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

Comparing OpenCL/OpenCL.pm (file contents):
Revision 1.32 by root, Thu Apr 19 12:12:03 2012 UTC vs.
Revision 1.64 by root, Mon Apr 30 23:12:43 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.
…		…
157	$id = get_global_id (0);	160	$id = get_global_id (0);
158	output [id] = input [id] * input [id];	161	output [id] = input [id] * input [id];
159	}	162	}
160	';	163	';
161		164
162	my $prog = $ctx->program_with_source ($src);	165	my $prog = $ctx->build_program ($src);
163
164	# build croaks on compile errors, so catch it and print the compile errors
165	eval { $prog->build ($dev); 1 }
166	or die $prog->build_log;
167
168	my $kernel = $prog->kernel ("squareit");	166	my $kernel = $prog->kernel ("squareit");
169		167
170	=head2 Create some input and output float buffers, then call the	168	=head2 Create some input and output float buffers, then call the
171	'squareit' kernel on them.	169	'squareit' kernel on them.
172		170
…		…
176	# set buffer	174	# set buffer
177	$kernel->set_buffer (0, $input);	175	$kernel->set_buffer (0, $input);
178	$kernel->set_buffer (1, $output);	176	$kernel->set_buffer (1, $output);
179		177
180	# execute it for all 4 numbers	178	# execute it for all 4 numbers
181	$queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef);	179	$queue->nd_range_kernel ($kernel, undef, [4], undef);
182		180
183	# enqueue a synchronous read	181	# enqueue a synchronous read
184	$queue->enqueue_read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data);	182	$queue->read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data);
185		183
186	# print the results:	184	# print the results:
187	printf "%s\n", join ", ", unpack "f*", $data;	185	printf "%s\n", join ", ", unpack "f*", $data;
188		186
189	=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,
190	showing off barriers.	188	showing off barriers.
191		189
192	# execute it for all 4 numbers	190	# execute it for all 4 numbers
193	$queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef);	191	$queue->nd_range_kernel ($kernel, undef, [4], undef);
194		192
195	# enqueue a barrier to ensure in-order execution	193	# enqueue a barrier to ensure in-order execution
196	$queue->enqueue_barrier;	194	$queue->barrier;
197		195
198	# enqueue an async read	196	# enqueue an async read
199	$queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data);	197	$queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data);
200		198
201	# wait for all requests to finish	199	# wait for all requests to finish
202	$queue->finish;	200	$queue->finish;
203		201
204	=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,
205	showing off event objects and wait lists.	203	showing off event objects and wait lists.
206		204
207	# execute it for all 4 numbers	205	# execute it for all 4 numbers
208	my $ev = $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef);	206	my $ev = $queue->nd_range_kernel ($kernel, undef, [4], undef);
209		207
210	# enqueue an async read	208	# enqueue an async read
211	$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);
212		210
213	# wait for the last event to complete	211	# wait for the last event to complete
214	$ev->wait;	212	$ev->wait;
		213
		214	=head2 Use the OpenGL module to share a texture between OpenCL and OpenGL and draw some julia
		215	set tunnel effect.
		216
		217	This is quite a long example to get you going - you can download it from
		218	L<http://cvs.schmorp.de/OpenCL/examples/juliaflight>.
		219
		220	use OpenGL ":all";
		221	use OpenCL;
		222
		223	my $S = $ARGV[0] \|\| 256; # window/texture size, smaller is faster
		224
		225	# open a window and create a gl texture
		226	OpenGL::glpOpenWindow width => $S, height => $S;
		227	my $texid = glGenTextures_p 1;
		228	glBindTexture GL_TEXTURE_2D, $texid;
		229	glTexImage2D_c GL_TEXTURE_2D, 0, GL_RGBA8, $S, $S, 0, GL_RGBA, GL_UNSIGNED_BYTE, 0;
		230
		231	# find and use the first opencl device that let's us get a shared opengl context
		232	my $platform;
		233	my $dev;
		234	my $ctx;
		235
		236	for (OpenCL::platforms) {
		237	$platform = $_;
		238	for ($platform->devices) {
		239	$dev = $_;
		240	$ctx = $platform->context ([OpenCL::GLX_DISPLAY_KHR, undef, OpenCL::GL_CONTEXT_KHR, undef], [$dev])
		241	and last;
		242	}
		243	}
		244
		245	$ctx
		246	or die "cannot find suitable OpenCL device\n";
		247
		248	my $queue = $ctx->queue ($dev);
		249
		250	# now attach an opencl image2d object to the opengl texture
		251	my $tex = $ctx->gl_texture2d (OpenCL::MEM_WRITE_ONLY, GL_TEXTURE_2D, 0, $texid);
		252
		253	# now the boring opencl code
		254	my $src = <<EOF;
		255	kernel void
		256	juliatunnel (write_only image2d_t img, float time)
		257	{
		258	int2 xy = (int2)(get_global_id (0), get_global_id (1));
		259	float2 p = convert_float2 (xy) / $S.f * 2.f - 1.f;
		260
		261	float2 m = (float2)(1.f, p.y) / fabs (p.x); // tunnel
		262	m.x = fabs (fmod (m.x + time * 0.05f, 4.f) - 2.f);
		263
		264	float2 z = m;
		265	float2 c = (float2)(sin (time * 0.01133f), cos (time * 0.02521f));
		266
		267	for (int i = 0; i < 25 && dot (z, z) < 4.f; ++i) // standard julia
		268	z = (float2)(z.x * z.x - z.y * z.y, 2.f * z.x * z.y) + c;
		269
		270	float3 colour = (float3)(z.x, z.y, atan2 (z.y, z.x));
		271	write_imagef (img, xy, (float4)(colour * p.x * p.x, 1.));
		272	}
		273	EOF
		274
		275	my $prog = $ctx->build_program ($src);
		276	my $kernel = $prog->kernel ("juliatunnel");
		277
		278	# program compiled, kernel ready, now draw and loop
		279
		280	for (my $time; ; ++$time) {
		281	# acquire objects from opengl
		282	$queue->acquire_gl_objects ([$tex]);
		283
		284	# configure and run our kernel
		285	$kernel->setf ("mf", $tex, $time*2); # mf = memory object, float
		286	$queue->nd_range_kernel ($kernel, undef, [$S, $S], undef);
		287
		288	# release objects to opengl again
		289	$queue->release_gl_objects ([$tex]);
		290
		291	# wait
		292	$queue->finish;
		293
		294	# now draw the texture, the defaults should be all right
		295	glTexParameterf GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST;
		296
		297	glEnable GL_TEXTURE_2D;
		298	glBegin GL_QUADS;
		299	glTexCoord2f 0, 1; glVertex3i -1, -1, -1;
		300	glTexCoord2f 0, 0; glVertex3i 1, -1, -1;
		301	glTexCoord2f 1, 0; glVertex3i 1, 1, -1;
		302	glTexCoord2f 1, 1; glVertex3i -1, 1, -1;
		303	glEnd;
		304
		305	glXSwapBuffers;
		306
		307	select undef, undef, undef, 1/60;
		308	}
215		309
216	=head1 DOCUMENTATION	310	=head1 DOCUMENTATION
217		311
218	=head2 BASIC CONVENTIONS	312	=head2 BASIC CONVENTIONS
219		313
…		…
241	=item * Structures are often specified by flattening out their components	335	=item * Structures are often specified by flattening out their components
242	as with short vectors, and returned as arrayrefs.	336	as with short vectors, and returned as arrayrefs.
