| 1 |
// ------------------------------------------------------------------------ |
| 2 |
// |
| 3 |
// SPDX-License-Identifier: LGPL-2.1-or-later |
| 4 |
// Copyright (C) 2020 - 2025 by the deal.II authors |
| 5 |
// |
| 6 |
// This file is part of the deal.II library. |
| 7 |
// |
| 8 |
// Part of the source code is dual licensed under Apache-2.0 WITH |
| 9 |
// LLVM-exception OR LGPL-2.1-or-later. Detailed license information |
| 10 |
// governing the source code and code contributions can be found in |
| 11 |
// LICENSE.md and CONTRIBUTING.md at the top level directory of deal.II. |
| 12 |
// |
| 13 |
// ------------------------------------------------------------------------ |
| 14 |
|
| 15 |
#ifndef dealii_mpi_consensus_algorithm_h |
| 16 |
#define dealii_mpi_consensus_algorithm_h |
| 17 |
|
| 18 |
#include <deal.II/base/config.h> |
| 19 |
|
| 20 |
#include <deal.II/base/mpi.h> |
| 21 |
#include <deal.II/base/mpi.templates.h> |
| 22 |
#include <deal.II/base/mpi_tags.h> |
| 23 |
|
| 24 |
#include <set> |
| 25 |
#include <vector> |
| 26 |
|
| 27 |
DEAL_II_NAMESPACE_OPEN |
| 28 |
|
| 29 |
|
| 30 |
namespace Utilities |
| 31 |
{ |
| 32 |
namespace MPI |
| 33 |
{ |
| 34 |
/** |
| 35 |
* A namespace for algorithms that implement the task of communicating |
| 36 |
* in a dynamic-sparse way. In computer science, this is often called a |
| 37 |
* <a href="https://en.wikipedia.org/wiki/Consensus_algorithm">consensus |
| 38 |
* problem</a>. |
| 39 |
* |
| 40 |
* The problem consensus algorithms are trying to solve is this: Let's |
| 41 |
* say you have $P$ processes that work together via MPI. Each (or at |
| 42 |
* least some) of these want to send information to some of the other |
| 43 |
* processes, or request information from other processes. No process |
| 44 |
* knows which other process wants to communicate with them. The challenge |
| 45 |
* is to determine who needs to talk to whom and what information needs to |
| 46 |
* be sent, and to come up with an algorithm that ensures that this |
| 47 |
* communication happens. |
| 48 |
* |
| 49 |
* That this is not a trivial problem can be seen by an analogy of the |
| 50 |
* postal service. There, some senders may request information from some |
| 51 |
* other participants in the postal service. So they send a letter that |
| 52 |
* requests the information, but the recipients do not know how many such |
| 53 |
* letters they need to expect (or that they should expect any at all). |
| 54 |
* They also do not know how long they need to keep checking their mailbox |
| 55 |
* for incoming requests. The recipients can be considered reliable, |
| 56 |
* however: We can assume that everyone who is sent a request puts a |
| 57 |
* letter with the answer in the mail. This time at least the recipients |
| 58 |
* of these answers know that they are waiting for these answers because |
| 59 |
* they have previously sent a request. They do not know in advance, |
| 60 |
* however, when the answer will arrive and how long to wait. The goal of |
| 61 |
* a consensus algorithm is then to come up with a strategy in which every |
| 62 |
* participant can say who they want to send requests to, what that |
| 63 |
* request is, and is then guaranteed an answer. The algorithm will only |
| 64 |
* return when all requests by all participants have been answered and the |
| 65 |
* answer delivered to the requesters. |
| 66 |
* |
| 67 |
* The problem is generally posed in terms of *requests* and *answers*. |
| 68 |
* In practice, either of these two may be empty messages. For example, |
| 69 |
* processes may simply want to send information to others that they know |
| 70 |
* these others need; in this case, the "answer" message may be empty |
| 71 |
* and its meaning is simply an affirmation that the information was |
| 72 |
* received. Similarly, in some cases processes simply need to inform |
| 73 |
* others that they want information, but the destination process knows |
| 74 |
* what information is being requested (based on where in the program |
| 75 |
* the request happens) and can send that information without there be |
| 76 |
* any identifying information in the request; in that case, the |
| 77 |
* request message may be empty and simply serve to identify the |
| 78 |
* requester. (Each message can be queried for its sender.) |
| 79 |
* |
| 80 |
* As mentioned in the first paragraph, the algorithms we are interested |
| 81 |
* in are "dynamic-sparse": |
| 82 |
* - Dynamic: By the time the algorithm is called, the other processes do |
| 83 |
* not know yet that they have to answer requests. |
| 84 |
* - Sparse: Each process only has to communicate with a small subset of |
| 85 |
* processes of the MPI communicator. |
| 86 |
* |
| 87 |
* In order to run the communication algorithms, users of this class have |
| 88 |
* to provide a number of pieces of information: |
| 89 |
* - An MPI communicator. |
| 90 |
* - On each process, a list of ranks of processes to communicate with. |
| 91 |
* - Functionality to pack/unpack data to send as either the original |
| 92 |
* request or as part of the answer. |
| 93 |
* This information is typically either provided as direct objects (for |
| 94 |
* the first two of the points above), or as function objects (for the |
| 95 |
* third point above). In the latter case, the function objects are often |
| 96 |
* simply lambda functions declared right in the context where one wants |
| 97 |
* to run a consensus algorithm; these lambda functions may then reference |
| 98 |
* variables that are active at the point of declaration of the lambda |
| 99 |
* function, such as variables local to the surrounding function. |
| 100 |
* |
| 101 |
* |
| 102 |
* <h3>Available implementations</h3> |
| 103 |
* |
| 104 |
* There are many ways to implement the general functionality required |
| 105 |
* for these "consensus algorithms". This namespace provides several |
| 106 |
* implementations of consensus algorithms, specifically the |
| 107 |
* NBX and PEX algorithms, along with a serial one for the case where |
| 108 |
* one wants to run such an algorithm on a single process. The key |
| 109 |
* entry points to these algorithms are the |
| 110 |
* nbx(), pex(), serial(), and selector() functions that take a |
| 111 |
* communicator, a list of targets, and a number of functions |
| 112 |
* as argument. The selector() function redirects to the other |
| 113 |
* implementations based on the number of processes that participate |
| 114 |
* in an MPI universe, since some implementations are better or worse |
| 115 |
* suited for large or small parallel computations. |
| 116 |
* |
| 117 |
* This namespace also implements specializations of each of the |
| 118 |
* functions for the specific case where a calling process is not |
| 119 |
* actually interested in receiving and processing answers -- that |
| 120 |
* is, the goal is simply to *send* messages to a number of targets, |
| 121 |
* but no answer is required; all we want to know is that by the end of |
| 122 |
* the call, all targets have been sent their respective data. This, |
| 123 |
* strictly speaking, does not fall under the umbrella of "consensus |
| 124 |
* algorithms", but is really just a "some-to-some" communication. |
| 125 |
* (This operation is also provided by the Utilities::MPI::some_to_some() |
| 126 |
* function, though with a different interface.) For this special |
| 127 |
* case, the functions in this namespace only need to receive |
| 128 |
* an MPI communicator, a list of targets, and function objects that |
| 129 |
* encode and decode the messages to be sent, but no functions for |
| 130 |
* encoding a reply, or processing a reply. |
| 131 |
*/ |
| 132 |
namespace ConsensusAlgorithms |
| 133 |
{ |
| 134 |
/** |
| 135 |
* A base class for concrete implementations of classes that |
| 136 |
* provide the information that the algorithms derived from |
| 137 |
* the ConsensusAlgorithms::Interface base class require. The main |
| 138 |
* functionality of this class is to return a list of process |
| 139 |
* ranks this process wants data from and to deal with the optional |
| 140 |
* payload of the messages sent/received by the ConsensusAlgorithm |
| 141 |
* classes. |
| 142 |
* |
| 143 |
* There are two kinds of messages: |
| 144 |
* - send/request message: A message consisting of a data request |
| 145 |
* which should be answered by another process. This message is |
| 146 |
* considered as a request message by the receiving rank. |
| 147 |
* - receive message: The answer to a send/request message. |
| 148 |
* |
| 149 |
* @tparam RequestType The type of the elements of the vector to sent. |
| 150 |
* @tparam AnswerType The type of the elements of the vector to received. |
| 151 |
* |
| 152 |
* @note Since the payloads of the messages are optional, users have |
| 153 |
* to deal with buffers themselves. The ConsensusAlgorithm classes |
| 154 |
* (1) deliver only references to empty vectors (of size 0) the data |
| 155 |
* to be sent can be inserted to or read from, and (2) communicate |
| 156 |
* these vectors blindly. |
| 157 |
* |
| 158 |
* @deprecated Instead of deriving a class from this base class and |
| 159 |
* providing a corresponding object to one of the run() functions, |
| 160 |
* use the free functions in this namespace that take function |
| 161 |
* objects as arguments. |
| 162 |
*/ |
| 163 |
template <typename RequestType, typename AnswerType> |
| 164 |
class DEAL_II_DEPRECATED_EARLY Process |
| 165 |
{ |
| 166 |
public: |
| 167 |
/** |
| 168 |
* Destructor. Made `virtual` to ensure that one can work with |
| 169 |
* derived classes. |
| 170 |
*/ |
| 171 |
virtual ~Process() = default; |
| 172 |
|
| 173 |
/** |
| 174 |
* @return A vector of ranks this process wants to send a request to. |
| 175 |
* |
| 176 |
* @note This is the only method which has to be implemented since the |
| 177 |
* payloads of the messages are optional. |
| 178 |
*/ |
| 179 |
virtual std::vector<unsigned int> |
| 180 |
compute_targets() = 0; |
| 181 |
|
| 182 |
/** |
| 183 |
* Add a payload to the request to the process with the specified rank. |
| 184 |
* |
| 185 |
* @param[in] other_rank Rank of the process. |
| 186 |
* @param[out] send_buffer data to be sent part of the request |
| 187 |
* (optional). |
| 188 |
* |
| 189 |
* @note The buffer is empty. Before using it, you have to set its size. |
| 190 |
*/ |
| 191 |
virtual void |
| 192 |
create_request(const unsigned int other_rank, RequestType &send_buffer); |
| 193 |
|
| 194 |
/** |
| 195 |
* Prepare the buffer where the payload of the answer of the request to |
| 196 |
* the process with the specified rank is saved in. |
| 197 |
* |
| 198 |
* @param[in] other_rank Rank of the process. |
| 199 |
* @param[in] buffer_recv Received payload (optional). |
| 200 |
* @param[out] request_buffer Payload to be sent as part of the request |
| 201 |
* (optional). |
| 202 |
* |
| 203 |
* @note The request_buffer is empty. Before using it, you have to set |
| 204 |
* its size. |
| 205 |
*/ |
| 206 |
virtual void |
| 207 |
answer_request(const unsigned int other_rank, |
| 208 |
const RequestType &buffer_recv, |
| 209 |
AnswerType &request_buffer); |
| 210 |
|
| 211 |
/** |
| 212 |
* Process the payload of the answer of the request to the process with |
| 213 |
* the specified rank. |
| 214 |
* |
| 215 |
* @param[in] other_rank rank of the process |
| 216 |
* @param[in] recv_buffer data to be sent part of the request (optional) |
