llc_90/code-async/readme.txt

From Bron Nelson, February 28, 2019

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.  A minimum of one full node of I/O
ranks is required.  The async I/O does allocate whole nodes to be
either an I/O node, or a compute node.  It is permitted for the last
*compute* node to have a "ragged edge", i.e., have fewer MPI processes
on it than the other nodes do.  But the I/O nodes are all "full size".

The other minimum value the I/O code requires is that there must
be at least one core for each field you want to write, e.g., if you
are dumping 20 different fields, there must be at least 20 cores
allocated to the I/O.  Note that the 20 (or whatever) number is
*aggregate* across all the I/O nodes, NOT a "per node" number.

Another important constraint is that the total memory on all the I/O
nodes *collectively* needs to be twice as big as the largest epoch you
write.  So, if you are writing a 1.5 TB pickup dump, then you should
have a sum total of 3TB of memory (or more) on the set of I/O nodes.

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.

Set run-time parameter: useSingleCPUio=.FALSE.

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

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	From Bron Nelson, February 28, 2019
2
3	In the newest version, it is no longer necessary to hand-edit the
4	constants in "recvTask.c" and "readtile_mpiio.c". Instead, the file
5	"SIZE.h" has been modified in two ways:
6	(1) SIZE.h now includes the constant "sFacet"
7	(2) SIZE.h may now be #include in both C and Fortran files
8	This means that "recvTask.c" and "readtile_mpiio.c" now get the
9	information they need directly from "SIZE.h", so the magic constants
10	for the run only need to be edited in one place (namely, SIZE.h).
11
12	One tile per rank is recommended, mostly for pickup input performance,
13	but it is not strictly necessary. A minimum of one full node of I/O
14	ranks is required. The async I/O does allocate whole nodes to be
15	either an I/O node, or a compute node. It is permitted for the last
16	compute node to have a "ragged edge", i.e., have fewer MPI processes
17	on it than the other nodes do. But the I/O nodes are all "full size".
18
19	The other minimum value the I/O code requires is that there must
20	be at least one core for each field you want to write, e.g., if you
21	are dumping 20 different fields, there must be at least 20 cores
22	allocated to the I/O. Note that the 20 (or whatever) number is
23	aggregate across all the I/O nodes, NOT a "per node" number.
24
25	Another important constraint is that the total memory on all the I/O
26	nodes collectively needs to be twice as big as the largest epoch you
27	write. So, if you are writing a 1.5 TB pickup dump, then you should
28	have a sum total of 3TB of memory (or more) on the set of I/O nodes.
29
30	Choose dumpFreq and pChkptFreq as usual. We're not set up
31	to do the rolling checkpoints yet. It'll dump u,v,t, and etan now -
32	send me a list of other fields you want, as it is rather involved
33	to change them. But this should be enough to see if it works.
34
35	Set run-time parameter: useSingleCPUio=.FALSE.
36
37	Only a couple of files are different from previous version.
38	But note in particular that "SIZE.h" is a new file in that directory,
39	and "recvTask.c" has a huge number of changes.
40
41	The input scheme implemented here is only invoked on
42	the 64bit pickup files. It is specific to the LLC decomposition and will
43	not work on e.g. the Monterey high-res simulations we did a couple years
44	ago. (Although, the code should work for any facet size as specified
45	in SIZE.h) The format of SIZE.h was changed so that it can be included
46	in both C and Fortran files, and I also added the "sFacet" constant that
47	specifies the base facet size (e.g. 1080). So SIZE.h will probably look
48	kinda weird at first, but shouldn't be hard to figure out. The major
49	advantage is that now you no longer need to edit any magic constants in
50	recvTask.c and readtile_mpiio.c - they now derive the info they need by
51	directly including SIZE.h
52
53	The code now automatically figures out how many ranks are running per node.
54	You can run with whatever number of ranks per node that you want, but the
55	number needs to be consistent for all nodes (except possibly the last node,
56	which can be short).
57
58	The initial burst of output generated by recvTask.c (the "map" describing
59	the way the I/O processes are allocated) is now somewhat longer and more
60	detailed, but can continue to be ignored.
61
62	I did NOT try to cure the "integer" problem. It seems that the code is
63	getting fairly close to bumping into the 2G (i.e. 2^31) limit on numbers
64	that fit into a default integer. I think you can probably do one more
65	doubling of the resolution (to 8640), but I'm also pretty sure that going
66	past that will break the code.