ViewVC Help
View File | Revision Log | Show Annotations | Download File
/cvs/OpenCL/OpenCL.pm
(Generate patch)

Comparing OpenCL/OpenCL.pm (file contents):
Revision 1.51 by root, Tue Apr 24 13:45:58 2012 UTC vs.
Revision 1.62 by root, Sat Apr 28 13:33:04 2012 UTC

43 43
44OpenCL::Event objects are used to signal when something is complete. 44OpenCL::Event objects are used to signal when something is complete.
45 45
46=head2 HELPFUL RESOURCES 46=head2 HELPFUL RESOURCES
47 47
48The OpenCL spec used to develop this module (1.2 spec was available, but 48The OpenCL specs used to develop this module:
49no implementation was available to me :).
50 49
51 http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf 50 http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf
51 http://www.khronos.org/registry/cl/specs/opencl-1.2.pdf
52 http://www.khronos.org/registry/cl/specs/opencl-1.2-extensions.pdf
52 53
53OpenCL manpages: 54OpenCL manpages:
54 55
55 http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/ 56 http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/
57 http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/
56 58
57If you are into UML class diagrams, the following diagram might help - if 59If you are into UML class diagrams, the following diagram might help - if
58not, it will be mildly cobfusing: 60not, it will be mildly confusing (also, the class hierarchy of this module
61is much more fine-grained):
59 62
60 http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/classDiagram.html 63 http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/classDiagram.html
61 64
62Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it 65Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it
63is, but at least it's free of charge: 66is, but at least it's free of charge:
64 67
65 http://developer.amd.com/zones/OpenCLZone/courses/Documents/Introduction_to_OpenCL_Programming%20Training_Guide%20%28201005%29.pdf 68 http://developer.amd.com/zones/OpenCLZone/courses/Documents/Introduction_to_OpenCL_Programming%20Training_Guide%20%28201005%29.pdf
138=head2 Create a buffer with some predefined data, read it back synchronously, 141=head2 Create a buffer with some predefined data, read it back synchronously,
139then asynchronously. 142then asynchronously.
140 143
141 my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); 144 my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut");
142 145
143 $queue->enqueue_read_buffer ($buf, 1, 1, 3, my $data); 146 $queue->read_buffer ($buf, 1, 1, 3, my $data);
144 print "$data\n"; 147 print "$data\n";
145 148
146 my $ev = $queue->enqueue_read_buffer ($buf, 0, 1, 3, my $data); 149 my $ev = $queue->read_buffer ($buf, 0, 1, 3, my $data);
147 $ev->wait; 150 $ev->wait;
148 print "$data\n"; # prints "elm" 151 print "$data\n"; # prints "elm"
149 152
150=head2 Create and build a program, then create a kernel out of one of its 153=head2 Create and build a program, then create a kernel out of one of its
151functions. 154functions.
171 # set buffer 174 # set buffer
172 $kernel->set_buffer (0, $input); 175 $kernel->set_buffer (0, $input);
173 $kernel->set_buffer (1, $output); 176 $kernel->set_buffer (1, $output);
174 177
175 # execute it for all 4 numbers 178 # execute it for all 4 numbers
176 $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); 179 $queue->nd_range_kernel ($kernel, undef, [4], undef);
177 180
178 # enqueue a synchronous read 181 # enqueue a synchronous read
179 $queue->enqueue_read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); 182 $queue->read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data);
180 183
181 # print the results: 184 # print the results:
182 printf "%s\n", join ", ", unpack "f*", $data; 185 printf "%s\n", join ", ", unpack "f*", $data;
183 186
184=head2 The same enqueue operations as before, but assuming an out-of-order queue, 187=head2 The same enqueue operations as before, but assuming an out-of-order queue,
185showing off barriers. 188showing off barriers.
186 189
187 # execute it for all 4 numbers 190 # execute it for all 4 numbers
188 $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); 191 $queue->nd_range_kernel ($kernel, undef, [4], undef);
189 192
190 # enqueue a barrier to ensure in-order execution 193 # enqueue a barrier to ensure in-order execution
191 $queue->enqueue_barrier; 194 $queue->barrier;
192 195
193 # enqueue an async read 196 # enqueue an async read
194 $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); 197 $queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data);
195 198
196 # wait for all requests to finish 199 # wait for all requests to finish
197 $queue->finish; 200 $queue->finish;
198 201
199=head2 The same enqueue operations as before, but assuming an out-of-order queue, 202=head2 The same enqueue operations as before, but assuming an out-of-order queue,
200showing off event objects and wait lists. 203showing off event objects and wait lists.
