[ViewVC] Diff of: cvs/OpenCL/OpenCL.pm

Comparing OpenCL/OpenCL.pm (file contents):
Revision 1.54 by root, Tue Apr 24 14:57:06 2012 UTC vs.
Revision 1.61 by root, Sat Apr 28 13:31:40 2012 UTC

…		…
43		43
44	OpenCL::Event objects are used to signal when something is complete.	44	OpenCL::Event objects are used to signal when something is complete.
45		45
46	=head2 HELPFUL RESOURCES	46	=head2 HELPFUL RESOURCES
47		47
48	The OpenCL spec used to develop this module (1.2 spec was available, but	48	The OpenCL specs used to develop this module:
49	no 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
53	OpenCL manpages:	54	OpenCL 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
57	If you are into UML class diagrams, the following diagram might help - if	59	If you are into UML class diagrams, the following diagram might help - if
58	not, it will be mildly cobfusing:	60	not, it will be mildly confusing (also, the class hierarchy of this module
		61	is 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
62	Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it	65	Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it
63	is, but at least it's free of charge:	66	is, 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,
139	then asynchronously.	142	then 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
151	functions.	154	functions.
…		…
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,
185	showing off barriers.	188	showing 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,
200	showing off event objects and wait lists.	203	showing 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
377	For this to work, the OpenGL library must be loaded, a GLX context must	380	For this to work, the OpenGL library must be loaded, a GLX context must
378	have been created and be made current, and C<dlsym> must be available and	381	have been created and be made current, and C<dlsym> must be available and
379	capable of finding the function via C<RTLD_DEFAULT>.	382	capable of finding the function via C<RTLD_DEFAULT>.
380		383
		384	=head2 EVENT SYSTEM
		385
		386	OpenCL can generate a number of (potentially) asynchronous events, for
		387	example, after compiling a program, to signal a context-related error or,
		388	perhaps most important, to signal completion of queued jobs (by setting
		389	callbacks on OpenCL::Event objects).
		390
		391	To facilitate this, this module maintains an event queue - each
		392	time an asynchronous event happens, it is queued, and perl will be
		393	interrupted. This is implemented via the L<Async::Interrupt> module. In
		394	addition, this module has L<AnyEvent> support, so it can seamlessly
		395	integrate itself into many event loops.
		396
		397	Since this module is a bit hard to understand, here are some case examples:
		398
		399	=head3 Don't use callbacks.
		400
		401	When your program never uses any callbacks, then there will never be any
		402	notifications you need to take care of, and therefore no need to worry
		403	about all this.
		404
		405	You can achieve a great deal by explicitly waiting for events, or using
		406	barriers and flush calls. In many programs, there is no need at all to
		407	tinker with asynchronous events.
		408
		409	=head3 Use AnyEvent
		410
		411	This module automatically registers a watcher that invokes all outstanding
		412	event callbacks when AnyEvent is initialised (and block asynchronous
		413	interruptions). Using this mode of operations is the safest and most
		414	recommended one.
		415
		416	To use this, simply use AnyEvent and this module normally, make sure you
		417	have 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	$e->cb (sub {
		427	warn "opencl is finished\n";
		428	})
		429
		430	main Gtk2;
		431
		432	Note that this module will not initialise AnyEvent for you. Before
		433	AnyEvent is initialised, the module will asynchronously interrupt perl
		434	instead. To avoid any surprises, it's best to explicitly initialise
		435	AnyEvent.
		436
		437	You can temporarily enable asynchronous interruptions (see next paragraph)
		438	by calling C<$OpenCL::INTERRUPT->unblock> and disable them again by
		439	calling C<$OpenCL::INTERRUPT->block>.
		440
		441	=head3 Let yourself be interrupted at any time
		442
		443	This mode is the default unless AnyEvent is loaded and initialised. In
		444	this mode, OpenCL asynchronously interrupts a running perl program. The
		445	emphasis is on both I<asynchronously> and I<running> here.
