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

Comparing OpenCL/OpenCL.pm (file contents):
Revision 1.51 by root, Tue Apr 24 13:45:58 2012 UTC vs.
Revision 1.68 by root, Tue May 1 22:25:13 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
		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	@OpenCL::MappedBuffer::ISA =
		564	@OpenCL::MappedImage::ISA = OpenCL::Mapped::;
		565	}
		566
381	=head2 THE OpenCL PACKAGE	567	=head2 THE OpenCL PACKAGE
382		568
383	=over 4	569	=over 4
384		570
385	=item $int = OpenCL::errno	571	=item $int = OpenCL::errno
386		572
387	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
388	and before calling another OpenCL function.	574	and before calling another OpenCL function.
389		575
390	=item $str = OpenCL::err2str $errval	576	=item $str = OpenCL::err2str [$errval]
391		577
392	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).
393		580
394	=item $str = OpenCL::enum2str $enum	581	=item $str = OpenCL::enum2str $enum
395		582
396	Converts most enum values (of parameter names, image format constants,	583	Converts most enum values (of parameter names, image format constants,
397	object types, addressing and filter modes, command types etc.) into a	584	object types, addressing and filter modes, command types etc.) into a
…		…
403		590
404	Returns all available OpenCL::Platform objects.	591	Returns all available OpenCL::Platform objects.
405		592
406	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>
407		594
408	=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
409		596
410	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.
411		598
412	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>
413		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
414	=item OpenCL::wait_for_events $wait_events...	608	=item OpenCL::wait_for_events $wait_events...
415		609
416	Waits for all events to complete.	610	Waits for all events to complete.
417		611
418	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>
419		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	}
		650
420	=back	651	=back
421		652
		653	=head2 THE OpenCL::Object CLASS
		654
		655	This is the base class for all objects in the OpenCL module. The only
		656	method it implements is the C<id> method, which is only useful if you want
		657	to interface to OpenCL on the C level.
		658
		659	=over 4
		660
		661	=item $iv = $obj->id
		662
		663	OpenCL objects are represented by pointers or integers on the C level. If
		664	you want to interface to an OpenCL object directly on the C level, then
		665	you need this value, which is returned by this method. You should use an
		666	C<IV> type in your code and cast that to the correct type.
		667
		668	=cut
		669
		670	sub OpenCL::Object::id {
		671	ref $_[0] eq "SCALAR"
		672	? ${ $_[0] }
		673	: $_[0][0]
		674	}
		675
		676	=back
		677
422	=head2 THE OpenCL::Platform CLASS	678	=head2 THE OpenCL::Platform CLASS
423		679
424	=over 4	680	=over 4
425		681
426	=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL)	682	=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL)
427		683
428	Returns a list of matching OpenCL::Device objects.	684	Returns a list of matching OpenCL::Device objects.
429		685
430	=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)
431		687
432	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.
433		689
434	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>
435		691
436	=item $ctx = $platform->context ($properties = undef, @$devices, $notify = undef)	692	=item $ctx = $platform->context ($properties, \@devices, $callback->($err, $pvt) = $print_stderr)
437		693
438	Create a new OpenCL::Context object using the given device object(s)- a	694	Create a new OpenCL::Context object using the given device object(s)- a
439	CL_CONTEXT_PLATFORM property is supplied automatically.	695	CL_CONTEXT_PLATFORM property is supplied automatically.
440		696
441	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>	697	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>
…		…
784	my ($self, $prog, $options) = @_;	1040	my ($self, $prog, $options) = @_;
785		1041
786	$prog = $self->program_with_source ($prog)	1042	$prog = $self->program_with_source ($prog)
787	unless ref $prog;	1043	unless ref $prog;
788		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
789	for my $dev ($self->devices) {	1051	for my $dev ($self->devices) {
790	eval { $prog->build ($dev, $options); 1 }	1052	$prog->build_status ($dev) == BUILD_SUCCESS
791	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"
792	. $prog->build_log ($dev);	1054	. $prog->build_log ($dev);
793	}	1055	}
794		1056
795	$prog	1057	$prog
796	}	1058	}
797		1059
…		…
821	=item $buf = $ctx->buffer_sv ($flags, $data)	1083	=item $buf = $ctx->buffer_sv ($flags, $data)
822		1084
823	Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and	1085	Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and
824	initialise it with the given data values.	1086	initialise it with the given data values.
