| 21 |
decomposition and parallelization. Cube faces (also called |
decomposition and parallelization. Cube faces (also called |
| 22 |
subdomains) may be divided into any number of tiles that divide evenly |
subdomains) may be divided into any number of tiles that divide evenly |
| 23 |
into the grid point dimensions of the subdomain. Furthermore, the |
into the grid point dimensions of the subdomain. Furthermore, the |
| 24 |
individual tiles may be run on separate processors in different |
individual tiles can run on separate processors in different |
| 25 |
combinations, and whether exchanges between particular tiles occur |
combinations, and whether exchanges between particular tiles occur |
| 26 |
between different processors is determined at runtime. This |
between different processors is determined at runtime. This |
| 27 |
flexibility provides for manual compile-time load balancing across a |
flexibility provides for manual compile-time load balancing across a |
| 65 |
configurations other than the one you intend to modify.\\ |
configurations other than the one you intend to modify.\\ |
| 66 |
|
|
| 67 |
$\bullet$ Files containing grid parameters, named |
$\bullet$ Files containing grid parameters, named |
| 68 |
\file{tile00$n$.mitgrid} where $n$=[1,6] (one per subdomain), must |
\file{tile00$n$.mitgrid} where $n$=\code{(1:6)} (one per subdomain), |
| 69 |
be in the working directory when the MITgcm executable is run. |
must be in the working directory when the MITgcm executable is run. |
| 70 |
These files are provided in the example experiments for cubed sphere |
These files are provided in the example experiments for cubed sphere |
| 71 |
configurations with 32$\times$32 cube sides and are non-trivial to |
configurations with 32$\times$32 cube sides and are non-trivial to |
| 72 |
generate -- please contact MITgcm support if you want to generate |
generate -- please contact MITgcm support if you want to generate |
| 73 |
files for other configurations. \\ |
files for other configurations. \\ |
| 74 |
|
|
| 75 |
$\bullet$ As always when compiling MITgcm, the file \file{SIZE.h} must |
$\bullet$ As always when compiling MITgcm, the file \file{SIZE.h} must |
| 76 |
be placed where \file{genmake2} will find it. In particular for the |
be placed where \file{genmake2} will find it. In particular for |
| 77 |
exch2, the domain decomposition specified in \file{SIZE.h} must |
exch2, the domain decomposition specified in \file{SIZE.h} must |
| 78 |
correspond with the particular configuration's topology specified in |
correspond with the particular configuration's topology specified in |
| 79 |
\file{W2\_EXCH2\_TOPOLOGY.h} and \file{w2\_e2setup.F}. Domain |
\file{W2\_EXCH2\_TOPOLOGY.h} and \file{w2\_e2setup.F}. Domain |
| 119 |
The first three determine the size of the subdomains and |
The first three determine the size of the subdomains and |
| 120 |
hence the size of the overall domain. Each one determines the number |
hence the size of the overall domain. Each one determines the number |
| 121 |
of grid points, and therefore the resolution, along the subdomain |
of grid points, and therefore the resolution, along the subdomain |
| 122 |
sides in a ``great circle'' around each axis of the cube. At the time |
sides in a ``great circle'' around an axis of the cube. At the time |
| 123 |
of this writing MITgcm requires these three parameters to be equal, |
of this writing MITgcm requires these three parameters to be equal, |
| 124 |
but they provide for future releases to accomodate different |
but they provide for future releases to accomodate different |
| 125 |
resolutions around the axes to allow (for example) greater resolution |
resolutions around the axes to allow (for example) greater resolution |
| 129 |
the tiles into which the subdomains are decomposed, and must evenly |
the tiles into which the subdomains are decomposed, and must evenly |
| 130 |
