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

Comparing OpenCL/OpenCL.pm (file contents):
Revision 1.40 by root, Thu Apr 19 22:33:27 2012 UTC vs.
Revision 1.65 by root, Mon Apr 30 23:35:16 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;
215		213
216	=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
217	set tunnel effect.	215	set tunnel effect.
218		216
219	This is quite a long example to get you going.	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>.
220		219
221	use OpenGL ":all";	220	use OpenGL ":all";
222	use OpenCL;	221	use OpenCL;
223		222
		223	my $S = $ARGV[0] \|\| 256; # window/texture size, smaller is faster
		224
224	# open a window and create a gl texture	225	# open a window and create a gl texture
225	OpenGL::glpOpenWindow width => 256, height => 256;	226	OpenGL::glpOpenWindow width => $S, height => $S;
226	my $texid = glGenTextures_p 1;	227	my $texid = glGenTextures_p 1;
227	glBindTexture GL_TEXTURE_2D, $texid;	228	glBindTexture GL_TEXTURE_2D, $texid;
228	glTexImage2D_c GL_TEXTURE_2D, 0, GL_RGBA8, 256, 256, 0, GL_RGBA, GL_UNSIGNED_BYTE, 0;	229	glTexImage2D_c GL_TEXTURE_2D, 0, GL_RGBA8, $S, $S, 0, GL_RGBA, GL_UNSIGNED_BYTE, 0;
229		230
230	# find and use the first opencl device that let's us get a shared opengl context	231	# find and use the first opencl device that let's us get a shared opengl context
231	my $platform;	232	my $platform;
232	my $dev;	233	my $dev;
233	my $ctx;	234	my $ctx;
…		…
252	# now the boring opencl code	253	# now the boring opencl code
253	my $src = <<EOF;	254	my $src = <<EOF;
254	kernel void	255	kernel void
255	juliatunnel (write_only image2d_t img, float time)	256	juliatunnel (write_only image2d_t img, float time)
256	{	257	{
257	float2 p = (float2)(get_global_id (0), get_global_id (1)) / 256.f * 2.f - 1.f;	258	int2 xy = (int2)(get_global_id (0), get_global_id (1));
		259	float2 p = convert_float2 (xy) / $S.f * 2.f - 1.f;
258		260
259	float2 m = (float2)(1.f, p.y) / fabs (p.x);	261	float2 m = (float2)(1.f, p.y) / fabs (p.x); // tunnel
260	m.x = fabs (fmod (m.x + time * 0.05f, 4.f)) - 2.f;	262	m.x = fabs (fmod (m.x + time * 0.05f, 4.f) - 2.f);
261		263
262	float2 z = m;	264	float2 z = m;
263	float2 c = (float2)(sin (time * 0.05005), cos (time * 0.06001));	265	float2 c = (float2)(sin (time * 0.01133f), cos (time * 0.02521f));
264		266
265	for (int i = 0; i < 25 && dot (z, z) < 4.f; ++i)	267	for (int i = 0; i < 25 && dot (z, z) < 4.f; ++i) // standard julia
266	z = (float2)(z.x * z.x - z.y * z.y, 2.f * z.x * z.y) + c;	268	z = (float2)(z.x * z.x - z.y * z.y, 2.f * z.x * z.y) + c;
267		269
268	float3 colour = (float3)(z.x, z.y, z.x * z.y);	270	float3 colour = (float3)(z.x, z.y, atan2 (z.y, z.x));
269	write_imagef (img, (int2)(get_global_id (0), get_global_id (1)), (float4)(colour * p.x * p.x, 1.));	271	write_imagef (img, xy, (float4)(colour * p.x * p.x, 1.));
270	}	272	}
271	EOF	273	EOF
		274
272	my $prog = $ctx->program_with_source ($src);	275	my $prog = $ctx->build_program ($src);
273	eval { $prog->build ($dev); 1 }
274	or die $prog->build_log ($dev);
275
276	my $kernel = $prog->kernel ("juliatunnel");	276	my $kernel = $prog->kernel ("juliatunnel");
277		277
278	# program compiled, kernel ready, now draw and loop	278	# program compiled, kernel ready, now draw and loop
279		279
280	for (my $time; ; ++$time) {	280	for (my $time; ; ++$time) {
281	# acquire objects from opengl	281	# acquire objects from opengl
282	$queue->enqueue_acquire_gl_objects ([$tex]);	282	$queue->acquire_gl_objects ([$tex]);
283		283
284	# configure and run our kernel	284	# configure and run our kernel
285	$kernel->set_image2d (0, $tex);	285	$kernel->setf ("mf", $tex, $time*2); # mf = memory object, float
286	$kernel->set_float (1, $time);
287	$queue->enqueue_nd_range_kernel ($kernel, undef, [256, 256], undef);	286	$queue->nd_range_kernel ($kernel, undef, [$S, $S], undef);
288		287
289	# release objects to opengl again	288	# release objects to opengl again
290	$queue->enqueue_release_gl_objects ([$tex]);	289	$queue->release_gl_objects ([$tex]);
291		290
292	# wait	291	# wait
293	$queue->finish;	292	$queue->finish;
294		293
295	# now draw the texture, the defaults should be all right	294	# now draw the texture, the defaults should be all right
…		…
306	glXSwapBuffers;	305	glXSwapBuffers;
307		306
308	select undef, undef, undef, 1/60;	307	select undef, undef, undef, 1/60;
309	}	308	}
310		309
		310	=item How to modify the previous example to not rely on GL sharing.
