diff options
| author | MuQun Yang <ymuqun@hdfgroup.org> | 2004-08-12 05:02:59 (GMT) |
|---|---|---|
| committer | MuQun Yang <ymuqun@hdfgroup.org> | 2004-08-12 05:02:59 (GMT) |
| commit | 4dfae9e8975c6331387dd3b4574ee5f177bdfafc (patch) | |
| tree | bf576c2a56a01db285bffce509d8b98bcb84d9c1 /testpar/testphdf5.h | |
| parent | 03ddea6cdaf07719b42ac60f2effdcdae3ef1d96 (diff) | |
| download | hdf5-4dfae9e8975c6331387dd3b4574ee5f177bdfafc.zip hdf5-4dfae9e8975c6331387dd3b4574ee5f177bdfafc.tar.gz hdf5-4dfae9e8975c6331387dd3b4574ee5f177bdfafc.tar.bz2 | |
[svn-r9072] Purpose:
To make collective chunk IO test more general
Description:
Previous collective chunk IO test only works with number of processor less than 4.
In case people would like to test with more processors, more general tests need to be used.
Solution:
The following changes have been made:
1. Change the way to use discontiguous hyperslab selection to work with larger number of processors,
2. Increase size of data array
Now, I can test with processor number = 12; however, the fourth test is very slow to the independent IO write and read.
Platforms tested:
eirene(only parallel test codes are modified, no need to test on other platforms).
Misc. update:
Diffstat (limited to 'testpar/testphdf5.h')
| -rw-r--r-- | testpar/testphdf5.h | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/testpar/testphdf5.h b/testpar/testphdf5.h index 359eb958..b295317 100644 --- a/testpar/testphdf5.h +++ b/testpar/testphdf5.h @@ -113,8 +113,8 @@ #define FACC_MPIPOSIX 0x8 /* MPIPOSIX */ /*Constants for collective chunk definitions */ -#define SPACE_DIM1 24 -#define SPACE_DIM2 24 +#define SPACE_DIM1 288 +#define SPACE_DIM2 288 #define BYROW_CONT 1 #define BYROW_DISCONT 2 #define DSET_COLLECTIVE_CHUNK_NAME "coll_chunk_name" |