825		1087
826	=item $img = $ctx->image ($self, $flags, $channel_order, $channel_type, $type, $width, $height, $depth, $array_size = 0, $row_pitch = 0, $slice_pitch = 0, $num_mip_level = 0, $num_samples = 0, $*data = &PL_sv_undef)	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)
827		1089
828	Creates a new OpenCL::Image object and optionally initialises it with	1090	Creates a new OpenCL::Image object and optionally initialises it with
829	the given data values.	1091	the given data values.
830		1092
831	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>
…		…
927	=back	1189	=back
928		1190
929	=head2 THE OpenCL::Queue CLASS	1191	=head2 THE OpenCL::Queue CLASS
930		1192
931	An OpenCL::Queue represents an execution queue for OpenCL. You execute	1193	An OpenCL::Queue represents an execution queue for OpenCL. You execute
932	requests by calling their respective C<enqueue_xxx> method and waitinf for	1194	requests by calling their respective method and waiting for it to complete
933	it to complete in some way.	1195	in some way.
934		1196
935	All the enqueue methods return an event object that can be used to wait	1197	Most methods that enqueue some request return an event object that can
936	for completion, unless the method is called in void context, in which case	1198	be used to wait for completion (optionally using a callback), unless
937	no event object is created.	1199	the method is called in void context, in which case no event object is
		1200	created.
938		1201
939	They also allow you to specify any number of other event objects that this	1202	They also allow you to specify any number of other event objects that this
940	request has to wait for before it starts executing, by simply passing the	1203	request has to wait for before it starts executing, by simply passing the
941	event objects as extra parameters to the enqueue methods. To simplify	1204	event objects as extra parameters to the enqueue methods. To simplify
942	program design, this module ignores any C<undef> values in the list of	1205	program design, this module ignores any C<undef> values in the list of
943	events. This makes it possible to code operations such as this, without	1206	events. This makes it possible to code operations such as this, without
944	having to put a valid event object into C<$event> first:	1207	having to put a valid event object into C<$event> first:
945		1208
946	$event = $queue->enqueue_xxx (..., $event);	1209	$event = $queue->xxx (..., $event);
947		1210
948	Queues execute in-order by default, without any parallelism, so in most	1211	Queues execute in-order by default, without any parallelism, so in most
949	cases (i.e. you use only one queue) it's not necessary to wait for or	1212	cases (i.e. you use only one queue) it's not necessary to wait for or
950	create event objects, althoguh an our of order queue is often a bit	1213	create event objects, althoguh an our of order queue is often a bit
951	faster.	1214	faster.
952		1215
953	=over 4	1216	=over 4
954		1217
955	=item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...)	1218	=item $ev = $queue->read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...)
956		1219
957	Reads data from buffer into the given string.	1220	Reads data from buffer into the given string.
958		1221
959	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html>	1222	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html>
960		1223
961	=item $ev = $queue->enqueue_write_buffer ($buffer, $blocking, $offset, $data, $wait_events...)	1224	=item $ev = $queue->write_buffer ($buffer, $blocking, $offset, $data, $wait_events...)
962		1225
963	Writes data to buffer from the given string.	1226	Writes data to buffer from the given string.
964		1227
965	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html>	1228	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html>
966		1229
967	=item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...)	1230	=item $ev = $queue->copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...)
968		1231
969	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html>	1232	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html>
970		1233
971	=item $ev = $queue->enqueue_read_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...)	1234	=item $ev = $queue->read_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...)
972		1235
973	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html	1236	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html
974		1237
975	=item $ev = $queue->enqueue_write_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...)	1238	=item $ev = $queue->write_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...)
976		1239
977	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html	1240	http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html
978		1241
979	=item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
980
981	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html>
982
983	=item $ev = $queue->enqueue_copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...)	1242	=item $ev = $queue->copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...)
		1243
		1244	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>
		1245
		1246	=item $ev = $queue->read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
		1247
		1248	C<$row_pitch> (and C<$slice_pitch>) can be C<0>, in which case the OpenCL
		1249	module uses the image width (and height) to supply default values.
984		1250
985	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html>	1251	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html>
986		1252
987	=item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)	1253	=item $ev = $queue->write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
988		1254
		1255	C<$row_pitch> (and C<$slice_pitch>) can be C<0>, in which case the OpenCL
		1256	module uses the image width (and height) to supply default values.
989	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html>	1257	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html>
990		1258
991	=item $ev = $queue->enqueue_copy_image ($src_image, $dst_image, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...)	1259	=item $ev = $queue->copy_image ($src_image, $dst_image, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...)