		311
		312	For those poor souls with only a sucky CPU OpenCL implementation, you
		313	currently have to read the image into some perl scalar, and then modify a
		314	texture or use glDrawPixels or so).
		315
		316	First, when you don't need gl sharing, you can create the context much simpler:
		317
		318	$ctx = $platform->context (undef, [$dev])
		319
		320	To use a texture, you would modify the above example by creating an
		321	OpenCL::Image manually instead of deriving it from a texture:
		322
		323	my $tex = $ctx->image2d (OpenCL::MEM_WRITE_ONLY, OpenCL::RGBA, OpenCL::UNORM_INT8, $S, $S);
		324
		325	And in the darw loop, intead of acquire_gl_objects/release_gl_objects, you
		326	would read the image2d after the kernel has written it:
		327
		328	$queue->read_image ($tex, 0, 0, 0, 0, $S, $S, 1, 0, 0, my $data);
		329
		330	And then you would upload the pixel data to the texture (or use glDrawPixels):
		331
		332	glTexSubImage2D_s GL_TEXTURE_2D, 0, 0, 0, $S, $S, GL_RGBA, GL_UNSIGNED_BYTE, $data;
		333
		334	The fully modified example can be found at
		335	L<http://cvs.schmorp.de/OpenCL/examples/juliaflight-nosharing>.
		336
311	=head1 DOCUMENTATION	337	=head1 DOCUMENTATION
312		338
313	=head2 BASIC CONVENTIONS	339	=head2 BASIC CONVENTIONS
314		340
315	This is not a one-to-one C-style translation of OpenCL to Perl - instead	341	This is not a one-to-one C-style translation of OpenCL to Perl - instead
…		…
336	=item * Structures are often specified by flattening out their components	362	=item * Structures are often specified by flattening out their components
337	as with short vectors, and returned as arrayrefs.	363	as with short vectors, and returned as arrayrefs.
338		364
339	=item * When enqueuing commands, the wait list is specified by adding	365	=item * When enqueuing commands, the wait list is specified by adding
340	extra arguments to the function - anywhere a C<$wait_events...> argument	366	extra arguments to the function - anywhere a C<$wait_events...> argument
341	is documented this can be any number of event objects.	367	is documented this can be any number of event objects. As an extsnion
		368	implemented by this module, C<undef> values will be ignored in the event
		369	list.
342		370
343	=item * When enqueuing commands, if the enqueue method is called in void	371	=item * When enqueuing commands, if the enqueue method is called in void
344	context, no event is created. In all other contexts an event is returned	372	context, no event is created. In all other contexts an event is returned
345	by the method.	373	by the method.
346		374
…		…
381		409
382	For this to work, the OpenGL library must be loaded, a GLX context must	410	For this to work, the OpenGL library must be loaded, a GLX context must
383	have been created and be made current, and C<dlsym> must be available and	411	have been created and be made current, and C<dlsym> must be available and
384	capable of finding the function via C<RTLD_DEFAULT>.	412	capable of finding the function via C<RTLD_DEFAULT>.
385		413
		414	=head2 EVENT SYSTEM
		415
		416	OpenCL can generate a number of (potentially) asynchronous events, for
		417	example, after compiling a program, to signal a context-related error or,
		418	perhaps most important, to signal completion of queued jobs (by setting
		419	callbacks on OpenCL::Event objects).
		420
		421	To facilitate this, this module maintains an event queue - each
		422	time an asynchronous event happens, it is queued, and perl will be
		423	interrupted. This is implemented via the L<Async::Interrupt> module. In
		424	addition, this module has L<AnyEvent> support, so it can seamlessly
		425	integrate itself into many event loops.
		426
		427	Since this module is a bit hard to understand, here are some case examples:
		428
		429	=head3 Don't use callbacks.
		430
		431	When your program never uses any callbacks, then there will never be any
		432	notifications you need to take care of, and therefore no need to worry
		433	about all this.
		434
		435	You can achieve a great deal by explicitly waiting for events, or using
		436	barriers and flush calls. In many programs, there is no need at all to
		437	tinker with asynchronous events.
		438
		439	=head3 Use AnyEvent
		440
		441	This module automatically registers a watcher that invokes all outstanding
		442	event callbacks when AnyEvent is initialised (and block asynchronous
		443	interruptions). Using this mode of operations is the safest and most
		444	recommended one.
		445
		446	To use this, simply use AnyEvent and this module normally, make sure you
		447	have an event loop running:
		448
		449	use Gtk2 -init;
		450	use AnyEvent;
		451
		452	# initialise AnyEvent, by creating a watcher, or:
		453	AnyEvent::detect;
		454
		455	my $e = $queue->marker;
		456	$e->cb (sub {
		457	warn "opencl is finished\n";
		458	})
		459
		460	main Gtk2;
		461
		462	Note that this module will not initialise AnyEvent for you. Before
		463	AnyEvent is initialised, the module will asynchronously interrupt perl
		464	instead. To avoid any surprises, it's best to explicitly initialise
		465	AnyEvent.
		466
		467	You can temporarily enable asynchronous interruptions (see next paragraph)
		468	by calling C<$OpenCL::INTERRUPT->unblock> and disable them again by
		469	calling C<$OpenCL::INTERRUPT->block>.
		470
		471	=head3 Let yourself be interrupted at any time
		472
		473	This mode is the default unless AnyEvent is loaded and initialised. In
		474	this mode, OpenCL asynchronously interrupts a running perl program. The
		475	emphasis is on both I<asynchronously> and I<running> here.