243		337
244	=item * When enqueuing commands, the wait list is specified by adding	338	=item * When enqueuing commands, the wait list is specified by adding
245	extra arguments to the function - anywhere a C<$wait_events...> argument	339	extra arguments to the function - anywhere a C<$wait_events...> argument
246	is documented this can be any number of event objects.	340	is documented this can be any number of event objects. As an extsnion
		341	implemented by this module, C<undef> values will be ignored in the event
		342	list.
247		343
248	=item * When enqueuing commands, if the enqueue method is called in void	344	=item * When enqueuing commands, if the enqueue method is called in void
249	context, no event is created. In all other contexts an event is returned	345	context, no event is created. In all other contexts an event is returned
250	by the method.	346	by the method.
251		347
…		…
271	ulong IV - Q	367	ulong IV - Q
272	float NV float f	368	float NV float f
273	half IV ushort S	369	half IV ushort S
274	double NV double d	370	double NV double d
275		371
276	=head2 OpenGL sharing	372	=head2 GLX SUPPORT
277		373
278	This module can be optionally compiled with support for	374	Due to the sad state that OpenGL support is in in Perl (mostly the OpenGL
279	OpenGL sharing. The sharing functions are only available when	375	module, which has little to no documentation and has little to no support
280	C<OpenCL::HAVE_OPENGL> returns true, otherwise they are absent and cannot	376	for glX), this module, as a special extension, treats context creation
281	be called.	377	properties C<OpenCL::GLX_DISPLAY_KHR> and C<OpenCL::GL_CONTEXT_KHR>
		378	specially: If either or both of these are C<undef>, then the OpenCL
		379	module tries to dynamically resolve C<glXGetCurrentDisplay> and
		380	C<glXGetCurrentContext>, call these functions and use their return values
		381	instead.
		382
		383	For this to work, the OpenGL library must be loaded, a GLX context must
		384	have been created and be made current, and C<dlsym> must be available and
		385	capable of finding the function via C<RTLD_DEFAULT>.
		386
		387	=head2 EVENT SYSTEM
		388
		389	OpenCL can generate a number of (potentially) asynchronous events, for
		390	example, after compiling a program, to signal a context-related error or,
		391	perhaps most important, to signal completion of queued jobs (by setting
		392	callbacks on OpenCL::Event objects).
		393
		394	To facilitate this, this module maintains an event queue - each
		395	time an asynchronous event happens, it is queued, and perl will be
		396	interrupted. This is implemented via the L<Async::Interrupt> module. In
		397	addition, this module has L<AnyEvent> support, so it can seamlessly
		398	integrate itself into many event loops.
		399
		400	Since this module is a bit hard to understand, here are some case examples:
		401
		402	=head3 Don't use callbacks.
		403
		404	When your program never uses any callbacks, then there will never be any
		405	notifications you need to take care of, and therefore no need to worry
		406	about all this.
		407
		408	You can achieve a great deal by explicitly waiting for events, or using
		409	barriers and flush calls. In many programs, there is no need at all to
		410	tinker with asynchronous events.
		411
		412	=head3 Use AnyEvent
		413
		414	This module automatically registers a watcher that invokes all outstanding
		415	event callbacks when AnyEvent is initialised (and block asynchronous
		416	interruptions). Using this mode of operations is the safest and most
		417	recommended one.
		418
		419	To use this, simply use AnyEvent and this module normally, make sure you
		420	have an event loop running:
		421
		422	use Gtk2 -init;
		423	use AnyEvent;
		424
		425	# initialise AnyEvent, by creating a watcher, or:
		426	AnyEvent::detect;
		427
		428	my $e = $queue->marker;
		429	$e->cb (sub {
		430	warn "opencl is finished\n";
		431	})
		432
		433	main Gtk2;
		434
		435	Note that this module will not initialise AnyEvent for you. Before
		436	AnyEvent is initialised, the module will asynchronously interrupt perl
		437	instead. To avoid any surprises, it's best to explicitly initialise
		438	AnyEvent.
		439
		440	You can temporarily enable asynchronous interruptions (see next paragraph)
		441	by calling C<$OpenCL::INTERRUPT->unblock> and disable them again by
		442	calling C<$OpenCL::INTERRUPT->block>.