201 204
202 # execute it for all 4 numbers 205 # execute it for all 4 numbers
203 my $ev = $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); 206 my $ev = $queue->nd_range_kernel ($kernel, undef, [4], undef);
204 207
205 # enqueue an async read 208 # enqueue an async read
206 $ev = $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev); 209 $ev = $queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev);
207 210
208 # wait for the last event to complete 211 # wait for the last event to complete
209 $ev->wait; 212 $ev->wait;
210 213
211=head2 Use the OpenGL module to share a texture between OpenCL and OpenGL and draw some julia 214=head2 Use the OpenGL module to share a texture between OpenCL and OpenGL and draw some julia
270 273
271 # program compiled, kernel ready, now draw and loop 274 # program compiled, kernel ready, now draw and loop
272 275
273 for (my $time; ; ++$time) { 276 for (my $time; ; ++$time) {
274 # acquire objects from opengl 277 # acquire objects from opengl
275 $queue->enqueue_acquire_gl_objects ([$tex]); 278 $queue->acquire_gl_objects ([$tex]);
276 279
277 # configure and run our kernel 280 # configure and run our kernel
278 $kernel->set_image2d (0, $tex); 281 $kernel->set_image2d (0, $tex);
279 $kernel->set_float (1, $time); 282 $kernel->set_float (1, $time);
280 $queue->enqueue_nd_range_kernel ($kernel, undef, [256, 256], undef); 283 $queue->nd_range_kernel ($kernel, undef, [256, 256], undef);
281 284
282 # release objects to opengl again 285 # release objects to opengl again
283 $queue->enqueue_release_gl_objects ([$tex]); 286 $queue->release_gl_objects ([$tex]);
284 287
285 # wait 288 # wait
286 $queue->finish; 289 $queue->finish;
287 290
288 # now draw the texture, the defaults should be all right 291 # now draw the texture, the defaults should be all right
376 379
377For this to work, the OpenGL library must be loaded, a GLX context must 380For this to work, the OpenGL library must be loaded, a GLX context must
378have been created and be made current, and C<dlsym> must be available and 381have been created and be made current, and C<dlsym> must be available and
379capable of finding the function via C<RTLD_DEFAULT>. 382capable of finding the function via C<RTLD_DEFAULT>.
380 383
384=head2 EVENT SYSTEM
385
386OpenCL can generate a number of (potentially) asynchronous events, for
387example, after compiling a program, to signal a context-related error or,
388perhaps most important, to signal completion of queued jobs (by setting
389callbacks on OpenCL::Event objects).
390
391To facilitate this, this module maintains an event queue - each
392time an asynchronous event happens, it is queued, and perl will be
393interrupted. This is implemented via the L<Async::Interrupt> module. In
394addition, this module has L<AnyEvent> support, so it can seamlessly
395integrate itself into many event loops.
396
397Since this module is a bit hard to understand, here are some case examples:
398
399=head3 Don't use callbacks.
400
401When your program never uses any callbacks, then there will never be any
402notifications you need to take care of, and therefore no need to worry
403about all this.
404
405You can achieve a great deal by explicitly waiting for events, or using
406barriers and flush calls. In many programs, there is no need at all to
407tinker with asynchronous events.
408
409=head3 Use AnyEvent
410
411This module automatically registers a watcher that invokes all outstanding
412event callbacks when AnyEvent is initialised (and block asynchronous
413interruptions). Using this mode of operations is the safest and most
414recommended one.
415
416To use this, simply use AnyEvent and this module normally, make sure you
417have an event loop running:
418
419 use Gtk2 -init;
420 use AnyEvent;
421
422 # initialise AnyEvent, by creating a watcher, or:
423 AnyEvent::detect;
424
425 my $e = $queue->marker;
426 $e->cb (sub {
427 warn "opencl is finished\n";
428 })
429
430 main Gtk2;
431
432Note that this module will not initialise AnyEvent for you. Before
433AnyEvent is initialised, the module will asynchronously interrupt perl
434instead. To avoid any surprises, it's best to explicitly initialise
435AnyEvent.
436
437You can temporarily enable asynchronous interruptions (see next paragraph)
438by calling C<$OpenCL::INTERRUPT->unblock> and disable them again by
439calling C<$OpenCL::INTERRUPT->block>.