		476
		477	Asynchronously means that perl might execute your callbacks at any
		478	time. For example, in the following code (I<THAT YOU SHOULD NOT COPY>),
		479	the C<until> loop following the marker call will be interrupted by the
		480	callback:
		481
		482	my $e = $queue->marker;
		483	my $flag;
		484	$e->cb (sub { $flag = 1 });
		485	1 until $flag;
		486	# $flag is now 1
		487
		488	The reason why you shouldn't blindly copy the above code is that
		489	busy waiting is a really really bad thing, and really really bad for
		490	performance.
		491
		492	While at first this asynchronous business might look exciting, it can be
		493	really hard, because you need to be prepared for the callback code to be
		494	executed at any time, which limits the amount of things the callback code
		495	can do safely.
		496
		497	This can be mitigated somewhat by using C<<
		498	$OpenCL::INTERRUPT->scope_block >> (see the L<Async::Interrupt>
		499	documentation for details).
		500
		501	The other problem is that your program must be actively I<running> to be
		502	interrupted. When you calculate stuff, your program is running. When you
		503	hang in some C functions or other block execution (by calling C<sleep>,
		504	C<select>, running an event loop and so on), your program is waiting, not
		505	running.
		506
		507	One way around that would be to attach a read watcher to your event loop,
		508	listening for events on C<< $OpenCL::INTERRUPT->pipe_fileno >>, using a
		509	dummy callback (C<sub { }>) to temporarily execute some perl code.
		510
		511	That is then awfully close to using the built-in AnyEvent support above,
		512	though, so consider that one instead.
		513
		514	=head3 Be creative
		515
		516	OpenCL exports the L<Async::Interrupt> object it uses in the global
		517	variable C<$OpenCL::INTERRUPT>. You can configure it in any way you like.
		518
		519	So if you want to feel like a real pro, err, wait, if you feel no risk
		520	menas no fun, you can experiment by implementing your own mode of
		521	operations.
		522
		523	=cut
		524
		525	package OpenCL;
		526
		527	use common::sense;
		528	use Carp ();
		529	use Async::Interrupt ();
		530
		531	our $POLL_FUNC; # set by XS
		532
		533	BEGIN {
		534	our $VERSION = '0.98';
		535
		536	require XSLoader;
		537	XSLoader::load (__PACKAGE__, $VERSION);
		538
		539	@OpenCL::Platform::ISA =
		540	@OpenCL::Device::ISA =
		541	@OpenCL::Context::ISA =
		542	@OpenCL::Queue::ISA =
		543	@OpenCL::Memory::ISA =
		544	@OpenCL::Sampler::ISA =
		545	@OpenCL::Program::ISA =
		546	@OpenCL::Kernel::ISA =
		547	@OpenCL::Event::ISA = OpenCL::Object::;
		548
		549	@OpenCL::Buffer::ISA =
		550	@OpenCL::Image::ISA = OpenCL::Memory::;
		551
		552	@OpenCL::BufferObj::ISA = OpenCL::Buffer::;
		553
		554	@OpenCL::Image2D::ISA =
		555	@OpenCL::Image3D::ISA =
		556	@OpenCL::Image2DArray::ISA =
		557	@OpenCL::Image1D::ISA =
		558	@OpenCL::Image1DArray::ISA =
		559	@OpenCL::Image1DBuffer::ISA = OpenCL::Image::;
		560
		561	@OpenCL::UserEvent::ISA = OpenCL::Event::;
		562	}
		563
386	=head2 THE OpenCL PACKAGE	564	=head2 THE OpenCL PACKAGE
387		565
388	=over 4	566	=over 4
389		567
390	=item $int = OpenCL::errno	568	=item $int = OpenCL::errno
391		569
392	The last error returned by a function - it's only valid after an error occured	570	The last error returned by a function - it's only valid after an error occured
393	and before calling another OpenCL function.	571	and before calling another OpenCL function.
394		572
395	=item $str = OpenCL::err2str $errval	573	=item $str = OpenCL::err2str [$errval]
396		574
397	Comverts an error value into a human readable string.	575	Converts an error value into a human readable string. IF no error value is
		576	given, then the last error will be used (as returned by OpenCL::errno).
398		577
399	=item $str = OpenCL::enum2str $enum	578	=item $str = OpenCL::enum2str $enum
400		579
401	Converts most enum values (of parameter names, image format constants,	580	Converts most enum values (of parameter names, image format constants,
402	object types, addressing and filter modes, command types etc.) into a	581	object types, addressing and filter modes, command types etc.) into a
…		…
408		587
409	Returns all available OpenCL::Platform objects.	588	Returns all available OpenCL::Platform objects.
410		589
411	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html>	590	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html>
412		591
413	=item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef	592	=item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr
414		593
415	Tries to create a context from a default device and platform - never worked for me.	594	Tries to create a context from a default device and platform type - never worked for me.
416		595
417	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>	596	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>
418		597
		598	=item $ctx = OpenCL::context $properties, \@devices, $callback->($err, $pvt) = $print_stderr)
		599
		600	Create a new OpenCL::Context object using the given device object(s). This
		601	function isn't implemented yet, use C<< $platform->context >> instead.
		602
		603	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>
		604
419	=item OpenCL::wait_for_events $wait_events...	605	=item OpenCL::wait_for_events $wait_events...
420		606
421	Waits for all events to complete.	607	Waits for all events to complete.
422		608
423	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>	609	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>
424		610
		611	=item OpenCL::poll
		612
		613	Checks if there are any outstanding events (see L<EVENT SYSTEM>) and
		614	invokes their callbacks.