divide the integer assigned to \code{nr}, \code{nb} and \code{ng}. |
divide the integer assigned to \code{nr}, \code{nb} and \code{ng}. |
| 131 |
The result is a rectangular tiling of the subdomain. Figure |
The result is a rectangular tiling of the subdomain. Figure |
| 132 |
\ref{fig:24tile} shows one possible topology for a twenty-four tile |
\ref{fig:24tile} shows one possible topology for a twentyfour-tile |
| 133 |
cube, and figure \ref{fig:12tile} shows one for twelve tiles. \\ |
cube, and figure \ref{fig:12tile} shows one for twelve tiles. \\ |
| 134 |
|
|
| 135 |
\begin{figure} |
\begin{figure} |
| 139 |
} |
} |
| 140 |
\end{center} |
\end{center} |
| 141 |
|
|
| 142 |
\caption{Plot of cubed sphere topology with a 32$\times$192 domain |
\caption{Plot of a cubed sphere topology with a 32$\times$192 domain |
| 143 |
divided into six 32$\times$32 subdomains, each of which is divided into four tiles |
divided into six 32$\times$32 subdomains, each of which is divided into four tiles |
| 144 |
(\code{tnx=16, tny=16}) for a total of twenty-four tiles. |
(\code{tnx=16, tny=16}) for a total of twentyfour tiles. |
| 145 |
} \label{fig:24tile} |
} \label{fig:24tile} |
| 146 |
\end{figure} |
\end{figure} |
| 147 |
|
|
| 151 |
\includegraphics{part6/s12t_16x32.ps} |
\includegraphics{part6/s12t_16x32.ps} |
| 152 |
} |
} |
| 153 |
\end{center} |
\end{center} |
| 154 |
\caption{Plot of cubed sphere topology with a 32$\times$192 domain |
\caption{Plot of a cubed sphere topology with a 32$\times$192 domain |
| 155 |
divided into six 32$\times$32 subdomains of two tiles each |
divided into six 32$\times$32 subdomains of two tiles each |
| 156 |
(\code{tnx=16, tny=32}). |
(\code{tnx=16, tny=32}). |
| 157 |
} \label{fig:12tile} |
} \label{fig:12tile} |
| 158 |
\end{figure} |
\end{figure} |
| 159 |
|
|
| 160 |
|
\begin{figure} |
| 161 |
|
\begin{center} |
| 162 |
|
\resizebox{4in}{!}{ |
| 163 |
|
\includegraphics{part6/s6t_32x32.ps} |
| 164 |
|
} |
| 165 |
|
\end{center} |
| 166 |
|
\caption{Plot of a cubed sphere topology with a 32$\times$192 domain |
| 167 |
|
divided into six 32$\times$32 subdomains with one tile each |
| 168 |
|
(\code{tnx=32, tny=32}). This is the default configuration. |
| 169 |
|
} |
| 170 |
|
\label{fig:6tile} |
| 171 |
|
\end{figure} |
| 172 |
|
|
| 173 |
|
|
| 174 |
Tiles can be selected from the topology to be omitted from being |
Tiles can be selected from the topology to be omitted from being |
| 175 |
allocated memory and processors. This tuning is useful in ocean |
allocated memory and processors. This tuning is useful in ocean |
| 176 |
modeling for omitting tiles that fall entirely on land. The tiles |
modeling for omitting tiles that fall entirely on land. The tiles |
| 185 |
\label{sec:exch2mpi} |
\label{sec:exch2mpi} |
| 186 |
|
|
| 187 |
Once the topology configuration files are created, the Fortran |
Once the topology configuration files are created, the Fortran |
| 188 |
parameters in \file{SIZE.h} must be configured to match. Section |
\code{PARAMETER}s in \file{SIZE.h} must be configured to match. |
| 189 |
\ref{sect:specifying_a_decomposition} \sectiontitle{Specifying a |
Section \ref{sect:specifying_a_decomposition} \sectiontitle{Specifying |
| 190 |
decomposition} provides a general description of domain decomposition |
a decomposition} provides a general description of domain |
| 191 |
within MITgcm and its relation to \file{SIZE.h}. The current section |
decomposition within MITgcm and its relation to \file{SIZE.h}. The |
| 192 |
specifies certain constraints the exch2 package imposes as well as |
current section specifies certain constraints the exch2 package |
| 193 |
describes how to enable parallel execution with MPI. \\ |
imposes as well as describes how to enable parallel execution with |
| 194 |
|
MPI. \\ |
| 195 |
|
|
| 196 |
As in the general case, the parameters \varlink{sNx}{sNx} and |
As in the general case, the parameters \varlink{sNx}{sNx} and |
| 197 |