992		1260
993	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html>	1261	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html>
994		1262
995	=item $ev = $queue->enqueue_copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...)	1263	=item $ev = $queue->copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...)
996		1264
997	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html>	1265	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html>
998		1266
999	=item $ev = $queue->enqueue_copy_buffer_rect ($src, $dst, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $src_row_pitch, $src_slice_pitch, $dst_row_pitch, $dst_slice_pitch, $wait_event...)	1267	=item $ev = $queue->copy_buffer_rect ($src, $dst, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $src_row_pitch, $src_slice_pitch, $dst_row_pitch, $dst_slice_pitch, $wait_event...)
1000		1268
1001	Yeah.	1269	Yeah.
1002		1270
1003	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>.	1271	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>.
1004		1272
		1273	=item $ev = $queue->fill_buffer ($mem, $pattern, $offset, $size, ...)
		1274
		1275	Fills the given buffer object with repeated applications of C<$pattern>,
		1276	starting at C<$offset> for C<$size> octets.
		1277
		1278	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html>
		1279
		1280	=item $ev = $queue->fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...)
		1281
		1282	Fills the given image area with the given rgba colour components. The
		1283	components are normally floating point values between C<0> and C<1>,
		1284	except when the image channel data type is a signe dor unsigned
		1285	unnormalised format, in which case the range is determined by the format.
		1286
		1287	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html>
		1288
1005	=item $ev = $queue->enqueue_task ($kernel, $wait_events...)	1289	=item $ev = $queue->task ($kernel, $wait_events...)
1006		1290
1007	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html>	1291	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html>
1008		1292
1009	=item $ev = $queue->enqueue_nd_range_kernel ($kernel, @$global_work_offset, @$global_work_size, @$local_work_size, $wait_events...)	1293	=item $ev = $queue->nd_range_kernel ($kernel, \@global_work_offset, \@global_work_size, \@local_work_size, $wait_events...)
1010		1294
1011	Enqueues a kernel execution.	1295	Enqueues a kernel execution.
1012		1296
1013	@$global_work_size must be specified as a reference to an array of	1297	\@global_work_size must be specified as a reference to an array of
1014	integers specifying the work sizes (element counts).	1298	integers specifying the work sizes (element counts).
1015		1299
1016	@$global_work_offset must be either C<undef> (in which case all offsets	1300	\@global_work_offset must be either C<undef> (in which case all offsets
1017	are C<0>), or a reference to an array of work offsets, with the same number	1301	are C<0>), or a reference to an array of work offsets, with the same number
1018	of elements as @$global_work_size.	1302	of elements as \@global_work_size.
1019		1303
1020	@$local_work_size must be either C<undef> (in which case the	1304	\@local_work_size must be either C<undef> (in which case the
1021	implementation is supposed to choose good local work sizes), or a	1305	implementation is supposed to choose good local work sizes), or a
1022	reference to an array of local work sizes, with the same number of	1306	reference to an array of local work sizes, with the same number of
1023	elements as @$global_work_size.	1307	elements as \@global_work_size.
1024		1308
1025	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html>	1309	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html>
1026		1310
1027	=item $ev = $queue->enqueue_acquire_gl_objects ([object, ...], $wait_events...)	1311	=item $ev = $queue->acquire_gl_objects ([object, ...], $wait_events...)
1028		1312
1029	Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired	1313	Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired
1030	for subsequent OpenCL usage.	1314	for subsequent OpenCL usage.
1031		1315
1032	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html>	1316	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html>
1033		1317
1034	=item $ev = $queue->enqueue_release_gl_objects ([object, ...], $wait_events...)	1318	=item $ev = $queue->release_gl_objects ([object, ...], $wait_events...)
1035		1319
1036	Enqueues a list (an array-ref of OpenCL::Memory objects) to be released	1320	Enqueues a list (an array-ref of OpenCL::Memory objects) to be released
1037	for subsequent OpenGL usage.	1321	for subsequent OpenGL usage.
1038		1322
1039	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html>	1323	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html>
1040		1324
1041	=item $ev = $queue->enqueue_wait_for_events ($wait_events...)	1325	=item $ev = $queue->wait_for_events ($wait_events...)
1042		1326
1043	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html>	1327	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html>
1044		1328
1045	=item $ev = $queue->enqueue_marker ($wait_events...)	1329	=item $ev = $queue->marker ($wait_events...)
