/usr/include/deal.II/base/timer.h is in libdeal.ii-dev 8.4.2-2+b1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 | // ---------------------------------------------------------------------
//
// Copyright (C) 1998 - 2015 by the deal.II authors
//
// This file is part of the deal.II library.
//
// The deal.II library is free software; you can use it, redistribute
// it, and/or modify it under the terms of the GNU Lesser General
// Public License as published by the Free Software Foundation; either
// version 2.1 of the License, or (at your option) any later version.
// The full text of the license can be found in the file LICENSE at
// the top level of the deal.II distribution.
//
// ---------------------------------------------------------------------
#ifndef dealii__timer_h
#define dealii__timer_h
#include <deal.II/base/config.h>
#include <deal.II/base/conditional_ostream.h>
#include <deal.II/base/thread_management.h>
#include <deal.II/base/utilities.h>
#ifdef DEAL_II_WITH_MPI
# include <mpi.h>
#endif
#include <string>
#include <list>
#include <map>
DEAL_II_NAMESPACE_OPEN
/**
* This is a very simple class which provides information about both the CPU
* time and the wallclock time elapsed since the timer was started last time.
* Information is retrieved from the system on the basis of clock cycles since
* last time the computer was booted for the CPU time. The wall time is based
* on the system clock accessed by @p gettimeofday, with a typical accuracy of
* 0.01 ms on linux systems.
*
*
* <h3>Usage</h3>
*
* Use of this class is as you might expect by looking at the member
* functions:
* @code
* Timer timer;
* timer.start ();
*
* // do some complicated computations here
* ...
*
* timer.stop ();
*
* std::cout << "Elapsed CPU time: " << timer() << " seconds.";
* std::cout << "Elapsed wall time: " << timer.wall_time() << " seconds.";
*
* // reset timer for the next thing it shall do
* timer.reset();
* @endcode
*
* Alternatively, you can also restart the timer instead of resetting it. The
* times between successive calls to start() / stop() will then be
* accumulated. The usage of this class is also explained in the step-28,
* step-29 and step-30 tutorial programs.
*
* @note Implementation of this class is system dependent. In case
* multithreaded routines (matrix-vector products, error estimators, etc.) are
* used, the CPU time is accumulated from all the children.
*
* @ingroup utilities
* @author G. Kanschat, W. Bangerth, M. Kronbichler
*/
class Timer
{
public:
/**
* Constructor. Starts the timer at 0 sec.
*/
Timer ();
#ifdef DEAL_II_WITH_MPI
/**
* Constructor that takes an MPI communicator as input. A timer constructed
* this way will sum up the CPU times over all processors in the MPI network
* when requested by the operator ().
*
* Starts the timer at 0 sec.
*
* If @p sync_wall_time is true, the wall time is synchronized between all
* CPUs using a MPI_Barrier() and a collective operation. Note that this
* only works if you stop() the timer before querying for the wall time. The
* time for the MPI operations are not included in the timing but may slow
* down your program.
*
* This constructor is only available if the deal.II compiler is an MPI
* compiler.
*/
Timer (MPI_Comm mpi_communicator,
const bool sync_wall_time = false);
/**
* Returns a reference to the data structure with global timing information.
* Filled after calling stop().
*/
const Utilities::MPI::MinMaxAvg &get_data() const;
/**
* Prints the data to the given stream.
*/
template <class StreamType>
void print_data(StreamType &stream) const;
#endif
/**
* Re-start the timer at the point where it was stopped. This way a
* cumulative measurement of time is possible.
*/
void start ();
/**
* Sets the current time as next starting time and return the elapsed time
* in seconds.
*/
double stop ();
/**
* Stop the timer if necessary and reset the elapsed time to zero.
*/
void reset ();
/**
* Resets the elapsed time to zero and starts the timer. This corresponds to
* calling @p reset() and @p start() on the Timer object.
*/
void restart();
/**
* Access to the current CPU time without disturbing time measurement. The
* elapsed time is returned in units of seconds.