\varlink{sNy}{sNy} define the size of the individual tiles, and so |
\varlink{sNy}{sNy} define the size of the individual tiles, and so |
| 281 |
The scalar parameters \varlink{exch2\_domain\_nxt}{exch2_domain_nxt} |
The scalar parameters \varlink{exch2\_domain\_nxt}{exch2_domain_nxt} |
| 282 |
and \varlink{exch2\_domain\_nyt}{exch2_domain_nyt} express the number |
and \varlink{exch2\_domain\_nyt}{exch2_domain_nyt} express the number |
| 283 |
of tiles in the $x$ and $y$ global indices. For example, the default |
of tiles in the $x$ and $y$ global indices. For example, the default |
| 284 |
setup of six tiles has \code{exch2\_domain\_nxt=6} and |
setup of six tiles (Fig. \ref{fig:6tile}) has \code{exch2\_domain\_nxt=6} and |
| 285 |
\code{exch2\_domain\_nyt=1}. A topology of twenty-four square tiles, |
\code{exch2\_domain\_nyt=1}. A topology of twenty-four square tiles, |
| 286 |
four per subdomain (as in figure \ref{fig:24tile}), will have |
four per subdomain (as in figure \ref{fig:24tile}), will have |
| 287 |
\code{exch2\_domain\_nxt=12} and \code{exch2\_domain\_nyt=2}. Note |
\code{exch2\_domain\_nxt=12} and \code{exch2\_domain\_nyt=2}. Note |
| 288 |
that these parameters express the tile layout to allow global data |
that these parameters express the tile layout to allow global data |
| 289 |
files that are tile-layout-neutral and have no bearing on the internal |
files that are tile-layout-neutral and have no bearing on the internal |
| 290 |
storage of the arrays. The tiles are internally stored in a range |
storage of the arrays. The tiles are internally stored in a range |
| 291 |
from [1,\varlink{bi}{bi}] the $x$ axis and $y$ axis variable |
from \code{(1:\varlink{bi}{bi})} the $x$ axis, and $y$ axis variable |
| 292 |
\varlink{bj}{bj} is generally ignored within the package. \\ |
\varlink{bj}{bj} is generally ignored within the package. \\ |
| 293 |
|
|
| 294 |
\subsubsection{Arrays Indexed to Tile Number} |
\subsubsection{Arrays Indexed to Tile Number} |
| 295 |
|
|
| 296 |
The following arrays are of size \code{NTILES}, are indexed to the |
The following arrays are of length \code{NTILES}, are indexed to the |
| 297 |
tile number, and the indices are omitted in their descriptions. \\ |
tile number, and the indices are omitted in their descriptions. \\ |
| 298 |
|
|
| 299 |
The arrays \varlink{exch2\_tnx}{exch2_tnx} and |
The arrays \varlink{exch2\_tnx}{exch2_tnx} and |
| 308 |
determined by the arrays \varlink{exch2\_tbasex}{exch2_tbasex} and |
determined by the arrays \varlink{exch2\_tbasex}{exch2_tbasex} and |
| 309 |
\varlink{exch2\_tbasey}{exch2_tbasey}. These variables are used to |
\varlink{exch2\_tbasey}{exch2_tbasey}. These variables are used to |
| 310 |
relate the location of the edges of different tiles to each other. As |
relate the location of the edges of different tiles to each other. As |
| 311 |
an example, in the default six-tile topology ?? each index in these |
an example, in the default six-tile topology (Fig. \ref{fig:6tile}) |
| 312 |
arrays are set to \code{0}. The twentyfour-tile case discussed above |
each index in these arrays is set to \code{0} since a tile occupies |
| 313 |
will have values of \code{0} or \code{16}, depending on the quadrant |
its entire subdomain. The twentyfour-tile case discussed above will |
| 314 |
the tile falls within the subdomain. The array |
have values of \code{0} or \code{16}, depending on the quadrant the |
| 315 |
\varlink{exch2\_myFace}{exch2_myFace} contains the number of the |
tile falls within the subdomain. The elements of the arrays |
| 316 |
subdomain of each tile, numbered \code{(1:6)} in the case of the |
\varlink{exch2\_txglobalo}{exch2_txglobalo} and |
| 317 |
standard cube topology and indicated by \textbf{\textsf{f}}$n$ in |
\varlink{exch2\_txglobalo}{exch2_txglobalo} are similar to |
|
figures \ref{fig:12tile}) and \ref{fig:24tile}). \\ |
|
|
|
|
|
The elements of the arrays \varlink{exch2\_txglobalo}{exch2_txglobalo} |