		443
		444	=head3 Let yourself be interrupted at any time
		445
		446	This mode is the default unless AnyEvent is loaded and initialised. In
		447	this mode, OpenCL asynchronously interrupts a running perl program. The
		448	emphasis is on both I<asynchronously> and I<running> here.
		449
		450	Asynchronously means that perl might execute your callbacks at any
		451	time. For example, in the following code (I<THAT YOU SHOULD NOT COPY>),
		452	the C<until> loop following the marker call will be interrupted by the
		453	callback:
		454
		455	my $e = $queue->marker;
		456	my $flag;
		457	$e->cb (sub { $flag = 1 });
		458	1 until $flag;
		459	# $flag is now 1
		460
		461	The reason why you shouldn't blindly copy the above code is that
		462	busy waiting is a really really bad thing, and really really bad for
		463	performance.
		464
		465	While at first this asynchronous business might look exciting, it can be
		466	really hard, because you need to be prepared for the callback code to be
		467	executed at any time, which limits the amount of things the callback code
		468	can do safely.
		469
		470	This can be mitigated somewhat by using C<<
		471	$OpenCL::INTERRUPT->scope_block >> (see the L<Async::Interrupt>
		472	documentation for details).
		473
		474	The other problem is that your program must be actively I<running> to be
		475	interrupted. When you calculate stuff, your program is running. When you
		476	hang in some C functions or other block execution (by calling C<sleep>,
		477	C<select>, running an event loop and so on), your program is waiting, not
		478	running.
		479
		480	One way around that would be to attach a read watcher to your event loop,
		481	listening for events on C<< $OpenCL::INTERRUPT->pipe_fileno >>, using a
		482	dummy callback (C<sub { }>) to temporarily execute some perl code.
		483
		484	That is then awfully close to using the built-in AnyEvent support above,
		485	though, so consider that one instead.
		486
		487	=head3 Be creative
		488
		489	OpenCL exports the L<Async::Interrupt> object it uses in the global
		490	variable C<$OpenCL::INTERRUPT>. You can configure it in any way you like.
		491
		492	So if you want to feel like a real pro, err, wait, if you feel no risk
		493	menas no fun, you can experiment by implementing your own mode of
		494	operations.
		495
		496	=cut
		497
		498	package OpenCL;
		499
		500	use common::sense;
		501	use Carp ();
		502	use Async::Interrupt ();
		503
		504	our $POLL_FUNC; # set by XS
		505
		506	BEGIN {
		507	our $VERSION = '0.98';
		508
		509	require XSLoader;
		510	XSLoader::load (__PACKAGE__, $VERSION);
		511
		512	@OpenCL::Platform::ISA =
		513	@OpenCL::Device::ISA =
		514	@OpenCL::Context::ISA =
		515	@OpenCL::Queue::ISA =
		516	@OpenCL::Memory::ISA =
		517	@OpenCL::Sampler::ISA =
		518	@OpenCL::Program::ISA =
		519	@OpenCL::Kernel::ISA =
		520	@OpenCL::Event::ISA = OpenCL::Object::;
		521
		522	@OpenCL::Buffer::ISA =
		523	@OpenCL::Image::ISA = OpenCL::Memory::;
		524
		525	@OpenCL::BufferObj::ISA = OpenCL::Buffer::;
		526
		527	@OpenCL::Image2D::ISA =
		528	@OpenCL::Image3D::ISA =
		529	@OpenCL::Image2DArray::ISA =
		530	@OpenCL::Image1D::ISA =
		531	@OpenCL::Image1DArray::ISA =
		532	@OpenCL::Image1DBuffer::ISA = OpenCL::Image::;
		533
		534	@OpenCL::UserEvent::ISA = OpenCL::Event::;
		535	}
282		536
283	=head2 THE OpenCL PACKAGE	537	=head2 THE OpenCL PACKAGE
284		538
285	=over 4	539	=over 4
286		540
287	=item $int = OpenCL::errno	541	=item $int = OpenCL::errno
288		542
289	The last error returned by a function - it's only valid after an error occured	543	The last error returned by a function - it's only valid after an error occured
290	and before calling another OpenCL function.	544	and before calling another OpenCL function.
291		545
292	=item $str = OpenCL::err2str $errval	546	=item $str = OpenCL::err2str [$errval]
293		547
294	Comverts an error value into a human readable string.	548	Converts an error value into a human readable string. IF no error value is
		549	given, then the last error will be used (as returned by OpenCL::errno).
295		550
296	=item $str = OpenCL::enum2str $enum	551	=item $str = OpenCL::enum2str $enum
297		552
298	Converts most enum values (of parameter names, image format constants,	553	Converts most enum values (of parameter names, image format constants,
299	object types, addressing and filter modes, command types etc.) into a	554	object types, addressing and filter modes, command types etc.) into a
…		…
305		560
306	Returns all available OpenCL::Platform objects.	561	Returns all available OpenCL::Platform objects.
307		562
308	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html>	563	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html>
309		564
310	=item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef	565	=item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr
311		566
312	Tries to create a context from a default device and platform - never worked for me.	567	Tries to create a context from a default device and platform type - never worked for me.
313		568
314	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>	569	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>
315		570
		571	=item $ctx = OpenCL::context $properties, \@devices, $callback->($err, $pvt) = $print_stderr)
		572
		573	Create a new OpenCL::Context object using the given device object(s). This
		574	function isn't implemented yet, use C<< $platform->context >> instead.
		575
		576	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>
		577
316	=item OpenCL::wait_for_events $wait_events...	578	=item OpenCL::wait_for_events $wait_events...
317		579
318	Waits for all events to complete.	580	Waits for all events to complete.
319		581
320	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>	582	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>
321		583
		584	=item OpenCL::poll
		585
		586	Checks if there are any outstanding events (see L<EVENT SYSTEM>) and
		587	invokes their callbacks.
