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

Comparing OpenCL/OpenCL.pm (file contents):
Revision 1.52 by root, Tue Apr 24 14:24:42 2012 UTC vs.
Revision 1.70 by root, Thu May 3 23:32:47 2012 UTC

…		…
43		43
44	OpenCL::Event objects are used to signal when something is complete.	44	OpenCL::Event objects are used to signal when something is complete.
45		45
46	=head2 HELPFUL RESOURCES	46	=head2 HELPFUL RESOURCES
47		47
48	The OpenCL spec used to develop this module (1.2 spec was available, but	48	The OpenCL specs used to develop this module:
49	no implementation was available to me :).
50		49
51	http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf	50	http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf
		51	http://www.khronos.org/registry/cl/specs/opencl-1.2.pdf
		52	http://www.khronos.org/registry/cl/specs/opencl-1.2-extensions.pdf
52		53
53	OpenCL manpages:	54	OpenCL manpages:
54		55
55	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/	56	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/
		57	http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/
56		58
57	If you are into UML class diagrams, the following diagram might help - if	59	If you are into UML class diagrams, the following diagram might help - if
58	not, it will be mildly cobfusing:	60	not, it will be mildly confusing (also, the class hierarchy of this module
		61	is much more fine-grained):
59		62
60	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/classDiagram.html	63	http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/classDiagram.html
61		64
62	Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it	65	Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it
63	is, but at least it's free of charge:	66	is, but at least it's free of charge:
64		67
65	http://developer.amd.com/zones/OpenCLZone/courses/Documents/Introduction_to_OpenCL_Programming%20Training_Guide%20%28201005%29.pdf	68	http://developer.amd.com/zones/OpenCLZone/courses/Documents/Introduction_to_OpenCL_Programming%20Training_Guide%20%28201005%29.pdf
…		…
138	=head2 Create a buffer with some predefined data, read it back synchronously,	141	=head2 Create a buffer with some predefined data, read it back synchronously,
139	then asynchronously.	142	then asynchronously.
140		143
141	my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut");	144	my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut");
142		145
143	$queue->enqueue_read_buffer ($buf, 1, 1, 3, my $data);	146	$queue->read_buffer ($buf, 1, 1, 3, my $data);
144	print "$data\n";	147	print "$data\n";
145		148
146	my $ev = $queue->enqueue_read_buffer ($buf, 0, 1, 3, my $data);	149	my $ev = $queue->read_buffer ($buf, 0, 1, 3, my $data);
147	$ev->wait;	150	$ev->wait;
148	print "$data\n"; # prints "elm"	151	print "$data\n"; # prints "elm"
149		152
150	=head2 Create and build a program, then create a kernel out of one of its	153	=head2 Create and build a program, then create a kernel out of one of its
151	functions.	154	functions.
…		…
171	# set buffer	174	# set buffer
172	$kernel->set_buffer (0, $input);	175	$kernel->set_buffer (0, $input);
173	$kernel->set_buffer (1, $output);	176	$kernel->set_buffer (1, $output);
174		177
175	# execute it for all 4 numbers	178	# execute it for all 4 numbers
176	$queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef);	179	$queue->nd_range_kernel ($kernel, undef, [4], undef);
177		180
178	# enqueue a synchronous read	181	# enqueue a synchronous read
179	$queue->enqueue_read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data);	182	$queue->read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data);
180		183
181	# print the results:	184	# print the results:
182	printf "%s\n", join ", ", unpack "f*", $data;	185	printf "%s\n", join ", ", unpack "f*", $data;
183		186
184	=head2 The same enqueue operations as before, but assuming an out-of-order queue,	187	=head2 The same enqueue operations as before, but assuming an out-of-order queue,
185	showing off barriers.	188	showing off barriers.
186		189
187	# execute it for all 4 numbers	190	# execute it for all 4 numbers
188	$queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef);	191	$queue->nd_range_kernel ($kernel, undef, [4], undef);
189		192
190	# enqueue a barrier to ensure in-order execution	193	# enqueue a barrier to ensure in-order execution
191	$queue->enqueue_barrier;	194	$queue->barrier;
192		195
193	# enqueue an async read	196	# enqueue an async read
194	$queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data);	197	$queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data);
195		198
196	# wait for all requests to finish	199	# wait for all requests to finish
197	$queue->finish;	200	$queue->finish;
198		201
199	=head2 The same enqueue operations as before, but assuming an out-of-order queue,	202	=head2 The same enqueue operations as before, but assuming an out-of-order queue,
200	showing off event objects and wait lists.	203	showing off event objects and wait lists.
201		204
202	# execute it for all 4 numbers	205	# execute it for all 4 numbers
203	my $ev = $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef);	206	my $ev = $queue->nd_range_kernel ($kernel, undef, [4], undef);
204		207
205	# enqueue an async read	208	# enqueue an async read
206	$ev = $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev);	209	$ev = $queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev);
207		210
208	# wait for the last event to complete	211	# wait for the last event to complete
209	$ev->wait;	212	$ev->wait;
210		213
211	=head2 Use the OpenGL module to share a texture between OpenCL and OpenGL and draw some julia	214	=head2 Use the OpenGL module to share a texture between OpenCL and OpenGL and draw some julia
212	set tunnel effect.	215	set tunnel effect.
213		216
214	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>.