| 217 |
*/ |
| 218 |
virtual void |
| 219 |
read_answer(const unsigned int other_rank, |
| 220 |
const AnswerType &recv_buffer); |
| 221 |
}; |
| 222 |
|
| 223 |
|
| 224 |
|
| 225 |
/** |
| 226 |
* A base class for algorithms that implement consensus algorithms, |
| 227 |
* see the documentation of the surrounding namespace for more |
| 228 |
* information. |
| 229 |
* |
| 230 |
* This base class only introduces a basic interface to achieve |
| 231 |
* these goals, while derived classes implement different algorithms |
| 232 |
* to actually compute such communication patterns and perform the |
| 233 |
* communication. |
| 234 |
* |
| 235 |
* @tparam RequestType The type of the elements of the vector to be sent. |
| 236 |
* @tparam AnswerType The type of the elements of the vector to be received. |
| 237 |
*/ |
| 238 |
template <typename RequestType, typename AnswerType> |
| 239 |
class Interface |
| 240 |
{ |
| 241 |
public: |
| 242 |
/** |
| 243 |
* Default constructor. |
| 244 |
*/ |
| 245 |
Interface() = default; |
| 246 |
|
| 247 |
/** |
| 248 |
* Destructor. Made `virtual` to ensure that one can work with |
| 249 |
* derived classes. |
| 250 |
*/ |
| 251 |
virtual ~Interface() = default; |
| 252 |
|
| 253 |
/** |
| 254 |
* Run the consensus algorithm and return a vector of process ranks |
| 255 |
* that have requested answers from the current process. |
| 256 |
* |
| 257 |
* This version of the run() function simply unpacks the functions |
| 258 |
* packaged in `process` and calls the version of the run() function |
| 259 |
* that takes a number of `std::function` arguments. |
| 260 |
* |
| 261 |
* @deprecated Instead of deriving a class from the Process base class and |
| 262 |
* providing a corresponding object to this function, |
| 263 |
* use the other run() function in this class that takes function |
| 264 |
* objects as arguments. |
| 265 |
*/ |
| 266 |
DEAL_II_DEPRECATED_EARLY |
| 267 |
std::vector<unsigned int> |
| 268 |
run(Process<RequestType, AnswerType> &process, const MPI_Comm comm); |
| 269 |
|
| 270 |
/** |
| 271 |
* Run the consensus algorithm and return a vector of process ranks |
| 272 |
* that have requested answers from the current process. |
| 273 |
* |
| 274 |
* @param[in] targets A vector that contains the ranks of processes |
| 275 |
* to which requests should be sent and from which answers need |
| 276 |
* to be received. |
| 277 |
* @param[in] create_request A function object that takes the rank |
| 278 |
* of a target process as argument and returns the message that |
| 279 |
* forms the request to this target. |
| 280 |
* @param[in] answer_request A function that takes as arguments the |
| 281 |
* rank of the process that has sent a request to us, along with |
| 282 |
* the message of the request, and returns the message that forms |
| 283 |
* the answer that should be sent back to the requesting process. |
| 284 |
* @param[in] process_answer A function object that takes as argument |
| 285 |
* the rank of a process from which we have received an answer |
| 286 |
* to a previously sent request, along with the message that |
| 287 |
* forms this answer. This function is used to describe what |
| 288 |
* the caller of the consensus algorithm wants to do with the |
| 289 |
* received answer. |
| 290 |
* @param[in] comm The MPI communicator on which the whole algorithm |
| 291 |
* is to be performed. |
| 292 |
*/ |
| 293 |
virtual std::vector<unsigned int> |
| 294 |
run( |
| 295 |
const std::vector<unsigned int> &targets, |
| 296 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 297 |
const std::function<AnswerType(const unsigned int, |
| 298 |
const RequestType &)> &answer_request, |
| 299 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 300 |
&process_answer, |
| 301 |
const MPI_Comm comm) = 0; |
| 302 |
}; |
| 303 |
|
| 304 |
|
| 305 |
/** |
| 306 |
* This class implements a concrete algorithm for the |
| 307 |
* ConsensusAlgorithms::Interface base class, using only point-to-point |
| 308 |
* communications and a single IBarrier. This algorithm is suitable |
| 309 |
* for very large process counts because it does not require the |
| 310 |
* allocation of arrays with size proportional to the number of processes. |
| 311 |
* |
| 312 |
* @note This class closely follows @cite hoefler2010scalable, but our |
| 313 |
* implementation also deals with payloads. |
| 314 |
* |
| 315 |
* @tparam RequestType The type of the elements of the vector to be sent. |
| 316 |
* @tparam AnswerType The type of the elements of the vector to be received. |
| 317 |
*/ |
| 318 |
template <typename RequestType, typename AnswerType> |
| 319 |
class NBX : public Interface<RequestType, AnswerType> |
| 320 |
{ |
| 321 |
public: |
| 322 |
/** |
| 323 |
* Default constructor. |
| 324 |
*/ |
| 325 |
NBX() = default; |
| 326 |
|
| 327 |
/** |
| 328 |
* Destructor. |
| 329 |
*/ |
| 330 |
virtual ~NBX() = default; |
| 331 |
|
| 332 |
// Import the declarations from the base class. |
| 333 |
using Interface<RequestType, AnswerType>::run; |
| 334 |
|
| 335 |
/** |
| 336 |
* @copydoc Interface::run() |
| 337 |
*/ |
| 338 |
virtual std::vector<unsigned int> |
| 339 |
run( |
| 340 |
const std::vector<unsigned int> &targets, |
| 341 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 342 |
const std::function<AnswerType(const unsigned int, |
| 343 |
const RequestType &)> &answer_request, |
| 344 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 345 |
&process_answer, |
| 346 |
const MPI_Comm comm) override; |
| 347 |
|
| 348 |
private: |
| 349 |
#ifdef DEAL_II_WITH_MPI |
| 350 |
/** |
| 351 |
* Buffers for sending requests. |
| 352 |
*/ |
| 353 |
std::vector<std::vector<char>> send_buffers; |
| 354 |
|
| 355 |
/** |
| 356 |
* Requests for sending requests. |
| 357 |
*/ |
| 358 |
std::vector<MPI_Request> send_requests; |
| 359 |
|
| 360 |
/** |
| 361 |
* Buffers for sending answers to requests. We use a vector of |
| 362 |
* pointers because that guarantees that the buffers themselves |
| 363 |
* are newer moved around in memory, even if the vector is |
| 364 |
* resized and consequently its elements (the pointers) are moved |
| 365 |
* around. |
| 366 |
*/ |
| 367 |
std::vector<std::unique_ptr<std::vector<char>>> request_buffers; |
| 368 |
|
| 369 |
/** |
| 370 |
* Requests for sending answers to requests. |
| 371 |
*/ |
| 372 |
std::vector<std::unique_ptr<MPI_Request>> request_requests; |
| 373 |
|
| 374 |
/** |
| 375 |
* The number of processes from which we are still expecting answers. |
| 376 |
*/ |
| 377 |
unsigned int n_outstanding_answers; |
| 378 |
|
| 379 |
// request for barrier |
| 380 |
MPI_Request barrier_request; |
| 381 |
#endif |
| 382 |
|
| 383 |
/** |
| 384 |
* List of processes who have made a request to this process. |
| 385 |
*/ |
| 386 |
std::set<unsigned int> requesting_processes; |
| 387 |
|
| 388 |
/** |
| 389 |
* Check whether all of the requests for answers that were created by |
| 390 |
* the communication posted from the current process to other ranks |
| 391 |
* have been satisfied. |
| 392 |
*/ |
| 393 |
bool |
| 394 |
all_locally_originated_receives_are_completed( |
| 395 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 396 |
&process_answer, |
| 397 |
const MPI_Comm comm); |
| 398 |
|
| 399 |
/** |
| 400 |
* Signal to all other ranks that this rank has received all request |
| 401 |
* answers via entering IBarrier. |
| 402 |
*/ |
| 403 |
void |
| 404 |
signal_finish(const MPI_Comm comm); |
| 405 |
|
| 406 |
/** |
| 407 |
* Check whether all of the requests for answers that were created by |
| 408 |
* communication posted from other processes to the current rank |
| 409 |
* have been satisfied. |
| 410 |
*/ |
| 411 |
bool |
| 412 |
all_remotely_originated_receives_are_completed(); |
| 413 |
|
| 414 |
/** |
| 415 |
* Check whether a request message from another rank has been received, |
| 416 |
* and if so, process the request by storing the data and sending an |
| 417 |
* answer. |
| 418 |
*/ |
| 419 |
void |
| 420 |
maybe_answer_one_request( |
| 421 |
const std::function<AnswerType(const unsigned int, |
| 422 |
const RequestType &)> &answer_request, |
| 423 |
const MPI_Comm comm); |
| 424 |
|
| 425 |
/** |
| 426 |
* Start to send all requests via ISend and post IRecvs for the incoming |
| 427 |
* answer messages. |
| 428 |
*/ |
| 429 |
void |
| 430 |
start_communication( |
| 431 |
const std::vector<unsigned int> &targets, |
| 432 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 433 |
const MPI_Comm comm); |
| 434 |
|
| 435 |
/** |
| 436 |
* After all rank has received all answers, the MPI data structures can |
| 437 |
* be freed and the received answers can be processed. |
| 438 |
*/ |
| 439 |
void |
| 440 |
clean_up_and_end_communication(const MPI_Comm comm); |
| 441 |
}; |
| 442 |
|
| 443 |
|
| 444 |
/** |
| 445 |
* This function implements a concrete algorithm for the |
| 446 |
* consensus algorithms problem (see the documentation of the |
| 447 |
* surrounding namespace), using only point-to-point |
| 448 |
* communications and a single IBarrier. This algorithm is suitable |
| 449 |
* for very large process counts because it does not require the |
| 450 |
* allocation of arrays with size proportional to the number of processes. |
| 451 |
* |
| 452 |
* @note This class closely follows @cite hoefler2010scalable, but our |
| 453 |
* implementation also deals with payloads. |
| 454 |
* |
| 455 |
* @param[in] targets A vector that contains the ranks of processes |
| 456 |
* to which requests should be sent and from which answers need |
| 457 |
* to be received. |
| 458 |
* @param[in] create_request A function object that takes the rank |
| 459 |
* of a target process as argument and returns the message that |
| 460 |
* forms the request to this target. |
| 461 |
* @param[in] answer_request A function that takes as arguments the |
| 462 |
* rank of the process that has sent a request to us, along with |
| 463 |
* the message of the request, and returns the message that forms |
| 464 |
* the answer that should be sent back to the requesting process. |
| 465 |
* @param[in] process_answer A function object that takes as argument |
| 466 |
* the rank of a process from which we have received an answer |
| 467 |
* to a previously sent request, along with the message that |
| 468 |
* forms this answer. This function is used to describe what |
| 469 |
* the caller of the consensus algorithm wants to do with the |
| 470 |
* received answer. |
| 471 |
* @param[in] comm The MPI communicator on which the whole algorithm |
| 472 |
* is to be performed. |
| 473 |
* |
| 474 |
* @tparam RequestType The type of the object to be sent. |
| 475 |
* @tparam AnswerType The type of the object to be received. |
| 476 |
* |
| 477 |
* @note Nothing good will generally happen if any of the function |
| 478 |
* objects passed as arguments throws an exception when called. |
| 479 |
* This is because when that happens, one MPI process will stop |
| 480 |
* participating in MPI communications, deadlocking the other |
| 481 |
* processes. As a consequence, the `create_request()`, |
| 482 |
* `answer_request()`, and `process_answer()` functions should |
| 483 |
* not throw any exceptions; if they encounter error |
| 484 |
* conditions, they should instead call `MPI_Abort()` or use |
| 485 |
* another way to reliably print an error message and then |
| 486 |
* bring the MPI universe down. |
| 487 |
*/ |
| 488 |
template <typename RequestType, typename AnswerType> |