		446
		447	Asynchronously means that perl might execute your callbacks at any
		448	time. For example, in the following code (I<THAT YOU SHOULD NOT COPY>),
		449	the C<until> loop following the marker call will be interrupted by the
		450	callback:
		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
		458	The reason why you shouldn't blindly copy the above code is that
		459	busy waiting is a really really bad thing, and really really bad for
		460	performance.
		461
		462	While at first this asynchronous business might look exciting, it can be
		463	really hard, because you need to be prepared for the callback code to be
		464	executed at any time, which limits the amount of things the callback code
		465	can do safely.
		466
		467	This can be mitigated somewhat by using C<<
		468	$OpenCL::INTERRUPT->scope_block >> (see the L<Async::Interrupt>
		469	documentation for details).
		470
		471	The other problem is that your program must be actively I<running> to be
		472	interrupted. When you calculate stuff, your program is running. When you
		473	hang in some C functions or other block execution (by calling C<sleep>,
		474	C<select>, running an event loop and so on), your program is waiting, not
		475	running.
		476
		477	One way around that would be to attach a read watcher to your event loop,
		478	listening for events on C<< $OpenCL::INTERRUPT->pipe_fileno >>, using a
		479	dummy callback (C<sub { }>) to temporarily execute some perl code.
		480
		481	That is then awfully close to using the built-in AnyEvent support above,
		482	though, so consider that one instead.
		483
		484	=head3 Be creative
		485
		486	OpenCL exports the L<Async::Interrupt> object it uses in the global
		487	variable C<$OpenCL::INTERRUPT>. You can configure it in any way you like.
		488
		489	So if you want to feel like a real pro, err, wait, if you feel no risk
		490	menas no fun, you can experiment by implementing your own mode of
		491	operations.
		492
381	=cut	493	=cut
382		494
383	package OpenCL;	495	package OpenCL;
384		496
385	use common::sense;	497	use common::sense;
		498	use Async::Interrupt ();
		499
		500	our $POLL_FUNC; # set by XS
386		501
387	BEGIN {	502	BEGIN {
388	our $VERSION = '0.97';	503	our $VERSION = '0.97';
389		504
390	require XSLoader;	505	require XSLoader;
…		…
422	=item $int = OpenCL::errno	537	=item $int = OpenCL::errno
423		538
424	The last error returned by a function - it's only valid after an error occured	539	The last error returned by a function - it's only valid after an error occured
425	and before calling another OpenCL function.	540	and before calling another OpenCL function.
426		541
427	=item $str = OpenCL::err2str $errval	542	=item $str = OpenCL::err2str [$errval]
428		543
429	Comverts an error value into a human readable string.	544	Converts an error value into a human readable string. IF no error value is
		545	given, then the last error will be used (as returned by OpenCL::errno).
430		546
431	=item $str = OpenCL::enum2str $enum	547	=item $str = OpenCL::enum2str $enum
432		548
433	Converts most enum values (of parameter names, image format constants,	549	Converts most enum values (of parameter names, image format constants,
434	object types, addressing and filter modes, command types etc.) into a	550	object types, addressing and filter modes, command types etc.) into a
…		…
440		556
441	Returns all available OpenCL::Platform objects.	557	Returns all available OpenCL::Platform objects.
442		558
443	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html>	559	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html>
444		560
445	=item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef	561	=item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr
446		562
447	Tries to create a context from a default device and platform - never worked for me.	563	Tries to create a context from a default device and platform type - never worked for me.
448		564
449	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>	565	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>
450		566
		567	=item $ctx = OpenCL::context $properties, \@devices, $callback->($err, $pvt) = $print_stderr)
		568
		569	Create a new OpenCL::Context object using the given device object(s). This
		570	function isn't implemented yet, use C<< $platform->context >> instead.
		571
		572	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>
		573
451	=item OpenCL::wait_for_events $wait_events...	574	=item OpenCL::wait_for_events $wait_events...
452		575
453	Waits for all events to complete.	576	Waits for all events to complete.
454		577
455	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>	578	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>
		579
		580	=item OpenCL::poll
		581
		582	Checks if there are any outstanding events (see L<EVENT SYSTEM>) and
		583	invokes their callbacks.
