llc_1080/code-async/readme.txt


In the newest version, it is no longer necessary to hand-edit the
constants in "recvTask.c" and "readtile_mpiio.c".  Instead, the file
"SIZE.h" has been modified in two ways:
  (1) SIZE.h  now includes the constant "sFacet"
  (2) SIZE.h  may now be #include in both C and Fortran files
This means that "recvTask.c" and "readtile_mpiio.c" now get the
information they need directly from "SIZE.h", so the magic constants
for the run only need to be edited in one place (namely, SIZE.h).


One tile per rank is recommended, mostly for pickup input performance,
but it is not strictly necessary.

Choose dumpFreq and pChkptFreq as usual. We're not set up
to do the rolling checkpoints yet. It'll dump u,v,t, and etan now -
send me a list of other fields you want, as it is rather involved
to change them. But this should be enough to see if it works.


>>>>>>>>>>>>>>>>>>>>>>>>>>>>
From Bron, February 28, 2019

To use, set run-time parameter: useSingleCPUio=.FALSE.

Only a couple of files are different from the sources I copied from you.
But note in particular that  "SIZE.h"  is a new file in that directory,
and "recvTask.c" has a huge number of changes.


A couple of notes:

The input scheme implemented here is only invoked on
the 64bit pickup files.  It is specific to the LLC decomposition and will
not work on e.g. the Monterey high-res simulations we did a couple years
ago.  (Although, the code should work for any facet size as specified
in SIZE.h)  The format of SIZE.h was changed so that it can be included
in both C and Fortran files, and I also added the "sFacet" constant that
specifies the base facet size (e.g. 1080).  So SIZE.h will probably look
kinda weird at first, but shouldn't be hard to figure out.  The major
advantage is that now you no longer need to edit any magic constants in
recvTask.c and readtile_mpiio.c - they now derive the info they need by
directly including SIZE.h

The code now automatically figures out how many ranks are running per node.
You can run with whatever number of ranks per node that you want, but the
number needs to be consistent for all nodes (except possibly the last node,
which can be short).

The initial burst of output generated by recvTask.c (the "map" describing
the way the I/O processes are allocated) is now somewhat longer and more
detailed, but can continue to be ignored.

I did NOT try to cure the "integer" problem.  It seems that the code is
getting fairly close to bumping into the 2G (i.e. 2^31) limit on numbers
that fit into a default integer.  I *think* you can probably do one more
doubling of the resolution (to 8640), but I'm also pretty sure that going
past that will break the code.
1
2	In the newest version, it is no longer necessary to hand-edit the
3	constants in "recvTask.c" and "readtile_mpiio.c". Instead, the file
4	"SIZE.h" has been modified in two ways:
5	(1) SIZE.h now includes the constant "sFacet"
6	(2) SIZE.h may now be #include in both C and Fortran files
7	This means that "recvTask.c" and "readtile_mpiio.c" now get the
8	information they need directly from "SIZE.h", so the magic constants
9	for the run only need to be edited in one place (namely, SIZE.h).
10
11
12	One tile per rank is recommended, mostly for pickup input performance,
13	but it is not strictly necessary.
14
15	Choose dumpFreq and pChkptFreq as usual. We're not set up
16	to do the rolling checkpoints yet. It'll dump u,v,t, and etan now -
17	send me a list of other fields you want, as it is rather involved
18	to change them. But this should be enough to see if it works.
19
20
21	>>>>>>>>>>>>>>>>>>>>>>>>>>>>
22	From Bron, February 28, 2019
23
24	To use, set run-time parameter: useSingleCPUio=.FALSE.
25
26	Only a couple of files are different from the sources I copied from you.
27	But note in particular that "SIZE.h" is a new file in that directory,
28	and "recvTask.c" has a huge number of changes.
29
30
31	A couple of notes:
32
33	The input scheme implemented here is only invoked on
34	the 64bit pickup files. It is specific to the LLC decomposition and will
35	not work on e.g. the Monterey high-res simulations we did a couple years
36	ago. (Although, the code should work for any facet size as specified
37	in SIZE.h) The format of SIZE.h was changed so that it can be included
38	in both C and Fortran files, and I also added the "sFacet" constant that
39	specifies the base facet size (e.g. 1080). So SIZE.h will probably look
40	kinda weird at first, but shouldn't be hard to figure out. The major
41	advantage is that now you no longer need to edit any magic constants in
42	recvTask.c and readtile_mpiio.c - they now derive the info they need by
43	directly including SIZE.h
44
45	The code now automatically figures out how many ranks are running per node.
46	You can run with whatever number of ranks per node that you want, but the
47	number needs to be consistent for all nodes (except possibly the last node,
48	which can be short).
49
50	The initial burst of output generated by recvTask.c (the "map" describing
51	the way the I/O processes are allocated) is now somewhat longer and more
52	detailed, but can continue to be ignored.
53
54	I did NOT try to cure the "integer" problem. It seems that the code is
55	getting fairly close to bumping into the 2G (i.e. 2^31) limit on numbers
56	that fit into a default integer. I think you can probably do one more
57	doubling of the resolution (to 8640), but I'm also pretty sure that going
58	past that will break the code.