|
|
and \varlink{exch2\_txglobalo}{exch2_txglobalo} are similar to |
|
| 318 |
\varlink{exch2\_tbasex}{exch2_tbasex} and |
\varlink{exch2\_tbasex}{exch2_tbasex} and |
| 319 |
\varlink{exch2\_tbasey}{exch2_tbasey}, but locate the tiles within the |
\varlink{exch2\_tbasey}{exch2_tbasey}, but locate the tiles within the |
| 320 |
global address space, similar to that used by global files. \\ |
global address space, similar to that used by global files. \\ |
| 321 |
|
|
| 322 |
|
The array \varlink{exch2\_myFace}{exch2_myFace} contains the number of |
| 323 |
|
the subdomain of each tile, in a range \code{(1:6)} in the case of the |
| 324 |
|
standard cube topology and indicated by \textbf{\textsf{f}}$n$ in |
| 325 |
|
figures \ref{fig:12tile} and |
| 326 |
|
\ref{fig:24tile}. \varlink{exch2\_nNeighbours}{exch2_nNeighbours} |
| 327 |
|
contains a count of how many neighboring tiles each tile has, and is |
| 328 |
|
used for setting bounds for looping over neighboring tiles. |
| 329 |
|
\varlink{exch2\_tProc}{exch2_tProc} holds the process rank of each |
| 330 |
|
tile, and is used in interprocess communication. \\ |
| 331 |
|
|
| 332 |
|
|
| 333 |
The arrays \varlink{exch2\_isWedge}{exch2_isWedge}, |
The arrays \varlink{exch2\_isWedge}{exch2_isWedge}, |
| 334 |
\varlink{exch2\_isEedge}{exch2_isEedge}, |
\varlink{exch2\_isEedge}{exch2_isEedge}, |
| 335 |
\varlink{exch2\_isSedge}{exch2_isSedge}, and |
\varlink{exch2\_isSedge}{exch2_isSedge}, and |
| 339 |
orientation of neighboring tiles, and to indicate whether a tile lies |
orientation of neighboring tiles, and to indicate whether a tile lies |
| 340 |
on the corner of a subdomain. The latter case requires special |
on the corner of a subdomain. The latter case requires special |
| 341 |
exchange and numerical handling for the singularities at the eight |
exchange and numerical handling for the singularities at the eight |
| 342 |
corners of the cube. \varlink{exch2\_nNeighbours}{exch2_nNeighbours} |
corners of the cube. \\ |
| 343 |
contains a count of how many neighboring tiles each tile has, and is |
|
|
used for setting bounds for looping over neighboring tiles. |
|
|
\varlink{exch2\_tProc}{exch2_tProc} holds the process rank of each |
|
|
tile, and is used in interprocess communication. \\ |
|
| 344 |
|
|
| 345 |
\subsubsection{Arrays Indexed to Tile Number and Neighbor} |
\subsubsection{Arrays Indexed to Tile Number and Neighbor} |
| 346 |
|
|
| 355 |
to bottom on the east and west edges. Maybe throw in a fig here, eh? |
to bottom on the east and west edges. Maybe throw in a fig here, eh? |
| 356 |
\\ |
\\ |
| 357 |
|
|
| 358 |
|
\sloppy |
| 359 |
The \code{exch2\_opposingSend\_record(a,T)} array holds the index |
The \code{exch2\_opposingSend\_record(a,T)} array holds the index |
| 360 |
\code{b} in \texttt{exch2\_neighbourId(b,Tn)} that holds the tile |
\code{b} in \texttt{exch2\_neighbourId(b,Tn)} that holds the tile |
| 361 |
number \code{T}. In other words, |
number \code{T}. In other words, |
| 365 |
\end{verbatim} |
\end{verbatim} |
| 366 |
This provides a back-reference from the neighbor tiles. \\ |
This provides a back-reference from the neighbor tiles. \\ |
| 367 |
|
|
| 368 |
The arrays \varlink{exch2\_pi}{exch2_pi}, |
The arrays \varlink{exch2\_pi}{exch2_pi} and |
| 369 |
\varlink{exch2\_pj}{exch2_pj}, \varlink{exch2\_oi}{exch2_oi}, |
\varlink{exch2\_pj}{exch2_pj} specify the transformations of variables |
| 370 |
\varlink{exch2\_oj}{exch2_oj}, \varlink{exch2\_oi\_f}{exch2_oi_f}, and |
in exchanges between the neighboring tiles. These transformations are |
| 371 |
\varlink{exch2\_oj\_f}{exch2_oj_f} specify the transformations in |
necessary in exchanges between subdomains because a physical vector |
| 372 |
exchanges between the neighboring tiles. The dimensions of |
component in one direction may map to one in a different direction in |
| 373 |
\code{exch2\_pi(t,N,T)} and \code{exch2\_pj(t,N,T)} are the neighbor |