		584
		585	=item $OpenCL::INTERRUPT
		586
		587	The L<Async::Interrupt> object used to signal asynchronous events (see
		588	L<EVENT SYSTEM>).
		589
		590	=cut
		591
		592	our $INTERRUPT = new Async::Interrupt c_cb => [$POLL_FUNC, 0];
		593
		594	&_eq_initialise ($INTERRUPT->signal_func);
		595
		596	=item $OpenCL::WATCHER
		597
		598	The L<AnyEvent> watcher object used to watch for asynchronous events (see
		599	L<EVENT SYSTEM>). This variable is C<undef> until L<AnyEvent> has been
		600	loaded I<and> initialised (e.g. by calling C<AnyEvent::detect>).
		601
		602	=cut
		603
		604	our $WATCHER;
		605
		606	sub _init_anyevent {
		607	$INTERRUPT->block;
		608	$WATCHER = AE::io ($INTERRUPT->pipe_fileno, 0, sub { $INTERRUPT->handle });
		609	}
		610
		611	if (defined $AnyEvent::MODEL) {
		612	_init_anyevent;
		613	} else {
		614	push @AnyEvent::post_detect, \&_init_anyevent;
		615	}
456		616
457	=back	617	=back
458		618
459	=head2 THE OpenCL::Object CLASS	619	=head2 THE OpenCL::Object CLASS
460		620
…		…
472	C<IV> type in your code and cast that to the correct type.	632	C<IV> type in your code and cast that to the correct type.
473		633
474	=cut	634	=cut
475		635
476	sub OpenCL::Object::id {	636	sub OpenCL::Object::id {
		637	ref $_[0] eq "SCALAR"
477	${$_[0]}	638	? ${ $_[0] }
		639	: $_[0][0]
478	}	640	}
479		641
480	=back	642	=back
481		643
482	=head2 THE OpenCL::Platform CLASS	644	=head2 THE OpenCL::Platform CLASS
…		…
485		647
486	=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL)	648	=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL)
487		649
488	Returns a list of matching OpenCL::Device objects.	650	Returns a list of matching OpenCL::Device objects.
489		651
490	=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef)	652	=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr)
491		653
492	Tries to create a context. Never worked for me, and you need devices explicitly anyway.	654	Tries to create a context. Never worked for me, and you need devices explicitly anyway.
493		655
494	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>	656	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>
495		657
496	=item $ctx = $platform->context ($properties = undef, @$devices, $notify = undef)	658	=item $ctx = $platform->context ($properties, \@devices, $callback->($err, $pvt) = $print_stderr)
497		659
498	Create a new OpenCL::Context object using the given device object(s)- a	660	Create a new OpenCL::Context object using the given device object(s)- a
499	CL_CONTEXT_PLATFORM property is supplied automatically.	661	CL_CONTEXT_PLATFORM property is supplied automatically.
500		662
501	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>	663	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>
…		…
846	require Carp;	1008	require Carp;
847		1009
848	$prog = $self->program_with_source ($prog)	1010	$prog = $self->program_with_source ($prog)
849	unless ref $prog;	1011	unless ref $prog;
850		1012
		1013	eval { $prog->build (undef, $options); 1 }
		1014	or errno == BUILD_PROGRAM_FAILURE
		1015	or Carp::croak "OpenCL::Context->build_program: " . err2str;
		1016
		1017	# we check status for all devices
851	for my $dev ($self->devices) {	1018	for my $dev ($self->devices) {
852	eval { $prog->build ($dev, $options); 1 }	1019	$prog->build_status ($dev) == BUILD_SUCCESS
853	or Carp::croak ("Building OpenCL program for device '" . $dev->name . "' failed:\n"	1020	or Carp::croak ("Building OpenCL program for device '" . $dev->name . "' failed:\n"
854	. $prog->build_log ($dev));	1021	. $prog->build_log ($dev));
855	}	1022	}
856		1023
857	$prog	1024	$prog
858	}	1025	}
859		1026
…		…
883	=item $buf = $ctx->buffer_sv ($flags, $data)	1050	=item $buf = $ctx->buffer_sv ($flags, $data)
884		1051
885	Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and	1052	Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and
886	initialise it with the given data values.	1053	initialise it with the given data values.