215		219
216	use OpenGL ":all";	220	use OpenGL ":all";
217	use OpenCL;	221	use OpenCL;
218		222
		223	my $S = $ARGV[0] \|\| 256; # window/texture size, smaller is faster
		224
219	# open a window and create a gl texture	225	# open a window and create a gl texture
220	OpenGL::glpOpenWindow width => 256, height => 256;	226	OpenGL::glpOpenWindow width => $S, height => $S;
221	my $texid = glGenTextures_p 1;	227	my $texid = glGenTextures_p 1;
222	glBindTexture GL_TEXTURE_2D, $texid;	228	glBindTexture GL_TEXTURE_2D, $texid;
223	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;
224		230
225	# 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
226	my $platform;	232	my $platform;
227	my $dev;	233	my $dev;
228	my $ctx;	234	my $ctx;
…		…
247	# now the boring opencl code	253	# now the boring opencl code
248	my $src = <<EOF;	254	my $src = <<EOF;
249	kernel void	255	kernel void
250	juliatunnel (write_only image2d_t img, float time)	256	juliatunnel (write_only image2d_t img, float time)
251	{	257	{
252	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;
253		260
254	float2 m = (float2)(1.f, p.y) / fabs (p.x);	261	float2 m = (float2)(1.f, p.y) / fabs (p.x); // tunnel
255	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);
256		263
257	float2 z = m;	264	float2 z = m;
258	float2 c = (float2)(sin (time * 0.05005), cos (time * 0.06001));	265	float2 c = (float2)(sin (time * 0.01133f), cos (time * 0.02521f));
259		266
260	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
261	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;
262		269
263	float3 colour = (float3)(z.x, z.y, z.x * z.y);	270	float3 colour = (float3)(z.x, z.y, atan2 (z.y, z.x));
264	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.));
265	}	272	}
266	EOF	273	EOF
267		274
268	my $prog = $ctx->build_program ($src);	275	my $prog = $ctx->build_program ($src);
269	my $kernel = $prog->kernel ("juliatunnel");	276	my $kernel = $prog->kernel ("juliatunnel");
270		277
271	# program compiled, kernel ready, now draw and loop	278	# program compiled, kernel ready, now draw and loop
272		279
273	for (my $time; ; ++$time) {	280	for (my $time; ; ++$time) {
274	# acquire objects from opengl	281	# acquire objects from opengl
275	$queue->enqueue_acquire_gl_objects ([$tex]);	282	$queue->acquire_gl_objects ([$tex]);
276		283
277	# configure and run our kernel	284	# configure and run our kernel
278	$kernel->set_image2d (0, $tex);	285	$kernel->setf ("mf", $tex, $time*2); # mf = memory object, float
279	$kernel->set_float (1, $time);
280	$queue->enqueue_nd_range_kernel ($kernel, undef, [256, 256], undef);	286	$queue->nd_range_kernel ($kernel, undef, [$S, $S], undef);
281		287
282	# release objects to opengl again	288	# release objects to opengl again
283	$queue->enqueue_release_gl_objects ([$tex]);	289	$queue->release_gl_objects ([$tex]);
284		290
285	# wait	291	# wait
286	$queue->finish;	292	$queue->finish;
287		293
288	# now draw the texture, the defaults should be all right	294	# now draw the texture, the defaults should be all right
…		…
298		304
299	glXSwapBuffers;	305	glXSwapBuffers;
300		306
301	select undef, undef, undef, 1/60;	307	select undef, undef, undef, 1/60;
302	}	308	}
		309
		310	=head2 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>.
303		336
304	=head1 DOCUMENTATION	337	=head1 DOCUMENTATION
305		338
306	=head2 BASIC CONVENTIONS	339	=head2 BASIC CONVENTIONS
307		340
…		…
376		409
377	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
378	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
379	capable of finding the function via C<RTLD_DEFAULT>.	412	capable of finding the function via C<RTLD_DEFAULT>.
380		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
381	=cut	523	=cut
382		524
383	package OpenCL;	525	package OpenCL;
384		526
385	use common::sense;	527	use common::sense;
		528	use Carp ();
		529	use Async::Interrupt ();
		530
		531	our $POLL_FUNC; # set by XS
386		532
387	BEGIN {	533	BEGIN {
388	our $VERSION = '0.96';	534	our $VERSION = '0.99';
389		535
390	require XSLoader;	536	require XSLoader;
391	XSLoader::load (__PACKAGE__, $VERSION);	537	XSLoader::load (__PACKAGE__, $VERSION);
392		538
393	@OpenCL::Platform::ISA =	539	@OpenCL::Platform::ISA =
…		…
411	@OpenCL::Image1D::ISA =	557	@OpenCL::Image1D::ISA =
412	@OpenCL::Image1DArray::ISA =	558	@OpenCL::Image1DArray::ISA =
413	@OpenCL::Image1DBuffer::ISA = OpenCL::Image::;	559	@OpenCL::Image1DBuffer::ISA = OpenCL::Image::;
414		560
415	@OpenCL::UserEvent::ISA = OpenCL::Event::;	561	@OpenCL::UserEvent::ISA = OpenCL::Event::;
		562
		563	@OpenCL::MappedBuffer::ISA =
		564	@OpenCL::MappedImage::ISA = OpenCL::Mapped::;
416	}	565	}
417		566
418	=head2 THE OpenCL PACKAGE	567	=head2 THE OpenCL PACKAGE
419		568
420	=over 4	569	=over 4
…		…
422	=item $int = OpenCL::errno	571	=item $int = OpenCL::errno
423		572
424	The last error returned by a function - it's only valid after an error occured	573	The last error returned by a function - it's only valid after an error occured
425	and before calling another OpenCL function.	574	and before calling another OpenCL function.