| 489 |
std::vector<unsigned int> |
| 490 |
nbx(const std::vector<unsigned int> &targets, |
| 491 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 492 |
const std::function<AnswerType(const unsigned int, |
| 493 |
const RequestType &)> &answer_request, |
| 494 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 495 |
&process_answer, |
| 496 |
const MPI_Comm comm); |
| 497 |
|
| 498 |
/** |
| 499 |
* This function provides a specialization of the one above for |
| 500 |
* the case where a sending process does not require an answer. |
| 501 |
* Strictly speaking, the name "request" is then incorrect, as it |
| 502 |
* is simply one process sending a message to another, but we keep |
| 503 |
* the name for symmetry with the function above that processes both |
| 504 |
* requests and answers. |
| 505 |
* |
| 506 |
* Since the function does not deal with answers, the algorithm |
| 507 |
* implemented is really just a "some-to-some algorithm", as |
| 508 |
* also provided by the Utilities::MPI::some_to_some() function. |
| 509 |
* |
| 510 |
* @param[in] targets A vector that contains the ranks of processes |
| 511 |
* to which requests should be sent and from which answers need |
| 512 |
* to be received. |
| 513 |
* @param[in] create_request A function object that takes the rank |
| 514 |
* of a target process as argument and returns the message that |
| 515 |
* forms the request to this target. |
| 516 |
* @param[in] process_request A function that takes as arguments the |
| 517 |
* rank of the process that has sent a request to us, along with |
| 518 |
* the message of the request, and processes that message. |
| 519 |
* @param[in] comm The MPI communicator on which the whole algorithm |
| 520 |
* is to be performed. |
| 521 |
* |
| 522 |
* @tparam RequestType The type of the object to be sent. |
| 523 |
* |
| 524 |
* @note Nothing good will generally happen if any of the function |
| 525 |
* objects passed as arguments throws an exception when called. |
| 526 |
* This is because when that happens, one MPI process will stop |
| 527 |
* participating in MPI communications, deadlocking the other |
| 528 |
* processes. As a consequence, the `create_request()` and |
| 529 |
* `process_request()` functions should |
| 530 |
* not throw any exceptions; if they encounter error |
| 531 |
* conditions, they should instead call `MPI_Abort()` or use |
| 532 |
* another way to reliably print an error message and then |
| 533 |
* bring the MPI universe down. |
| 534 |
*/ |
| 535 |
template <typename RequestType> |
| 536 |
std::vector<unsigned int> |
| 537 |
nbx(const std::vector<unsigned int> &targets, |
| 538 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 539 |
const std::function<void(const unsigned int, const RequestType &)> |
| 540 |
&process_request, |
| 541 |
const MPI_Comm comm); |
| 542 |
|
| 543 |
/** |
| 544 |
* This class implements a concrete algorithm for the |
| 545 |
* ConsensusAlgorithms::Interface base class, using a two step approach. |
| 546 |
* In the first step the source ranks are determined and in the second |
| 547 |
* step a static sparse data exchange is performed. This algorithm is most |
| 548 |
* suitable for relatively small process counts -- say, less than 100. |
| 549 |
* |
| 550 |
* @note In contrast to NBX, this class splits the same |
| 551 |
* task into two distinct steps. In the first step, all processes |
| 552 |
* are identified who want to send a request to this process. In the |
| 553 |
* second step, the data is exchanged. However, since - in the |
| 554 |
* second step - now it is clear how many requests have to be answered, |
| 555 |
* i.e. when this process can stop waiting for requests, no IBarrier is |
| 556 |
* needed. |
| 557 |
* |
| 558 |
* @note Under the hood, this function uses |
| 559 |
* Utilities::MPI::compute_point_to_point_communication_pattern() |
| 560 |
* to determine the source processes, which itself is based on the |
| 561 |
* NBX-algorithm from @cite hoefler2010scalable that is implemented |
| 562 |
* in the ConsensusAlgorithms::NBX class (a sister class to the |
| 563 |
* current one). |
| 564 |
* |
| 565 |
* @tparam RequestType The type of the elements of the vector to be sent. |
| 566 |
* @tparam AnswerType The type of the elements of the vector to be received. |
| 567 |
*/ |
| 568 |
template <typename RequestType, typename AnswerType> |
| 569 |
class PEX : public Interface<RequestType, AnswerType> |
| 570 |
{ |
| 571 |
public: |
| 572 |
/** |
| 573 |
* Default constructor. |
| 574 |
*/ |
| 575 |
PEX() = default; |
| 576 |
|
| 577 |
/** |
| 578 |
* Destructor. |
| 579 |
*/ |
| 580 |
virtual ~PEX() = default; |
| 581 |
|
| 582 |
// Import the declarations from the base class. |
| 583 |
using Interface<RequestType, AnswerType>::run; |
| 584 |
|
| 585 |
/** |
| 586 |
* @copydoc Interface::run() |
| 587 |
*/ |
| 588 |
virtual std::vector<unsigned int> |
| 589 |
run( |
| 590 |
const std::vector<unsigned int> &targets, |
| 591 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 592 |
const std::function<AnswerType(const unsigned int, |
| 593 |
const RequestType &)> &answer_request, |
| 594 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 595 |
&process_answer, |
| 596 |
const MPI_Comm comm) override; |
| 597 |
|
| 598 |
private: |
| 599 |
#ifdef DEAL_II_WITH_MPI |
| 600 |
/** |
| 601 |
* Buffers for sending requests. |
| 602 |
*/ |
| 603 |
std::vector<std::vector<char>> send_buffers; |
| 604 |
|
| 605 |
/** |
| 606 |
* Buffers for receiving answers to requests. |
| 607 |
*/ |
| 608 |
std::vector<std::vector<char>> recv_buffers; |
| 609 |
|
| 610 |
/** |
| 611 |
* MPI request objects for sending request messages. |
| 612 |
*/ |
| 613 |
std::vector<MPI_Request> send_request_requests; |
| 614 |
|
| 615 |
/** |
| 616 |
* Buffers for sending answers to requests. |
| 617 |
*/ |
| 618 |
std::vector<std::vector<char>> requests_buffers; |
| 619 |
|
| 620 |
/** |
| 621 |
* Requests for sending answers to requests. |
| 622 |
*/ |
| 623 |
std::vector<MPI_Request> send_answer_requests; |
| 624 |
#endif |
| 625 |
/** |
| 626 |
* List of processes who have made a request to this process. |
| 627 |
*/ |
| 628 |
std::set<unsigned int> requesting_processes; |
| 629 |
|
| 630 |
/** |
| 631 |
* Start to send all requests via ISend and post IRecvs for the incoming |
| 632 |
* answer messages. |
| 633 |
*/ |
| 634 |
unsigned int |
| 635 |
start_communication( |
| 636 |
const std::vector<unsigned int> &targets, |
| 637 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 638 |
const MPI_Comm comm); |
| 639 |
|
| 640 |
/** |
| 641 |
* The `index`th request message from another rank has been received: |
| 642 |
* process the request and send an answer. |
| 643 |
*/ |
| 644 |
void |
| 645 |
answer_one_request( |
| 646 |
const unsigned int index, |
| 647 |
const std::function<AnswerType(const unsigned int, |
| 648 |
const RequestType &)> &answer_request, |
| 649 |
const MPI_Comm comm); |
| 650 |
|
| 651 |
/** |
| 652 |
* Receive and process all of the incoming responses to the |
| 653 |
* requests we sent. |
| 654 |
*/ |
| 655 |
void |
| 656 |
process_incoming_answers( |
| 657 |
const unsigned int n_targets, |
| 658 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 659 |
&process_answer, |
| 660 |
const MPI_Comm comm); |
| 661 |
|
| 662 |
/** |
| 663 |
* After all answers have been exchanged, the MPI data structures can be |
| 664 |
* freed and the received answers can be processed. |
| 665 |
*/ |
| 666 |
void |
| 667 |
clean_up_and_end_communication(); |
| 668 |
}; |
| 669 |
|
| 670 |
|
| 671 |
|
| 672 |
/** |
| 673 |
* This function implements a concrete algorithm for the |
| 674 |
* consensus algorithms problem (see the documentation of the |
| 675 |
* surrounding namespace), using a two step approach. |
| 676 |
* In the first step the source ranks are determined and in the second |
| 677 |
* step a static sparse data exchange is performed. This algorithm is most |
| 678 |
* suitable for relatively small process counts -- say, less than 100. |
| 679 |
* |
| 680 |
* @note In contrast to NBX, this class splits the same |
| 681 |
* task into two distinct steps. In the first step, all processes |
| 682 |
* are identified who want to send a request to this process. In the |
| 683 |
* second step, the data is exchanged. However, since - in the |
| 684 |
* second step - now it is clear how many requests have to be answered, |
| 685 |
* i.e. when this process can stop waiting for requests, no IBarrier is |
| 686 |
* needed. |
| 687 |
* |
| 688 |
* @note Under the hood, this function uses |
| 689 |
* Utilities::MPI::compute_point_to_point_communication_pattern() |
| 690 |
* to determine the source processes, which itself is based on the |
| 691 |
* NBX-algorithm from @cite hoefler2010scalable that is implemented |
| 692 |
* in the ConsensusAlgorithms::NBX class (a sister class to the |
| 693 |
* current one). |
| 694 |
* |
| 695 |
* @param[in] targets A vector that contains the ranks of processes |
| 696 |
* to which requests should be sent and from which answers need |
| 697 |
* to be received. |
| 698 |
* @param[in] create_request A function object that takes the rank |
| 699 |
* of a target process as argument and returns the message that |
| 700 |
* forms the request to this target. |
| 701 |
* @param[in] answer_request A function that takes as arguments the |
| 702 |
* rank of the process that has sent a request to us, along with |
| 703 |
* the message of the request, and returns the message that forms |
| 704 |
* the answer that should be sent back to the requesting process. |
| 705 |
* @param[in] process_answer A function object that takes as argument |
| 706 |
* the rank of a process from which we have received an answer |
| 707 |
* to a previously sent request, along with the message that |
| 708 |
* forms this answer. This function is used to describe what |
| 709 |
* the caller of the consensus algorithm wants to do with the |
| 710 |
* received answer. |
| 711 |
* @param[in] comm The MPI communicator on which the whole algorithm |
| 712 |
* is to be performed. |
| 713 |
* |
| 714 |
* @tparam RequestType The type of the object to be sent. |
| 715 |
* @tparam AnswerType The type of the object to be received. |
| 716 |
* |
| 717 |
* @note Nothing good will generally happen if any of the function |
| 718 |
* objects passed as arguments throws an exception when called. |
| 719 |
* This is because when that happens, one MPI process will stop |
| 720 |
* participating in MPI communications, deadlocking the other |
| 721 |
* processes. As a consequence, the `create_request()`, |
| 722 |
* `answer_request()`, and `process_answer()` functions should |
| 723 |
* not throw any exceptions; if they encounter error |
| 724 |
* conditions, they should instead call `MPI_Abort()` or use |
| 725 |
* another way to reliably print an error message and then |
| 726 |
* bring the MPI universe down. |
| 727 |
*/ |
| 728 |
template <typename RequestType, typename AnswerType> |
| 729 |
std::vector<unsigned int> |
| 730 |
pex(const std::vector<unsigned int> &targets, |
| 731 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 732 |
const std::function<AnswerType(const unsigned int, |
| 733 |
const RequestType &)> &answer_request, |
| 734 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 735 |
&process_answer, |
| 736 |
const MPI_Comm comm); |
| 737 |
|
| 738 |
/** |
| 739 |