1046		1330
1047	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html>	1331	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html>
1048		1332
1049	=item $ev = $queue->enqueue_barrier ($wait_events...)	1333	=item $ev = $queue->barrier ($wait_events...)
1050		1334
1051	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html>	1335	L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html>
1052		1336
1053	=item $queue->flush	1337	=item $queue->flush
1054		1338
…		…
1081	=item $command_queue_properties = $command_queue->properties	1365	=item $command_queue_properties = $command_queue->properties
1082		1366
1083	Calls C<clGetCommandQueueInfo> with C<CL_QUEUE_PROPERTIES> and returns the result.	1367	Calls C<clGetCommandQueueInfo> with C<CL_QUEUE_PROPERTIES> and returns the result.
1084		1368
1085	=for gengetinfo end command_queue	1369	=for gengetinfo end command_queue
		1370
		1371	=back
		1372
		1373	=head3 MEMORY MAPPED BUFFERS
		1374
		1375	OpenCL allows you to map buffers and images to host memory (read: perl
		1376	scalars). This is done much like reading or copying a buffer, by enqueuing
		1377	a map or unmap operation on the command queue.
		1378
		1379	The map operations return a C<OpenCL::Mapped> object - see L<THE
		1380	OpenCL::Mapped CLASS> section for details on what to do with these
		1381	objects.
		1382
		1383	The object will be unmapped automatically when the mapped object is
		1384	destroyed (you can use a barrier to make sure the unmap has finished,
		1385	before using the buffer in a kernel), but you can also enqueue an unmap
		1386	operation manually.
		1387
		1388	=over 4
		1389
		1390	=item $mapped_buffer = $queue->map_buffer ($buf, $data, $blocking=1, $map_flags=OpenCL::MAP_READ\|OpenCL::MAP_WRITE, $offset=0, $size=0, $wait_events...)
		1391
		1392	Maps the given buffer into host memory and returns a C<OpenCL::MappedBuffer> object.
		1393
		1394	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueMapBuffer.html>
		1395
		1396	=item $mapped_image = $queue->map_image ($img, $data, $blocking=1, $map_flags=OpenCL::MAP_READ\|OpenCL::MAP_WRITE, $x=0, $y=0, $z=0, $width=0, $height=0, $depth=0, $wait_events...)
		1397
		1398	Maps the given image area into host memory and return a
		1399	C<OpenCL::MappedImage> object. Although there are default values for most
		1400	arguments, you currently have to specify all arguments, otherwise the call
		1401	will fail.
		1402
		1403	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueMapImage.html>
		1404
		1405	=item $ev = $queue->unmap ($mapped, $wait_events...)
		1406
		1407	Unmaps the data from host memory. You must not call any methods that
		1408	modify the data, or modify the data scalar directly, after calling this
		1409	method.
		1410
		1411	The mapped event object will always be passed as part of the
		1412	$wait_events. The mapped event object will be replaced by the new event
		1413	object that this request creates.
1086		1414
1087	=back	1415	=back
1088		1416
1089	=head2 THE OpenCL::Memory CLASS	1417	=head2 THE OpenCL::Memory CLASS
1090		1418
…		…
1177	OpenCL::Image1DArray, OpenCL::Image1DBuffer, OpenCL::Image2D,	1505	OpenCL::Image1DArray, OpenCL::Image1DBuffer, OpenCL::Image2D,
1178	OpenCL::Image2DArray and OpenCL::Image3D.	1506	OpenCL::Image2DArray and OpenCL::Image3D.
1179		1507
1180	=over 4	1508	=over 4
1181		1509
1182	=item $packed_value = $ev->image_info ($name)	1510	=item $packed_value = $image->image_info ($name)
1183		1511
1184	See C<< $platform->info >> for details.	1512	See C<< $platform->info >> for details.
1185		1513
1186	The reason this method is not called C<info> is that there already is an	1514	The reason this method is not called C<info> is that there already is an
1187	C<< ->info >> method inherited from C<OpenCL::Memory>.	1515	C<< ->info >> method inherited from C<OpenCL::Memory>.
1188		1516
1189	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html>	1517	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html>
1190		1518
		1519	=item ($channel_order, $channel_data_type) = $image->format
		1520
		1521	Returns the channel order and type used to create the image by calling
		1522	C<clGetImageInfo> with C<CL_IMAGE_FORMAT>.
		1523
1191	=for gengetinfo begin image	1524	=for gengetinfo begin image
1192		1525
1193	=item $int = $image->element_size	1526	=item $int = $image->element_size
1194		1527
1195	Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result.	1528	Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result.