426		575
427	=item $str = OpenCL::err2str $errval	576	=item $str = OpenCL::err2str [$errval]
428		577
429	Comverts an error value into a human readable string.	578	Converts an error value into a human readable string. IF no error value is
		579	given, then the last error will be used (as returned by OpenCL::errno).
430		580
431	=item $str = OpenCL::enum2str $enum	581	=item $str = OpenCL::enum2str $enum
432		582
433	Converts most enum values (of parameter names, image format constants,	583	Converts most enum values (of parameter names, image format constants,
434	object types, addressing and filter modes, command types etc.) into a	584	object types, addressing and filter modes, command types etc.) into a
…		…
440		590
441	Returns all available OpenCL::Platform objects.	591	Returns all available OpenCL::Platform objects.
442		592
443	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html>	593	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html>
444		594
445	=item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef	595	=item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr
446		596
447	Tries to create a context from a default device and platform - never worked for me.	597	Tries to create a context from a default device and platform type - never worked for me.
448		598
449	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>	599	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>
450		600
		601	=item $ctx = OpenCL::context $properties, \@devices, $callback->($err, $pvt) = $print_stderr)
		602
		603	Create a new OpenCL::Context object using the given device object(s). This
		604	function isn't implemented yet, use C<< $platform->context >> instead.
		605
		606	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>
		607
451	=item OpenCL::wait_for_events $wait_events...	608	=item OpenCL::wait_for_events $wait_events...
452		609
453	Waits for all events to complete.	610	Waits for all events to complete.
454		611
455	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>	612	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>
		613
		614	=item OpenCL::poll
		615
		616	Checks if there are any outstanding events (see L<EVENT SYSTEM>) and
		617	invokes their callbacks.
		618
		619	=item $OpenCL::INTERRUPT
		620
		621	The L<Async::Interrupt> object used to signal asynchronous events (see
		622	L<EVENT SYSTEM>).
		623
		624	=cut
		625
		626	our $INTERRUPT = new Async::Interrupt c_cb => [$POLL_FUNC, 0];
		627
		628	&_eq_initialise ($INTERRUPT->signal_func);
		629
		630	=item $OpenCL::WATCHER
		631
		632	The L<AnyEvent> watcher object used to watch for asynchronous events (see
		633	L<EVENT SYSTEM>). This variable is C<undef> until L<AnyEvent> has been
		634	loaded I<and> initialised (e.g. by calling C<AnyEvent::detect>).
		635
		636	=cut
		637
		638	our $WATCHER;
		639
		640	sub _init_anyevent {
		641	$INTERRUPT->block;
		642	$WATCHER = AE::io ($INTERRUPT->pipe_fileno, 0, sub { $INTERRUPT->handle });
		643	}
		644
		645	if (defined $AnyEvent::MODEL) {
		646	_init_anyevent;
		647	} else {
		648	push @AnyEvent::post_detect, \&_init_anyevent;
		649	}
456		650
457	=back	651	=back
458		652
459	=head2 THE OpenCL::Object CLASS	653	=head2 THE OpenCL::Object CLASS
460		654
…		…
472	C<IV> type in your code and cast that to the correct type.	666	C<IV> type in your code and cast that to the correct type.
473		667
474	=cut	668	=cut
475		669
476	sub OpenCL::Object::id {	670	sub OpenCL::Object::id {
		671	ref $_[0] eq "SCALAR"
477	${$_[0]}	672	? ${ $_[0] }
		673	: $_[0][0]
478	}	674	}
479		675
480	=back	676	=back
481		677
482	=head2 THE OpenCL::Platform CLASS	678	=head2 THE OpenCL::Platform CLASS
…		…
485		681
486	=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL)	682	=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL)
487		683
488	Returns a list of matching OpenCL::Device objects.	684	Returns a list of matching OpenCL::Device objects.
489		685
490	=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef)	686	=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr)
491		687
492	Tries to create a context. Never worked for me, and you need devices explicitly anyway.	688	Tries to create a context. Never worked for me, and you need devices explicitly anyway.
493		689
494	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>	690	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>
495		691
496	=item $ctx = $platform->context ($properties = undef, @$devices, $notify = undef)	692	=item $ctx = $platform->context ($properties, \@devices, $callback->($err, $pvt) = $print_stderr)
497		693
498	Create a new OpenCL::Context object using the given device object(s)- a	694	Create a new OpenCL::Context object using the given device object(s)- a
499	CL_CONTEXT_PLATFORM property is supplied automatically.	695	CL_CONTEXT_PLATFORM property is supplied automatically.
500		696
501	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>	697	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>
…		…
844	my ($self, $prog, $options) = @_;	1040	my ($self, $prog, $options) = @_;
845		1041
846	$prog = $self->program_with_source ($prog)	1042	$prog = $self->program_with_source ($prog)
847	unless ref $prog;	1043	unless ref $prog;
848		1044
		1045	eval { $prog->build (undef, $options); 1 }
		1046	or errno == BUILD_PROGRAM_FAILURE
		1047	or errno == INVALID_BINARY # workaround nvidia bug
		1048	or Carp::croak "OpenCL::Context->build_program: " . err2str;
		1049
		1050	# we check status for all devices
849	for my $dev ($self->devices) {	1051	for my $dev ($self->devices) {
850	eval { $prog->build ($dev, $options); 1 }	1052	$prog->build_status ($dev) == BUILD_SUCCESS
851	or Carp::croak "Building OpenCL program for device '" . $dev->name . "' failed:\n"	1053	or Carp::croak "Building OpenCL program for device '" . $dev->name . "' failed:\n"
852	. $prog->build_log ($dev);	1054	. $prog->build_log ($dev);
853	}	1055	}
854		1056
855	$prog	1057	$prog
856	}	1058	}
857		1059
…		…
881	=item $buf = $ctx->buffer_sv ($flags, $data)	1083	=item $buf = $ctx->buffer_sv ($flags, $data)
882		1084
883	Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and	1085	Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and
884	initialise it with the given data values.	1086	initialise it with the given data values.
