ports/openmpi
ports/openmpi
1
1
Форкнуть 0
Код Релизы Активность
7 116 коммитов 3 Ветки 0 Теги 130 MiB
deb1b237a7
Граф коммитов

174 Коммитов

Автор SHA1 Сообщение Дата
George Bosilca
deb1b237a7 First cut of a unique architecture base master convertor. It will hold the sizes 
of the predefined types as seen by the remote architecture, as well as some
pointers to the conversion functions. Still in progress, but it should just fine
for what we have today in Open MPI.

This commit was SVN r9433.
 2006-03-28 03:16:53 +00:00
Galen Shipman
af02867322 Use ones compiliment so we don't kill previously set flags.. 
This commit was SVN r9428.
 2006-03-27 16:12:22 +00:00
George Bosilca
52e5d90a53 ompi_dt_swap_bytes is the way to go. 
This commit was SVN r9424.
 2006-03-25 07:12:07 +00:00
Brian Barrett
b6ddded1fa * Fix bug in determining size of C++ bool when creating the predefined 
datatype MPI::BOOL.
* Add first round of support for heterogeneous platforms.  This includes
  endianness and size difference for C++ bool and Fortran LOGICAL.  It
  does not include differences in sizes for any other datatype or for
  different representations of floating point numbers.

This commit was SVN r9422.
 2006-03-25 02:53:41 +00:00
George Bosilca
b22836ea93 Reset the completed flag when we roll-back the convertor. 
This commit was SVN r9419.
 2006-03-24 20:33:53 +00:00
Tim Woodall
b09c2dc1cd correction of checksum for pending/buffered data 
This commit was SVN r9367.
 2006-03-22 16:47:12 +00:00
Brian Barrett
b74d3112ec * add missing header file to headers list so that it ends up in the dist 
tarball

This commit was SVN r9336.
 2006-03-20 04:37:33 +00:00
Brian Barrett
01603d3d9f * reorder copy_functions array to match current predefined datatype ordering 
and add missing datatypes.

This commit was SVN r9335.
 2006-03-20 01:16:30 +00:00
Tim Woodall
bd870519fd - modified convertor copy_and_prepare routines to accept an addition 
flag, new flags to be included when convertor is initialized
- modified pml/btl module defs and added stub functions for diagnostic
  output routines to dump state of queues / endpoints
- updates to data reliability pml

This commit was SVN r9329.
 2006-03-17 18:46:48 +00:00
George Bosilca
5819304916 Unfortunately, I cannot remove the log from SVN to erase all trace (for the sake 
of the future generations) of my own way to define function prototypes.
Shame on me ...

This commit was SVN r9327.
 2006-03-17 16:39:36 +00:00
George Bosilca
c2f001c0f2 Remove the dependency to datatype_memcpy.c. It's not yet ready for primetime. 
This commit was SVN r9326.
 2006-03-17 16:03:23 +00:00
George Bosilca
0fe57bb44c Allow the convertor to select between pack/unpack with or without 
checksum. Specify CONVERTOR_WITH_CHECKSUM when the convertor is
created and all the pack/unpack functions attached to this convertor
will be checksum aware.

This commit was SVN r9325.
 2006-03-17 08:27:17 +00:00
George Bosilca
6babf2f874 Rename files. 
This commit was SVN r9324.
 2006-03-17 08:10:37 +00:00
George Bosilca
9955eb2f2e Last step for the generation of 2 set of pack/unpack functions. One with 
checksum and the other without. Split the large files into smaller one, and
put similar functions together.

This commit was SVN r9323.
 2006-03-17 08:04:59 +00:00
George Bosilca
229f26dc55 First split of the datatype. More files and a cleaner distribution of functions 
in the corresponding files. There are few others changes to come ...

This commit was SVN r9319.
 2006-03-16 21:04:34 +00:00
George Bosilca
e79f35fe6c Copy the last fake DT_END_LOOP too when we duplicate the data. 
This commit was SVN r9309.
 2006-03-16 17:21:10 +00:00
Rainer Keller
2ce64c6fc7 - Add missing signed_char 
All hail the moog!

This commit was SVN r9299.
 2006-03-16 11:06:59 +00:00
George Bosilca
49c40f596b No data validation by default. 
This commit was SVN r9295.
 2006-03-16 01:35:49 +00:00
Tim Woodall
9e958f727f additional macros for csum 
This commit was SVN r9293.
 2006-03-16 00:19:55 +00:00
Brian Barrett
5c7751f9a2 * configure changes required to support the double compile of the ddt engine. 
still need to coordinate some Makefile.am changes with george tomorrow, but
  this is the stuff that will require re-autogening

This commit was SVN r9285.
 2006-03-15 03:35:30 +00:00
Graham Fagg
fcca36d280 Add missing ifdef 
This commit was SVN r9279.
 2006-03-14 20:48:50 +00:00
Tim Woodall
0b366e912c macros to compute checksum while moving data 
This commit was SVN r9278.
 2006-03-14 19:33:27 +00:00
George Bosilca
d5cee0cd75 Data validation should only be used with DR PML. 
This commit was SVN r9210.
 2006-03-06 20:01:26 +00:00
Tim Woodall
d350232c04 work in progress 
This commit was SVN r9209.
 2006-03-06 19:30:37 +00:00
Rainer Keller
5627fb5627 - Get rid of compiler warning: init type to DT_MAX_PREDEFINED 
and assert it is below when accessing ompi_ddt_basicDatatypes
 - datatype in ompi_ddt_pack_description_length is and will not be
   changed.