887		1054
888	=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)	1055	=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)
889		1056
890	Creates a new OpenCL::Image object and optionally initialises it with	1057	Creates a new OpenCL::Image object and optionally initialises it with
891	the given data values.	1058	the given data values.
892		1059
893	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html>	1060	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html>
…		…
989	=back	1156	=back
990		1157
991	=head2 THE OpenCL::Queue CLASS	1158	=head2 THE OpenCL::Queue CLASS
992		1159
993	An OpenCL::Queue represents an execution queue for OpenCL. You execute	1160	An OpenCL::Queue represents an execution queue for OpenCL. You execute
994	requests by calling their respective C<enqueue_xxx> method and waitinf for	1161	requests by calling their respective method and waiting for it to complete
995	it to complete in some way.	1162	in some way.
996		1163
997	All the enqueue methods return an event object that can be used to wait	1164	Most methods that enqueue some request return an event object that can
998	for completion, unless the method is called in void context, in which case	1165	be used to wait for completion (optionally using a callback), unless
999	no event object is created.	1166	the method is called in void context, in which case no event object is
		1167	created.
1000		1168
1001	They also allow you to specify any number of other event objects that this	1169	They also allow you to specify any number of other event objects that this
1002	request has to wait for before it starts executing, by simply passing the	1170	request has to wait for before it starts executing, by simply passing the
1003	event objects as extra parameters to the enqueue methods. To simplify	1171	event objects as extra parameters to the enqueue methods. To simplify
1004	program design, this module ignores any C<undef> values in the list of	1172	program design, this module ignores any C<undef> values in the list of
1005	events. This makes it possible to code operations such as this, without	1173	events. This makes it possible to code operations such as this, without
1006	having to put a valid event object into C<$event> first:	1174	having to put a valid event object into C<$event> first:
1007		1175
1008	$event = $queue->enqueue_xxx (..., $event);	1176	$event = $queue->xxx (..., $event);
1009		1177
1010	Queues execute in-order by default, without any parallelism, so in most	1178	Queues execute in-order by default, without any parallelism, so in most
1011	cases (i.e. you use only one queue) it's not necessary to wait for or	1179	cases (i.e. you use only one queue) it's not necessary to wait for or
1012	create event objects, althoguh an our of order queue is often a bit	1180	create event objects, althoguh an our of order queue is often a bit
1013	faster.	1181	faster.
1014		1182
1015	=over 4	1183	=over 4
1016		1184
1017	=item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...)	1185	=item $ev = $queue->read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...)
1018		1186
1019	Reads data from buffer into the given string.	1187	Reads data from buffer into the given string.
1020		1188
1021	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html>	1189	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html>
1022		1190
1023	=item $ev = $queue->enqueue_write_buffer ($buffer, $blocking, $offset, $data, $wait_events...)	1191	=item $ev = $queue->write_buffer ($buffer, $blocking, $offset, $data, $wait_events...)
1024		1192
1025	Writes data to buffer from the given string.	1193	Writes data to buffer from the given string.
1026		1194
1027	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html>	1195	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html>
1028		1196
1029	=item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...)	1197	=item $ev = $queue->copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...)
1030		1198
1031	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html>	1199	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html>
1032		1200
1033	=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...)	1201	=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...)
1034		1202
1035	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html	1203	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html
1036		1204
1037	=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...)	1205	=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...)
1038		1206
1039	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html	1207	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html
1040		1208
1041	=item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)	1209	=item $ev = $queue->read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
1042		1210
1043	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html>	1211	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html>
1044		1212
1045	=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...)	1213	=item $ev = $queue->copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...)
1046		1214
1047	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html>	1215	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html>
1048		1216
1049	=item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)	1217	=item $ev = $queue->write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
1050		1218
1051	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html>	1219	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html>
1052		1220
1053	=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...)	1221	=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...)