885		1087
886	=item $img = $ctx->image ($self, $flags, $channel_order, $channel_type, $type, $width, $height, $depth, $array_size = 0, $row_pitch = 0, $slice_pitch = 0, $num_mip_level = 0, $num_samples = 0, $*data = &PL_sv_undef)	1088	=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, $*data = &PL_sv_undef)
887		1089
888	Creates a new OpenCL::Image object and optionally initialises it with	1090	Creates a new OpenCL::Image object and optionally initialises it with
889	the given data values.	1091	the given data values.
890		1092
891	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html>	1093	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html>
…		…
956		1158
957	Creates a new OpenCL::Program object from the given source code.	1159	Creates a new OpenCL::Program object from the given source code.
958		1160
959	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateProgramWithSource.html>	1161	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateProgramWithSource.html>
960		1162
		1163	=item ($program, \@status) = $ctx->program_with_binary (\@devices, \@binaries)
		1164
		1165	Creates a new OpenCL::Program object from the given binaries.
		1166
		1167	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateProgramWithBinary.html>
		1168
		1169	Example: clone an existing program object that contains a successfully
		1170	compiled program, no matter how useless this is.
		1171
		1172	my $clone = $ctx->program_with_binary ([$prog->devices], [$prog->binaries]);
		1173
961	=item $packed_value = $ctx->info ($name)	1174	=item $packed_value = $ctx->info ($name)
962		1175
963	See C<< $platform->info >> for details.	1176	See C<< $platform->info >> for details.
964		1177
965	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetContextInfo.html>	1178	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetContextInfo.html>
…		…
987	=back	1200	=back
988		1201
989	=head2 THE OpenCL::Queue CLASS	1202	=head2 THE OpenCL::Queue CLASS
990		1203
991	An OpenCL::Queue represents an execution queue for OpenCL. You execute	1204	An OpenCL::Queue represents an execution queue for OpenCL. You execute
992	requests by calling their respective C<enqueue_xxx> method and waitinf for	1205	requests by calling their respective method and waiting for it to complete
993	it to complete in some way.	1206	in some way.
994		1207
995	All the enqueue methods return an event object that can be used to wait	1208	Most methods that enqueue some request return an event object that can
996	for completion, unless the method is called in void context, in which case	1209	be used to wait for completion (optionally using a callback), unless
997	no event object is created.	1210	the method is called in void context, in which case no event object is
		1211	created.
998		1212
999	They also allow you to specify any number of other event objects that this	1213	They also allow you to specify any number of other event objects that this
1000	request has to wait for before it starts executing, by simply passing the	1214	request has to wait for before it starts executing, by simply passing the
1001	event objects as extra parameters to the enqueue methods. To simplify	1215	event objects as extra parameters to the enqueue methods. To simplify
1002	program design, this module ignores any C<undef> values in the list of	1216	program design, this module ignores any C<undef> values in the list of
1003	events. This makes it possible to code operations such as this, without	1217	events. This makes it possible to code operations such as this, without
1004	having to put a valid event object into C<$event> first:	1218	having to put a valid event object into C<$event> first:
1005		1219
1006	$event = $queue->enqueue_xxx (..., $event);	1220	$event = $queue->xxx (..., $event);
1007		1221
1008	Queues execute in-order by default, without any parallelism, so in most	1222	Queues execute in-order by default, without any parallelism, so in most
1009	cases (i.e. you use only one queue) it's not necessary to wait for or	1223	cases (i.e. you use only one queue) it's not necessary to wait for or
1010	create event objects, althoguh an our of order queue is often a bit	1224	create event objects, althoguh an our of order queue is often a bit
1011	faster.	1225	faster.
1012		1226
1013	=over 4	1227	=over 4
1014		1228
1015	=item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...)	1229	=item $ev = $queue->read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...)
1016		1230
1017	Reads data from buffer into the given string.	1231	Reads data from buffer into the given string.
1018		1232
1019	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html>	1233	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html>
1020		1234
1021	=item $ev = $queue->enqueue_write_buffer ($buffer, $blocking, $offset, $data, $wait_events...)	1235	=item $ev = $queue->write_buffer ($buffer, $blocking, $offset, $data, $wait_events...)
1022		1236
1023	Writes data to buffer from the given string.	1237	Writes data to buffer from the given string.
1024		1238
1025	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html>	1239	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html>
1026		1240
1027	=item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...)	1241	=item $ev = $queue->copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...)
1028		1242
1029	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html>	1243	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html>
1030		1244
1031	=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...)	1245	=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...)
1032		1246
1033	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html	1247	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html
1034		1248
1035	=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...)	1249	=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...)
1036		1250
1037	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html	1251	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html
1038		1252
1039	=item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
1040
1041	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html>
1042
1043	=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...)	1253	=item $ev = $queue->copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...)