		588
		589	=item $OpenCL::INTERRUPT
		590
		591	The L<Async::Interrupt> object used to signal asynchronous events (see
		592	L<EVENT SYSTEM>).
		593
		594	=cut
		595
		596	our $INTERRUPT = new Async::Interrupt c_cb => [$POLL_FUNC, 0];
		597
		598	&_eq_initialise ($INTERRUPT->signal_func);
		599
		600	=item $OpenCL::WATCHER
		601
		602	The L<AnyEvent> watcher object used to watch for asynchronous events (see
		603	L<EVENT SYSTEM>). This variable is C<undef> until L<AnyEvent> has been
		604	loaded I<and> initialised (e.g. by calling C<AnyEvent::detect>).
		605
		606	=cut
		607
		608	our $WATCHER;
		609
		610	sub _init_anyevent {
		611	$INTERRUPT->block;
		612	$WATCHER = AE::io ($INTERRUPT->pipe_fileno, 0, sub { $INTERRUPT->handle });
		613	}
		614
		615	if (defined $AnyEvent::MODEL) {
		616	_init_anyevent;
		617	} else {
		618	push @AnyEvent::post_detect, \&_init_anyevent;
		619	}
		620
322	=back	621	=back
323		622
		623	=head2 THE OpenCL::Object CLASS
		624
		625	This is the base class for all objects in the OpenCL module. The only
		626	method it implements is the C<id> method, which is only useful if you want
		627	to interface to OpenCL on the C level.
		628
		629	=over 4
		630
		631	=item $iv = $obj->id
		632
		633	OpenCL objects are represented by pointers or integers on the C level. If
		634	you want to interface to an OpenCL object directly on the C level, then
		635	you need this value, which is returned by this method. You should use an
		636	C<IV> type in your code and cast that to the correct type.
		637
		638	=cut
		639
		640	sub OpenCL::Object::id {
		641	ref $_[0] eq "SCALAR"
		642	? ${ $_[0] }
		643	: $_[0][0]
		644	}
		645
		646	=back
		647
324	=head2 THE OpenCL::Platform CLASS	648	=head2 THE OpenCL::Platform CLASS
325		649
326	=over 4	650	=over 4
327		651
328	=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL)	652	=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL)
329		653
330	Returns a list of matching OpenCL::Device objects.	654	Returns a list of matching OpenCL::Device objects.
331		655
332	=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef)	656	=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr)
333		657
334	Tries to create a context. Never worked for me, and you need devices explicitly anyway.	658	Tries to create a context. Never worked for me, and you need devices explicitly anyway.
335		659
336	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>	660	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>
337		661
338	=item $ctx = $platform->context ($properties = undef, @$devices, $notify = undef)	662	=item $ctx = $platform->context ($properties, \@devices, $callback->($err, $pvt) = $print_stderr)
339		663
340	Create a new OpenCL::Context object using the given device object(s)- a	664	Create a new OpenCL::Context object using the given device object(s)- a
341	CL_CONTEXT_PLATFORM property is supplied automatically.	665	CL_CONTEXT_PLATFORM property is supplied automatically.
342		666
343	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>	667	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>
…		…
351	It's best to avoid this method and use one of the following convenience	675	It's best to avoid this method and use one of the following convenience
352	wrappers.	676	wrappers.
353		677
354	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html>	678	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html>
355		679
		680	=item $platform->unload_compiler
		681
		682	Attempts to unload the compiler for this platform, for endless
		683	profit. Does nothing on OpenCL 1.1.
		684
		685	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clUnloadPlatformCompiler.html>
		686
356	=for gengetinfo begin platform	687	=for gengetinfo begin platform
357		688
358	=item $string = $platform->profile	689	=item $string = $platform->profile
359		690
360	Calls C<clGetPlatformInfo> with C<CL_PLATFORM_PROFILE> and returns the result.	691	Calls C<clGetPlatformInfo> with C<CL_PLATFORM_PROFILE> and returns the result.
…		…
645		976
646	=item @device_partition_property_exts = $device->affinity_domains_ext	977	=item @device_partition_property_exts = $device->affinity_domains_ext
647		978
648	Calls C<clGetDeviceInfo> with C<CL_DEVICE_AFFINITY_DOMAINS_EXT> and returns the result.	979	Calls C<clGetDeviceInfo> with C<CL_DEVICE_AFFINITY_DOMAINS_EXT> and returns the result.
649		980
650	=item $uint = $device->reference_count_ext	981	=item $uint = $device->reference_count_ext
651		982
652	Calls C<clGetDeviceInfo> with C<CL_DEVICE_REFERENCE_COUNT_EXT > and returns the result.	983	Calls C<clGetDeviceInfo> with C<CL_DEVICE_REFERENCE_COUNT_EXT> and returns the result.
653		984
654	=item @device_partition_property_exts = $device->partition_style_ext	985	=item @device_partition_property_exts = $device->partition_style_ext
655		986
656	Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_STYLE_EXT> and returns the result.	987	Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_STYLE_EXT> and returns the result.
657		988
…		…
661		992
662	=head2 THE OpenCL::Context CLASS	993	=head2 THE OpenCL::Context CLASS
663		994
664	=over 4	995	=over 4
665		996
		997	=item $prog = $ctx->build_program ($program, $options = "")
		998
		999	This convenience function tries to build the program on all devices in
		1000	the context. If the build fails, then the function will C<croak> with the
		1001	build log. Otherwise ti returns the program object.
		1002
		1003	The C<$program> can either be a C<OpenCL::Program> object or a string
		1004	containing the program. In the latter case, a program objetc will be
		1005	created automatically.