440
441=head3 Let yourself be interrupted at any time
442
443This mode is the default unless AnyEvent is loaded and initialised. In
444this mode, OpenCL asynchronously interrupts a running perl program. The
445emphasis is on both I<asynchronously> and I<running> here.
446
447Asynchronously means that perl might execute your callbacks at any
448time. For example, in the following code (I<THAT YOU SHOULD NOT COPY>),
449the C<until> loop following the marker call will be interrupted by the
450callback:
451
452 my $e = $queue->marker;
453 my $flag;
454 $e->cb (sub { $flag = 1 });
455 1 until $flag;
456 # $flag is now 1
457
458The reason why you shouldn't blindly copy the above code is that
459busy waiting is a really really bad thing, and really really bad for
460performance.
461
462While at first this asynchronous business might look exciting, it can be
463really hard, because you need to be prepared for the callback code to be
464executed at any time, which limits the amount of things the callback code
465can do safely.
466
467This can be mitigated somewhat by using C<<
468$OpenCL::INTERRUPT->scope_block >> (see the L<Async::Interrupt>
469documentation for details).
470
471The other problem is that your program must be actively I<running> to be
472interrupted. When you calculate stuff, your program is running. When you
473hang in some C functions or other block execution (by calling C<sleep>,
474C<select>, running an event loop and so on), your program is waiting, not
475running.
476
477One way around that would be to attach a read watcher to your event loop,
478listening for events on C<< $OpenCL::INTERRUPT->pipe_fileno >>, using a
479dummy callback (C<sub { }>) to temporarily execute some perl code.
480
481That is then awfully close to using the built-in AnyEvent support above,
482though, so consider that one instead.
483
484=head3 Be creative
485
486OpenCL exports the L<Async::Interrupt> object it uses in the global
487variable C<$OpenCL::INTERRUPT>. You can configure it in any way you like.
488
489So if you want to feel like a real pro, err, wait, if you feel no risk
490menas no fun, you can experiment by implementing your own mode of
491operations.
492
493=cut
494
495package OpenCL;
496
497use common::sense;
498use Carp ();
499use Async::Interrupt ();
500
501our $POLL_FUNC; # set by XS
502
503BEGIN {
504 our $VERSION = '0.98';
505
506 require XSLoader;
507 XSLoader::load (__PACKAGE__, $VERSION);
508
509 @OpenCL::Platform::ISA =
510 @OpenCL::Device::ISA =
511 @OpenCL::Context::ISA =
512 @OpenCL::Queue::ISA =
513 @OpenCL::Memory::ISA =
514 @OpenCL::Sampler::ISA =
515 @OpenCL::Program::ISA =
516 @OpenCL::Kernel::ISA =
517 @OpenCL::Event::ISA = OpenCL::Object::;
518
519 @OpenCL::Buffer::ISA =
520 @OpenCL::Image::ISA = OpenCL::Memory::;
521
522 @OpenCL::BufferObj::ISA = OpenCL::Buffer::;
523
524 @OpenCL::Image2D::ISA =
525 @OpenCL::Image3D::ISA =
526 @OpenCL::Image2DArray::ISA =
527 @OpenCL::Image1D::ISA =
528 @OpenCL::Image1DArray::ISA =
529 @OpenCL::Image1DBuffer::ISA = OpenCL::Image::;
530
531 @OpenCL::UserEvent::ISA = OpenCL::Event::;
532}
533
381=head2 THE OpenCL PACKAGE 534=head2 THE OpenCL PACKAGE
382 535
383=over 4 536=over 4
384 537
385=item $int = OpenCL::errno 538=item $int = OpenCL::errno
386 539
387The last error returned by a function - it's only valid after an error occured 540The last error returned by a function - it's only valid after an error occured
388and before calling another OpenCL function. 541and before calling another OpenCL function.
389 542
390=item $str = OpenCL::err2str $errval 543=item $str = OpenCL::err2str [$errval]
391 544
392Comverts an error value into a human readable string. 545Converts an error value into a human readable string. IF no error value is
546given, then the last error will be used (as returned by OpenCL::errno).
393 547
394=item $str = OpenCL::enum2str $enum 548=item $str = OpenCL::enum2str $enum
395 549
396Converts most enum values (of parameter names, image format constants, 550Converts most enum values (of parameter names, image format constants,
397object types, addressing and filter modes, command types etc.) into a 551object types, addressing and filter modes, command types etc.) into a
403 557
404Returns all available OpenCL::Platform objects. 558Returns all available OpenCL::Platform objects.