		1254
		1255	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>
		1256
		1257	=item $ev = $queue->read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
		1258
		1259	C<$row_pitch> (and C<$slice_pitch>) can be C<0>, in which case the OpenCL
		1260	module uses the image width (and height) to supply default values.
1044		1261
1045	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html>	1262	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html>
1046		1263
1047	=item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)	1264	=item $ev = $queue->write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
1048		1265
		1266	C<$row_pitch> (and C<$slice_pitch>) can be C<0>, in which case the OpenCL
		1267	module uses the image width (and height) to supply default values.
1049	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html>	1268	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html>
1050		1269
1051	=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...)	1270	=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...)
1052		1271
1053	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html>	1272	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html>
1054		1273
1055	=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...)	1274	=item $ev = $queue->copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...)
1056		1275
1057	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html>	1276	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html>
1058		1277
1059	=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...)	1278	=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...)
1060		1279
1061	Yeah.	1280	Yeah.
1062		1281
1063	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>.	1282	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>.
1064		1283
1065	=item $ev = $queue->enqueue_fill_buffer ($mem, $pattern, $offset, $size, ...)	1284	=item $ev = $queue->fill_buffer ($mem, $pattern, $offset, $size, ...)
1066		1285
1067	Fills the given buffer object with repeated applications of C<$pattern>,	1286	Fills the given buffer object with repeated applications of C<$pattern>,
1068	starting at C<$offset> for C<$size> octets.	1287	starting at C<$offset> for C<$size> octets.
1069		1288
1070	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html>	1289	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html>
1071		1290
1072	=item $ev = $queue->enqueue_fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...)	1291	=item $ev = $queue->fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...)
1073		1292
1074	Fills the given image area with the given rgba colour components. The	1293	Fills the given image area with the given rgba colour components. The
1075	components are normally floating point values between C<0> and C<1>,	1294	components are normally floating point values between C<0> and C<1>,
1076	except when the image channel data type is a signe dor unsigned	1295	except when the image channel data type is a signe dor unsigned
1077	unnormalised format, in which case the range is determined by the format.	1296	unnormalised format, in which case the range is determined by the format.
1078		1297
1079	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html>	1298	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html>
1080		1299
1081	=item $ev = $queue->enqueue_task ($kernel, $wait_events...)	1300	=item $ev = $queue->task ($kernel, $wait_events...)
1082		1301
1083	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html>	1302	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html>
1084		1303
1085	=item $ev = $queue->enqueue_nd_range_kernel ($kernel, @$global_work_offset, @$global_work_size, @$local_work_size, $wait_events...)	1304	=item $ev = $queue->nd_range_kernel ($kernel, \@global_work_offset, \@global_work_size, \@local_work_size, $wait_events...)
1086		1305
1087	Enqueues a kernel execution.	1306	Enqueues a kernel execution.
1088		1307
1089	@$global_work_size must be specified as a reference to an array of	1308	\@global_work_size must be specified as a reference to an array of
1090	integers specifying the work sizes (element counts).	1309	integers specifying the work sizes (element counts).
1091		1310
1092	@$global_work_offset must be either C<undef> (in which case all offsets	1311	\@global_work_offset must be either C<undef> (in which case all offsets
1093	are C<0>), or a reference to an array of work offsets, with the same number	1312	are C<0>), or a reference to an array of work offsets, with the same number
1094	of elements as @$global_work_size.	1313	of elements as \@global_work_size.
1095		1314
1096	@$local_work_size must be either C<undef> (in which case the	1315	\@local_work_size must be either C<undef> (in which case the
1097	implementation is supposed to choose good local work sizes), or a	1316	implementation is supposed to choose good local work sizes), or a
1098	reference to an array of local work sizes, with the same number of	1317	reference to an array of local work sizes, with the same number of
1099	elements as @$global_work_size.	1318	elements as \@global_work_size.
1100		1319
1101	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html>	1320	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html>
1102		1321
1103	=item $ev = $queue->enqueue_acquire_gl_objects ([object, ...], $wait_events...)	1322	=item $ev = $queue->acquire_gl_objects ([object, ...], $wait_events...)
1104		1323
1105	Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired	1324	Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired
1106	for subsequent OpenCL usage.	1325	for subsequent OpenCL usage.
1107		1326
1108	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html>	1327	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html>
1109		1328
1110	=item $ev = $queue->enqueue_release_gl_objects ([object, ...], $wait_events...)	1329	=item $ev = $queue->release_gl_objects ([object, ...], $wait_events...)
1111		1330
1112	Enqueues a list (an array-ref of OpenCL::Memory objects) to be released	1331	Enqueues a list (an array-ref of OpenCL::Memory objects) to be released
1113	for subsequent OpenGL usage.	1332	for subsequent OpenGL usage.
1114		1333
1115	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html>	1334	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html>
1116		1335
1117	=item $ev = $queue->enqueue_wait_for_events ($wait_events...)	1336	=item $ev = $queue->wait_for_events ($wait_events...)
1118		1337
1119	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html>	1338	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html>
1120		1339
1121	=item $ev = $queue->enqueue_marker ($wait_events...)	1340	=item $ev = $queue->marker ($wait_events...)
1122		1341
1123	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html>	1342	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html>
1124		1343
1125	=item $ev = $queue->enqueue_barrier ($wait_events...)	1344	=item $ev = $queue->barrier ($wait_events...)