1054		1222
1055	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html>	1223	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html>
1056		1224
1057	=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...)	1225	=item $ev = $queue->copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...)
1058		1226
1059	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html>	1227	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html>
1060		1228
1061	=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...)	1229	=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...)
1062		1230
1063	Yeah.	1231	Yeah.
1064		1232
1065	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>.	1233	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>.
1066		1234
1067	=item $ev = $queue->enqueue_fill_buffer ($mem, $pattern, $offset, $size, ...)	1235	=item $ev = $queue->fill_buffer ($mem, $pattern, $offset, $size, ...)
1068		1236
1069	Fills the given buffer object with repeated applications of C<$pattern>,	1237	Fills the given buffer object with repeated applications of C<$pattern>,
1070	starting at C<$offset> for C<$size> octets.	1238	starting at C<$offset> for C<$size> octets.
1071		1239
1072	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html>	1240	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html>
1073		1241
1074	=item $ev = $queue->enqueue_fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...)	1242	=item $ev = $queue->fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...)
1075		1243
1076	Fills the given image area with the given rgba colour components. The	1244	Fills the given image area with the given rgba colour components. The
1077	components are normally floating point values between C<0> and C<1>,	1245	components are normally floating point values between C<0> and C<1>,
1078	except when the image channel data type is a signe dor unsigned	1246	except when the image channel data type is a signe dor unsigned
1079	unnormalised format, in which case the range is determined by the format.	1247	unnormalised format, in which case the range is determined by the format.
1080		1248
1081	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html>	1249	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html>
1082		1250
1083	=item $ev = $queue->enqueue_task ($kernel, $wait_events...)	1251	=item $ev = $queue->task ($kernel, $wait_events...)
1084		1252
1085	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html>	1253	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html>
1086		1254
1087	=item $ev = $queue->enqueue_nd_range_kernel ($kernel, @$global_work_offset, @$global_work_size, @$local_work_size, $wait_events...)	1255	=item $ev = $queue->nd_range_kernel ($kernel, \@global_work_offset, \@global_work_size, \@local_work_size, $wait_events...)
1088		1256
1089	Enqueues a kernel execution.	1257	Enqueues a kernel execution.
1090		1258
1091	@$global_work_size must be specified as a reference to an array of	1259	\@global_work_size must be specified as a reference to an array of
1092	integers specifying the work sizes (element counts).	1260	integers specifying the work sizes (element counts).
1093		1261
1094	@$global_work_offset must be either C<undef> (in which case all offsets	1262	\@global_work_offset must be either C<undef> (in which case all offsets
1095	are C<0>), or a reference to an array of work offsets, with the same number	1263	are C<0>), or a reference to an array of work offsets, with the same number
1096	of elements as @$global_work_size.	1264	of elements as \@global_work_size.
1097		1265
1098	@$local_work_size must be either C<undef> (in which case the	1266	\@local_work_size must be either C<undef> (in which case the
1099	implementation is supposed to choose good local work sizes), or a	1267	implementation is supposed to choose good local work sizes), or a
1100	reference to an array of local work sizes, with the same number of	1268	reference to an array of local work sizes, with the same number of
1101	elements as @$global_work_size.	1269	elements as \@global_work_size.
1102		1270
1103	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html>	1271	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html>
1104		1272
1105	=item $ev = $queue->enqueue_acquire_gl_objects ([object, ...], $wait_events...)	1273	=item $ev = $queue->acquire_gl_objects ([object, ...], $wait_events...)
1106		1274
1107	Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired	1275	Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired
1108	for subsequent OpenCL usage.	1276	for subsequent OpenCL usage.
1109		1277
1110	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html>	1278	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html>
1111		1279
1112	=item $ev = $queue->enqueue_release_gl_objects ([object, ...], $wait_events...)	1280	=item $ev = $queue->release_gl_objects ([object, ...], $wait_events...)
1113		1281
1114	Enqueues a list (an array-ref of OpenCL::Memory objects) to be released	1282	Enqueues a list (an array-ref of OpenCL::Memory objects) to be released
1115	for subsequent OpenGL usage.	1283	for subsequent OpenGL usage.
