fixes for Solaris
This commit was SVN r2156.
2004-08-15 23:55:10 +00:00
David Daniel
e865b75241 fixes for Solaris
This commit was SVN r2155.
2004-08-15 23:54:30 +00:00
Ralph Castain
b433fc3ad9 Added the local support functions for the replica. Everything compiles fine on my machine - next step is to test these functions.
This commit was SVN r2154.
2004-08-15 22:37:01 +00:00
David Daniel
6bdf9c0cbc Adding file to instantiate assembly level code for non-GNU C compilers. Not added to build system yet.
This commit was SVN r2153.
2004-08-15 22:06:01 +00:00
David Daniel
6e9ebc2ad1 Adding atomic operations for non-gcc on ia32
This commit was SVN r2152.
2004-08-15 21:56:25 +00:00
David Daniel
d0ff366809 Adding atomic operations for non-gcc on powerpc
This commit was SVN r2151.
2004-08-15 21:54:29 +00:00
David Daniel
2c84951869 Updating inline assembler for sparc
This commit was SVN r2150.
2004-08-15 21:47:31 +00:00
David Daniel
d318bc310f Adding assembler file for atomic operations on sparc with Sun C
This commit was SVN r2149.
2004-08-15 21:46:25 +00:00
David Daniel
b6f3022954 Updating top-level atomic.h
This commit was SVN r2148.
2004-08-15 21:44:39 +00:00
Ralph Castain
bfc815f614 Fix a pointer problem to remove warning messages.
This commit was SVN r2147.
2004-08-15 05:53:36 +00:00
Ralph Castain
49e8e16148 Fix the registry software to compile - get all the naming errors finally out, etc. The functionality is not present, so don't use it yet - nothing will happen. I'll be restoring the functionality over the next week or two.
This commit was SVN r2146.
2004-08-15 05:49:55 +00:00
Ralph Castain
c0121cb927 Major update to the general purpose registry. Cleaned up the mess from name changes, begin building the functionality. Long way to go....
I have to commit this to cleanup a break in my tree. I'm hoping it won't break the compile of the tree, but will fix it as quickly as possible.

Jeff - you are welcome to set an "ignore" on the gpr if you like - I'll let you know when I've got the "kinks" out.

This commit was SVN r2145.
2004-08-15 03:33:13 +00:00
Sayantan Sur
d7f2e6c2a3 Added files
This commit was SVN r2144.
2004-08-14 14:56:18 +00:00
Jeff Squyres
6bad44dd3b Oops -- missed a word in the warning message. :)
This commit was SVN r2143.
2004-08-14 13:09:19 +00:00
Jeff Squyres
2df3a8fd6d Add a few warning messages for if you try to do things and
MPI_PARAM_CHECK was previously set to disable MPI API param checking
at compile time (and our hands are tied at run-time) and implict MCA
param assignements

This commit was SVN r2142.
2004-08-14 13:07:30 +00:00
Jeff Squyres
3274e80b0c Oops -- wtick and wtime are not supposed to be profiled. This fixes
the nightly build on frood from last night.

This commit was SVN r2141.
2004-08-14 12:49:38 +00:00
Jeff Squyres
1787645a3d After consulting with Edgar and MPI-2:4.12.4, decide the following:
- the f2c functions should return the corresponding *_NULL functions
  and not invoke an MPI exception if an invalid fortran handle is
  passed
- the error check should be outside MPI_PARAM_CHECK -- MPI defines the
  behavior of when an invalid fortran handle is passed; it is not
  dependant upon whether we are checking parameters or not

This commit was SVN r2140.
2004-08-14 12:28:25 +00:00
George Bosilca
2ee4f0898c At first glance there is no difference. But by rewriting the 2 lines I think I have removed some strnage chars in the file. So now it compiles in 64 bits architectures. AND RUN correctly :)
This commit was SVN r2139.
2004-08-14 06:39:58 +00:00
George Bosilca
82046fd2e5 Correct the pointer usage when we call the corresponding C funtion. If
the function expect a pointer we just have to cast it.