1126		1345
1127	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html>	1346	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html>
1128		1347
1129	=item $queue->flush	1348	=item $queue->flush
1130		1349
…		…
1157	=item $command_queue_properties = $command_queue->properties	1376	=item $command_queue_properties = $command_queue->properties
1158		1377
1159	Calls C<clGetCommandQueueInfo> with C<CL_QUEUE_PROPERTIES> and returns the result.	1378	Calls C<clGetCommandQueueInfo> with C<CL_QUEUE_PROPERTIES> and returns the result.
1160		1379
1161	=for gengetinfo end command_queue	1380	=for gengetinfo end command_queue
		1381
		1382	=back
		1383
		1384	=head3 MEMORY MAPPED BUFFERS
		1385
		1386	OpenCL allows you to map buffers and images to host memory (read: perl
		1387	scalars). This is done much like reading or copying a buffer, by enqueuing
		1388	a map or unmap operation on the command queue.
		1389
		1390	The map operations return an C<OpenCL::Mapped> object - see L<THE
		1391	OpenCL::Mapped CLASS> section for details on what to do with these
		1392	objects.
		1393
		1394	The object will be unmapped automatically when the mapped object is
		1395	destroyed (you can use a barrier to make sure the unmap has finished,
		1396	before using the buffer in a kernel), but you can also enqueue an unmap
		1397	operation manually.
		1398
		1399	=over 4
		1400
		1401	=item $mapped_buffer = $queue->map_buffer ($buf, $blocking=1, $map_flags=OpenCL::MAP_READ\|OpenCL::MAP_WRITE, $offset=0, $size=undef, $wait_events...)
		1402
		1403	Maps the given buffer into host memory and returns an
		1404	C<OpenCL::MappedBuffer> object. If C<$size> is specified as undef, then
		1405	the map will extend to the end of the buffer.
		1406
		1407	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueMapBuffer.html>
		1408
		1409	Example: map the buffer $buf fully and replace the first 4 bytes by "abcd", then unmap.
		1410
		1411	{
		1412	my $mapped = $queue->map_buffer ($buf, 1, OpenCL::MAP_WRITE);
		1413	substr $$mapped, 0, 4, "abcd";
		1414	} # asynchronously unmap because $mapped is destroyed
		1415
		1416	=item $mapped_image = $queue->map_image ($img, $blocking=1, $map_flags=OpenCL::MAP_READ\|OpenCL::MAP_WRITE, $x=0, $y=0, $z=0, $width=undef, $height=undef, $depth=undef, $wait_events...)
		1417
		1418	Maps the given image area into host memory and return an
		1419	C<OpenCL::MappedImage> object.
		1420
		1421	If any of C<$width>, C<$height> and/or C<$depth> are C<undef> then they
		1422	will be replaced by the maximum possible value.
		1423
		1424	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueMapImage.html>
		1425
		1426	Example: map an image (with OpenCL::UNSIGNED_INT8 channel type) and set
		1427	the first channel of the leftmost column to 5, then explicitly unmap
		1428	it. You are not necessarily meant to do it this way, this example just
		1429	shows you the accessors to use :)
		1430
		1431	my $mapped = $queue->map_image ($image, 1, OpenCL::MAP_WRITE);
		1432
		1433	$mapped->set ($_ * $mapped->row_pitch, pack "C", 5)
		1434	for 0..$image->height;
		1435
		1436	$mapped->unmap;.
		1437	$mapped->wait; # only needed for out of order queues normally
		1438
		1439	=item $ev = $queue->unmap ($mapped, $wait_events...)
		1440
		1441	Unmaps the data from host memory. You must not call any methods that
		1442	modify the data, or modify the data scalar directly, after calling this
		1443	method.
		1444
		1445	The mapped event object will always be passed as part of the
		1446	$wait_events. The mapped event object will be replaced by the new event
		1447	object that this request creates.
1162		1448
1163	=back	1449	=back
1164		1450
1165	=head2 THE OpenCL::Memory CLASS	1451	=head2 THE OpenCL::Memory CLASS
1166		1452
…		…
1253	OpenCL::Image1DArray, OpenCL::Image1DBuffer, OpenCL::Image2D,	1539	OpenCL::Image1DArray, OpenCL::Image1DBuffer, OpenCL::Image2D,
1254	OpenCL::Image2DArray and OpenCL::Image3D.	1540	OpenCL::Image2DArray and OpenCL::Image3D.
1255		1541
1256	=over 4	1542	=over 4
1257		1543
1258	=item $packed_value = $ev->image_info ($name)	1544	=item $packed_value = $image->image_info ($name)
1259		1545
1260	See C<< $platform->info >> for details.	1546	See C<< $platform->info >> for details.
1261		1547
1262	The reason this method is not called C<info> is that there already is an	1548	The reason this method is not called C<info> is that there already is an
1263	C<< ->info >> method inherited from C<OpenCL::Memory>.	1549	C<< ->info >> method inherited from C<OpenCL::Memory>.
1264		1550
1265	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html>	1551	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html>
1266		1552
		1553	=item ($channel_order, $channel_data_type) = $image->format
		1554
		1555	Returns the channel order and type used to create the image by calling
		1556	C<clGetImageInfo> with C<CL_IMAGE_FORMAT>.
		1557
1267	=for gengetinfo begin image	1558	=for gengetinfo begin image
1268		1559
1269	=item $int = $image->element_size	1560	=item $int = $image->element_size
1270		1561
1271	Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result.	1562	Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result.