* This function provides a specialization of the one above for |
| 740 |
* the case where a sending process does not require an answer. |
| 741 |
* Strictly speaking, the name "request" is then incorrect, as it |
| 742 |
* is simply one process sending a message to another, but we keep |
| 743 |
* the name for symmetry with the function above that processes both |
| 744 |
* requests and answers. |
| 745 |
* |
| 746 |
* Since the function does not deal with answers, the algorithm |
| 747 |
* implemented is really just a "some-to-some algorithm", as |
| 748 |
* also provided by the Utilities::MPI::some_to_some() function. |
| 749 |
* |
| 750 |
* @param[in] targets A vector that contains the ranks of processes |
| 751 |
* to which requests should be sent and from which answers need |
| 752 |
* to be received. |
| 753 |
* @param[in] create_request A function object that takes the rank |
| 754 |
* of a target process as argument and returns the message that |
| 755 |
* forms the request to this target. |
| 756 |
* @param[in] process_request A function that takes as arguments the |
| 757 |
* rank of the process that has sent a request to us, along with |
| 758 |
* the message of the request, and processes that message. |
| 759 |
* @param[in] comm The MPI communicator on which the whole algorithm |
| 760 |
* is to be performed. |
| 761 |
* |
| 762 |
* @tparam RequestType The type of the object to be sent. |
| 763 |
* |
| 764 |
* @note Nothing good will generally happen if any of the function |
| 765 |
* objects passed as arguments throws an exception when called. |
| 766 |
* This is because when that happens, one MPI process will stop |
| 767 |
* participating in MPI communications, deadlocking the other |
| 768 |
* processes. As a consequence, the `create_request()` and |
| 769 |
* `process_request()` functions should |
| 770 |
* not throw any exceptions; if they encounter error |
| 771 |
* conditions, they should instead call `MPI_Abort()` or use |
| 772 |
* another way to reliably print an error message and then |
| 773 |
* bring the MPI universe down. |
| 774 |
*/ |
| 775 |
template <typename RequestType> |
| 776 |
std::vector<unsigned int> |
| 777 |
pex(const std::vector<unsigned int> &targets, |
| 778 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 779 |
const std::function<void(const unsigned int, const RequestType &)> |
| 780 |
&process_request, |
| 781 |
const MPI_Comm comm); |
| 782 |
|
| 783 |
|
| 784 |
/** |
| 785 |
* A serial fall back for the above classes to allow programming |
| 786 |
* independently of whether MPI is used or not. |
| 787 |
*/ |
| 788 |
template <typename RequestType, typename AnswerType> |
| 789 |
class Serial : public Interface<RequestType, AnswerType> |
| 790 |
{ |
| 791 |
public: |
| 792 |
/** |
| 793 |
* Default constructor. |
| 794 |
*/ |
| 795 |
Serial() = default; |
| 796 |
|
| 797 |
// Import the declarations from the base class. |
| 798 |
using Interface<RequestType, AnswerType>::run; |
| 799 |
|
| 800 |
/** |
| 801 |
* @copydoc Interface::run() |
| 802 |
*/ |
| 803 |
virtual std::vector<unsigned int> |
| 804 |
run( |
| 805 |
const std::vector<unsigned int> &targets, |
| 806 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 807 |
const std::function<AnswerType(const unsigned int, |
| 808 |
const RequestType &)> &answer_request, |
| 809 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 810 |
&process_answer, |
| 811 |
const MPI_Comm comm) override; |
| 812 |
}; |
| 813 |
|
| 814 |
|
| 815 |
|
| 816 |
/** |
| 817 |
* This function implements a concrete algorithm for the |
| 818 |
* consensus algorithms problem (see the documentation of the |
| 819 |
* surrounding namespace), as a fall-back option for the case |
| 820 |
* where the communicator provided has only one rank (or when |
| 821 |
* MPI is simply not used at all). |
| 822 |
* |
| 823 |
* @param[in] targets A vector that contains the ranks of processes |
| 824 |
* to which requests should be sent and from which answers need |
| 825 |
* to be received. |
| 826 |
* @param[in] create_request A function object that takes the rank |
| 827 |
* of a target process as argument and returns the message that |
| 828 |
* forms the request to this target. |
| 829 |
* @param[in] answer_request A function that takes as arguments the |
| 830 |
* rank of the process that has sent a request to us, along with |
| 831 |
* the message of the request, and returns the message that forms |
| 832 |
* the answer that should be sent back to the requesting process. |
| 833 |
* @param[in] process_answer A function object that takes as argument |
| 834 |
* the rank of a process from which we have received an answer |
| 835 |
* to a previously sent request, along with the message that |
| 836 |
* forms this answer. This function is used to describe what |
| 837 |
* the caller of the consensus algorithm wants to do with the |
| 838 |
* received answer. |
| 839 |
* @param[in] comm The MPI communicator on which the whole algorithm |
| 840 |
* is to be performed. Since this function is supposed to be run |
| 841 |
* only for serial cases, the function throws an exception if |
| 842 |
* the provided communicator denotes an MPI universe with more |
| 843 |
* than one process. |
| 844 |
* |
| 845 |
* @tparam RequestType The type of the object to be sent. |
| 846 |
* @tparam AnswerType The type of the object to be received. |
| 847 |
*/ |
| 848 |
template <typename RequestType, typename AnswerType> |
| 849 |
std::vector<unsigned int> |
| 850 |
serial( |
| 851 |
const std::vector<unsigned int> &targets, |
| 852 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 853 |
const std::function<AnswerType(const unsigned int, const RequestType &)> |
| 854 |
&answer_request, |
| 855 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 856 |
&process_answer, |
| 857 |
const MPI_Comm comm); |
| 858 |
|
| 859 |
/** |
| 860 |
* This function provides a specialization of the one above for |
| 861 |
* the case where a sending process does not require an answer. |
| 862 |
* Strictly speaking, the name "request" is then incorrect, as it |
| 863 |
* is simply one process sending a message to another, but we keep |
| 864 |
* the name for symmetry with the function above that processes both |
| 865 |
* requests and answers. |
| 866 |
* |
| 867 |
* Since the function does not deal with answers, the algorithm |
| 868 |
* implemented is really just a "some-to-some algorithm", as |
| 869 |
* also provided by the Utilities::MPI::some_to_some() function. |
| 870 |
* |
| 871 |
* @param[in] targets A vector that contains the ranks of processes |
| 872 |
* to which requests should be sent and from which answers need |
| 873 |
* to be received. |
| 874 |
* @param[in] create_request A function object that takes the rank |
| 875 |
* of a target process as argument and returns the message that |
| 876 |
* forms the request to this target. |
| 877 |
* @param[in] process_request A function that takes as arguments the |
| 878 |
* rank of the process that has sent a request to us, along with |
| 879 |
* the message of the request, and processes that message. |
| 880 |
* @param[in] comm The MPI communicator on which the whole algorithm |
| 881 |
* is to be performed. Since this function is supposed to be run |
| 882 |
* only for serial cases, the function throws an exception if |
| 883 |
* the provided communicator denotes an MPI universe with more |
| 884 |
* than one process. |
| 885 |
* |
| 886 |
* @tparam RequestType The type of the object to be sent. |
| 887 |
*/ |
| 888 |
template <typename RequestType> |
| 889 |
std::vector<unsigned int> |
| 890 |
serial( |
| 891 |
const std::vector<unsigned int> &targets, |
| 892 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 893 |
const std::function<void(const unsigned int, const RequestType &)> |
| 894 |
&process_request, |
| 895 |
const MPI_Comm comm); |
| 896 |
|
| 897 |
|
| 898 |
|
| 899 |
/** |
| 900 |
* A class which delegates its task to other |
| 901 |
* ConsensusAlgorithms::Interface implementations depending on the number |
| 902 |
* of processes in the MPI communicator. For a small number of processes |
| 903 |
* it uses PEX and for a large number of processes NBX. The threshold |
| 904 |
* depends if the program is compiled in debug or release mode, but the |
| 905 |
* goal is to always use the most efficient algorithm for however many |
| 906 |
* processes participate in the communication. |
| 907 |
* |
| 908 |
* @tparam RequestType The type of the elements of the vector to be sent. |
| 909 |
* @tparam AnswerType The type of the elements of the vector to be received. |
| 910 |
*/ |
| 911 |
template <typename RequestType, typename AnswerType> |
| 912 |
class Selector : public Interface<RequestType, AnswerType> |
| 913 |
{ |
| 914 |
public: |
| 915 |
/** |
| 916 |
* Default constructor. |
| 917 |
*/ |
| 918 |
Selector() = default; |
| 919 |
|
| 920 |
/** |
| 921 |
* Destructor. |
| 922 |
*/ |
| 923 |
virtual ~Selector() = default; |
| 924 |
|
| 925 |
// Import the declarations from the base class. |
| 926 |
using Interface<RequestType, AnswerType>::run; |
| 927 |
|
| 928 |
/** |
| 929 |
* @copydoc Interface::run() |
| 930 |
* |
| 931 |
* @note The function call is delegated to another ConsensusAlgorithms::Interface implementation. |
| 932 |
*/ |
| 933 |
virtual std::vector<unsigned int> |
| 934 |
run( |
| 935 |
const std::vector<unsigned int> &targets, |
| 936 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 937 |
const std::function<AnswerType(const unsigned int, |
| 938 |
const RequestType &)> &answer_request, |
| 939 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 940 |
&process_answer, |
| 941 |
const MPI_Comm comm) override; |
| 942 |
|
| 943 |
private: |
| 944 |
// Pointer to the actual ConsensusAlgorithms::Interface implementation. |
| 945 |
std::shared_ptr<Interface<RequestType, AnswerType>> consensus_algo; |
| 946 |
}; |
| 947 |
|
| 948 |
|
| 949 |
|
| 950 |
/** |
| 951 |
* This function implements a concrete algorithm for the |
| 952 |
* consensus algorithms problem (see the documentation of the |
| 953 |
* surrounding namespace). In particular, it delegates its work |
| 954 |
* to one of the other functions in this namespace depending on the number |
| 955 |
* of processes in the MPI communicator. For a small number of processes |
| 956 |
* it uses pex() and for a large number of processes nbx(). The threshold |
| 957 |
* depends if the program is compiled in debug or release mode, but the |
| 958 |
* goal is to always use the most efficient algorithm for however many |
| 959 |
* processes participate in the communication. |
| 960 |
* |
| 961 |
* @param[in] targets A vector that contains the ranks of processes |
| 962 |
* to which requests should be sent and from which answers need |
| 963 |
* to be received. |
| 964 |
* @param[in] create_request A function object that takes the rank |
| 965 |
* of a target process as argument and returns the message that |
| 966 |
* forms the request to this target. |
| 967 |
* @param[in] answer_request A function that takes as arguments the |
| 968 |
* rank of the process that has sent a request to us, along with |
| 969 |
* the message of the request, and returns the message that forms |
| 970 |
* the answer that should be sent back to the requesting process. |
| 971 |
* @param[in] process_answer A function object that takes as argument |
| 972 |
* the rank of a process from which we have received an answer |
| 973 |