an adjacent subdomain, and may be have its indexing reversed. This |
| 374 |
ID \code{N} and the tile number \code{T} as explained above, plus a |
swapping arises from the ``folding'' of two-dimensional arrays into a |
| 375 |
vector of length 2 containing transformation factors \code{t}. The |
three-dimensional cube. |
| 376 |
first element of the transformation vector indicates the factor |
|
| 377 |
\code{t} by which variables representing the same vector component of |
The dimensions of \code{exch2\_pi(t,N,T)} and \code{exch2\_pj(t,N,T)} |
| 378 |
a tile \code{T} will be multiplied in exchanges with neighbor |
are the neighbor ID \code{N} and the tile number \code{T} as explained |
| 379 |
\code{N}, and the second element indicates the transform to the |
above, plus a vector of length 2 containing transformation factors |
| 380 |
variable in the other direction. As an example, |
\code{t}. The first element of the transformation vector indicates |
| 381 |
\code{exch2\_pi(1,N,T)} holds the transform of the $i$ component of a |
the factor \code{t} by which variables representing the same |
| 382 |
vector variable in tile \code{T} to the $i$ component of tile |
\emph{physical} vector component of a tile \code{T} will be multiplied |
| 383 |
\code{T}'s neighbor \code{N}, and \code{exch2\_pi(2,N,T)} hold the |
in exchanges with neighbor \code{N}, and the second element indicates |
| 384 |
component of neighbor \code{N}'s $j$ component. \\ |
the transform to the physical vector in the other direction. To |
| 385 |
|
clarify (hopefully), \code{exch2\_pi(1,N,T)} holds the transform of |
| 386 |
|
the $i$ component of a vector variable in tile \code{T} to the $i$ |
| 387 |
|
component of tile \code{T}'s neighbor \code{N}, and |
| 388 |
|
\code{exch2\_pi(2,N,T)} holds the transform of \code{T}'s $i$ |
| 389 |
|
components to the neighbor \code{N}'s $j$ component. \\ |
| 390 |
|
|
| 391 |
Under the current cube topology, one of the two elements of |
Under the current cube topology, one of the two elements of |
| 392 |
\code{exch2\_pi} or \code{exch2\_pj} for a given tile \code{T} and |
\code{exch2\_pi} or \code{exch2\_pj} for a given tile \code{T} and |
| 393 |
neighbor \code{N} will be \code{0}, reflecting the fact that the two |
neighbor \code{N} will be \code{0}, reflecting the fact that the two |
| 394 |
vector components are orthogonal. The other element will be 1 or -1, |
vector components are orthogonal. The other element will be \code{1} |
| 395 |
depending on whether the components are indexed in the same or |
or \code{-1}, depending on whether the components are indexed in the |
| 396 |
opposite directions. For example, the transform vector of the arrays |
same or opposite directions. For example, the transform vector of the |
| 397 |
for all tile neighbors on the same subdomain will be \code{(1,0)}, |
arrays for all tile neighbors on the same subdomain will be |
| 398 |
since all tiles on the same subdomain are oriented identically. A |
\code{(1,0)}, since all tiles on the same subdomain are oriented |
| 399 |
vector direction that corresponds to the orthogonal dimension with the |
identically. A vector direction that corresponds to the orthogonal |
| 400 |
same index direction in a particular tile-neighbor orientation will |
dimension with the same index direction in a particular tile-neighbor |
| 401 |
have \code{(0,1)}, whereas those in the opposite index direction will |
orientation will have \code{(0,1)}, whereas those in the opposite |
| 402 |
have \code{(0,-1)}. This needs some diagrams. |
index direction will have \code{(0,-1)}. \\ |
| 403 |
|
|
| 404 |
|
|
| 405 |
|
\varlink{exch2\_oi}{exch2_oi}, |
| 406 |
|
\varlink{exch2\_oj}{exch2_oj}, \varlink{exch2\_oi\_f}{exch2_oi_f}, and |
| 407 |
|
\varlink{exch2\_oj\_f}{exch2_oj_f} |
| 408 |
|
|
| 409 |
|
|
| 410 |
|
|
| 411 |
|
|
| 412 |
|
This needs some diagrams. \\ |
| 413 |
|
|
| 414 |
|
|
| 415 |
{\footnotesize |
{\footnotesize |