405 559
406L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html> 560L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html>
407 561
408=item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef 562=item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr
409 563
410Tries to create a context from a default device and platform - never worked for me. 564Tries to create a context from a default device and platform type - never worked for me.
411 565
412L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> 566L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>
413 567
568=item $ctx = OpenCL::context $properties, \@devices, $callback->($err, $pvt) = $print_stderr)
569
570Create a new OpenCL::Context object using the given device object(s). This
571function isn't implemented yet, use C<< $platform->context >> instead.
572
573L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>
574
414=item OpenCL::wait_for_events $wait_events... 575=item OpenCL::wait_for_events $wait_events...
415 576
416Waits for all events to complete. 577Waits for all events to complete.
417 578
418L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> 579L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>
419 580
581=item OpenCL::poll
582
583Checks if there are any outstanding events (see L<EVENT SYSTEM>) and
584invokes their callbacks.
585
586=item $OpenCL::INTERRUPT
587
588The L<Async::Interrupt> object used to signal asynchronous events (see
589L<EVENT SYSTEM>).
590
591=cut
592
593our $INTERRUPT = new Async::Interrupt c_cb => [$POLL_FUNC, 0];
594
595&_eq_initialise ($INTERRUPT->signal_func);
596
597=item $OpenCL::WATCHER
598
599The L<AnyEvent> watcher object used to watch for asynchronous events (see
600L<EVENT SYSTEM>). This variable is C<undef> until L<AnyEvent> has been
601loaded I<and> initialised (e.g. by calling C<AnyEvent::detect>).
602
603=cut
604
605our $WATCHER;
606
607sub _init_anyevent {
608 $INTERRUPT->block;
609 $WATCHER = AE::io ($INTERRUPT->pipe_fileno, 0, sub { $INTERRUPT->handle });
610}
611
612if (defined $AnyEvent::MODEL) {
613 _init_anyevent;
614} else {
615 push @AnyEvent::post_detect, \&_init_anyevent;
616}
617
420=back 618=back
421 619
620=head2 THE OpenCL::Object CLASS
621
622This is the base class for all objects in the OpenCL module. The only
623method it implements is the C<id> method, which is only useful if you want
624to interface to OpenCL on the C level.
625
626=over 4
627
628=item $iv = $obj->id
629
630OpenCL objects are represented by pointers or integers on the C level. If
631you want to interface to an OpenCL object directly on the C level, then
632you need this value, which is returned by this method. You should use an
633C<IV> type in your code and cast that to the correct type.
634
635=cut
636
637sub OpenCL::Object::id {
638 ref $_[0] eq "SCALAR"
639 ? ${ $_[0] }
640 : $_[0][0]
641}
642
643=back
644
422=head2 THE OpenCL::Platform CLASS 645=head2 THE OpenCL::Platform CLASS
423 646
424=over 4 647=over 4
425 648
426=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL) 649=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL)
427 650
428Returns a list of matching OpenCL::Device objects. 651Returns a list of matching OpenCL::Device objects.
429 652
430=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef) 653=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr)
431 654
432Tries to create a context. Never worked for me, and you need devices explicitly anyway. 655Tries to create a context. Never worked for me, and you need devices explicitly anyway.
433 656
434L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> 657L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>
435 658
436=item $ctx = $platform->context ($properties = undef, @$devices, $notify = undef) 659=item $ctx = $platform->context ($properties, \@devices, $callback->($err, $pvt) = $print_stderr)
437 660
438Create a new OpenCL::Context object using the given device object(s)- a 661Create a new OpenCL::Context object using the given device object(s)- a
439CL_CONTEXT_PLATFORM property is supplied automatically. 662CL_CONTEXT_PLATFORM property is supplied automatically.
440 663
441L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> 664L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>
784 my ($self, $prog, $options) = @_; 1007 my ($self, $prog, $options) = @_;
785 1008
786 $prog = $self->program_with_source ($prog) 1009 $prog = $self->program_with_source ($prog)
787 unless ref $prog; 1010 unless ref $prog;
788 1011
1012 eval { $prog->build (undef, $options); 1 }
1013 or errno == BUILD_PROGRAM_FAILURE
1014 or Carp::croak "OpenCL::Context->build_program: " . err2str;
1015
1016 # we check status for all devices
789 for my $dev ($self->devices) { 1017 for my $dev ($self->devices) {
790 eval { $prog->build ($dev, $options); 1 } 1018 $prog->build_status ($dev) == BUILD_SUCCESS
791 or Carp::croak "Building OpenCL program for device '" . $dev->name . "' failed:\n" 1019 or Carp::croak "Building OpenCL program for device '" . $dev->name . "' failed:\n"
792 . $prog->build_log ($dev); 1020 . $prog->build_log ($dev);
793 } 1021 }
794 1022
795 $prog 1023 $prog
796} 1024}
797 1025
821=item $buf = $ctx->buffer_sv ($flags, $data) 1049=item $buf = $ctx->buffer_sv ($flags, $data)
822 1050
823Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and 1051Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and
824initialise it with the given data values. 1052initialise it with the given data values.