* to a previously sent request, along with the message that |
| 974 |
* forms this answer. This function is used to describe what |
| 975 |
* the caller of the consensus algorithm wants to do with the |
| 976 |
* received answer. |
| 977 |
* @param[in] comm The MPI communicator on which the whole algorithm |
| 978 |
* is to be performed. |
| 979 |
* |
| 980 |
* @tparam RequestType The type of the object to be sent. |
| 981 |
* @tparam AnswerType The type of the object to be received. |
| 982 |
* |
| 983 |
* @note Nothing good will generally happen if any of the function |
| 984 |
* objects passed as arguments throws an exception when called. |
| 985 |
* This is because when that happens, one MPI process will stop |
| 986 |
* participating in MPI communications, deadlocking the other |
| 987 |
* processes. As a consequence, the `create_request()`, |
| 988 |
* `answer_request()`, and `process_answer()` functions should |
| 989 |
* not throw any exceptions; if they encounter error |
| 990 |
* conditions, they should instead call `MPI_Abort()` or use |
| 991 |
* another way to reliably print an error message and then |
| 992 |
* bring the MPI universe down. |
| 993 |
*/ |
| 994 |
template <typename RequestType, typename AnswerType> |
| 995 |
std::vector<unsigned int> |
| 996 |
selector( |
| 997 |
const std::vector<unsigned int> &targets, |
| 998 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 999 |
const std::function<AnswerType(const unsigned int, const RequestType &)> |
| 1000 |
&answer_request, |
| 1001 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 1002 |
&process_answer, |
| 1003 |
const MPI_Comm comm); |
| 1004 |
|
| 1005 |
/** |
| 1006 |
* This function provides a specialization of the one above for |
| 1007 |
* the case where a sending process does not require an answer. |
| 1008 |
* Strictly speaking, the name "request" is then incorrect, as it |
| 1009 |
* is simply one process sending a message to another, but we keep |
| 1010 |
* the name for symmetry with the function above that processes both |
| 1011 |
* requests and answers. |
| 1012 |
* |
| 1013 |
* Since the function does not deal with answers, the algorithm |
| 1014 |
* implemented is really just a "some-to-some algorithm", as |
| 1015 |
* also provided by the Utilities::MPI::some_to_some() function. |
| 1016 |
* |
| 1017 |
* @param[in] targets A vector that contains the ranks of processes |
| 1018 |
* to which requests should be sent and from which answers need |
| 1019 |
* to be received. |
| 1020 |
* @param[in] create_request A function object that takes the rank |
| 1021 |
* of a target process as argument and returns the message that |
| 1022 |
* forms the request to this target. |
| 1023 |
* @param[in] process_request A function that takes as arguments the |
| 1024 |
* rank of the process that has sent a request to us, along with |
| 1025 |
* the message of the request, and processes that message. |
| 1026 |
* @param[in] comm The MPI communicator on which the whole algorithm |
| 1027 |
* is to be performed. |
| 1028 |
* |
| 1029 |
* @tparam RequestType The type of the object to be sent. |
| 1030 |
* |
| 1031 |
* @note Nothing good will generally happen if any of the function |
| 1032 |
* objects passed as arguments throws an exception when called. |
| 1033 |
* This is because when that happens, one MPI process will stop |
| 1034 |
* participating in MPI communications, deadlocking the other |
| 1035 |
* processes. As a consequence, the `create_request()` |
| 1036 |
* and `process_request()` functions should |
| 1037 |
* not throw any exceptions; if they encounter error |
| 1038 |
* conditions, they should instead call `MPI_Abort()` or use |
| 1039 |
* another way to reliably print an error message and then |
| 1040 |
* bring the MPI universe down. |
| 1041 |
*/ |
| 1042 |
template <typename RequestType> |
| 1043 |
std::vector<unsigned int> |
| 1044 |
selector( |
| 1045 |
const std::vector<unsigned int> &targets, |
| 1046 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 1047 |
const std::function<void(const unsigned int, const RequestType &)> |
| 1048 |
&process_request, |
| 1049 |
const MPI_Comm comm); |
| 1050 |
|
| 1051 |
|
| 1052 |
|
| 1053 |
#ifndef DOXYGEN |
| 1054 |
// Implementation of the functions in this namespace. |
| 1055 |
|
| 1056 |
template <typename RequestType, typename AnswerType> |
| 1057 |
std::vector<unsigned int> |
| 1058 |
nbx(const std::vector<unsigned int> &targets, |
| 1059 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 1060 |
const std::function<AnswerType(const unsigned int, |
| 1061 |
const RequestType &)> &answer_request, |
| 1062 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 1063 |
&process_answer, |
| 1064 |
const MPI_Comm comm) |
| 1065 |
{ |
| 1066 |
return NBX<RequestType, AnswerType>().run( |
| 1067 |
targets, create_request, answer_request, process_answer, comm); |
| 1068 |
} |
| 1069 |
|
| 1070 |
|
| 1071 |
|
| 1072 |
template <typename RequestType> |
| 1073 |
std::vector<unsigned int> |
| 1074 |
nbx(const std::vector<unsigned int> &targets, |
| 1075 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 1076 |
const std::function<void(const unsigned int, const RequestType &)> |
| 1077 |
&process_request, |
| 1078 |
const MPI_Comm comm) |
| 1079 |
{ |
| 1080 |
// TODO: For the moment, simply implement this special case by |
| 1081 |
// forwarding to the other function with rewritten function |
| 1082 |
// objects and using an empty type as answer type. This way, |
| 1083 |
// we have the interface in place and can provide a more |
| 1084 |
// efficient implementation later on. |
| 1085 |
using EmptyType = std::tuple<>; |
| 1086 |
|
| 1087 |
return nbx<RequestType, EmptyType>( |
| 1088 |
targets, |
| 1089 |
create_request, |
| 1090 |
// answer_request: |
| 1091 |
[&process_request](const unsigned int source_rank, |
| 1092 |
const RequestType &request) -> EmptyType { |
| 1093 |
process_request(source_rank, request); |
| 1094 |
// Return something. What it is is arbitrary here, except that |
| 1095 |
// we want it to be as small an object as possible. Using |
| 1096 |
// std::tuple<> is interpreted as an empty object that is packed |
| 1097 |
// down to a zero-length char array. |
| 1098 |
return {}; |
| 1099 |
}, |
| 1100 |
// process_answer: |
| 1101 |
[](const unsigned int /*target_rank */, |
| 1102 |
const EmptyType & /*answer*/) {}, |
| 1103 |
comm); |
| 1104 |
} |
| 1105 |
|
| 1106 |
|
| 1107 |
|
| 1108 |
template <typename RequestType, typename AnswerType> |
| 1109 |
std::vector<unsigned int> |
| 1110 |
pex(const std::vector<unsigned int> &targets, |
| 1111 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 1112 |
const std::function<AnswerType(const unsigned int, |
| 1113 |
const RequestType &)> &answer_request, |
| 1114 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 1115 |
&process_answer, |
| 1116 |
const MPI_Comm comm) |
| 1117 |
{ |
| 1118 |
return PEX<RequestType, AnswerType>().run( |
| 1119 |
targets, create_request, answer_request, process_answer, comm); |
| 1120 |
} |
| 1121 |
|
| 1122 |
|
| 1123 |
|
| 1124 |
template <typename RequestType> |
| 1125 |
std::vector<unsigned int> |
| 1126 |
pex(const std::vector<unsigned int> &targets, |
| 1127 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 1128 |
const std::function<void(const unsigned int, const RequestType &)> |
| 1129 |
&process_request, |
| 1130 |
const MPI_Comm comm) |
| 1131 |
{ |
| 1132 |
// TODO: For the moment, simply implement this special case by |
| 1133 |
// forwarding to the other function with rewritten function |
| 1134 |
// objects and using an empty type as answer type. This way, |
| 1135 |
// we have the interface in place and can provide a more |
| 1136 |
// efficient implementation later on. |
| 1137 |
using EmptyType = std::tuple<>; |
| 1138 |
|
| 1139 |
return pex<RequestType, EmptyType>( |
| 1140 |
targets, |
| 1141 |
create_request, |
| 1142 |
// answer_request: |
| 1143 |
[&process_request](const unsigned int source_rank, |
| 1144 |
const RequestType &request) -> EmptyType { |
| 1145 |
process_request(source_rank, request); |
| 1146 |
// Return something. What it is is arbitrary here, except that |
| 1147 |
// we want it to be as small an object as possible. Using |
| 1148 |
// std::tuple<> is interpreted as an empty object that is packed |
| 1149 |
// down to a zero-length char array. |
| 1150 |
return {}; |
| 1151 |
}, |
| 1152 |
// process_answer: |
| 1153 |
[](const unsigned int /*target_rank */, |
| 1154 |
const EmptyType & /*answer*/) {}, |
| 1155 |
comm); |
| 1156 |
} |
| 1157 |
|
| 1158 |
|
| 1159 |
|
| 1160 |
template <typename RequestType, typename AnswerType> |
| 1161 |
std::vector<unsigned int> |
| 1162 |
serial( |
| 1163 |
const std::vector<unsigned int> &targets, |
| 1164 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 1165 |
const std::function<AnswerType(const unsigned int, const RequestType &)> |
| 1166 |
&answer_request, |
| 1167 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 1168 |
&process_answer, |
| 1169 |
const MPI_Comm comm) |
| 1170 |
{ |
| 1171 |
return Serial<RequestType, AnswerType>().run( |
| 1172 |
targets, create_request, answer_request, process_answer, comm); |
| 1173 |
} |
| 1174 |
|
| 1175 |
|
| 1176 |
|
| 1177 |
template <typename RequestType> |
| 1178 |
std::vector<unsigned int> |
| 1179 |
serial( |
| 1180 |
const std::vector<unsigned int> &targets, |
| 1181 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 1182 |
const std::function<void(const unsigned int, const RequestType &)> |
| 1183 |
&process_request, |
| 1184 |
const MPI_Comm comm) |
| 1185 |
{ |
| 1186 |
// TODO: For the moment, simply implement this special case by |
| 1187 |
// forwarding to the other function with rewritten function |
| 1188 |
// objects and using an empty type as answer type. This way, |
| 1189 |
// we have the interface in place and can provide a more |
| 1190 |
// efficient implementation later on. |
| 1191 |
using EmptyType = std::tuple<>; |
| 1192 |
|
| 1193 |
return serial<RequestType, EmptyType>( |
| 1194 |
targets, |
| 1195 |
create_request, |
| 1196 |
// answer_request: |
| 1197 |
[&process_request](const unsigned int source_rank, |
| 1198 |
const RequestType &request) -> EmptyType { |
| 1199 |
process_request(source_rank, request); |
| 1200 |
// Return something. What it is is arbitrary here, except that |
| 1201 |
// we want it to be as small an object as possible. Using |
| 1202 |
// std::tuple<> is interpreted as an empty object that is packed |
| 1203 |
// down to a zero-length char array. |
| 1204 |
return {}; |
| 1205 |
}, |
| 1206 |
// process_answer: |
| 1207 |
[](const unsigned int /*target_rank */, |
| 1208 |
const EmptyType & /*answer*/) {}, |
| 1209 |
comm); |
| 1210 |
} |
| 1211 |
|
| 1212 |
|
| 1213 |
|
| 1214 |
template <typename RequestType, typename AnswerType> |
| 1215 |
std::vector<unsigned int> |
| 1216 |
selector( |
| 1217 |
const std::vector<unsigned int> &targets, |
| 1218 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 1219 |
const std::function<AnswerType(const unsigned int, const RequestType &)> |
| 1220 |
&answer_request, |
| 1221 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 1222 |
&process_answer, |
| 1223 |
const MPI_Comm comm) |
| 1224 |
{ |
| 1225 |
return Selector<RequestType, AnswerType>().run( |
| 1226 |
targets, create_request, answer_request, process_answer, comm); |
| 1227 |
} |
| 1228 |
|
| 1229 |
|
| 1230 |
|
| 1231 |
template <typename RequestType> |