		1006
		1007	=cut
		1008
		1009	sub OpenCL::Context::build_program {
		1010	my ($self, $prog, $options) = @_;
		1011
		1012	$prog = $self->program_with_source ($prog)
		1013	unless ref $prog;
		1014
		1015	eval { $prog->build (undef, $options); 1 }
		1016	or errno == BUILD_PROGRAM_FAILURE
		1017	or errno == INVALID_BINARY # workaround nvidia bug
		1018	or Carp::croak "OpenCL::Context->build_program: " . err2str;
		1019
		1020	# we check status for all devices
		1021	for my $dev ($self->devices) {
		1022	$prog->build_status ($dev) == BUILD_SUCCESS
		1023	or Carp::croak "Building OpenCL program for device '" . $dev->name . "' failed:\n"
		1024	. $prog->build_log ($dev);
		1025	}
		1026
		1027	$prog
		1028	}
		1029
666	=item $queue = $ctx->queue ($device, $properties)	1030	=item $queue = $ctx->queue ($device, $properties)
667		1031
668	Create a new OpenCL::Queue object from the context and the given device.	1032	Create a new OpenCL::Queue object from the context and the given device.
669		1033
670	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html>	1034	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html>
		1035
		1036	Example: create an out-of-order queue.
		1037
		1038	$queue = $ctx->queue ($device, OpenCL::QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE);
671		1039
672	=item $ev = $ctx->user_event	1040	=item $ev = $ctx->user_event
673		1041
674	Creates a new OpenCL::UserEvent object.	1042	Creates a new OpenCL::UserEvent object.
675		1043
…		…
685	=item $buf = $ctx->buffer_sv ($flags, $data)	1053	=item $buf = $ctx->buffer_sv ($flags, $data)
686		1054
687	Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and	1055	Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and
688	initialise it with the given data values.	1056	initialise it with the given data values.
689		1057
		1058	=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)
		1059
		1060	Creates a new OpenCL::Image object and optionally initialises it with
		1061	the given data values.
		1062
		1063	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html>
		1064
690	=item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $row_pitch = 0, $data = undef)	1065	=item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $row_pitch = 0, $data = undef)
691		1066
692	Creates a new OpenCL::Image2D object and optionally initialises it with	1067	Creates a new OpenCL::Image2D object and optionally initialises it with
693	the given data values.	1068	the given data values.
694		1069
…		…
699	Creates a new OpenCL::Image3D object and optionally initialises it with	1074	Creates a new OpenCL::Image3D object and optionally initialises it with
700	the given data values.	1075	the given data values.
701		1076
702	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage3D.html>	1077	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage3D.html>
703		1078
		1079	=item $buffer = $ctx->gl_buffer ($flags, $bufobj)
		1080
		1081	Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object that refers to the given
		1082	OpenGL buffer object.
		1083
		1084	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLBuffer.html
		1085
		1086	=item $img = $ctx->gl_texture ($flags, $target, $miplevel, $texture)
		1087
		1088	Creates a new OpenCL::Image object that refers to the given OpenGL
		1089	texture object or buffer.
		1090
		1091	http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateFromGLTexture.html
		1092
		1093	=item $img = $ctx->gl_texture2d ($flags, $target, $miplevel, $texture)
		1094
		1095	Creates a new OpenCL::Image2D object that refers to the given OpenGL
		1096	2D texture object.
		1097
		1098	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture2D.html
		1099
		1100	=item $img = $ctx->gl_texture3d ($flags, $target, $miplevel, $texture)
		1101
		1102	Creates a new OpenCL::Image3D object that refers to the given OpenGL
		1103	3D texture object.
		1104
		1105	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture3D.html
		1106
		1107	=item $ctx->gl_renderbuffer ($flags, $renderbuffer)
		1108
		1109	Creates a new OpenCL::Image2D object that refers to the given OpenGL
		1110	render buffer.
		1111
		1112	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLRenderbuffer.html
		1113
704	=item @formats = $ctx->supported_image_formats ($flags, $image_type)	1114	=item @formats = $ctx->supported_image_formats ($flags, $image_type)
705		1115
706	Returns a list of matching image formats - each format is an arrayref with	1116	Returns a list of matching image formats - each format is an arrayref with
707	two values, $channel_order and $channel_type, in it.	1117	two values, $channel_order and $channel_type, in it.
708		1118
…		…
749	=back	1159	=back
750		1160
751	=head2 THE OpenCL::Queue CLASS	1161	=head2 THE OpenCL::Queue CLASS
752		1162
753	An OpenCL::Queue represents an execution queue for OpenCL. You execute	1163	An OpenCL::Queue represents an execution queue for OpenCL. You execute
754	requests by calling their respective C<enqueue_xxx> method and waitinf for	1164	requests by calling their respective method and waiting for it to complete
755	it to complete in some way.	1165	in some way.
756		1166
757	All the enqueue methods return an event object that can be used to wait	1167	Most methods that enqueue some request return an event object that can
758	for completion, unless the method is called in void context, in which case	1168	be used to wait for completion (optionally using a callback), unless
759	no event object is created.	1169	the method is called in void context, in which case no event object is
		1170	created.
760		1171
761	They also allow you to specify any number of other event objects that this	1172	They also allow you to specify any number of other event objects that this
762	request has to wait for before it starts executing, by simply passing the	1173	request has to wait for before it starts executing, by simply passing the
763	event objects as extra parameters to the enqueue methods.	1174	event objects as extra parameters to the enqueue methods. To simplify
		1175	program design, this module ignores any C<undef> values in the list of
		1176	events. This makes it possible to code operations such as this, without
		1177	having to put a valid event object into C<$event> first:
		1178
		1179	$event = $queue->xxx (..., $event);
764		1180
765	Queues execute in-order by default, without any parallelism, so in most	1181	Queues execute in-order by default, without any parallelism, so in most
766	cases (i.e. you use only one queue) it's not necessary to wait for or	1182	cases (i.e. you use only one queue) it's not necessary to wait for or
767	create event objects.	1183	create event objects, althoguh an our of order queue is often a bit
		1184	faster.