*/
double operator() () const;
/**
* Access to the current wall time without disturbing time measurement. The
* elapsed time is returned in units of seconds.
*/
double wall_time () const;
/**
* Returns the last lap time; the time taken between the last start()/stop()
* call.
*/
double get_lap_time () const;
private:
/**
* Value of the user time when start() was called the last time or when the
* object was created and no stop() was issued in between.
*/
double start_time;
/**
* Similar to #start_time, but needed for children threads in multithread
* mode. Value of the user time when start() was called the last time or
* when the object was created and no stop() was issued in between.
*
* For some reason (error in operating system?) the function call
* <tt>getrusage(RUSAGE_CHILDREN,.)</tt> gives always 0 (at least on
* Solaris7). Hence the Timer class still does not yet work for
* multithreading mode.
*/
double start_time_children;
/**
* Value of the wall time when start() was called the last time or when the
* object was created and no stop() was issued in between.
*/
double start_wall_time;
/**
* Accumulated time for all previous start()/stop() cycles. The time for the
* present cycle is not included.
*/
double cumulative_time;
/**
* Accumulated wall time for all previous start()/stop() cycles. The wall
* time for the present cycle is not included.
*/
double cumulative_wall_time;
/**
* Stores the last lap time; the time between the last start()/stop() cycle.
*/
double last_lap_time;
/**
* Store whether the timer is presently running.
*/
bool running;
/**
* Store whether the timer is presently running.
*/
MPI_Comm mpi_communicator;
#ifdef DEAL_II_WITH_MPI
/**
* Store whether the wall time is synchronized between machines.
*/
bool sync_wall_time;
/**
* A structure for parallel wall time measurement that includes the minimum
* time recorded among all processes, the maximum time as well as the
* average time defined as the sum of all individual times divided by the
* number of MPI processes in the MPI_Comm.
*/
Utilities::MPI::MinMaxAvg mpi_data;
#endif
};
//TODO: The following class is not thread-safe
/**
* This class can be used to generate formatted output from time measurements
* of different subsections in a program. It is possible to create several
* sections that perform certain aspects of the program. A section can be
* entered several times. By changing the options in OutputFrequency and
* OutputType, the user can choose whether output should be generated every
* time a section is joined or just in the end of the program. Moreover, it is
* possible to show CPU times, wall times or both.
*
* <h3>Usage</h3>
*
* Use of this class could be as follows:
* @code
* TimerOutput timer (std::cout, TimerOutput::summary,
* TimerOutput::wall_times);
*
* timer.enter_subsection ("Setup dof system");
* setup_dofs();
* timer.leave_subsection();
*
* timer.enter_subsection ("Assemble");
* assemble_system_1();
* timer.leave_subsection();
*
* timer.enter_subsection ("Solve");
* solve_system_1();
* timer.leave_subsection();
*
* timer.enter_subsection ("Assemble");
* assemble_system_2();
* timer.leave_subsection();
*
* timer.enter_subsection ("Solve");
* solve_system_2();
* timer.leave_subsection();
*
* // do something else...
* @endcode
* When run, this program will return an output like this:
* @code
* +---------------------------------------------+------------+------------+
* | Total wallclock time elapsed since start | 88.8s | |
* | | | |
* | Section | no. calls | wall time | % of total |
* +---------------------------------+-----------+------------+------------+
* | Assemble | 2 | 19.7s | 22% |
* | Solve | 2 | 3.03s | 3.4% |
* | Setup dof system | 1 | 3.97s | 4.5% |
* +---------------------------------+-----------+------------+------------+
* @endcode
* The output will see that we entered the assembly and solve section twice,
* and reports how much time we spent there. Moreover, the class measures the
* total time spent from start to termination of the TimerOutput object. In
* this case, we did a lot of other stuff, so that the time proportions of the
* functions we measured are far away from 100 percent.