| 1232 |
std::vector<unsigned int> |
| 1233 |
selector( |
| 1234 |
const std::vector<unsigned int> &targets, |
| 1235 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 1236 |
const std::function<void(const unsigned int, const RequestType &)> |
| 1237 |
&process_request, |
| 1238 |
const MPI_Comm comm) |
| 1239 |
{ |
| 1240 |
// TODO: For the moment, simply implement this special case by |
| 1241 |
// forwarding to the other function with rewritten function |
| 1242 |
// objects and using an empty type as answer type. This way, |
| 1243 |
// we have the interface in place and can provide a more |
| 1244 |
// efficient implementation later on. |
| 1245 |
using EmptyType = std::tuple<>; |
| 1246 |
|
| 1247 |
return selector<RequestType, EmptyType>( |
| 1248 |
targets, |
| 1249 |
create_request, |
| 1250 |
// answer_request: |
| 1251 |
[&process_request](const unsigned int source_rank, |
| 1252 |
const RequestType &request) -> EmptyType { |
| 1253 |
process_request(source_rank, request); |
| 1254 |
// Return something. What it is is arbitrary here, except that |
| 1255 |
// we want it to be as small an object as possible. Using |
| 1256 |
// std::tuple<> is interpreted as an empty object that is packed |
| 1257 |
// down to a zero-length char array. |
| 1258 |
return {}; |
| 1259 |
}, |
| 1260 |
// process_answer: |
| 1261 |
[](const unsigned int /*target_rank */, |
| 1262 |
const EmptyType & /*answer*/) {}, |
| 1263 |
comm); |
| 1264 |
} |
| 1265 |
|
| 1266 |
#endif |
| 1267 |
|
| 1268 |
|
| 1269 |
} // namespace ConsensusAlgorithms |
| 1270 |
} // end of namespace MPI |
| 1271 |
} // end of namespace Utilities |
| 1272 |
|
| 1273 |
|
| 1274 |
|
| 1275 |
#ifndef DOXYGEN |
| 1276 |
|
| 1277 |
// ----------------- Implementation of template functions |
| 1278 |
|
| 1279 |
namespace Utilities |
| 1280 |
{ |
| 1281 |
namespace MPI |
| 1282 |
{ |
| 1283 |
namespace ConsensusAlgorithms |
| 1284 |
{ |
| 1285 |
namespace internal |
| 1286 |
{ |
| 1287 |
/** |
| 1288 |
* Return whether a vector of targets (MPI ranks) has only unique |
| 1289 |
* elements. |
| 1290 |
*/ |
| 1291 |
inline bool |
| 1292 |
has_unique_elements(const std::vector<unsigned int> &targets) |
| 1293 |
{ |
| 1294 |
std::vector<unsigned int> my_destinations = targets; |
| 1295 |
std::sort(my_destinations.begin(), my_destinations.end()); |
| 1296 |
return (std::adjacent_find(my_destinations.begin(), |
| 1297 |
my_destinations.end()) == |
| 1298 |
my_destinations.end()); |
| 1299 |
} |
| 1300 |
|
| 1301 |
|
| 1302 |
|
| 1303 |
/** |
| 1304 |
* Handle exceptions inside the ConsensusAlgorithm::run() functions. |
| 1305 |
*/ |
| 1306 |
inline void |
| 1307 |
handle_exception(std::exception_ptr &&exception, const MPI_Comm comm) |
| 1308 |
{ |
| 1309 |
# ifdef DEAL_II_WITH_MPI |
| 1310 |
// an exception within a ConsensusAlgorithm likely causes an |
| 1311 |
// MPI deadlock. Abort with a reasonable error message instead. |
| 1312 |
try |
| 1313 |
{ |
| 1314 |
std::rethrow_exception(exception); |
| 1315 |
} |
| 1316 |
catch (ExceptionBase &exc) |
| 1317 |
{ |
| 1318 |
// report name of the deal.II exception: |
| 1319 |
std::cerr |
| 1320 |
<< std::endl |
| 1321 |
<< std::endl |
| 1322 |
<< "----------------------------------------------------" |
| 1323 |
<< std::endl; |
| 1324 |
std::cerr |
| 1325 |
<< "Exception '" << exc.get_exc_name() << "'" |
| 1326 |
<< " on rank " << Utilities::MPI::this_mpi_process(comm) |
| 1327 |
<< " on processing: " << std::endl |
| 1328 |
<< exc.what() << std::endl |
| 1329 |
<< "Aborting!" << std::endl |
| 1330 |
<< "----------------------------------------------------" |
| 1331 |
<< std::endl; |
| 1332 |
|
| 1333 |
// Then bring down the whole MPI world |
| 1334 |
MPI_Abort(comm, 255); |
| 1335 |
} |
| 1336 |
catch (std::exception &exc) |
| 1337 |
{ |
| 1338 |
std::cerr |
| 1339 |
<< std::endl |
| 1340 |
<< std::endl |
| 1341 |
<< "----------------------------------------------------" |
| 1342 |
<< std::endl; |
| 1343 |
std::cerr |
| 1344 |
<< "Exception within ConsensusAlgorithm" |
| 1345 |
<< " on rank " << Utilities::MPI::this_mpi_process(comm) |
| 1346 |
<< " on processing: " << std::endl |
| 1347 |
<< exc.what() << std::endl |
| 1348 |
<< "Aborting!" << std::endl |
| 1349 |
<< "----------------------------------------------------" |
| 1350 |
<< std::endl; |
| 1351 |
|
| 1352 |
// Then bring down the whole MPI world |
| 1353 |
MPI_Abort(comm, 255); |
| 1354 |
} |
| 1355 |
catch (...) |
| 1356 |
{ |
| 1357 |
std::cerr |
| 1358 |
<< std::endl |
| 1359 |
<< std::endl |
| 1360 |
<< "----------------------------------------------------" |
| 1361 |
<< std::endl; |
| 1362 |
std::cerr |
| 1363 |
<< "Unknown exception within ConsensusAlgorithm!" << std::endl |
| 1364 |
<< "Aborting!" << std::endl |
| 1365 |
<< "----------------------------------------------------" |
| 1366 |
<< std::endl; |
| 1367 |
|
| 1368 |
// Then bring down the whole MPI world |
| 1369 |
MPI_Abort(comm, 255); |
| 1370 |
} |
| 1371 |
# else |
| 1372 |
(void)comm; |
| 1373 |
|
| 1374 |
// No need to be concerned about deadlocks without MPI. |
| 1375 |
// Defer to exception handling further up the callstack. |
| 1376 |
std::rethrow_exception(exception); |
| 1377 |
# endif |
| 1378 |
} |
| 1379 |
} // namespace internal |
| 1380 |
|
| 1381 |
|
| 1382 |
|
| 1383 |
template <typename RequestType, typename AnswerType> |
| 1384 |
void |
| 1385 |
Process<RequestType, AnswerType>::answer_request(const unsigned int, |
| 1386 |
const RequestType &, |
| 1387 |
AnswerType &) |
| 1388 |
{ |
| 1389 |
// nothing to do |
| 1390 |
} |
| 1391 |
|
| 1392 |
|
| 1393 |
|
| 1394 |
template <typename RequestType, typename AnswerType> |
| 1395 |
void |
| 1396 |
Process<RequestType, AnswerType>::create_request(const unsigned int, |
| 1397 |
RequestType &) |
| 1398 |
{ |
| 1399 |
// nothing to do |
| 1400 |
} |
| 1401 |
|
| 1402 |
|
| 1403 |
|
| 1404 |
template <typename RequestType, typename AnswerType> |
| 1405 |
void |
| 1406 |
Process<RequestType, AnswerType>::read_answer(const unsigned int, |
| 1407 |
const AnswerType &) |
| 1408 |
{ |
| 1409 |
// nothing to do |
| 1410 |
} |
| 1411 |
|
| 1412 |
|
| 1413 |
|
| 1414 |
template <typename RequestType, typename AnswerType> |
| 1415 |
std::vector<unsigned int> |
| 1416 |
Interface<RequestType, AnswerType>::run( |
| 1417 |
Process<RequestType, AnswerType> &process, |
| 1418 |
const MPI_Comm comm) |
| 1419 |
{ |
| 1420 |
// Unpack the 'process' object and call the function that takes |
| 1421 |
// function objects for all operations. |
| 1422 |
return run( |
| 1423 |
process.compute_targets(), |
| 1424 |
/* create_request: */ |
| 1425 |
[&process](const unsigned int target) { |
| 1426 |
RequestType request; |
| 1427 |
process.create_request(target, request); |
| 1428 |
return request; |
| 1429 |
}, |
| 1430 |
/* answer_request: */ |
| 1431 |
[&process](const unsigned int source, const RequestType &request) { |
| 1432 |
AnswerType answer; |
| 1433 |
process.answer_request(source, request, answer); |
| 1434 |
return answer; |
| 1435 |
}, |
| 1436 |
/* process_answer: */ |
| 1437 |
[&process](const unsigned int target, const AnswerType &answer) { |
| 1438 |
process.read_answer(target, answer); |
| 1439 |
}, |
| 1440 |
comm); |
| 1441 |
} |
| 1442 |
|
| 1443 |
|
| 1444 |
|
| 1445 |
template <typename RequestType, typename AnswerType> |
| 1446 |
std::vector<unsigned int> |
| 1447 |
NBX<RequestType, AnswerType>::run( |
| 1448 |
const std::vector<unsigned int> &targets, |
| 1449 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 1450 |
const std::function<AnswerType(const unsigned int, const RequestType &)> |
| 1451 |
&answer_request, |
| 1452 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 1453 |
&process_answer, |
| 1454 |
const MPI_Comm comm) |
| 1455 |
{ |
| 1456 |
Assert(internal::has_unique_elements(targets), |
| 1457 |
ExcMessage("The consensus algorithms expect that each process " |
| 1458 |
"only sends a single message to another process, " |
| 1459 |
"but the targets provided include duplicates.")); |
| 1460 |
|
| 1461 |
static CollectiveMutex mutex; |
| 1462 |
CollectiveMutex::ScopedLock lock(mutex, comm); |
| 1463 |
|
| 1464 |
try |
| 1465 |
{ |
| 1466 |
// 1) Send data to identified targets and start receiving |
| 1467 |
// the answers from these very same processes. |
| 1468 |
start_communication(targets, create_request, comm); |
| 1469 |
|
| 1470 |
// 2) Until all posted receive operations are known to have |
| 1471 |
// completed, answer requests and keep checking whether all |
| 1472 |
// requests of this process have been answered. |
| 1473 |
// |
| 1474 |
// The requests that we catch in the answer_requests() |
| 1475 |
// function originate elsewhere, that is, they are not in |
| 1476 |
// response to our own messages |
| 1477 |
// |
| 1478 |
// Note also that we may not catch all incoming requests in |
| 1479 |
// the following two lines: our own requests may have been |
| 1480 |
// satisfied before we've dealt with all incoming requests. |
| 1481 |
// That's ok: We will get around to dealing with all |
| 1482 |
// remaining message later. We just want to move on to the |
| 1483 |
// next step as early as possible. |
| 1484 |
while (all_locally_originated_receives_are_completed(process_answer, |
| 1485 |
comm) == false) |
| 1486 |
maybe_answer_one_request(answer_request, comm); |
| 1487 |
|
| 1488 |
// 3) Signal to all other processes that all requests of this |
| 1489 |
// process have been answered |
| 1490 |
signal_finish(comm); |
| 1491 |
|
| 1492 |
// 4) Nevertheless, this process has to keep on answering |
| 1493 |
// (potential) incoming requests until all processes have |
| 1494 |
// received the answer to all requests |
| 1495 |
while (all_remotely_originated_receives_are_completed() == false) |
| 1496 |
maybe_answer_one_request(answer_request, comm); |
| 1497 |
|
| 1498 |
// 5) process the answer to all requests |
| 1499 |
clean_up_and_end_communication(comm); |
| 1500 |
} |
| 1501 |
catch (...) |
| 1502 |
{ |
| 1503 |
internal::handle_exception(std::current_exception(), comm); |
| 1504 |
} |
| 1505 |
|
| 1506 |
return std::vector<unsigned int>(requesting_processes.begin(), |
| 1507 |
requesting_processes.end()); |
| 1508 |
} |
| 1509 |
|
| 1510 |
|
| 1511 |
|
| 1512 |
template <typename RequestType, typename AnswerType> |
| 1513 |
void |
| 1514 |
NBX<RequestType, AnswerType>::start_communication( |
| 1515 |
const std::vector<unsigned int> &targets, |
| 1516 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 1517 |
const MPI_Comm comm) |
| 1518 |
{ |
| 1519 |
# ifdef DEAL_II_WITH_MPI |
| 1520 |
// 1) |
| 1521 |
const auto n_targets = targets.size(); |
| 1522 |
|
| 1523 |
const int tag_request = Utilities::MPI::internal::Tags:: |
| 1524 |
consensus_algorithm_nbx_answer_request; |
| 1525 |
|
| 1526 |
// 2) allocate memory |
| 1527 |
send_requests.resize(n_targets); |
| 1528 |
send_buffers.resize(n_targets); |
| 1529 |
|
| 1530 |
{ |
| 1531 |
// 4) send and receive |
| 1532 |
for (unsigned int index = 0; index < n_targets; ++index) |
| 1533 |
{ |
| 1534 |
const unsigned int rank = targets[index]; |
| 1535 |
AssertIndexRange(rank, Utilities::MPI::n_mpi_processes(comm)); |
| 1536 |
|
| 1537 |
auto &send_buffer = send_buffers[index]; |
| 1538 |
send_buffer = |
| 1539 |
(create_request ? Utilities::pack(create_request(rank), false) : |
| 1540 |
std::vector<char>()); |
| 1541 |
|
| 1542 |
// Post a request to send data |
| 1543 |
auto ierr = MPI_Isend(send_buffer.data(), |