768		1185
769	=over 4	1186	=over 4
770		1187
771	=item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...)	1188	=item $ev = $queue->read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...)
772		1189
773	Reads data from buffer into the given string.	1190	Reads data from buffer into the given string.
774		1191
775	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html>	1192	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html>
776		1193
777	=item $ev = $queue->enqueue_write_buffer ($buffer, $blocking, $offset, $data, $wait_events...)	1194	=item $ev = $queue->write_buffer ($buffer, $blocking, $offset, $data, $wait_events...)
778		1195
779	Writes data to buffer from the given string.	1196	Writes data to buffer from the given string.
780		1197
781	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html>	1198	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html>
782		1199
783	=item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...)	1200	=item $ev = $queue->copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...)
784		1201
785	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html>	1202	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html>
786		1203
787	=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...)	1204	=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...)
788		1205
789	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html	1206	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html
790		1207
791	=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...)	1208	=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...)
792		1209
793	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html	1210	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html
794		1211
795	=item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)	1212	=item $ev = $queue->read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
796		1213
797	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html>	1214	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html>
798		1215
799	=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...)	1216	=item $ev = $queue->copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...)
800		1217
801	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html>	1218	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html>
802		1219
803	=item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)	1220	=item $ev = $queue->write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
804		1221
805	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html>	1222	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html>
806		1223
807	=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...)	1224	=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...)
808		1225
809	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html>	1226	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html>
810		1227
811	=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...)	1228	=item $ev = $queue->copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...)
812		1229
813	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html>	1230	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html>
814		1231
815	=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...)	1232	=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...)
816		1233
817	Yeah.	1234	Yeah.
818		1235
819	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>.	1236	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>.
820		1237
		1238	=item $ev = $queue->fill_buffer ($mem, $pattern, $offset, $size, ...)
		1239
		1240	Fills the given buffer object with repeated applications of C<$pattern>,
		1241	starting at C<$offset> for C<$size> octets.
		1242
		1243	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html>
		1244
		1245	=item $ev = $queue->fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...)
		1246
		1247	Fills the given image area with the given rgba colour components. The
		1248	components are normally floating point values between C<0> and C<1>,
		1249	except when the image channel data type is a signe dor unsigned
		1250	unnormalised format, in which case the range is determined by the format.
		1251
		1252	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html>
		1253
821	=item $ev = $queue->enqueue_task ($kernel, $wait_events...)	1254	=item $ev = $queue->task ($kernel, $wait_events...)
822		1255
823	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html>	1256	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html>
824		1257
825	=item $ev = $queue->enqueue_nd_range_kernel ($kernel, @$global_work_offset, @$global_work_size, @$local_work_size, $wait_events...)	1258	=item $ev = $queue->nd_range_kernel ($kernel, \@global_work_offset, \@global_work_size, \@local_work_size, $wait_events...)
826		1259
827	Enqueues a kernel execution.	1260	Enqueues a kernel execution.
828		1261
829	@$global_work_size must be specified as a reference to an array of	1262	\@global_work_size must be specified as a reference to an array of
830	integers specifying the work sizes (element counts).	1263	integers specifying the work sizes (element counts).
831		1264
832	@$global_work_offset must be either C<undef> (in which case all offsets	1265	\@global_work_offset must be either C<undef> (in which case all offsets
833	are C<0>), or a reference to an array of work offsets, with the same number	1266	are C<0>), or a reference to an array of work offsets, with the same number
834	of elements as @$global_work_size.	1267	of elements as \@global_work_size.
835		1268
836	@$local_work_size must be either C<undef> (in which case the	1269	\@local_work_size must be either C<undef> (in which case the
837	implementation is supposed to choose good local work sizes), or a	1270	implementation is supposed to choose good local work sizes), or a
838	reference to an array of local work sizes, with the same number of	1271	reference to an array of local work sizes, with the same number of
839	elements as @$global_work_size.	1272	elements as \@global_work_size.
840		1273
841	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html>	1274	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html>
842		1275
843	=item $ev = $queue->enqueue_marker	1276	=item $ev = $queue->acquire_gl_objects ([object, ...], $wait_events...)
844		1277
		1278	Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired
		1279	for subsequent OpenCL usage.
		1280
845	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueMarker.html>	1281	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html>
846		1282
		1283	=item $ev = $queue->release_gl_objects ([object, ...], $wait_events...)
		1284
		1285	Enqueues a list (an array-ref of OpenCL::Memory objects) to be released
		1286	for subsequent OpenGL usage.
		1287
		1288	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html>
		1289
847	=item $ev = $queue->enqueue_wait_for_events ($wait_events...)	1290	=item $ev = $queue->wait_for_events ($wait_events...)
848		1291
849	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html>	1292	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html>
850		1293
851	=item $queue->enqueue_barrier	1294	=item $ev = $queue->marker ($wait_events...)
852		1295
		1296	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html>
		1297
		1298	=item $ev = $queue->barrier ($wait_events...)
		1299
853	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueBarrier.html>	1300	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html>
854		1301
855	=item $queue->flush	1302	=item $queue->flush
856		1303
857	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html>	1304	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html>
858		1305
…		…
938	=item $int = $mem->offset	1385	=item $int = $mem->offset
939		1386
940	Calls C<clGetMemObjectInfo> with C<CL_MEM_OFFSET> and returns the result.	1387	Calls C<clGetMemObjectInfo> with C<CL_MEM_OFFSET> and returns the result.
941		1388
942	=for gengetinfo end mem	1389	=for gengetinfo end mem
		1390
		1391	=item ($type, $name) = $mem->gl_object_info
		1392
		1393	Returns the OpenGL object type (e.g. OpenCL::GL_OBJECT_TEXTURE2D) and the
		1394	object "name" (e.g. the texture name) used to create this memory object.