*
*
* <h3>Using scoped timers</h3>
*
* The scheme above where you have to have calls to
* TimerOutput::enter_subsection() and TimerOutput::leave_subsection() is
* awkward if the sections in between these calls contain <code>return</code>
* statements or may throw exceptions. In that case, it is easy to forget that
* one nevertheless needs to leave the section somehow, somewhere. An easier
* approach is to use "scoped" sections. This is a variable that when you
* create it enters a section, and leaves the section when you destroy it. If
* this is a variable local to a particular scope (a code block between curly
* braces) and you leave this scope due to a <code>return</code> statements or
* an exception, then the variable is destroyed and the timed section is left
* automatically. Consequently, we could have written the code piece above as
* follows, with exactly the same result but now exception-safe:
* @code
* TimerOutput timer (std::cout, TimerOutput::summary,
* TimerOutput::wall_times);
*
* {
* TimerOutput::Scope timer_section(timer, "Setup dof system");
* setup_dofs();
* }
*
* {
* TimerOutput::Scope timer_section(timer, "Assemble");
* assemble_system_1();
* }
*
* {
* TimerOutput::Scope timer_section(timer, "Solve");
* solve_system_1();
* }
*
* {
* TimerOutput::Scope timer_section(timer, "Assemble");
* assemble_system_2();
* }
*
* {
* TimerOutput::Scope timer_section(timer, "Solve");
* solve_system_2();
* }
*
* // do something else...
* @endcode
*
*
* <h3>Usage in parallel programs using MPI</h3>
*
* In a parallel program built on MPI, using the class in a way such as the
* one shown above would result in a situation where each process times the
* corresponding sections and then outputs the resulting timing information at
* the end. This is annoying since you'd get a lot of output -- one set of
* timing information from each processor.
*
* This can be avoided by only letting one processor generate screen output,
* typically by using an object of type ConditionalOStream instead of
* <code>std::cout</code> to write to screen (see, for example, step-17,
* step-18, step-32 and step-40, all of which use this method).
*
* This way, only a single processor outputs timing information, typically the
* first process in the MPI universe. However, if you take the above code
* snippet as an example, imagine what would happen if
* <code>setup_dofs()</code> is fast on processor zero and slow on at least
* one of the other processors; and if the first thing
* <code>assemble_system_1()</code> does is something that requires all
* processors to communicate. In this case, on processor zero, the timing
* section with name <code>"Setup dof system"</code> will yield a short run
* time on processor zero, whereas the section <code> "Assemble"</code> will
* take a long time: not because <code>assemble_system_1()</code> takes a
* particularly long time, but because on the processor on which we time (or,
* rather, the one on which we generate output) happens to have to wait for a
* long time till the other processor is finally done with
* <code>setup_dofs()</code> and starts to participate in
* <code>assemble_system_1()</code>. In other words, the timing that is
* reported is unreliable because it reflects run times from other processors.
* Furthermore, the run time of this section on processor zero has nothing to
* do with the run time of the section on other processors but instead with
* the run time of <i>the previous section</i> on another processor.
*
* The usual way to avoid this is to introduce a barrier into the parallel
* code just before we start and stop timing sections. This ensures that all
* processes are at the same place and the timing information then reflects
* the maximal run time across all processors. To achieve this, you need to
* initialize the TimerOutput object with an MPI communicator object, for
* example as in the following code:
* @code
* TimerOutput timer (MPI_COMM_WORLD,
* pcout,
* TimerOutput::summary,
* TimerOutput::wall_times);
* @endcode
* Here, <code>pcout</code> is an object of type ConditionalOStream that makes
* sure that we only generate output on a single processor. See the step-32
* and step-40 tutorial programs for this kind of usage of this class.
*
* @ingroup utilities
* @author M. Kronbichler, 2009.
*/
class TimerOutput
{
public:
/**
* Helper class to enter/exit sections in TimerOutput be constructing a
* simple scope-based object. The purpose of this class is explained in the
* documentation of TimerOutput.