| 1544 |
send_buffer.size(), |
| 1545 |
MPI_CHAR, |
| 1546 |
rank, |
| 1547 |
tag_request, |
| 1548 |
comm, |
| 1549 |
&send_requests[index]); |
| 1550 |
AssertThrowMPI(ierr); |
| 1551 |
} |
| 1552 |
|
| 1553 |
// Also record that we expect an answer from each target we sent |
| 1554 |
// a request to: |
| 1555 |
n_outstanding_answers = n_targets; |
| 1556 |
} |
| 1557 |
# else |
| 1558 |
(void)targets; |
| 1559 |
(void)create_request; |
| 1560 |
(void)comm; |
| 1561 |
# endif |
| 1562 |
} |
| 1563 |
|
| 1564 |
|
| 1565 |
|
| 1566 |
template <typename RequestType, typename AnswerType> |
| 1567 |
bool |
| 1568 |
NBX<RequestType, AnswerType>:: |
| 1569 |
all_locally_originated_receives_are_completed( |
| 1570 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 1571 |
&process_answer, |
| 1572 |
const MPI_Comm comm) |
| 1573 |
{ |
| 1574 |
# ifdef DEAL_II_WITH_MPI |
| 1575 |
// We know that all requests have come in when we have pending |
| 1576 |
// messages from all targets with the right tag (some of which we may |
| 1577 |
// have already taken care of below, after discovering their existence). |
| 1578 |
// We can check for pending messages with MPI_IProbe, which returns |
| 1579 |
// immediately with a return code that indicates whether |
| 1580 |
// it has found a message from any process with a given |
| 1581 |
// tag. |
| 1582 |
if (n_outstanding_answers == 0) |
| 1583 |
return true; |
| 1584 |
else |
| 1585 |
{ |
| 1586 |
const int tag_deliver = Utilities::MPI::internal::Tags:: |
| 1587 |
consensus_algorithm_nbx_process_deliver; |
| 1588 |
|
| 1589 |
int request_is_pending; |
| 1590 |
MPI_Status status; |
| 1591 |
const auto ierr = MPI_Iprobe( |
| 1592 |
MPI_ANY_SOURCE, tag_deliver, comm, &request_is_pending, &status); |
| 1593 |
AssertThrowMPI(ierr); |
| 1594 |
|
| 1595 |
// If there is no pending message with this tag, |
| 1596 |
// then we are clearly not done receiving everything |
| 1597 |
// yet -- so return false. |
| 1598 |
if (request_is_pending == 0) |
| 1599 |
return false; |
| 1600 |
else |
| 1601 |
{ |
| 1602 |
// OK, so we have gotten a reply to our request from |
| 1603 |
// one rank. Let us process it. |
| 1604 |
const auto target = status.MPI_SOURCE; |
| 1605 |
|
| 1606 |
// Then query the size of the message, allocate enough memory, |
| 1607 |
// receive the data, and process it. |
| 1608 |
int message_size; |
| 1609 |
{ |
| 1610 |
const int ierr = |
| 1611 |
MPI_Get_count(&status, MPI_CHAR, &message_size); |
| 1612 |
AssertThrowMPI(ierr); |
| 1613 |
} |
| 1614 |
std::vector<char> recv_buffer(message_size); |
| 1615 |
|
| 1616 |
{ |
| 1617 |
const int tag_deliver = Utilities::MPI::internal::Tags:: |
| 1618 |
consensus_algorithm_nbx_process_deliver; |
| 1619 |
|
| 1620 |
const int ierr = MPI_Recv(recv_buffer.data(), |
| 1621 |
recv_buffer.size(), |
| 1622 |
MPI_CHAR, |
| 1623 |
target, |
| 1624 |
tag_deliver, |
| 1625 |
comm, |
| 1626 |
MPI_STATUS_IGNORE); |
| 1627 |
AssertThrowMPI(ierr); |
| 1628 |
} |
| 1629 |
|
| 1630 |
if (process_answer) |
| 1631 |
process_answer(target, |
| 1632 |
Utilities::unpack<AnswerType>(recv_buffer, |
| 1633 |
false)); |
| 1634 |
|
| 1635 |
// Finally, remove this rank from the list of outstanding |
| 1636 |
// targets: |
| 1637 |
--n_outstanding_answers; |
| 1638 |
|
| 1639 |
// We could do another go-around from the top of this |
| 1640 |
// else-branch to see whether there are actually other messages |
| 1641 |
// that are currently pending. But that would mean spending |
| 1642 |
// substantial time in receiving answers while we should also be |
| 1643 |
// sending answers to requests we have received from other |
| 1644 |
// places. So let it be enough for now. If there are outstanding |
| 1645 |
// answers, we will get back to this function before long and |
| 1646 |
// can take care of them then. |
| 1647 |
return (n_outstanding_answers == 0); |
| 1648 |
} |
| 1649 |
} |
| 1650 |
|
| 1651 |
# else |
| 1652 |
(void)process_answer; |
| 1653 |
(void)comm; |
| 1654 |
|
| 1655 |
return true; |
| 1656 |
# endif |
| 1657 |
} |
| 1658 |
|
| 1659 |
|
| 1660 |
|
| 1661 |
template <typename RequestType, typename AnswerType> |
| 1662 |
void |
| 1663 |
NBX<RequestType, AnswerType>::maybe_answer_one_request( |
| 1664 |
const std::function<AnswerType(const unsigned int, const RequestType &)> |
| 1665 |
&answer_request, |
| 1666 |
const MPI_Comm comm) |
| 1667 |
{ |
| 1668 |
# ifdef DEAL_II_WITH_MPI |
| 1669 |
|
| 1670 |
const int tag_request = Utilities::MPI::internal::Tags:: |
| 1671 |
consensus_algorithm_nbx_answer_request; |
| 1672 |
const int tag_deliver = Utilities::MPI::internal::Tags:: |
| 1673 |
consensus_algorithm_nbx_process_deliver; |
| 1674 |
|
| 1675 |
// Check if there is a request pending. By selecting the |
| 1676 |
// tag_request tag, these are other processes asking for |
| 1677 |
// our own replies, not these other processes' replies |
| 1678 |
// to our own requests. |
| 1679 |
// |
| 1680 |
// There may be multiple such pending messages. We |
| 1681 |
// only answer one. |
| 1682 |
MPI_Status status; |
| 1683 |
int request_is_pending; |
| 1684 |
const auto ierr = MPI_Iprobe( |
| 1685 |
MPI_ANY_SOURCE, tag_request, comm, &request_is_pending, &status); |
| 1686 |
AssertThrowMPI(ierr); |
| 1687 |
|
| 1688 |
if (request_is_pending != 0) |
| 1689 |
{ |
| 1690 |
// Get the rank of the requesting process and add it to the |
| 1691 |
// list of requesting processes (which may contain duplicates). |
| 1692 |
const auto other_rank = status.MPI_SOURCE; |
| 1693 |
|
| 1694 |
Assert(requesting_processes.find(other_rank) == |
| 1695 |
requesting_processes.end(), |
| 1696 |
ExcMessage("Process is requesting a second time!")); |
| 1697 |
requesting_processes.insert(other_rank); |
| 1698 |
|
| 1699 |
// get size of incoming message |
| 1700 |
int number_amount; |
| 1701 |
auto ierr = MPI_Get_count(&status, MPI_CHAR, &number_amount); |
| 1702 |
AssertThrowMPI(ierr); |
| 1703 |
|
| 1704 |
// allocate memory for incoming message |
| 1705 |
std::vector<char> buffer_recv(number_amount); |
| 1706 |
ierr = MPI_Recv(buffer_recv.data(), |
| 1707 |
number_amount, |
| 1708 |
MPI_CHAR, |
| 1709 |
other_rank, |
| 1710 |
tag_request, |
| 1711 |
comm, |
| 1712 |
MPI_STATUS_IGNORE); |
| 1713 |
AssertThrowMPI(ierr); |
| 1714 |
|
| 1715 |
// Allocate memory for an answer message to the current request, |
| 1716 |
// and ask the 'process' object to produce an answer: |
| 1717 |
request_buffers.emplace_back(std::make_unique<std::vector<char>>()); |
| 1718 |
auto &request_buffer = *request_buffers.back(); |
| 1719 |
if (answer_request) |
| 1720 |
request_buffer = |
| 1721 |
Utilities::pack(answer_request(other_rank, |
| 1722 |
Utilities::unpack<RequestType>( |
| 1723 |
buffer_recv, false)), |
| 1724 |
false); |
| 1725 |
|
| 1726 |
// Then initiate sending the answer back to the requester. |
| 1727 |
request_requests.emplace_back(std::make_unique<MPI_Request>()); |
| 1728 |
ierr = MPI_Isend(request_buffer.data(), |
| 1729 |
request_buffer.size(), |
| 1730 |
MPI_CHAR, |
| 1731 |
other_rank, |
| 1732 |
tag_deliver, |
| 1733 |
comm, |
| 1734 |
request_requests.back().get()); |
| 1735 |
AssertThrowMPI(ierr); |
| 1736 |
} |
| 1737 |
# else |
| 1738 |
(void)answer_request; |
| 1739 |
(void)comm; |
| 1740 |
# endif |
| 1741 |
} |
| 1742 |
|
| 1743 |
|
| 1744 |
|
| 1745 |
template <typename RequestType, typename AnswerType> |
| 1746 |
void |
| 1747 |
NBX<RequestType, AnswerType>::signal_finish(const MPI_Comm comm) |
| 1748 |
{ |
| 1749 |
# ifdef DEAL_II_WITH_MPI |
| 1750 |
const auto ierr = MPI_Ibarrier(comm, &barrier_request); |
| 1751 |
AssertThrowMPI(ierr); |
| 1752 |
# else |
| 1753 |
(void)comm; |
| 1754 |
# endif |
| 1755 |
} |
| 1756 |
|
| 1757 |
|
| 1758 |
|
| 1759 |
template <typename RequestType, typename AnswerType> |
| 1760 |
bool |
| 1761 |
NBX<RequestType, |
| 1762 |
AnswerType>::all_remotely_originated_receives_are_completed() |
| 1763 |
{ |
| 1764 |
# ifdef DEAL_II_WITH_MPI |
| 1765 |
int all_ranks_reached_barrier; |
| 1766 |
const auto ierr = MPI_Test(&barrier_request, |
| 1767 |
&all_ranks_reached_barrier, |
| 1768 |
MPI_STATUS_IGNORE); |
| 1769 |
AssertThrowMPI(ierr); |
| 1770 |
return all_ranks_reached_barrier != 0; |
| 1771 |
# else |
| 1772 |
return true; |
| 1773 |
# endif |
| 1774 |
} |
| 1775 |
|
| 1776 |
|
| 1777 |
|
| 1778 |
template <typename RequestType, typename AnswerType> |
| 1779 |
void |
| 1780 |
NBX<RequestType, AnswerType>::clean_up_and_end_communication( |
| 1781 |
const MPI_Comm comm) |
| 1782 |
{ |
| 1783 |
(void)comm; |
| 1784 |
# ifdef DEAL_II_WITH_MPI |
| 1785 |
// clean up |
| 1786 |
{ |
| 1787 |
if (send_requests.size() > 0) |
| 1788 |
{ |
| 1789 |
const int ierr = MPI_Waitall(send_requests.size(), |
| 1790 |
send_requests.data(), |
| 1791 |
MPI_STATUSES_IGNORE); |
| 1792 |
AssertThrowMPI(ierr); |
| 1793 |
} |
| 1794 |
|
| 1795 |
int ierr = MPI_Wait(&barrier_request, MPI_STATUS_IGNORE); |
| 1796 |
AssertThrowMPI(ierr); |
| 1797 |
|
| 1798 |
for (auto &i : request_requests) |
| 1799 |
{ |
| 1800 |
ierr = MPI_Wait(i.get(), MPI_STATUS_IGNORE); |
| 1801 |
AssertThrowMPI(ierr); |
| 1802 |
} |
| 1803 |
|
| 1804 |
if constexpr (running_in_debug_mode()) |
| 1805 |
{ |
| 1806 |
// note: IBarrier seems to make problem during testing, this |
| 1807 |
// additional Barrier seems to help |
| 1808 |
ierr = MPI_Barrier(comm); |
| 1809 |
AssertThrowMPI(ierr); |
| 1810 |
} |
| 1811 |
} |
| 1812 |
# endif |
| 1813 |
} |
| 1814 |
|
| 1815 |
|
| 1816 |
|
| 1817 |
template <typename RequestType, typename AnswerType> |
| 1818 |
std::vector<unsigned int> |
| 1819 |
PEX<RequestType, AnswerType>::run( |
| 1820 |
const std::vector<unsigned int> &targets, |
| 1821 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 1822 |
const std::function<AnswerType(const unsigned int, const RequestType &)> |
| 1823 |
&answer_request, |
| 1824 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 1825 |
&process_answer, |
| 1826 |
const MPI_Comm comm) |
| 1827 |
{ |
| 1828 |
Assert(internal::has_unique_elements(targets), |
| 1829 |
ExcMessage("The consensus algorithms expect that each process " |
| 1830 |
"only sends a single message to another process, " |
| 1831 |
"but the targets provided include duplicates.")); |
| 1832 |
|
| 1833 |
static CollectiveMutex mutex; |
| 1834 |
CollectiveMutex::ScopedLock lock(mutex, comm); |
| 1835 |
|
| 1836 |
try |
| 1837 |
{ |
| 1838 |
// 1) Send requests and start receiving the answers. |
| 1839 |
// In particular, determine how many requests we should expect |
| 1840 |
// on the current process. |
| 1841 |
const unsigned int n_requests = |
| 1842 |
start_communication(targets, create_request, comm); |
| 1843 |
|
| 1844 |
// 2) Answer requests: |
| 1845 |
for (unsigned int request = 0; request < n_requests; ++request) |
| 1846 |
answer_one_request(request, answer_request, comm); |
| 1847 |
|
| 1848 |
// 3) Process answers: |
| 1849 |
process_incoming_answers(targets.size(), process_answer, comm); |
| 1850 |
|
| 1851 |
// 4) Make sure all sends have successfully terminated: |
| 1852 |
clean_up_and_end_communication(); |
| 1853 |
} |
| 1854 |
catch (...) |
| 1855 |
{ |
| 1856 |
internal::handle_exception(std::current_exception(), comm); |
| 1857 |
} |
| 1858 |
|
| 1859 |
return std::vector<unsigned int>(requesting_processes.begin(), |
| 1860 |
requesting_processes.end()); |
| 1861 |
} |
| 1862 |
|
| 1863 |
|
| 1864 |
|
| 1865 |
template <typename RequestType, typename AnswerType> |
| 1866 |