		1395
		1396	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetGLObjectInfo.html>
943		1397
944	=back	1398	=back
945		1399
946	=head2 THE OpenCL::Buffer CLASS	1400	=head2 THE OpenCL::Buffer CLASS
947		1401
…		…
966		1420
967	=back	1421	=back
968		1422
969	=head2 THE OpenCL::Image CLASS	1423	=head2 THE OpenCL::Image CLASS
970		1424
971	This is the superclass of all image objects - OpenCL::Image2D and OpenCL::Image3D.	1425	This is the superclass of all image objects - OpenCL::Image1D,
		1426	OpenCL::Image1DArray, OpenCL::Image1DBuffer, OpenCL::Image2D,
		1427	OpenCL::Image2DArray and OpenCL::Image3D.
972		1428
973	=over 4	1429	=over 4
974		1430
975	=item $packed_value = $ev->image_info ($name)	1431	=item $packed_value = $image->image_info ($name)
976		1432
977	See C<< $platform->info >> for details.	1433	See C<< $platform->info >> for details.
978		1434
979	The reason this method is not called C<info> is that there already is an	1435	The reason this method is not called C<info> is that there already is an
980	C<< ->info >> method inherited from C<OpenCL::Memory>.	1436	C<< ->info >> method inherited from C<OpenCL::Memory>.
981		1437
982	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html>	1438	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html>
983		1439
		1440	=item ($channel_order, $channel_data_type) = $image->format
		1441
		1442	Returns the channel order and type used to create the image by calling
		1443	C<clGetImageInfo> with C<CL_IMAGE_FORMAT>.
		1444
984	=for gengetinfo begin image	1445	=for gengetinfo begin image
985		1446
986	=item $int = $image->element_size	1447	=item $int = $image->element_size
987		1448
988	Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result.	1449	Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result.
…		…
1007		1468
1008	Calls C<clGetImageInfo> with C<CL_IMAGE_DEPTH> and returns the result.	1469	Calls C<clGetImageInfo> with C<CL_IMAGE_DEPTH> and returns the result.
1009		1470
1010	=for gengetinfo end image	1471	=for gengetinfo end image
1011		1472
		1473	=for gengetinfo begin gl_texture
		1474
		1475	=item $GLenum = $gl_texture->target
		1476
		1477	Calls C<clGetGLTextureInfo> with C<CL_GL_TEXTURE_TARGET> and returns the result.
		1478
		1479	=item $GLint = $gl_texture->gl_mipmap_level
		1480
		1481	Calls C<clGetGLTextureInfo> with C<CL_GL_MIPMAP_LEVEL> and returns the result.
		1482
		1483	=for gengetinfo end gl_texture
		1484
1012	=back	1485	=back
1013		1486
1014	=head2 THE OpenCL::Sampler CLASS	1487	=head2 THE OpenCL::Sampler CLASS
1015		1488
1016	=over 4	1489	=over 4
…		…
1049		1522
1050	=head2 THE OpenCL::Program CLASS	1523	=head2 THE OpenCL::Program CLASS
1051		1524
1052	=over 4	1525	=over 4
1053		1526
1054	=item $program->build ($device, $options = "")	1527	=item $program->build (\@devices = undef, $options = "", $cb->($program) = undef)
1055		1528
1056	Tries to build the program with the givne options.	1529	Tries to build the program with the given options. See also the
		1530	C<$ctx->build> convenience function.
		1531
		1532	If a callback is specified, then it will be called when compilation is
		1533	finished. Note that many OpenCL implementations block your program while
		1534	compiling whether you use a callback or not. See C<build_async> if you
		1535	want to make sure the build is done in the background.
		1536
		1537	Note that some OpenCL implementations act up badly, and don't call the
		1538	callback in some error cases (but call it in others). This implementation
		1539	assumes the callback will always be called, and leaks memory if this is
		1540	not so. So best make sure you don't pass in invalid values.
		1541
		1542	Some implementations fail with C<OpenCL::INVALID_BINARY> when the
		1543	compilation state is successful but some later stage fails.
1057		1544
1058	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html>	1545	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html>
		1546
		1547	=item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef)
		1548
		1549	Similar to C<< ->build >>, except it starts a thread, and never fails (you
		1550	need to check the compilation status form the callback, or by polling).
1059		1551
1060	=item $packed_value = $program->build_info ($device, $name)	1552	=item $packed_value = $program->build_info ($device, $name)
1061		1553
1062	Similar to C<< $platform->info >>, but returns build info for a previous	1554	Similar to C<< $platform->info >>, but returns build info for a previous
1063	build attempt for the given device.	1555	build attempt for the given device.
…		…
1068		1560
1069	Creates an OpenCL::Kernel object out of the named C<__kernel> function in	1561	Creates an OpenCL::Kernel object out of the named C<__kernel> function in
1070	the program.	1562	the program.
1071		1563
1072	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html>	1564	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html>
		1565
		1566	=item @kernels = $program->kernels_in_program
		1567
		1568	Returns all kernels successfully compiled for all devices in program.
		1569
		1570	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernelsInProgram.html
1073		1571
1074	=for gengetinfo begin program_build	1572	=for gengetinfo begin program_build
1075		1573
1076	=item $build_status = $program->build_status ($device)	1574	=item $build_status = $program->build_status ($device)
1077		1575
…		…
1199		1697
1200	Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result.	1698	Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result.
1201		1699
1202	=for gengetinfo end kernel_work_group	1700	=for gengetinfo end kernel_work_group
1203		1701
		1702	=item $kernel->setf ($format, ...)
		1703
		1704	Sets the arguments of a kernel. Since OpenCL 1.1 doesn't have a generic
		1705	way to set arguments (and with OpenCL 1.2 it might be rather slow), you
		1706	need to specify a format argument, much as with C<printf>, to tell OpenCL
		1707	what type of argument it is.