*/
class Scope
{
public:
/**
* Enter the given section in the timer. Exit automatically when calling
* stop() or destructor runs.
*/
Scope(dealii::TimerOutput &timer_, const std::string §ion_name);
/**
* Destructor calls stop()
*/
~Scope();
/**
* In case you want to exit the scope before the destructor is executed,
* call this function.
*/
void stop();
private:
/**
* Reference to the TimerOutput object
*/
dealii::TimerOutput &timer;
/**
* Do we still need to exit the section we are in?
*/
bool in;
};
/**
* An enumeration data type that describes whether to generate output every
* time we exit a section, just in the end, both, or never.
*/
enum OutputFrequency
{
every_call,
summary,
every_call_and_summary,
never
};
/**
* An enumeration data type that describes whether to show CPU times, wall
* times, or both CPU and wall times whenever we generate output.
*/
enum OutputType
{
cpu_times,
wall_times,
cpu_and_wall_times
};
/**
* Constructor.
*
* @param stream The stream (of type std::ostream) to which output is
* written.
* @param output_frequency A variable indicating when output is to be
* written to the given stream.
* @param output_type A variable indicating what kind of timing the output
* should represent (CPU or wall time).
*/
TimerOutput (std::ostream &stream,
const enum OutputFrequency output_frequency,
const enum OutputType output_type);
/**
* Constructor.
*
* @param stream The stream (of type ConditionalOstream) to which output is
* written.
* @param output_frequency A variable indicating when output is to be
* written to the given stream.
* @param output_type A variable indicating what kind of timing the output
* should represent (CPU or wall time).
*/
TimerOutput (ConditionalOStream &stream,
const enum OutputFrequency output_frequency,
const enum OutputType output_type);
#ifdef DEAL_II_WITH_MPI
/**
* Constructor that takes an MPI communicator as input. A timer constructed
* this way will sum up the CPU times over all processors in the MPI network
* for calculating the CPU time, or take the maximum over all processors,
* depending on the value of @p output_type . See the documentation of this
* class for the rationale for this constructor and an example.
*
* @param mpi_comm An MPI communicator across which we should accumulate or
* otherwise synchronize the timing information we produce on every MPI
* process.
* @param stream The stream (of type std::ostream) to which output is
* written.
* @param output_frequency A variable indicating when output is to be
* written to the given stream.
* @param output_type A variable indicating what kind of timing the output
* should represent (CPU or wall time). In this parallel context, when this
* argument selects CPU time, then times are accumulated over all processes
* participating in the MPI communicator. If this argument selects wall
* time, then reported times are the maximum over all processors' run times
* for this section. (The latter is computed by placing an
* <code>MPI_Barrier</code> call before starting and stopping the timer for
* each section.
*/
TimerOutput (MPI_Comm mpi_comm,
std::ostream &stream,
const enum OutputFrequency output_frequency,
const enum OutputType output_type);
/**
* Constructor that takes an MPI communicator as input. A timer constructed
* this way will sum up the CPU times over all processors in the MPI network
* for calculating the CPU time, or take the maximum over all processors,
* depending on the value of @p output_type . See the documentation of this
* class for the rationale for this constructor and an example.
*
* @param mpi_comm An MPI communicator across which we should accumulate or
* otherwise synchronize the timing information we produce on every MPI
* process.
* @param stream The stream (of type ConditionalOstream) to which output is
* written.
* @param output_frequency A variable indicating when output is to be
* written to the given stream.
* @param output_type A variable indicating what kind of timing the output
* should represent (CPU or wall time). In this parallel context, when this
* argument selects CPU time, then times are accumulated over all processes
* participating in the MPI communicator. If this argument selects wall
* time, then reported times are the maximum over all processors' run times
* for this section. (The latter is computed by placing an
* <code>MPI_Barrier</code> call before starting and stopping the timer for
* each section.)
*/
TimerOutput (MPI_Comm mpi_comm,
ConditionalOStream &stream,
const enum OutputFrequency output_frequency,
const enum OutputType output_type);
#endif
/**
* Destructor. Calls print_summary() in case the option for writing the
* summary output is set.