		615
		616	=item $OpenCL::INTERRUPT
		617
		618	The L<Async::Interrupt> object used to signal asynchronous events (see
		619	L<EVENT SYSTEM>).
		620
		621	=cut
		622
		623	our $INTERRUPT = new Async::Interrupt c_cb => [$POLL_FUNC, 0];
		624
		625	&_eq_initialise ($INTERRUPT->signal_func);
		626
		627	=item $OpenCL::WATCHER
		628
		629	The L<AnyEvent> watcher object used to watch for asynchronous events (see
		630	L<EVENT SYSTEM>). This variable is C<undef> until L<AnyEvent> has been
		631	loaded I<and> initialised (e.g. by calling C<AnyEvent::detect>).
		632
		633	=cut
		634
		635	our $WATCHER;
		636
		637	sub _init_anyevent {
		638	$INTERRUPT->block;
		639	$WATCHER = AE::io ($INTERRUPT->pipe_fileno, 0, sub { $INTERRUPT->handle });
		640	}
		641
		642	if (defined $AnyEvent::MODEL) {
		643	_init_anyevent;
		644	} else {
		645	push @AnyEvent::post_detect, \&_init_anyevent;
		646	}
		647
425	=back	648	=back
426		649
		650	=head2 THE OpenCL::Object CLASS
		651
		652	This is the base class for all objects in the OpenCL module. The only
		653	method it implements is the C<id> method, which is only useful if you want
		654	to interface to OpenCL on the C level.
		655
		656	=over 4
		657
		658	=item $iv = $obj->id
		659
		660	OpenCL objects are represented by pointers or integers on the C level. If
		661	you want to interface to an OpenCL object directly on the C level, then
		662	you need this value, which is returned by this method. You should use an
		663	C<IV> type in your code and cast that to the correct type.
		664
		665	=cut
		666
		667	sub OpenCL::Object::id {
		668	ref $_[0] eq "SCALAR"
		669	? ${ $_[0] }
		670	: $_[0][0]
		671	}
		672
		673	=back
		674
427	=head2 THE OpenCL::Platform CLASS	675	=head2 THE OpenCL::Platform CLASS
428		676
429	=over 4	677	=over 4
430		678
431	=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL)	679	=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL)
432		680
433	Returns a list of matching OpenCL::Device objects.	681	Returns a list of matching OpenCL::Device objects.
434		682
435	=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef)	683	=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr)
436		684
437	Tries to create a context. Never worked for me, and you need devices explicitly anyway.	685	Tries to create a context. Never worked for me, and you need devices explicitly anyway.
438		686
439	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>	687	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>
440		688
441	=item $ctx = $platform->context ($properties = undef, @$devices, $notify = undef)	689	=item $ctx = $platform->context ($properties, \@devices, $callback->($err, $pvt) = $print_stderr)
442		690
443	Create a new OpenCL::Context object using the given device object(s)- a	691	Create a new OpenCL::Context object using the given device object(s)- a
444	CL_CONTEXT_PLATFORM property is supplied automatically.	692	CL_CONTEXT_PLATFORM property is supplied automatically.
445		693
446	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>	694	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>
…		…
454	It's best to avoid this method and use one of the following convenience	702	It's best to avoid this method and use one of the following convenience
455	wrappers.	703	wrappers.
456		704
457	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html>	705	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html>
458		706
		707	=item $platform->unload_compiler
		708
		709	Attempts to unload the compiler for this platform, for endless
		710	profit. Does nothing on OpenCL 1.1.
		711
		712	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clUnloadPlatformCompiler.html>
		713
459	=for gengetinfo begin platform	714	=for gengetinfo begin platform
460		715
461	=item $string = $platform->profile	716	=item $string = $platform->profile
462		717
463	Calls C<clGetPlatformInfo> with C<CL_PLATFORM_PROFILE> and returns the result.	718	Calls C<clGetPlatformInfo> with C<CL_PLATFORM_PROFILE> and returns the result.
…		…
748		1003
749	=item @device_partition_property_exts = $device->affinity_domains_ext	1004	=item @device_partition_property_exts = $device->affinity_domains_ext
750		1005
751	Calls C<clGetDeviceInfo> with C<CL_DEVICE_AFFINITY_DOMAINS_EXT> and returns the result.	1006	Calls C<clGetDeviceInfo> with C<CL_DEVICE_AFFINITY_DOMAINS_EXT> and returns the result.
752		1007
753	=item $uint = $device->reference_count_ext	1008	=item $uint = $device->reference_count_ext
754		1009
755	Calls C<clGetDeviceInfo> with C<CL_DEVICE_REFERENCE_COUNT_EXT > and returns the result.	1010	Calls C<clGetDeviceInfo> with C<CL_DEVICE_REFERENCE_COUNT_EXT> and returns the result.
756		1011
757	=item @device_partition_property_exts = $device->partition_style_ext	1012	=item @device_partition_property_exts = $device->partition_style_ext
758		1013
759	Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_STYLE_EXT> and returns the result.	1014	Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_STYLE_EXT> and returns the result.
760		1015
…		…
764		1019
765	=head2 THE OpenCL::Context CLASS	1020	=head2 THE OpenCL::Context CLASS
766		1021
767	=over 4	1022	=over 4
768		1023
		1024	=item $prog = $ctx->build_program ($program, $options = "")
		1025
		1026	This convenience function tries to build the program on all devices in
		1027	the context. If the build fails, then the function will C<croak> with the
		1028	build log. Otherwise ti returns the program object.