825 1053
826=item $img = $ctx->image ($self, $flags, $channel_order, $channel_type, $type, $width, $height, $depth, $array_size = 0, $row_pitch = 0, $slice_pitch = 0, $num_mip_level = 0, $num_samples = 0, $*data = &PL_sv_undef) 1054=item $img = $ctx->image ($self, $flags, $channel_order, $channel_type, $type, $width, $height, $depth = 0, $array_size = 0, $row_pitch = 0, $slice_pitch = 0, $num_mip_level = 0, $num_samples = 0, $*data = &PL_sv_undef)
827 1055
828Creates a new OpenCL::Image object and optionally initialises it with 1056Creates a new OpenCL::Image object and optionally initialises it with
829the given data values. 1057the given data values.
830 1058
831L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html> 1059L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html>
927=back 1155=back
928 1156
929=head2 THE OpenCL::Queue CLASS 1157=head2 THE OpenCL::Queue CLASS
930 1158
931An OpenCL::Queue represents an execution queue for OpenCL. You execute 1159An OpenCL::Queue represents an execution queue for OpenCL. You execute
932requests by calling their respective C<enqueue_xxx> method and waitinf for 1160requests by calling their respective method and waiting for it to complete
933it to complete in some way. 1161in some way.
934 1162
935All the enqueue methods return an event object that can be used to wait 1163Most methods that enqueue some request return an event object that can
936for completion, unless the method is called in void context, in which case 1164be used to wait for completion (optionally using a callback), unless
937no event object is created. 1165the method is called in void context, in which case no event object is
1166created.
938 1167
939They also allow you to specify any number of other event objects that this 1168They also allow you to specify any number of other event objects that this
940request has to wait for before it starts executing, by simply passing the 1169request has to wait for before it starts executing, by simply passing the
941event objects as extra parameters to the enqueue methods. To simplify 1170event objects as extra parameters to the enqueue methods. To simplify
942program design, this module ignores any C<undef> values in the list of 1171program design, this module ignores any C<undef> values in the list of
943events. This makes it possible to code operations such as this, without 1172events. This makes it possible to code operations such as this, without
944having to put a valid event object into C<$event> first: 1173having to put a valid event object into C<$event> first:
945 1174
946 $event = $queue->enqueue_xxx (..., $event); 1175 $event = $queue->xxx (..., $event);
947 1176
948Queues execute in-order by default, without any parallelism, so in most 1177Queues execute in-order by default, without any parallelism, so in most
949cases (i.e. you use only one queue) it's not necessary to wait for or 1178cases (i.e. you use only one queue) it's not necessary to wait for or
950create event objects, althoguh an our of order queue is often a bit 1179create event objects, althoguh an our of order queue is often a bit
951faster. 1180faster.
952 1181
953=over 4 1182=over 4
954 1183
955=item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) 1184=item $ev = $queue->read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...)
956 1185
957Reads data from buffer into the given string. 1186Reads data from buffer into the given string.
958 1187
959L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html> 1188L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html>
960 1189
961=item $ev = $queue->enqueue_write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) 1190=item $ev = $queue->write_buffer ($buffer, $blocking, $offset, $data, $wait_events...)
962 1191
963Writes data to buffer from the given string. 1192Writes data to buffer from the given string.
964 1193
965L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html> 1194L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html>
966 1195
967=item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) 1196=item $ev = $queue->copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...)
968 1197
969L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> 1198L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html>
970 1199
971=item $ev = $queue->enqueue_read_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) 1200=item $ev = $queue->read_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...)
972 1201
973http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html 1202http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html
974 1203
975=item $ev = $queue->enqueue_write_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) 1204=item $ev = $queue->write_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...)
976 1205
977http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html 1206http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html
978 1207
979=item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) 1208=item $ev = $queue->read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
980 1209
981L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html> 1210L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html>
982 1211
983=item $ev = $queue->enqueue_copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) 1212=item $ev = $queue->copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...)