This commit was SVN r2138.
2004-08-14 06:37:17 +00:00
Jeff Squyres
1218debb6e Oops -- buglet crawled in at the last minute. :-)
This commit was SVN r2137.
2004-08-14 02:12:01 +00:00
Jeff Squyres
cfd5524ad5 Committing several things under one commit, but they're all at least
somewhat tied together and I'd rather have a consistent commit rather
than several smaller commits that individually break the tree:
- first cut of src/file/file.c: MPI_File handling.  More to come here.
- tweaked MPI_Info handling a bit: cause MPI_Info_f2c to invoke error
  handler if provided index is out of range (vs. returing
  MPI_INFO_NULL without invoking an error handler)
- moved general MPI MCA params off into their own .h and .c file (so
  that ompi_info can call it and therefore display MPI MCA params)
- first [abbreviated] cut of src/mca/io/base/* -- much more to come
  here; stripped down to basics for this commit
- filled in a small number of MPI_File* functions for testing purposes
- updated a bunch of doxygen docs
--> Unresolved questions about MPI_ERRORS_RETURN, MPI_ERRORS_ABORT,
    and MPI::ERRORS_THROW_EXCEPTIONS because of vagueness in MPI
    standard -- Edgar and I are discussing what to do here
--> Unresolved questions about what to do in a case like this:
      MPI_File_open(..., &file);
      MPI_File_close(&file);
      MPI_File_read(..., &file);
    because MPI-2:9.7 says that the default error handler on MPI_File
    handles is MPI_ERRORS_RETURN -- we can't even print a warning
    here!  This certainly violates the Law of Least Astonishment for
    MPI users (who certainly expect MPI functions that fail to
    complain loudly and to abort by default).

This commit was SVN r2136.
2004-08-14 01:56:05 +00:00
Sayantan Sur
c6d6ea8482 Getting Dynamic connection management and UD transport to work.
This commit was SVN r2135.
2004-08-14 00:27:00 +00:00
Jeff Squyres
a5848eb249 Oops -- minor logic error w.r.t. fortran libs. Fixed.
This commit was SVN r2134.
2004-08-13 21:00:42 +00:00
Jeff Squyres
50ef741777 Temporary fix -- Edgar is going to go home and look up proper, modern
fortran 77 syntax for strings.  Stupid fortran!

This commit was SVN r2133.
2004-08-13 20:43:54 +00:00
Jeff Squyres
6cfe8bdfb9 Fix some Makefile.am issues with respect to profiling
This commit was SVN r2132.
2004-08-13 20:42:38 +00:00
Jeff Squyres
96f56affd5 Add some missing files in
This commit was SVN r2131.
2004-08-13 20:16:07 +00:00
Jeff Squyres
2693c5791c Edgar correctly pointed out that I declared the SVN character string
incorrectly

This commit was SVN r2130.
2004-08-13 20:06:48 +00:00
Rich Graham
0ac3e819ac fix numerous bugs - code now compiles.
This commit was SVN r2129.
2004-08-13 19:49:13 +00:00
Rich Graham
0fbf919658 start to implement test for the circular buffer fifo implementation.
This commit was SVN r2128.
2004-08-13 19:48:32 +00:00
Jeff Squyres
7cf2055530 Make OMPI_SVN_VERSION be a string in mpif.h.in
This commit was SVN r2127.
2004-08-13 19:46:09 +00:00
Brian Barrett
5540dc37bc * Change from ompi_list_t to ompi_list_t* in the schedule and allocation
structures to make it easier to swap around lists when doing process ->
  resource mapping
* Fix spawn interface to take an ompi_list_t* instead of an ompi_list_t
  since you can't pass an ompi_list_t by value
* Change allocate_resource to return an ompi_list_t* instead of having
  an ompi_list_t** as an argument, since it's a bit cleaner and makes
  who should call OBJ_NEW much more clear
* Clean up deallocation in error cases for the llm_base_allocate function
* Update test case for llm to not depend on current environment for
  correctness

This commit was SVN r2126.
2004-08-13 19:39:06 +00:00