		1029
		1030	The C<$program> can either be a C<OpenCL::Program> object or a string
		1031	containing the program. In the latter case, a program objetc will be
		1032	created automatically.
		1033
		1034	=cut
		1035
		1036	sub OpenCL::Context::build_program {
		1037	my ($self, $prog, $options) = @_;
		1038
		1039	$prog = $self->program_with_source ($prog)
		1040	unless ref $prog;
		1041
		1042	eval { $prog->build (undef, $options); 1 }
		1043	or errno == BUILD_PROGRAM_FAILURE
		1044	or errno == INVALID_BINARY # workaround nvidia bug
		1045	or Carp::croak "OpenCL::Context->build_program: " . err2str;
		1046
		1047	# we check status for all devices
		1048	for my $dev ($self->devices) {
		1049	$prog->build_status ($dev) == BUILD_SUCCESS
		1050	or Carp::croak "Building OpenCL program for device '" . $dev->name . "' failed:\n"
		1051	. $prog->build_log ($dev);
		1052	}
		1053
		1054	$prog
		1055	}
		1056
769	=item $queue = $ctx->queue ($device, $properties)	1057	=item $queue = $ctx->queue ($device, $properties)
770		1058
771	Create a new OpenCL::Queue object from the context and the given device.	1059	Create a new OpenCL::Queue object from the context and the given device.
772		1060
773	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html>	1061	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html>
		1062
		1063	Example: create an out-of-order queue.
		1064
		1065	$queue = $ctx->queue ($device, OpenCL::QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE);
774		1066
775	=item $ev = $ctx->user_event	1067	=item $ev = $ctx->user_event
776		1068
777	Creates a new OpenCL::UserEvent object.	1069	Creates a new OpenCL::UserEvent object.
778		1070
…		…
788	=item $buf = $ctx->buffer_sv ($flags, $data)	1080	=item $buf = $ctx->buffer_sv ($flags, $data)
789		1081
790	Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and	1082	Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and
791	initialise it with the given data values.	1083	initialise it with the given data values.
792		1084
		1085	=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)
		1086
		1087	Creates a new OpenCL::Image object and optionally initialises it with
		1088	the given data values.
		1089
		1090	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html>
		1091
793	=item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $row_pitch = 0, $data = undef)	1092	=item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $row_pitch = 0, $data = undef)
794		1093
795	Creates a new OpenCL::Image2D object and optionally initialises it with	1094	Creates a new OpenCL::Image2D object and optionally initialises it with
796	the given data values.	1095	the given data values.
797		1096
…		…
809	Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object that refers to the given	1108	Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object that refers to the given
810	OpenGL buffer object.	1109	OpenGL buffer object.
811		1110
812	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLBuffer.html	1111	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLBuffer.html
813		1112
		1113	=item $img = $ctx->gl_texture ($flags, $target, $miplevel, $texture)
		1114
		1115	Creates a new OpenCL::Image object that refers to the given OpenGL
		1116	texture object or buffer.
		1117
		1118	http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateFromGLTexture.html
		1119
814	=item $ctx->gl_texture2d ($flags, $target, $miplevel, $texture)	1120	=item $img = $ctx->gl_texture2d ($flags, $target, $miplevel, $texture)
815		1121
816	Creates a new OpenCL::Image2D object that refers to the given OpenGL	1122	Creates a new OpenCL::Image2D object that refers to the given OpenGL
817	2D texture object.	1123	2D texture object.
818		1124
819	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture2D.html	1125	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture2D.html
820		1126
821	=item $ctx->gl_texture3d ($flags, $target, $miplevel, $texture)	1127	=item $img = $ctx->gl_texture3d ($flags, $target, $miplevel, $texture)
822		1128
823	Creates a new OpenCL::Image3D object that refers to the given OpenGL	1129	Creates a new OpenCL::Image3D object that refers to the given OpenGL
824	3D texture object.	1130	3D texture object.
825		1131
826	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture3D.html	1132	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture3D.html
…		…
880	=back	1186	=back
881		1187
882	=head2 THE OpenCL::Queue CLASS	1188	=head2 THE OpenCL::Queue CLASS
883		1189
884	An OpenCL::Queue represents an execution queue for OpenCL. You execute	1190	An OpenCL::Queue represents an execution queue for OpenCL. You execute
885	requests by calling their respective C<enqueue_xxx> method and waitinf for	1191	requests by calling their respective method and waiting for it to complete
886	it to complete in some way.	1192	in some way.
887		1193
888	All the enqueue methods return an event object that can be used to wait	1194	Most methods that enqueue some request return an event object that can
889	for completion, unless the method is called in void context, in which case	1195	be used to wait for completion (optionally using a callback), unless
890	no event object is created.	1196	the method is called in void context, in which case no event object is
		1197	created.
891		1198
892	They also allow you to specify any number of other event objects that this	1199	They also allow you to specify any number of other event objects that this
893	request has to wait for before it starts executing, by simply passing the	1200	request has to wait for before it starts executing, by simply passing the
894	event objects as extra parameters to the enqueue methods.	1201	event objects as extra parameters to the enqueue methods. To simplify
		1202	program design, this module ignores any C<undef> values in the list of
		1203	events. This makes it possible to code operations such as this, without
		1204	having to put a valid event object into C<$event> first:
		1205
		1206	$event = $queue->xxx (..., $event);
895		1207
896	Queues execute in-order by default, without any parallelism, so in most	1208	Queues execute in-order by default, without any parallelism, so in most
897	cases (i.e. you use only one queue) it's not necessary to wait for or	1209	cases (i.e. you use only one queue) it's not necessary to wait for or
898	create event objects.	1210	create event objects, althoguh an our of order queue is often a bit
		1211	faster.