1116		1284
1117	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html>	1285	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html>
1118		1286
1119	=item $ev = $queue->enqueue_wait_for_events ($wait_events...)	1287	=item $ev = $queue->wait_for_events ($wait_events...)
1120		1288
1121	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html>	1289	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html>
1122		1290
1123	=item $ev = $queue->enqueue_marker ($wait_events...)	1291	=item $ev = $queue->marker ($wait_events...)
1124		1292
1125	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html>	1293	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html>
1126		1294
1127	=item $ev = $queue->enqueue_barrier ($wait_events...)	1295	=item $ev = $queue->barrier ($wait_events...)
1128		1296
1129	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html>	1297	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html>
1130		1298
1131	=item $queue->flush	1299	=item $queue->flush
1132		1300
…		…
1351		1519
1352	=head2 THE OpenCL::Program CLASS	1520	=head2 THE OpenCL::Program CLASS
1353		1521
1354	=over 4	1522	=over 4
1355		1523
1356	=item $program->build ($device, $options = "")	1524	=item $program->build (\@devices = undef, $options = "", $cb->($program) = undef)
1357		1525
1358	Tries to build the program with the given options. See also the	1526	Tries to build the program with the given options. See also the
1359	C<$ctx->build> convenience function.	1527	C<$ctx->build> convenience function.
1360		1528
		1529	If a callback is specified, then it will be called when compilation is
		1530	finished. Note that many OpenCL implementations block your program while
		1531	compiling whether you use a callback or not. See C<build_async> if you
		1532	want to make sure the build is done in the background.
		1533
		1534	Note that some OpenCL implementations atc up badly, and don't call the
		1535	callback in some error cases (but call it in others). This implementation
		1536	assumes the callback will always be called, and leaks memory if this is
		1537	not so. So best make sure you don't pass in invalid values.
		1538
1361	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html>	1539	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html>
		1540
		1541	=item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef)
		1542
		1543	Similar to C<< ->build >>, except it starts a thread, and never fails (you
		1544	need to check the compilation status form the callback, or by polling).
1362		1545
1363	=item $packed_value = $program->build_info ($device, $name)	1546	=item $packed_value = $program->build_info ($device, $name)
1364		1547
1365	Similar to C<< $platform->info >>, but returns build info for a previous	1548	Similar to C<< $platform->info >>, but returns build info for a previous
1366	build attempt for the given device.	1549	build attempt for the given device.
…		…
1508		1691
1509	Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result.	1692	Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result.
1510		1693
1511	=for gengetinfo end kernel_work_group	1694	=for gengetinfo end kernel_work_group
1512		1695
		1696	=item $kernel->setf ($format, ...)
		1697
		1698	Sets the arguments of a kernel. Since OpenCL 1.1 doesn't have a generic
		1699	way to set arguments (and with OpenCL 1.2 it might be rather slow), you
		1700	need to specify a format argument, much as with C<printf>, to tell OpenCL
		1701	what type of argument it is.
		1702
		1703	The format arguments are single letters:
		1704
		1705	c char
		1706	C unsigned char
		1707	s short
		1708	S unsigned short
		1709	i int
		1710	I unsigned int
		1711	l long
		1712	L unsigned long
		1713
		1714	h half float (0..65535)
		1715	f float
		1716	d double
		1717
		1718	z local (octet size)
		1719
		1720	m memory object (buffer or image)