This commit was SVN r9193.
 2006-03-04 13:16:04 +00:00
Tim Woodall
274ee03df6 work in progress 
This commit was SVN r9192.
 2006-03-04 00:36:16 +00:00
George Bosilca
ca116e3cf3 Where we create a duplicate data-type for the get_content MPI function we have to attach the 
args from the old data-type. As this args are only read-only, I don't want to have several
copies around, so I add a reference count to them and simply attach them to the new
datatype. The args array now get freed only when the last reference dissapear.

This commit was SVN r9191.
 2006-03-03 20:51:36 +00:00
Rainer Keller
b8d1189091 - Use the actual _count parameter passed through the macro 
This commit was SVN r9189.
 2006-03-02 20:23:07 +00:00
George Bosilca
06def0b2d6 Not one .. but i. We're looking at the current position not at the first position 
in the buffer ...

This commit was SVN r9132.
 2006-02-23 15:59:17 +00:00
George Bosilca
0c1c650c91 Do not forget to commit the data-type once it is created from the 
packed description.

This commit was SVN r9125.
 2006-02-23 04:29:21 +00:00
George Bosilca
574c384ad4 This is the internal function so we should return the correct type. The 
external function is type_size and it's used only at the MPI level as MPI
only support integers for the size.

This commit was SVN r9124.
 2006-02-23 04:28:44 +00:00
George Bosilca
9dd522e350 Correct the MPI_COMBINER_DUP case when we generate the data description. Now, we have an 
optimized version here, where we pack only 2 integers instead of 6.

This commit was SVN r9102.
 2006-02-21 17:16:30 +00:00
George Bosilca
3ac541a722 Remove some debugging code. 
This commit was SVN r9101.
 2006-02-21 15:17:50 +00:00
George Bosilca
d4ab61aec5 Homogeneously handle the one-sided features of the datatype. 
This commit was SVN r9096.
 2006-02-20 17:22:29 +00:00
George Bosilca
79be2dbcdb Anything else than void* cannot be print with %p ... 
This commit was SVN r9094.
 2006-02-19 16:34:15 +00:00
George Bosilca
a2a08b2282 Add the missing prototype and use the function (ompi_ddt_print_args) 
in ompi_ddt_dump.

This commit was SVN r9093.
 2006-02-18 18:15:54 +00:00
George Bosilca
19fb826caf Add a new function to print how a datatype was created based on the 
MPI informations stored in args (the MPI_COMBINER stuff). This function
print only one level of information but it expand the name of the
datatype if the data is a predefined one.

This commit was SVN r9090.
 2006-02-18 04:18:39 +00:00
George Bosilca
b62b4eb5b8 icc point out a lot of useless comparaison as well as some warnings about 
inlined functions. Thie patch fix them all.

This commit was SVN r9082.
 2006-02-17 05:15:59 +00:00
George Bosilca
f4d1bea50e Allow us to add zero length datatype ... 
This commit was SVN r9079.
 2006-02-17 05:07:28 +00:00
George Bosilca
1740ab1209 I just wanted to add a flag not to replace the old ones. 
This commit was SVN r9076.
 2006-02-16 22:39:06 +00:00
George Bosilca
09aa367563 When we create a convertor if the data size is zero mark it as completed. That avoid 
problems with 0 length datatype used for pack/unpack.

This commit was SVN r9075.
 2006-02-16 22:36:42 +00:00
George Bosilca
eef3b6b2ba A lot better with a comma inside ... 
This commit was SVN r9070.
 2006-02-16 21:13:17 +00:00
George Bosilca
7d9f1992f2 Print more information about the convertor in ompi_convertor_dump. 
This commit was SVN r9069.
 2006-02-16 21:01:29 +00:00
George Bosilca
745ec1057f Remove the compilation warning. 
This commit was SVN r9047.
 2006-02-15 15:07:40 +00:00
Galen Shipman
fca3a36bc0 if data is contiguous need_buffers should return 0, not 1 
This commit was SVN r9009.
 2006-02-13 17:49:31 +00:00
George Bosilca
bde56ce528 Cleanup the convertor construct function. Do not set any useless values, instead rely on the 
calls to convertor_create and convertor_prepare to finish setting up the correct values for
the convertor.

This commit was SVN r9008.
 2006-02-13 17:03:36 +00:00
George Bosilca
ecc3e00362 Various cleanups. 
This commit was SVN r9002.
 2006-02-12 21:36:07 +00:00
George Bosilca
8b525ef21b Include the count when computing the remote size. 
This commit was SVN r9001.
 2006-02-12 21:34:55 +00:00
George Bosilca
13170eec52 Make sure all datatype files have the correct updated copyright information. 
This commit was SVN r8998.
 2006-02-12 21:03:01 +00:00
George Bosilca
25020f58c1 Correct the MPI_Indexed bug. Actually it can be triggered by any type of 
data, if the packed data is contiguous and the unpacked one is not. The
problem was that the unpack function did not update the bConverted value
to the real number of bytes extracted from the iovecs, but limit the update
to the number of bytes moved into the user buffers. So, if there were some
bytes copied in the internal pending buffer, they were lost because the next
convertor instead of using the correct bConverted (with the total number of
bytes) has only the transfered number. The result of this bug, is a shift to
left by few bytes of the values in the user buffers.
Add a protection against such kind of errors in the new_position.c.

This commit was SVN r8997.
 2006-02-12 20:19:22 +00:00