899		1212
900	=over 4	1213	=over 4
901		1214
902	=item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...)	1215	=item $ev = $queue->read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...)
903		1216
904	Reads data from buffer into the given string.	1217	Reads data from buffer into the given string.
905		1218
906	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html>	1219	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html>
907		1220
908	=item $ev = $queue->enqueue_write_buffer ($buffer, $blocking, $offset, $data, $wait_events...)	1221	=item $ev = $queue->write_buffer ($buffer, $blocking, $offset, $data, $wait_events...)
909		1222
910	Writes data to buffer from the given string.	1223	Writes data to buffer from the given string.
911		1224
912	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html>	1225	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html>
913		1226
914	=item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...)	1227	=item $ev = $queue->copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...)
915		1228
916	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html>	1229	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html>
917		1230
918	=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...)	1231	=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...)
919		1232
920	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html	1233	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html
921		1234
922	=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...)	1235	=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...)
923		1236
924	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html	1237	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html
925		1238
926	=item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
927
928	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html>
929
930	=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...)	1239	=item $ev = $queue->copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...)
		1240
		1241	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>
		1242
		1243	=item $ev = $queue->read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
		1244
		1245	C<$row_pitch> (and C<$slice_pitch>) can be C<0>, in which case the OpenCL
		1246	module uses the image width (and height) to supply default values.
931		1247
932	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html>	1248	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html>
933		1249
934	=item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)	1250	=item $ev = $queue->write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
935		1251
		1252	C<$row_pitch> (and C<$slice_pitch>) can be C<0>, in which case the OpenCL
		1253	module uses the image width (and height) to supply default values.
936	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html>	1254	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html>
937		1255
938	=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...)	1256	=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...)
939		1257
940	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html>	1258	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html>
941		1259
942	=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...)	1260	=item $ev = $queue->copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...)
943		1261
944	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html>	1262	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html>
945		1263
946	=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...)	1264	=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...)
947		1265
948	Yeah.	1266	Yeah.
949		1267
950	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>.	1268	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>.
951		1269
		1270	=item $ev = $queue->fill_buffer ($mem, $pattern, $offset, $size, ...)
		1271
		1272	Fills the given buffer object with repeated applications of C<$pattern>,
		1273	starting at C<$offset> for C<$size> octets.
		1274
		1275	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html>
		1276
		1277	=item $ev = $queue->fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...)
		1278
		1279	Fills the given image area with the given rgba colour components. The
		1280	components are normally floating point values between C<0> and C<1>,
		1281	except when the image channel data type is a signe dor unsigned
		1282	unnormalised format, in which case the range is determined by the format.
		1283
		1284	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html>
		1285
952	=item $ev = $queue->enqueue_task ($kernel, $wait_events...)	1286	=item $ev = $queue->task ($kernel, $wait_events...)
953		1287
954	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html>	1288	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html>
955		1289
956	=item $ev = $queue->enqueue_nd_range_kernel ($kernel, @$global_work_offset, @$global_work_size, @$local_work_size, $wait_events...)	1290	=item $ev = $queue->nd_range_kernel ($kernel, \@global_work_offset, \@global_work_size, \@local_work_size, $wait_events...)
957		1291
958	Enqueues a kernel execution.	1292	Enqueues a kernel execution.
959		1293
960	@$global_work_size must be specified as a reference to an array of	1294	\@global_work_size must be specified as a reference to an array of
961	integers specifying the work sizes (element counts).	1295	integers specifying the work sizes (element counts).
962		1296
963	@$global_work_offset must be either C<undef> (in which case all offsets	1297	\@global_work_offset must be either C<undef> (in which case all offsets
964	are C<0>), or a reference to an array of work offsets, with the same number	1298	are C<0>), or a reference to an array of work offsets, with the same number
965	of elements as @$global_work_size.	1299	of elements as \@global_work_size.
966		1300
967	@$local_work_size must be either C<undef> (in which case the	1301	\@local_work_size must be either C<undef> (in which case the
968	implementation is supposed to choose good local work sizes), or a	1302	implementation is supposed to choose good local work sizes), or a
969	reference to an array of local work sizes, with the same number of	1303	reference to an array of local work sizes, with the same number of
970	elements as @$global_work_size.	1304	elements as \@global_work_size.
971		1305
972	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html>	1306	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html>
973		1307
974	=item $ev = $queue->enqueue_marker ($wait_events...)
975
976	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueMarker.html>
977
978	=item $ev = $queue->enqueue_acquire_gl_objects ([object, ...], $wait_events...)	1308	=item $ev = $queue->acquire_gl_objects ([object, ...], $wait_events...)
979		1309
980	Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired	1310	Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired
981	for subsequent OpenCL usage.	1311	for subsequent OpenCL usage.
982		1312
983	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html>	1313	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html>
984		1314
985	=item $ev = $queue->enqueue_release_gl_objects ([object, ...], $wait_events...)	1315	=item $ev = $queue->release_gl_objects ([object, ...], $wait_events...)
986		1316
987	Enqueues a list (an array-ref of OpenCL::Memory objects) to be released	1317	Enqueues a list (an array-ref of OpenCL::Memory objects) to be released
988	for subsequent OpenGL usage.	1318	for subsequent OpenGL usage.