…		…
1344		1635
1345	=head2 THE OpenCL::Program CLASS	1636	=head2 THE OpenCL::Program CLASS
1346		1637
1347	=over 4	1638	=over 4
1348		1639
1349	=item $program->build ($device, $options = "")	1640	=item $program->build (\@devices = undef, $options = "", $cb->($program) = undef)
1350		1641
1351	Tries to build the program with the given options. See also the	1642	Tries to build the program with the given options. See also the
1352	C<$ctx->build> convenience function.	1643	C<$ctx->build> convenience function.
1353		1644
		1645	If a callback is specified, then it will be called when compilation is
		1646	finished. Note that many OpenCL implementations block your program while
		1647	compiling whether you use a callback or not. See C<build_async> if you
		1648	want to make sure the build is done in the background.
		1649
		1650	Note that some OpenCL implementations act up badly, and don't call the
		1651	callback in some error cases (but call it in others). This implementation
		1652	assumes the callback will always be called, and leaks memory if this is
		1653	not so. So best make sure you don't pass in invalid values.
		1654
		1655	Some implementations fail with C<OpenCL::INVALID_BINARY> when the
		1656	compilation state is successful but some later stage fails.
		1657
1354	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html>	1658	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html>
		1659
		1660	=item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef)
		1661
		1662	Similar to C<< ->build >>, except it starts a thread, and never fails (you
		1663	need to check the compilation status form the callback, or by polling).
1355		1664
1356	=item $packed_value = $program->build_info ($device, $name)	1665	=item $packed_value = $program->build_info ($device, $name)
1357		1666
1358	Similar to C<< $platform->info >>, but returns build info for a previous	1667	Similar to C<< $platform->info >>, but returns build info for a previous
1359	build attempt for the given device.	1668	build attempt for the given device.
…		…
1501		1810
1502	Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result.	1811	Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result.
1503		1812
1504	=for gengetinfo end kernel_work_group	1813	=for gengetinfo end kernel_work_group
1505		1814
		1815	=item $kernel->setf ($format, ...)
		1816
		1817	Sets the arguments of a kernel. Since OpenCL 1.1 doesn't have a generic
		1818	way to set arguments (and with OpenCL 1.2 it might be rather slow), you
		1819	need to specify a format argument, much as with C<printf>, to tell OpenCL
		1820	what type of argument it is.
		1821
		1822	The format arguments are single letters:
		1823
		1824	c char
		1825	C unsigned char
		1826	s short
		1827	S unsigned short
		1828	i int
		1829	I unsigned int
		1830	l long
		1831	L unsigned long
		1832
		1833	h half float (0..65535)
		1834	f float
		1835	d double
		1836
		1837	z local (octet size)
		1838
		1839	m memory object (buffer or image)
		1840	a sampler
		1841	e event
		1842
		1843	Space characters in the format string are ignored.
		1844
		1845	Example: set the arguments for a kernel that expects an int, two floats, a buffer and an image.
		1846
		1847	$kernel->setf ("i ff mm", 5, 0.5, 3, $buffer, $image);
		1848
1506	=item $kernel->set_TYPE ($index, $value)	1849	=item $kernel->set_TYPE ($index, $value)
1507		1850
		1851	=item $kernel->set_char ($index, $value)
		1852
		1853	=item $kernel->set_uchar ($index, $value)
		1854
		1855	=item $kernel->set_short ($index, $value)
		1856
		1857	=item $kernel->set_ushort ($index, $value)
		1858
		1859	=item $kernel->set_int ($index, $value)
		1860
		1861	=item $kernel->set_uint ($index, $value)
		1862
		1863	=item $kernel->set_long ($index, $value)
		1864
		1865	=item $kernel->set_ulong ($index, $value)
		1866
		1867	=item $kernel->set_half ($index, $value)
		1868
		1869	=item $kernel->set_float ($index, $value)
		1870
		1871	=item $kernel->set_double ($index, $value)
		1872
		1873	=item $kernel->set_memory ($index, $value)
		1874
		1875	=item $kernel->set_buffer ($index, $value)
		1876
		1877	=item $kernel->set_image ($index, $value)
		1878
		1879	=item $kernel->set_sampler ($index, $value)
		1880
		1881	=item $kernel->set_local ($index, $value)
		1882
		1883	=item $kernel->set_event ($index, $value)
		1884
1508	This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>.	1885	This is a family of methods to set the kernel argument with the number
1509		1886	C<$index> to the give C<$value>.
1510	TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>,
1511	C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>,
1512	C<image2d>, C<image3d>, C<sampler>, C<local> or C<event>.
1513		1887
1514	Chars and integers (including the half type) are specified as integers,	1888	Chars and integers (including the half type) are specified as integers,
1515	float and double as floating point values, memory/buffer/image2d/image3d	1889	float and double as floating point values, memory/buffer/image must be
1516	must be an object of that type or C<undef>, local-memory arguments are	1890	an object of that type or C<undef>, local-memory arguments are set by
1517	set by specifying the size, and sampler and event must be objects of that	1891	specifying the size, and sampler and event must be objects of that type.
1518	type.	1892
		1893	Note that C<set_memory> works for all memory objects (all types of buffers
		1894	and images) - the main purpose of the more specific C<set_TYPE> functions
		1895	is type checking.
1519		1896
1520	Setting an argument for a kernel does NOT keep a reference to the object -	1897	Setting an argument for a kernel does NOT keep a reference to the object -
1521	for example, if you set an argument to some image object, free the image,	1898	for example, if you set an argument to some image object, free the image,
1522	and call the kernel, you will run into undefined behaviour.	1899	and call the kernel, you will run into undefined behaviour.