		1721	a sampler
		1722	e event
		1723
		1724	Space characters in the format string are ignored.
		1725
		1726	Example: set the arguments for a kernel that expects an int, two floats, a buffer and an image.
		1727
		1728	$kernel->setf ("i ff mm", 5, 0.5, 3, $buffer, $image);
		1729
1513	=item $kernel->set_TYPE ($index, $value)	1730	=item $kernel->set_TYPE ($index, $value)
1514		1731
		1732	=item $kernel->set_char ($index, $value)
		1733
		1734	=item $kernel->set_uchar ($index, $value)
		1735
		1736	=item $kernel->set_short ($index, $value)
		1737
		1738	=item $kernel->set_ushort ($index, $value)
		1739
		1740	=item $kernel->set_int ($index, $value)
		1741
		1742	=item $kernel->set_uint ($index, $value)
		1743
		1744	=item $kernel->set_long ($index, $value)
		1745
		1746	=item $kernel->set_ulong ($index, $value)
		1747
		1748	=item $kernel->set_half ($index, $value)
		1749
		1750	=item $kernel->set_float ($index, $value)
		1751
		1752	=item $kernel->set_double ($index, $value)
		1753
		1754	=item $kernel->set_memory ($index, $value)
		1755
		1756	=item $kernel->set_buffer ($index, $value)
		1757
		1758	=item $kernel->set_image ($index, $value)
		1759
		1760	=item $kernel->set_sampler ($index, $value)
		1761
		1762	=item $kernel->set_local ($index, $value)
		1763
		1764	=item $kernel->set_event ($index, $value)
		1765
1515	This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>.	1766	This is a family of methods to set the kernel argument with the number
1516		1767	C<$index> to the give C<$value>.
1517	TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>,
1518	C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>,
1519	C<image2d>, C<image3d>, C<sampler>, C<local> or C<event>.
1520		1768
1521	Chars and integers (including the half type) are specified as integers,	1769	Chars and integers (including the half type) are specified as integers,
1522	float and double as floating point values, memory/buffer/image2d/image3d	1770	float and double as floating point values, memory/buffer/image must be
1523	must be an object of that type or C<undef>, local-memory arguments are	1771	an object of that type or C<undef>, local-memory arguments are set by
1524	set by specifying the size, and sampler and event must be objects of that	1772	specifying the size, and sampler and event must be objects of that type.
1525	type.	1773
		1774	Note that C<set_memory> works for all memory objects (all types of buffers
		1775	and images) - the main purpose of the more specific C<set_TYPE> functions
		1776	is type checking.
1526		1777
1527	Setting an argument for a kernel does NOT keep a reference to the object -	1778	Setting an argument for a kernel does NOT keep a reference to the object -
1528	for example, if you set an argument to some image object, free the image,	1779	for example, if you set an argument to some image object, free the image,
1529	and call the kernel, you will run into undefined behaviour.	1780	and call the kernel, you will run into undefined behaviour.
1530		1781
…		…
1543		1794
1544	Waits for the event to complete.	1795	Waits for the event to complete.
1545		1796
1546	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>	1797	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>
1547		1798
		1799	=item $ev->cb ($exec_callback_type, $callback->($event, $event_command_exec_status))
		1800
		1801	Adds a callback to the callback stack for the given event type. There is
		1802	no way to remove a callback again.
		1803
		1804	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetEventCallback.html>
		1805
1548	=item $packed_value = $ev->info ($name)	1806	=item $packed_value = $ev->info ($name)
1549		1807
1550	See C<< $platform->info >> for details.	1808	See C<< $platform->info >> for details.
1551		1809
1552	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html>	1810	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html>
…		…
1612		1870
1613	=over 4	1871	=over 4
1614		1872
1615	=item $ev->set_status ($execution_status)	1873	=item $ev->set_status ($execution_status)
1616		1874
		1875	Sets the execution status of the user event. Can only be called once,
		1876	either with OpenCL::COMPLETE or a negative number as status.
		1877
1617	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html>	1878	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html>
1618		1879
1619	=back	1880	=back
1620		1881
1621	=cut	1882	=cut

Diff Legend

-–
+Removed lines
-+
+Added lines
-<
+Changed lines
->
+Changed lines

Comparing OpenCL/OpenCL.pm (file contents): Revision 1.54 by root, Tue Apr 24 14:57:06 2012 UTC vs. Revision 1.61 by root, Sat Apr 28 13:31:40 2012 UTC

Diff Legend

Comparing OpenCL/OpenCL.pm (file contents):
Revision 1.54 by root, Tue Apr 24 14:57:06 2012 UTC vs.
Revision 1.61 by root, Sat Apr 28 13:31:40 2012 UTC