989		1319
990	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html>	1320	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html>
991		1321
992	=item $ev = $queue->enqueue_wait_for_events ($wait_events...)	1322	=item $ev = $queue->wait_for_events ($wait_events...)
993		1323
994	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html>	1324	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html>
995		1325
996	=item $queue->enqueue_barrier	1326	=item $ev = $queue->marker ($wait_events...)
997		1327
		1328	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html>
		1329
		1330	=item $ev = $queue->barrier ($wait_events...)
		1331
998	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueBarrier.html>	1332	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html>
999		1333
1000	=item $queue->flush	1334	=item $queue->flush
1001		1335
1002	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html>	1336	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html>
1003		1337
…		…
1118		1452
1119	=back	1453	=back
1120		1454
1121	=head2 THE OpenCL::Image CLASS	1455	=head2 THE OpenCL::Image CLASS
1122		1456
1123	This is the superclass of all image objects - OpenCL::Image2D and OpenCL::Image3D.	1457	This is the superclass of all image objects - OpenCL::Image1D,
		1458	OpenCL::Image1DArray, OpenCL::Image1DBuffer, OpenCL::Image2D,
		1459	OpenCL::Image2DArray and OpenCL::Image3D.
1124		1460
1125	=over 4	1461	=over 4
1126		1462
1127	=item $packed_value = $ev->image_info ($name)	1463	=item $packed_value = $image->image_info ($name)
1128		1464
1129	See C<< $platform->info >> for details.	1465	See C<< $platform->info >> for details.
1130		1466
1131	The reason this method is not called C<info> is that there already is an	1467	The reason this method is not called C<info> is that there already is an
1132	C<< ->info >> method inherited from C<OpenCL::Memory>.	1468	C<< ->info >> method inherited from C<OpenCL::Memory>.
1133		1469
1134	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html>	1470	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html>
1135		1471
		1472	=item ($channel_order, $channel_data_type) = $image->format
		1473
		1474	Returns the channel order and type used to create the image by calling
		1475	C<clGetImageInfo> with C<CL_IMAGE_FORMAT>.
		1476
1136	=for gengetinfo begin image	1477	=for gengetinfo begin image
1137		1478
1138	=item $int = $image->element_size	1479	=item $int = $image->element_size
1139		1480
1140	Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result.	1481	Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result.
…		…
1213		1554
1214	=head2 THE OpenCL::Program CLASS	1555	=head2 THE OpenCL::Program CLASS
1215		1556
1216	=over 4	1557	=over 4
1217		1558
1218	=item $program->build ($device, $options = "")	1559	=item $program->build (\@devices = undef, $options = "", $cb->($program) = undef)
1219		1560
1220	Tries to build the program with the givne options.	1561	Tries to build the program with the given options. See also the
		1562	C<$ctx->build> convenience function.
		1563
		1564	If a callback is specified, then it will be called when compilation is
		1565	finished. Note that many OpenCL implementations block your program while
		1566	compiling whether you use a callback or not. See C<build_async> if you
		1567	want to make sure the build is done in the background.
		1568
		1569	Note that some OpenCL implementations act up badly, and don't call the
		1570	callback in some error cases (but call it in others). This implementation
		1571	assumes the callback will always be called, and leaks memory if this is
		1572	not so. So best make sure you don't pass in invalid values.
		1573
		1574	Some implementations fail with C<OpenCL::INVALID_BINARY> when the
		1575	compilation state is successful but some later stage fails.
1221		1576
1222	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html>	1577	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html>
		1578
		1579	=item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef)
		1580
		1581	Similar to C<< ->build >>, except it starts a thread, and never fails (you
		1582	need to check the compilation status form the callback, or by polling).
1223		1583
1224	=item $packed_value = $program->build_info ($device, $name)	1584	=item $packed_value = $program->build_info ($device, $name)
1225		1585
1226	Similar to C<< $platform->info >>, but returns build info for a previous	1586	Similar to C<< $platform->info >>, but returns build info for a previous
1227	build attempt for the given device.	1587	build attempt for the given device.
…		…
1232		1592
1233	Creates an OpenCL::Kernel object out of the named C<__kernel> function in	1593	Creates an OpenCL::Kernel object out of the named C<__kernel> function in
1234	the program.	1594	the program.
1235		1595
1236	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html>	1596	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html>
		1597
		1598	=item @kernels = $program->kernels_in_program
		1599
		1600	Returns all kernels successfully compiled for all devices in program.
		1601
		1602	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernelsInProgram.html
1237		1603
1238	=for gengetinfo begin program_build	1604	=for gengetinfo begin program_build
1239		1605
1240	=item $build_status = $program->build_status ($device)	1606	=item $build_status = $program->build_status ($device)
1241		1607
…		…
1363		1729
1364	Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result.	1730	Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result.
1365		1731
1366	=for gengetinfo end kernel_work_group	1732	=for gengetinfo end kernel_work_group
1367		1733
		1734	=item $kernel->setf ($format, ...)
		1735
		1736	Sets the arguments of a kernel. Since OpenCL 1.1 doesn't have a generic
		1737	way to set arguments (and with OpenCL 1.2 it might be rather slow), you
		1738	need to specify a format argument, much as with C<printf>, to tell OpenCL
		1739	what type of argument it is.