984 1213
985L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> 1214L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html>
986 1215
987=item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) 1216=item $ev = $queue->write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
988 1217
989L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> 1218L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html>
990 1219
991=item $ev = $queue->enqueue_copy_image ($src_image, $dst_image, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) 1220=item $ev = $queue->copy_image ($src_image, $dst_image, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...)
992 1221
993L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> 1222L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html>
994 1223
995=item $ev = $queue->enqueue_copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...) 1224=item $ev = $queue->copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...)
996 1225
997L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html> 1226L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html>
998 1227
999=item $ev = $queue->enqueue_copy_buffer_rect ($src, $dst, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $src_row_pitch, $src_slice_pitch, $dst_row_pitch, $dst_slice_pitch, $wait_event...) 1228=item $ev = $queue->copy_buffer_rect ($src, $dst, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $src_row_pitch, $src_slice_pitch, $dst_row_pitch, $dst_slice_pitch, $wait_event...)
1000 1229
1001Yeah. 1230Yeah.
1002 1231
1003L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. 1232L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>.
1004 1233
1234=item $ev = $queue->fill_buffer ($mem, $pattern, $offset, $size, ...)
1235
1236Fills the given buffer object with repeated applications of C<$pattern>,
1237starting at C<$offset> for C<$size> octets.
1238
1239L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html>
1240
1241=item $ev = $queue->fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...)
1242
1243Fills the given image area with the given rgba colour components. The
1244components are normally floating point values between C<0> and C<1>,
1245except when the image channel data type is a signe dor unsigned
1246unnormalised format, in which case the range is determined by the format.
1247
1248L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html>
1249
1005=item $ev = $queue->enqueue_task ($kernel, $wait_events...) 1250=item $ev = $queue->task ($kernel, $wait_events...)
1006 1251
1007L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> 1252L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html>
1008 1253
1009=item $ev = $queue->enqueue_nd_range_kernel ($kernel, @$global_work_offset, @$global_work_size, @$local_work_size, $wait_events...) 1254=item $ev = $queue->nd_range_kernel ($kernel, \@global_work_offset, \@global_work_size, \@local_work_size, $wait_events...)
1010 1255
1011Enqueues a kernel execution. 1256Enqueues a kernel execution.
1012 1257
1013@$global_work_size must be specified as a reference to an array of 1258\@global_work_size must be specified as a reference to an array of
1014integers specifying the work sizes (element counts). 1259integers specifying the work sizes (element counts).
1015 1260
1016@$global_work_offset must be either C<undef> (in which case all offsets 1261\@global_work_offset must be either C<undef> (in which case all offsets
1017are C<0>), or a reference to an array of work offsets, with the same number 1262are C<0>), or a reference to an array of work offsets, with the same number
1018of elements as @$global_work_size. 1263of elements as \@global_work_size.
1019 1264
1020@$local_work_size must be either C<undef> (in which case the 1265\@local_work_size must be either C<undef> (in which case the
1021implementation is supposed to choose good local work sizes), or a 1266implementation is supposed to choose good local work sizes), or a
1022reference to an array of local work sizes, with the same number of 1267reference to an array of local work sizes, with the same number of
1023elements as @$global_work_size. 1268elements as \@global_work_size.
1024 1269
1025L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> 1270L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html>
1026 1271
1027=item $ev = $queue->enqueue_acquire_gl_objects ([object, ...], $wait_events...) 1272=item $ev = $queue->acquire_gl_objects ([object, ...], $wait_events...)
1028 1273
1029Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired 1274Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired
1030for subsequent OpenCL usage. 1275for subsequent OpenCL usage.
1031 1276
1032L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html> 1277L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html>
1033 1278
1034=item $ev = $queue->enqueue_release_gl_objects ([object, ...], $wait_events...) 1279=item $ev = $queue->release_gl_objects ([object, ...], $wait_events...)
1035 1280
1036Enqueues a list (an array-ref of OpenCL::Memory objects) to be released 1281Enqueues a list (an array-ref of OpenCL::Memory objects) to be released
1037for subsequent OpenGL usage. 1282for subsequent OpenGL usage.
1038 1283
1039L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html> 1284L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html>
1040 1285
1041=item $ev = $queue->enqueue_wait_for_events ($wait_events...) 1286=item $ev = $queue->wait_for_events ($wait_events...)
1042 1287
1043L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> 1288L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html>
1044 1289
1045=item $ev = $queue->enqueue_marker ($wait_events...) 1290=item $ev = $queue->marker ($wait_events...)