1523		1900
…		…
1536		1913
1537	Waits for the event to complete.	1914	Waits for the event to complete.
1538		1915
1539	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>	1916	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>
1540		1917
		1918	=item $ev->cb ($exec_callback_type, $callback->($event, $event_command_exec_status))
		1919
		1920	Adds a callback to the callback stack for the given event type. There is
		1921	no way to remove a callback again.
		1922
		1923	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetEventCallback.html>
		1924
1541	=item $packed_value = $ev->info ($name)	1925	=item $packed_value = $ev->info ($name)
1542		1926
1543	See C<< $platform->info >> for details.	1927	See C<< $platform->info >> for details.
1544		1928
1545	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html>	1929	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html>
…		…
1605		1989
1606	=over 4	1990	=over 4
1607		1991
1608	=item $ev->set_status ($execution_status)	1992	=item $ev->set_status ($execution_status)
1609		1993
		1994	Sets the execution status of the user event. Can only be called once,
		1995	either with OpenCL::COMPLETE or a negative number as status.
		1996
1610	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html>	1997	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html>
1611		1998
1612	=back	1999	=back
		2000
		2001	=head2 THE OpenCL::Mapped CLASS
		2002
		2003	This class represents objects mapped into host memory. They are
		2004	represented by a blessed string scalar. The string data is the mapped
		2005	memory area, that is, if you read or write it, then the mapped object is
		2006	accessed directly.
		2007
		2008	You must only ever use operations that modify the string in-place - for
		2009	example, a C<substr> that doesn't change the length, or maybe a regex that
		2010	doesn't change the length. Any other operation might cause the data to be
		2011	copied.
		2012
		2013	When the object is destroyed it will enqueue an implicit unmap operation
		2014	on the queue that was used to create it.
		2015
		2016	Keep in mind that you I<need> to unmap (or destroy) mapped objects before
		2017	OpenCL sees the changes, even if some implementations don't need this
		2018	sometimes.
		2019
		2020	Example, replace the first two floats in the mapped buffer by 1 and 2.
		2021
		2022	my $mapped = $queue->map_buffer ($buf, ...
		2023	$mapped->event->wait; # make sure it's there
		2024
		2025	# now replace first 8 bytes by new data, which is exactly 8 bytes long
		2026	# we blindly assume device endianness to equal host endianness
		2027	# (and of course, we assume iee 754 single precision floats :)
		2028	substr $$mapped, 0, 8, pack "f*", 1, 2;
		2029
		2030	=over 4
		2031
		2032	=item $ev = $mapped->unmap ($wait_events...)
		2033
		2034	Unmaps the mapped memory object, using the queue originally used to create
		2035	it, quite similarly to C<< $queue->unmap ($mapped, ...) >>.
		2036
		2037	=item $bool = $mapped->mapped
		2038
		2039	Returns whether the object is still mapped - true before an C<unmap> is
		2040	enqueued, false afterwards.
		2041
		2042	=item $ev = $mapped->event
		2043
		2044	Return the event object associated with the mapped object. Initially, this
		2045	will be the event object created when mapping the object, and after an
		2046	unmap, this will be the event object that the unmap operation created.
		2047
		2048	=item $mapped->wait
		2049
		2050	Same as C<< $mapped->event->wait >> - makes sure no operations on this
		2051	mapped object are outstanding.
		2052
		2053	=item $bytes = $mapped->size
		2054
		2055	Returns the size of the mapped area, in bytes. Same as C<length $$mapped>.
		2056
		2057	=item $ptr = $mapped->ptr
		2058
		2059	Returns the raw memory address of the mapped area.
		2060
		2061	=item $mapped->set ($offset, $data)
		2062
		2063	Replaces the data at the given C<$offset> in the memory area by the new
		2064	C<$data>. This method is safer than direct manipulation of C<$mapped>
		2065	because it does bounds-checking, but also slower.
		2066
		2067	=item $data = $mapped->get ($offset, $length)
		2068
		2069	Returns (without copying) a scalar representing the data at the given
		2070	C<$offset> and C<$length> in the mapped memory area. This is the same as
		2071	the following substr, except much slower;
		2072
		2073	$data = substr $$mapped, $offset, $length
		2074
		2075	=cut
		2076
		2077	sub OpenCL::Mapped::get {
		2078	substr ${$_[0]}, $_[1], $_[2]
		2079	}
		2080
		2081	=back
		2082
		2083	=head2 THE OpenCL::MappedBuffer CLASS
		2084
		2085	This is a subclass of OpenCL::Mapped, representing mapped buffers.
		2086
		2087	=head2 THE OpenCL::MappedImage CLASS
		2088
		2089	This is a subclass of OpenCL::Mapped, representing mapped images.
		2090
		2091	=over 4
		2092
		2093	=item $bytes = $mapped->row_pitch
		2094
		2095	=item $bytes = $mapped->slice_pitch
		2096
		2097	Return the row or slice pitch of the image that has been mapped.
		2098
		2099	=back
		2100
1613		2101
1614	=cut	2102	=cut
1615		2103
1616	1;	2104	1;
1617		2105

Diff Legend

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

Comparing OpenCL/OpenCL.pm (file contents): Revision 1.52 by root, Tue Apr 24 14:24:42 2012 UTC vs. Revision 1.70 by root, Thu May 3 23:32:47 2012 UTC

Diff Legend

Comparing OpenCL/OpenCL.pm (file contents):
Revision 1.52 by root, Tue Apr 24 14:24:42 2012 UTC vs.
Revision 1.70 by root, Thu May 3 23:32:47 2012 UTC