		1740
		1741	The format arguments are single letters:
		1742
		1743	c char
		1744	C unsigned char
		1745	s short
		1746	S unsigned short
		1747	i int
		1748	I unsigned int
		1749	l long
		1750	L unsigned long
		1751
		1752	h half float (0..65535)
		1753	f float
		1754	d double
		1755
		1756	z local (octet size)
		1757
		1758	m memory object (buffer or image)
		1759	a sampler
		1760	e event
		1761
		1762	Space characters in the format string are ignored.
		1763
		1764	Example: set the arguments for a kernel that expects an int, two floats, a buffer and an image.
		1765
		1766	$kernel->setf ("i ff mm", 5, 0.5, 3, $buffer, $image);
		1767
1368	=item $kernel->set_TYPE ($index, $value)	1768	=item $kernel->set_TYPE ($index, $value)
1369		1769
		1770	=item $kernel->set_char ($index, $value)
		1771
		1772	=item $kernel->set_uchar ($index, $value)
		1773
		1774	=item $kernel->set_short ($index, $value)
		1775
		1776	=item $kernel->set_ushort ($index, $value)
		1777
		1778	=item $kernel->set_int ($index, $value)
		1779
		1780	=item $kernel->set_uint ($index, $value)
		1781
		1782	=item $kernel->set_long ($index, $value)
		1783
		1784	=item $kernel->set_ulong ($index, $value)
		1785
		1786	=item $kernel->set_half ($index, $value)
		1787
		1788	=item $kernel->set_float ($index, $value)
		1789
		1790	=item $kernel->set_double ($index, $value)
		1791
		1792	=item $kernel->set_memory ($index, $value)
		1793
		1794	=item $kernel->set_buffer ($index, $value)
		1795
		1796	=item $kernel->set_image ($index, $value)
		1797
		1798	=item $kernel->set_sampler ($index, $value)
		1799
		1800	=item $kernel->set_local ($index, $value)
		1801
		1802	=item $kernel->set_event ($index, $value)
		1803
1370	This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>.	1804	This is a family of methods to set the kernel argument with the number
1371		1805	C<$index> to the give C<$value>.
1372	TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>,
1373	C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>,
1374	C<image2d>, C<image3d>, C<sampler> or C<event>.
1375		1806
1376	Chars and integers (including the half type) are specified as integers,	1807	Chars and integers (including the half type) are specified as integers,
1377	float and double as floating point values, memory/buffer/image2d/image3d	1808	float and double as floating point values, memory/buffer/image must be
1378	must be an object of that type or C<undef>, and sampler and event must be	1809	an object of that type or C<undef>, local-memory arguments are set by
1379	objects of that type.	1810	specifying the size, and sampler and event must be objects of that type.
		1811
		1812	Note that C<set_memory> works for all memory objects (all types of buffers
		1813	and images) - the main purpose of the more specific C<set_TYPE> functions
		1814	is type checking.
		1815
		1816	Setting an argument for a kernel does NOT keep a reference to the object -
		1817	for example, if you set an argument to some image object, free the image,
		1818	and call the kernel, you will run into undefined behaviour.
1380		1819
1381	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html>	1820	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html>
1382		1821
1383	=back	1822	=back
1384		1823
…		…
1393		1832
1394	Waits for the event to complete.	1833	Waits for the event to complete.
1395		1834
1396	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>	1835	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>
1397		1836
		1837	=item $ev->cb ($exec_callback_type, $callback->($event, $event_command_exec_status))
		1838
		1839	Adds a callback to the callback stack for the given event type. There is
		1840	no way to remove a callback again.
		1841
		1842	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetEventCallback.html>
		1843
1398	=item $packed_value = $ev->info ($name)	1844	=item $packed_value = $ev->info ($name)
1399		1845
1400	See C<< $platform->info >> for details.	1846	See C<< $platform->info >> for details.
1401		1847
1402	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html>	1848	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html>
…		…
1462		1908
1463	=over 4	1909	=over 4
1464		1910
1465	=item $ev->set_status ($execution_status)	1911	=item $ev->set_status ($execution_status)
1466		1912
		1913	Sets the execution status of the user event. Can only be called once,
		1914	either with OpenCL::COMPLETE or a negative number as status.
		1915
1467	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html>	1916	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html>
1468		1917
1469	=back	1918	=back
1470		1919
1471	=cut	1920	=cut
1472
1473	package OpenCL;
1474
1475	use common::sense;
1476
1477	BEGIN {
1478	our $VERSION = '0.95';
1479
1480	require XSLoader;
1481	XSLoader::load (__PACKAGE__, $VERSION);
1482
1483	@OpenCL::Buffer::ISA =
1484	@OpenCL::Image::ISA = OpenCL::Memory::;
1485
1486	@OpenCL::BufferObj::ISA = OpenCL::Buffer::;
1487
1488	@OpenCL::Image2D::ISA =
1489	@OpenCL::Image3D::ISA = OpenCL::Image::;
1490
1491	@OpenCL::UserEvent::ISA = OpenCL::Event::;
1492	}
1493		1921
1494	1;	1922	1;
1495		1923
1496	=head1 AUTHOR	1924	=head1 AUTHOR
1497		1925

Diff Legend

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

Comparing OpenCL/OpenCL.pm (file contents): Revision 1.40 by root, Thu Apr 19 22:33:27 2012 UTC vs. Revision 1.65 by root, Mon Apr 30 23:35:16 2012 UTC

Diff Legend

Comparing OpenCL/OpenCL.pm (file contents):
Revision 1.40 by root, Thu Apr 19 22:33:27 2012 UTC vs.
Revision 1.65 by root, Mon Apr 30 23:35:16 2012 UTC