1046 1291
1047L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html> 1292L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html>
1048 1293
1049=item $ev = $queue->enqueue_barrier ($wait_events...) 1294=item $ev = $queue->barrier ($wait_events...)
1050 1295
1051L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html> 1296L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html>
1052 1297
1053=item $queue->flush 1298=item $queue->flush
1054 1299
1177OpenCL::Image1DArray, OpenCL::Image1DBuffer, OpenCL::Image2D, 1422OpenCL::Image1DArray, OpenCL::Image1DBuffer, OpenCL::Image2D,
1178OpenCL::Image2DArray and OpenCL::Image3D. 1423OpenCL::Image2DArray and OpenCL::Image3D.
1179 1424
1180=over 4 1425=over 4
1181 1426
1182=item $packed_value = $ev->image_info ($name) 1427=item $packed_value = $image->image_info ($name)
1183 1428
1184See C<< $platform->info >> for details. 1429See C<< $platform->info >> for details.
1185 1430
1186The reason this method is not called C<info> is that there already is an 1431The reason this method is not called C<info> is that there already is an
1187C<< ->info >> method inherited from C<OpenCL::Memory>. 1432C<< ->info >> method inherited from C<OpenCL::Memory>.
1188 1433
1189L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html> 1434L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html>
1190 1435
1436=item ($channel_order, $channel_data_type) = $image->format
1437
1438Returns the channel order and type used to create the image by calling
1439C<clGetImageInfo> with C<CL_IMAGE_FORMAT>.
1440
1191=for gengetinfo begin image 1441=for gengetinfo begin image
1192 1442
1193=item $int = $image->element_size 1443=item $int = $image->element_size
1194 1444
1195Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result. 1445Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result.
1268 1518
1269=head2 THE OpenCL::Program CLASS 1519=head2 THE OpenCL::Program CLASS
1270 1520
1271=over 4 1521=over 4
1272 1522
1273=item $program->build ($device, $options = "") 1523=item $program->build (\@devices = undef, $options = "", $cb->($program) = undef)
1274 1524
1275Tries to build the program with the given options. See also the 1525Tries to build the program with the given options. See also the
1276C<$ctx->build> convenience function. 1526C<$ctx->build> convenience function.
1277 1527
1528If a callback is specified, then it will be called when compilation is
1529finished. Note that many OpenCL implementations block your program while
1530compiling whether you use a callback or not. See C<build_async> if you
1531want to make sure the build is done in the background.
1532
1533Note that some OpenCL implementations atc up badly, and don't call the
1534callback in some error cases (but call it in others). This implementation
1535assumes the callback will always be called, and leaks memory if this is
1536not so. So best make sure you don't pass in invalid values.
1537
1278L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> 1538L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html>
1539
1540=item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef)
1541
1542Similar to C<< ->build >>, except it starts a thread, and never fails (you
1543need to check the compilation status form the callback, or by polling).
1279 1544
1280=item $packed_value = $program->build_info ($device, $name) 1545=item $packed_value = $program->build_info ($device, $name)
1281 1546
1282Similar to C<< $platform->info >>, but returns build info for a previous 1547Similar to C<< $platform->info >>, but returns build info for a previous
1283build attempt for the given device. 1548build attempt for the given device.
1425 1690
1426Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result. 1691Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result.
1427 1692
1428=for gengetinfo end kernel_work_group 1693=for gengetinfo end kernel_work_group
1429 1694
1695=item $kernel->setf ($format, ...)
1696
1697Sets the arguments of a kernel. Since OpenCL 1.1 doesn't have a generic
1698way to set arguments (and with OpenCL 1.2 it might be rather slow), you
1699need to specify a format argument, much as with C<printf>, to tell OpenCL
1700what type of argument it is.
1701
1702The format arguments are single letters:
1703
1704 c char
1705 C unsigned char
1706 s short
1707 S unsigned short
1708 i int
1709 I unsigned int
1710 l long
1711 L unsigned long
1712
1713 h half float (0..65535)
1714 f float
1715 d double
1716
1717 z local (octet size)
1718
1719 m memory object (buffer or image)
1720 a sampler
1721 e event
1722
1723Space characters in the format string are ignored.
1724
1725Example: set the arguments for a kernel that expects an int, two floats, a buffer and an image.
