Steven G. Johnson wrote:
> PS. Reading the PHDF5 documentation again, I notice that we also
> really should be calling H5Pset_dxpl_mpio to do collective I/O for the
> field datasets, for better performance. Another thing for the TODO
> list...
>
Steven G. Johnson wrote:
> On Nov 10, 2008, at 1:55 PM, Steven G. Johnson wrote:
>
>> if (IF_EXCLUSIVE(am_master(), 1)) {
>>
>
> Actually, I think that should be:
>
>if (IF_EXCLUSIVE(am_master(), parallel || am_master()) {
>
> Even with parallel-HDF5, only the master process should wr
On Nov 10, 2008, at 1:55 PM, Steven G. Johnson wrote:
> if (IF_EXCLUSIVE(am_master(), 1)) {
Actually, I think that should be:
if (IF_EXCLUSIVE(am_master(), parallel || am_master()) {
Even with parallel-HDF5, only the master process should write if !
parallel (i.e. if the file was opened in
On Nov 4, 2008, at 6:24 AM, Zheng Li wrote:
Hi, everyone :
I compiled meep-0.20.3 with mpich in ubuntu and found the function
call
void h5file::write(const char *dataname, const char *data)
in
file->write("stringtest", "Hello, world!\n"); @h5test.cpp:103
causes
file->close_id();
to fail in
del
Hi, everyone :
I compiled meep-0.20.3 with mpich in ubuntu and found the function call
*void h5file::write(const char *dataname, const char *data)*
in
*file->write("stringtest", "Hello, world!\n"); [EMAIL PROTECTED]:103
causes
*file->close_id();*
to fail in
*delete file;*
with the outputs being
HD
5 matches
Mail list logo