*/
~TimerOutput();
/**
* Open a section by given a string name of it. In case the name already
* exists, that section is entered once again and times are accumulated.
*/
void enter_subsection (const std::string §ion_name);
/**
* Same as @p enter_subsection.
*/
void enter_section (const std::string §ion_name);
//TODO: make some of these functions DEPRECATED (I would keep enter/exit_section)
/**
* Leave a section. If no name is given, the last section that was entered
* is left.
*/
void leave_subsection (const std::string §ion_name = std::string());
/**
* Same as @p leave_subsection.
*/
void exit_section (const std::string §ion_name = std::string());
/**
* Print a formatted table that summarizes the time consumed in the various
* sections.
*/
void print_summary () const;
/**
* By calling this function, all output can be disabled. This function
* together with enable_output() can be useful if one wants to control the
* output in a flexible way without putting a lot of <tt>if</tt> clauses in
* the program.
*/
void disable_output ();
/**
* This function re-enables output of this class if it was previously
* disabled with disable_output(). This function together with
* disable_output() can be useful if one wants to control the output in a
* flexible way without putting a lot of <tt>if</tt> clauses in the program.
*/
void enable_output ();
/**
* Resets the recorded timing information.
*/
void reset ();
private:
/**
* When to output information to the output stream.
*/
OutputFrequency output_frequency;
/**
* Whether to show CPU times, wall times, or both CPU and wall times.
*/
OutputType output_type;
/**
* A timer object for the overall run time. If we are using MPI, this timer
* also accumulates over all MPI processes.
*/
Timer timer_all;
/**
* A structure that groups all information that we collect about each of the
* sections.
*/
struct Section
{
Timer timer;
double total_cpu_time;
double total_wall_time;
unsigned int n_calls;
};
/**
* A list of all the sections and their information.
*/
std::map<std::string, Section> sections;
/**
* The stream object to which we are to output.
*/
ConditionalOStream out_stream;
/**
* A boolean variable that sets whether output of this class is currently on
* or off.
*/
bool output_is_enabled;
/**
* A list of the sections that have been entered and not exited. The list is
* kept in the order in which sections have been entered, but elements may
* be removed in the middle if an argument is given to the exit_section()
* function.
*/
std::list<std::string> active_sections;
/**
* mpi communicator
*/
MPI_Comm mpi_communicator;
/**
* A lock that makes sure that this class gives reasonable results even when
* used with several threads.
*/
Threads::Mutex mutex;
};
/* ---------------- inline functions ----------------- */
inline
void Timer::restart ()
{
reset();
start();
}
#ifdef DEAL_II_WITH_MPI
inline
const Utilities::MPI::MinMaxAvg &
Timer::get_data() const
{
return mpi_data;
}
template <class StreamType>
inline
void
Timer::print_data(StreamType &stream) const
{
unsigned int my_id = dealii::Utilities::MPI::this_mpi_process(mpi_communicator);
if (my_id==0)
stream << mpi_data.max << " wall,"
<< " max @" << mpi_data.max_index
<< ", min=" << mpi_data.min << " @" << mpi_data.min_index
<< ", avg=" << mpi_data.avg
<< std::endl;
}
#endif
inline
void
TimerOutput::enter_section (const std::string §ion_name)
{
enter_subsection(section_name);
}
inline
void
TimerOutput::exit_section (const std::string §ion_name)
{
leave_subsection(section_name);
}
inline
TimerOutput::Scope::Scope(dealii::TimerOutput &timer_, const std::string §ion_name)
:
timer(timer_), in(true)
{
timer.enter_section(section_name);
}
inline
TimerOutput::Scope::~Scope()
{
stop();
}
inline
void
TimerOutput::Scope::stop()
{
if (!in) return;
in=false;
timer.exit_section();
}
DEAL_II_NAMESPACE_CLOSE
#endif
|