1726
1727 $kernel->setf ("i ff mm", 5, 0.5, 3, $buffer, $image);
1728
1430=item $kernel->set_TYPE ($index, $value) 1729=item $kernel->set_TYPE ($index, $value)
1431 1730
1731=item $kernel->set_char ($index, $value)
1732
1733=item $kernel->set_uchar ($index, $value)
1734
1735=item $kernel->set_short ($index, $value)
1736
1737=item $kernel->set_ushort ($index, $value)
1738
1739=item $kernel->set_int ($index, $value)
1740
1741=item $kernel->set_uint ($index, $value)
1742
1743=item $kernel->set_long ($index, $value)
1744
1745=item $kernel->set_ulong ($index, $value)
1746
1747=item $kernel->set_half ($index, $value)
1748
1749=item $kernel->set_float ($index, $value)
1750
1751=item $kernel->set_double ($index, $value)
1752
1753=item $kernel->set_memory ($index, $value)
1754
1755=item $kernel->set_buffer ($index, $value)
1756
1757=item $kernel->set_image ($index, $value)
1758
1759=item $kernel->set_sampler ($index, $value)
1760
1761=item $kernel->set_local ($index, $value)
1762
1763=item $kernel->set_event ($index, $value)
1764
1432This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>. 1765This is a family of methods to set the kernel argument with the number
1433 1766C<$index> to the give C<$value>.
1434TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>,
1435C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>,
1436C<image2d>, C<image3d>, C<sampler>, C<local> or C<event>.
1437 1767
1438Chars and integers (including the half type) are specified as integers, 1768Chars and integers (including the half type) are specified as integers,
1439float and double as floating point values, memory/buffer/image2d/image3d 1769float and double as floating point values, memory/buffer/image must be
1440must be an object of that type or C<undef>, local-memory arguments are 1770an object of that type or C<undef>, local-memory arguments are set by
1441set by specifying the size, and sampler and event must be objects of that 1771specifying the size, and sampler and event must be objects of that type.
1442type. 1772
1773Note that C<set_memory> works for all memory objects (all types of buffers
1774and images) - the main purpose of the more specific C<set_TYPE> functions
1775is type checking.
1443 1776
1444Setting an argument for a kernel does NOT keep a reference to the object - 1777Setting an argument for a kernel does NOT keep a reference to the object -
1445for example, if you set an argument to some image object, free the image, 1778for example, if you set an argument to some image object, free the image,
1446and call the kernel, you will run into undefined behaviour. 1779and call the kernel, you will run into undefined behaviour.
1447 1780
1460 1793
1461Waits for the event to complete. 1794Waits for the event to complete.
1462 1795
1463L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> 1796L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>
1464 1797
1798=item $ev->cb ($exec_callback_type, $callback->($event, $event_command_exec_status))
1799
1800Adds a callback to the callback stack for the given event type. There is
1801no way to remove a callback again.
1802
1803L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetEventCallback.html>
1804
1465=item $packed_value = $ev->info ($name) 1805=item $packed_value = $ev->info ($name)
1466 1806
1467See C<< $platform->info >> for details. 1807See C<< $platform->info >> for details.
1468 1808
1469L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html> 1809L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html>
1529 1869
1530=over 4 1870=over 4
1531 1871
1532=item $ev->set_status ($execution_status) 1872=item $ev->set_status ($execution_status)
1533 1873
1874Sets the execution status of the user event. Can only be called once,
1875either with OpenCL::COMPLETE or a negative number as status.
1876
1534L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html> 1877L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html>
1535 1878
1536=back 1879=back
1537 1880
1538=cut 1881=cut
1539
1540package OpenCL;
1541
1542use common::sense;
1543
1544BEGIN {
1545 our $VERSION = '0.96';
1546
1547 require XSLoader;
1548 XSLoader::load (__PACKAGE__, $VERSION);
1549
1550 @OpenCL::Buffer::ISA =
1551 @OpenCL::Image::ISA = OpenCL::Memory::;
1552
1553 @OpenCL::BufferObj::ISA = OpenCL::Buffer::;
1554
1555 @OpenCL::Image2D::ISA =
1556 @OpenCL::Image3D::ISA =
1557 @OpenCL::Image2DArray::ISA =
1558 @OpenCL::Image1D::ISA =
1559 @OpenCL::Image1DArray::ISA =
1560 @OpenCL::Image1DBuffer::ISA = OpenCL::Image::;
1561
1562 @OpenCL::UserEvent::ISA = OpenCL::Event::;
1563}
1564 1882
15651; 18831;
1566 1884
1567=head1 AUTHOR 1885=head1 AUTHOR
1568 1886

Diff Legend

Removed lines
+ Added lines
< Changed lines
> Changed lines