		1708
		1709	The format arguments are single letters:
		1710
		1711	c char
		1712	C unsigned char
		1713	s short
		1714	S unsigned short
		1715	i int
		1716	I unsigned int
		1717	l long
		1718	L unsigned long
		1719
		1720	h half float (0..65535)
		1721	f float
		1722	d double
		1723
		1724	z local (octet size)
		1725
		1726	m memory object (buffer or image)
		1727	a sampler
		1728	e event
		1729
		1730	Space characters in the format string are ignored.
		1731
		1732	Example: set the arguments for a kernel that expects an int, two floats, a buffer and an image.
		1733
		1734	$kernel->setf ("i ff mm", 5, 0.5, 3, $buffer, $image);
		1735
1204	=item $kernel->set_TYPE ($index, $value)	1736	=item $kernel->set_TYPE ($index, $value)
1205		1737
		1738	=item $kernel->set_char ($index, $value)
		1739
		1740	=item $kernel->set_uchar ($index, $value)
		1741
		1742	=item $kernel->set_short ($index, $value)
		1743
		1744	=item $kernel->set_ushort ($index, $value)
		1745
		1746	=item $kernel->set_int ($index, $value)
		1747
		1748	=item $kernel->set_uint ($index, $value)
		1749
		1750	=item $kernel->set_long ($index, $value)
		1751
		1752	=item $kernel->set_ulong ($index, $value)
		1753
		1754	=item $kernel->set_half ($index, $value)
		1755
		1756	=item $kernel->set_float ($index, $value)
		1757
		1758	=item $kernel->set_double ($index, $value)
		1759
		1760	=item $kernel->set_memory ($index, $value)
		1761
		1762	=item $kernel->set_buffer ($index, $value)
		1763
		1764	=item $kernel->set_image ($index, $value)
		1765
		1766	=item $kernel->set_sampler ($index, $value)
		1767
		1768	=item $kernel->set_local ($index, $value)
		1769
		1770	=item $kernel->set_event ($index, $value)
		1771
1206	This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>.	1772	This is a family of methods to set the kernel argument with the number
1207		1773	C<$index> to the give C<$value>.
1208	TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>,
1209	C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>,
1210	C<image2d>, C<image3d>, C<sampler> or C<event>.
1211		1774
1212	Chars and integers (including the half type) are specified as integers,	1775	Chars and integers (including the half type) are specified as integers,
1213	float and double as floating point values, memory/buffer/image2d/image3d	1776	float and double as floating point values, memory/buffer/image must be
1214	must be an object of that type or C<undef>, and sampler and event must be	1777	an object of that type or C<undef>, local-memory arguments are set by
1215	objects of that type.	1778	specifying the size, and sampler and event must be objects of that type.
		1779
		1780	Note that C<set_memory> works for all memory objects (all types of buffers
		1781	and images) - the main purpose of the more specific C<set_TYPE> functions
		1782	is type checking.
		1783
		1784	Setting an argument for a kernel does NOT keep a reference to the object -
		1785	for example, if you set an argument to some image object, free the image,
		1786	and call the kernel, you will run into undefined behaviour.
1216		1787
1217	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html>	1788	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html>
1218		1789
1219	=back	1790	=back
1220		1791
…		…
1229		1800
1230	Waits for the event to complete.	1801	Waits for the event to complete.
1231		1802
1232	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>	1803	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>
1233		1804
		1805	=item $ev->cb ($exec_callback_type, $callback->($event, $event_command_exec_status))
		1806
		1807	Adds a callback to the callback stack for the given event type. There is
		1808	no way to remove a callback again.
		1809
		1810	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetEventCallback.html>
		1811
1234	=item $packed_value = $ev->info ($name)	1812	=item $packed_value = $ev->info ($name)
1235		1813
1236	See C<< $platform->info >> for details.	1814	See C<< $platform->info >> for details.
1237		1815
1238	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html>	1816	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html>
…		…
1298		1876
1299	=over 4	1877	=over 4
1300		1878
1301	=item $ev->set_status ($execution_status)	1879	=item $ev->set_status ($execution_status)
1302		1880
		1881	Sets the execution status of the user event. Can only be called once,
		1882	either with OpenCL::COMPLETE or a negative number as status.
		1883
1303	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html>	1884	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html>
1304		1885
1305	=back	1886	=back
1306		1887
1307	=cut	1888	=cut
1308
1309	package OpenCL;
1310
1311	use common::sense;
1312
1313	BEGIN {
1314	our $VERSION = '0.92';
1315
1316	require XSLoader;
1317	XSLoader::load (__PACKAGE__, $VERSION);
1318
1319	@OpenCL::Buffer::ISA =
1320	@OpenCL::Image::ISA = OpenCL::Memory::;
1321
1322	@OpenCL::BufferObj::ISA = OpenCL::Buffer::;
1323
1324	@OpenCL::Image2D::ISA =
1325	@OpenCL::Image3D::ISA = OpenCL::Image::;
1326
1327	@OpenCL::UserEvent::ISA = OpenCL::Event::;
1328	}
1329		1889
1330	1;	1890	1;
1331		1891
1332	=head1 AUTHOR	1892	=head1 AUTHOR
1333		1893

Diff Legend

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

Comparing OpenCL/OpenCL.pm (file contents): Revision 1.32 by root, Thu Apr 19 12:12:03 2012 UTC vs. Revision 1.64 by root, Mon Apr 30 23:12:43 2012 UTC

Diff Legend

Comparing OpenCL/OpenCL.pm (file contents):
Revision 1.32 by root, Thu Apr 19 12:12:03 2012 UTC vs.
Revision 1.64 by root, Mon Apr 30 23:12:43 2012 UTC