unsigned int |
| 1867 |
PEX<RequestType, AnswerType>::start_communication( |
| 1868 |
const std::vector<unsigned int> &targets, |
| 1869 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 1870 |
const MPI_Comm comm) |
| 1871 |
{ |
| 1872 |
# ifdef DEAL_II_WITH_MPI |
| 1873 |
const int tag_request = Utilities::MPI::internal::Tags:: |
| 1874 |
consensus_algorithm_pex_answer_request; |
| 1875 |
|
| 1876 |
// 1) determine with which processes this process wants to communicate |
| 1877 |
// with |
| 1878 |
const unsigned int n_targets = targets.size(); |
| 1879 |
|
| 1880 |
// 2) determine who wants to communicate with this process |
| 1881 |
const unsigned int n_sources = |
| 1882 |
compute_n_point_to_point_communications(comm, targets); |
| 1883 |
|
| 1884 |
// 2) allocate memory |
| 1885 |
recv_buffers.resize(n_targets); |
| 1886 |
send_buffers.resize(n_targets); |
| 1887 |
send_request_requests.resize(n_targets); |
| 1888 |
|
| 1889 |
send_answer_requests.resize(n_sources); |
| 1890 |
requests_buffers.resize(n_sources); |
| 1891 |
|
| 1892 |
// 4) send and receive |
| 1893 |
for (unsigned int i = 0; i < n_targets; ++i) |
| 1894 |
{ |
| 1895 |
const unsigned int rank = targets[i]; |
| 1896 |
AssertIndexRange(rank, Utilities::MPI::n_mpi_processes(comm)); |
| 1897 |
|
| 1898 |
// pack data which should be sent |
| 1899 |
auto &send_buffer = send_buffers[i]; |
| 1900 |
if (create_request) |
| 1901 |
send_buffer = Utilities::pack(create_request(rank), false); |
| 1902 |
|
| 1903 |
// start to send data |
| 1904 |
auto ierr = MPI_Isend(send_buffer.data(), |
| 1905 |
send_buffer.size(), |
| 1906 |
MPI_CHAR, |
| 1907 |
rank, |
| 1908 |
tag_request, |
| 1909 |
comm, |
| 1910 |
&send_request_requests[i]); |
| 1911 |
AssertThrowMPI(ierr); |
| 1912 |
} |
| 1913 |
|
| 1914 |
return n_sources; |
| 1915 |
# else |
| 1916 |
(void)targets; |
| 1917 |
(void)create_request; |
| 1918 |
(void)comm; |
| 1919 |
return 0; |
| 1920 |
# endif |
| 1921 |
} |
| 1922 |
|
| 1923 |
|
| 1924 |
|
| 1925 |
template <typename RequestType, typename AnswerType> |
| 1926 |
void |
| 1927 |
PEX<RequestType, AnswerType>::answer_one_request( |
| 1928 |
const unsigned int index, |
| 1929 |
const std::function<AnswerType(const unsigned int, const RequestType &)> |
| 1930 |
&answer_request, |
| 1931 |
const MPI_Comm comm) |
| 1932 |
{ |
| 1933 |
# ifdef DEAL_II_WITH_MPI |
| 1934 |
const int tag_request = Utilities::MPI::internal::Tags:: |
| 1935 |
consensus_algorithm_pex_answer_request; |
| 1936 |
const int tag_deliver = Utilities::MPI::internal::Tags:: |
| 1937 |
consensus_algorithm_pex_process_deliver; |
| 1938 |
|
| 1939 |
// Wait until we have a message ready for retrieval, though we don't |
| 1940 |
// care which process it is from. |
| 1941 |
MPI_Status status; |
| 1942 |
int ierr = MPI_Probe(MPI_ANY_SOURCE, tag_request, comm, &status); |
| 1943 |
AssertThrowMPI(ierr); |
| 1944 |
|
| 1945 |
// Get rank of incoming message and verify that it makes sense |
| 1946 |
const unsigned int other_rank = status.MPI_SOURCE; |
| 1947 |
|
| 1948 |
Assert(requesting_processes.find(other_rank) == |
| 1949 |
requesting_processes.end(), |
| 1950 |
ExcMessage( |
| 1951 |
"A process is sending a request after a request from " |
| 1952 |
"the same process has previously already been " |
| 1953 |
"received. This algorithm does not expect this to happen.")); |
| 1954 |
requesting_processes.insert(other_rank); |
| 1955 |
|
| 1956 |
// Actually get the incoming message: |
| 1957 |
int number_amount; |
| 1958 |
ierr = MPI_Get_count(&status, MPI_CHAR, &number_amount); |
| 1959 |
AssertThrowMPI(ierr); |
| 1960 |
|
| 1961 |
std::vector<char> buffer_recv(number_amount); |
| 1962 |
ierr = MPI_Recv(buffer_recv.data(), |
| 1963 |
number_amount, |
| 1964 |
MPI_CHAR, |
| 1965 |
other_rank, |
| 1966 |
tag_request, |
| 1967 |
comm, |
| 1968 |
&status); |
| 1969 |
AssertThrowMPI(ierr); |
| 1970 |
|
| 1971 |
// Process request by asking the user-provided function for |
| 1972 |
// the answer and post a send for it. |
| 1973 |
auto &request_buffer = requests_buffers[index]; |
| 1974 |
request_buffer = |
| 1975 |
(answer_request ? |
| 1976 |
Utilities::pack(answer_request(other_rank, |
| 1977 |
Utilities::unpack<RequestType>( |
| 1978 |
buffer_recv, false)), |
| 1979 |
false) : |
| 1980 |
std::vector<char>()); |
| 1981 |
|
| 1982 |
ierr = MPI_Isend(request_buffer.data(), |
| 1983 |
request_buffer.size(), |
| 1984 |
MPI_CHAR, |
| 1985 |
other_rank, |
| 1986 |
tag_deliver, |
| 1987 |
comm, |
| 1988 |
&send_answer_requests[index]); |
| 1989 |
AssertThrowMPI(ierr); |
| 1990 |
# else |
| 1991 |
(void)answer_request; |
| 1992 |
(void)comm; |
| 1993 |
(void)index; |
| 1994 |
# endif |
| 1995 |
} |
| 1996 |
|
| 1997 |
|
| 1998 |
|
| 1999 |
template <typename RequestType, typename AnswerType> |
| 2000 |
void |
| 2001 |
PEX<RequestType, AnswerType>::process_incoming_answers( |
| 2002 |
const unsigned int n_targets, |
| 2003 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 2004 |
&process_answer, |
| 2005 |
const MPI_Comm comm) |
| 2006 |
{ |
| 2007 |
# ifdef DEAL_II_WITH_MPI |
| 2008 |
const int tag_deliver = Utilities::MPI::internal::Tags:: |
| 2009 |
consensus_algorithm_pex_process_deliver; |
| 2010 |
|
| 2011 |
// We know how many targets we have sent requests to. These |
| 2012 |
// targets will all eventually send us their responses, but |
| 2013 |
// we need not process them in order -- rather, just see what |
| 2014 |
// comes in and then look at message originators' ranks and |
| 2015 |
// message sizes |
| 2016 |
for (unsigned int i = 0; i < n_targets; ++i) |
| 2017 |
{ |
| 2018 |
MPI_Status status; |
| 2019 |
{ |
| 2020 |
const int ierr = |
| 2021 |
MPI_Probe(MPI_ANY_SOURCE, tag_deliver, comm, &status); |
| 2022 |
AssertThrowMPI(ierr); |
| 2023 |
} |
| 2024 |
|
| 2025 |
const auto other_rank = status.MPI_SOURCE; |
| 2026 |
int message_size; |
| 2027 |
{ |
| 2028 |
const int ierr = MPI_Get_count(&status, MPI_CHAR, &message_size); |
| 2029 |
AssertThrowMPI(ierr); |
| 2030 |
} |
| 2031 |
std::vector<char> recv_buffer(message_size); |
| 2032 |
|
| 2033 |
// Now actually receive the answer. Because the MPI_Probe |
| 2034 |
// above blocks until we have a message, we know that the |
| 2035 |
// following MPI_Recv call will immediately succeed. |
| 2036 |
{ |
| 2037 |
const int ierr = MPI_Recv(recv_buffer.data(), |
| 2038 |
recv_buffer.size(), |
| 2039 |
MPI_CHAR, |
| 2040 |
other_rank, |
| 2041 |
tag_deliver, |
| 2042 |
comm, |
| 2043 |
MPI_STATUS_IGNORE); |
| 2044 |
AssertThrowMPI(ierr); |
| 2045 |
} |
| 2046 |
|
| 2047 |
if (process_answer) |
| 2048 |
process_answer(other_rank, |
| 2049 |
Utilities::unpack<AnswerType>(recv_buffer, false)); |
| 2050 |
} |
| 2051 |
# else |
| 2052 |
(void)n_targets; |
| 2053 |
(void)process_answer; |
| 2054 |
(void)comm; |
| 2055 |
# endif |
| 2056 |
} |
| 2057 |
|
| 2058 |
|
| 2059 |
|
| 2060 |
template <typename RequestType, typename AnswerType> |
| 2061 |
void |
| 2062 |
PEX<RequestType, AnswerType>::clean_up_and_end_communication() |
| 2063 |
{ |
| 2064 |
# ifdef DEAL_II_WITH_MPI |
| 2065 |
// Finalize all MPI_Request objects for both the |
| 2066 |
// send-request and receive-answer operations. |
| 2067 |
if (send_request_requests.size() > 0) |
| 2068 |
{ |
| 2069 |
const int ierr = MPI_Waitall(send_request_requests.size(), |
| 2070 |
send_request_requests.data(), |
| 2071 |
MPI_STATUSES_IGNORE); |
| 2072 |
AssertThrowMPI(ierr); |
| 2073 |
} |
| 2074 |
|
| 2075 |
// Then also check the send-answer requests. |
| 2076 |
if (send_answer_requests.size() > 0) |
| 2077 |
{ |
| 2078 |
const int ierr = MPI_Waitall(send_answer_requests.size(), |
| 2079 |
send_answer_requests.data(), |
| 2080 |
MPI_STATUSES_IGNORE); |
| 2081 |
AssertThrowMPI(ierr); |
| 2082 |
} |
| 2083 |
# endif |
| 2084 |
} |
| 2085 |
|
| 2086 |
|
| 2087 |
|
| 2088 |
template <typename RequestType, typename AnswerType> |
| 2089 |
std::vector<unsigned int> |
| 2090 |
Serial<RequestType, AnswerType>::run( |
| 2091 |
const std::vector<unsigned int> &targets, |
| 2092 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 2093 |
const std::function<AnswerType(const unsigned int, const RequestType &)> |
| 2094 |
&answer_request, |
| 2095 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 2096 |
&process_answer, |
| 2097 |
const MPI_Comm comm) |
| 2098 |
{ |
| 2099 |
Assert(Utilities::MPI::n_mpi_processes(comm) == 1, |
| 2100 |
ExcMessage("You shouldn't use the 'Serial' class on " |
| 2101 |
"communicators that have more than one process " |
| 2102 |
"associated with it.")); |
| 2103 |
|
| 2104 |
// The only valid target for a serial program is itself. |
| 2105 |
if (targets.size() != 0) |
| 2106 |
{ |
| 2107 |
Assert(targets.size() == 1, |
| 2108 |
ExcMessage( |
| 2109 |
"On a single process, the only valid target " |
| 2110 |
"is process zero (the process itself), which can only be " |
| 2111 |
"listed once.")); |
| 2112 |
AssertDimension(targets[0], 0); |
| 2113 |
|
| 2114 |
// Since the caller indicates that there is a target, and since we |
| 2115 |
// know that it is the current process, let the process send |
| 2116 |
// something to itself. |
| 2117 |
const RequestType request = |
| 2118 |
(create_request ? create_request(0) : RequestType()); |
| 2119 |
const AnswerType answer = |
| 2120 |
(answer_request ? answer_request(0, request) : AnswerType()); |
| 2121 |
|
| 2122 |
if (process_answer) |
| 2123 |
process_answer(0, answer); |
| 2124 |
} |
| 2125 |
|
| 2126 |
return targets; // nothing to do |
| 2127 |
} |
| 2128 |
|
| 2129 |
|
| 2130 |
|
| 2131 |
template <typename RequestType, typename AnswerType> |
| 2132 |
std::vector<unsigned int> |
| 2133 |
Selector<RequestType, AnswerType>::run( |
| 2134 |
const std::vector<unsigned int> &targets, |
| 2135 |
const std::function<RequestType(const unsigned int)> &create_request, |
| 2136 |
const std::function<AnswerType(const unsigned int, const RequestType &)> |
| 2137 |
&answer_request, |
| 2138 |
const std::function<void(const unsigned int, const AnswerType &)> |
| 2139 |
&process_answer, |
| 2140 |
const MPI_Comm comm) |
| 2141 |
{ |
| 2142 |
// Depending on the number of processes we switch between |
| 2143 |
// implementations. We reduce the threshold for debug mode to be |
| 2144 |
// able to test also the non-blocking implementation. This feature |
| 2145 |
// is tested by: |
| 2146 |
// tests/multigrid/transfer_matrix_free_06.with_mpi=true.with_p4est=true.with_trilinos=true.mpirun=10.output |
| 2147 |
|
| 2148 |
const unsigned int n_procs = (Utilities::MPI::job_supports_mpi() ? |
| 2149 |
Utilities::MPI::n_mpi_processes(comm) : |
| 2150 |
1); |
| 2151 |
# ifdef DEAL_II_WITH_MPI |
| 2152 |
# ifdef DEBUG |
| 2153 |
if (n_procs > 10) |
| 2154 |
# else |
| 2155 |
if (n_procs > 99) |
| 2156 |
# endif |
| 2157 |
consensus_algo.reset(new NBX<RequestType, AnswerType>()); |
| 2158 |
else |
| 2159 |
# endif |
| 2160 |
if (n_procs > 1) |
| 2161 |
consensus_algo.reset(new PEX<RequestType, AnswerType>()); |
| 2162 |
else |
| 2163 |
consensus_algo.reset(new Serial<RequestType, AnswerType>()); |
| 2164 |
|
| 2165 |
return consensus_algo->run( |
| 2166 |
targets, create_request, answer_request, process_answer, comm); |
| 2167 |
} |
| 2168 |
|
| 2169 |
|
| 2170 |
} // namespace ConsensusAlgorithms |
| 2171 |
} // end of namespace MPI |
| 2172 |
} // end of namespace Utilities |
| 2173 |
|
| 2174 |
#endif // DOXYGEN |
| 2175 |
|
| 2176 |
|
| 2177 |
DEAL_II_NAMESPACE_CLOSE |
| 2178 |
|
| 2179 |
#endif |