…		…
1268		1601
1269	=head2 THE OpenCL::Program CLASS	1602	=head2 THE OpenCL::Program CLASS
1270		1603
1271	=over 4	1604	=over 4
1272		1605
1273	=item $program->build ($device, $options = "")	1606	=item $program->build (\@devices = undef, $options = "", $cb->($program) = undef)
1274		1607
1275	Tries to build the program with the given options. See also the	1608	Tries to build the program with the given options. See also the
1276	C<$ctx->build> convenience function.	1609	C<$ctx->build> convenience function.
1277		1610
		1611	If a callback is specified, then it will be called when compilation is
		1612	finished. Note that many OpenCL implementations block your program while
		1613	compiling whether you use a callback or not. See C<build_async> if you
		1614	want to make sure the build is done in the background.
		1615
		1616	Note that some OpenCL implementations act up badly, and don't call the
		1617	callback in some error cases (but call it in others). This implementation
		1618	assumes the callback will always be called, and leaks memory if this is
		1619	not so. So best make sure you don't pass in invalid values.
		1620
		1621	Some implementations fail with C<OpenCL::INVALID_BINARY> when the
		1622	compilation state is successful but some later stage fails.
		1623
1278	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html>	1624	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html>
		1625
		1626	=item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef)
		1627
		1628	Similar to C<< ->build >>, except it starts a thread, and never fails (you
		1629	need to check the compilation status form the callback, or by polling).
1279		1630
1280	=item $packed_value = $program->build_info ($device, $name)	1631	=item $packed_value = $program->build_info ($device, $name)
1281		1632
1282	Similar to C<< $platform->info >>, but returns build info for a previous	1633	Similar to C<< $platform->info >>, but returns build info for a previous
1283	build attempt for the given device.	1634	build attempt for the given device.
…		…
1425		1776
1426	Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result.	1777	Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result.
1427		1778
1428	=for gengetinfo end kernel_work_group	1779	=for gengetinfo end kernel_work_group
1429		1780
		1781	=item $kernel->setf ($format, ...)
		1782
		1783	Sets the arguments of a kernel. Since OpenCL 1.1 doesn't have a generic
		1784	way to set arguments (and with OpenCL 1.2 it might be rather slow), you
		1785	need to specify a format argument, much as with C<printf>, to tell OpenCL
		1786	what type of argument it is.
		1787
		1788	The format arguments are single letters:
		1789
		1790	c char
		1791	C unsigned char
		1792	s short
		1793	S unsigned short
		1794	i int
		1795	I unsigned int
		1796	l long
		1797	L unsigned long
		1798
		1799	h half float (0..65535)
		1800	f float
		1801	d double
		1802
		1803	z local (octet size)
		1804
		1805	m memory object (buffer or image)
		1806	a sampler
		1807	e event
		1808
		1809	Space characters in the format string are ignored.
		1810
		1811	Example: set the arguments for a kernel that expects an int, two floats, a buffer and an image.
		1812
		1813	$kernel->setf ("i ff mm", 5, 0.5, 3, $buffer, $image);
		1814
1430	=item $kernel->set_TYPE ($index, $value)	1815	=item $kernel->set_TYPE ($index, $value)
1431		1816
		1817	=item $kernel->set_char ($index, $value)
		1818
		1819	=item $kernel->set_uchar ($index, $value)
		1820
		1821	=item $kernel->set_short ($index, $value)
		1822
		1823	=item $kernel->set_ushort ($index, $value)
		1824
		1825	=item $kernel->set_int ($index, $value)
		1826
		1827	=item $kernel->set_uint ($index, $value)
		1828
		1829	=item $kernel->set_long ($index, $value)
		1830
		1831	=item $kernel->set_ulong ($index, $value)
		1832
		1833	=item $kernel->set_half ($index, $value)
		1834
		1835	=item $kernel->set_float ($index, $value)
		1836
		1837	=item $kernel->set_double ($index, $value)
		1838
		1839	=item $kernel->set_memory ($index, $value)
		1840
		1841	=item $kernel->set_buffer ($index, $value)
		1842
		1843	=item $kernel->set_image ($index, $value)
		1844
		1845	=item $kernel->set_sampler ($index, $value)
		1846
		1847	=item $kernel->set_local ($index, $value)
		1848
		1849	=item $kernel->set_event ($index, $value)
		1850
1432	This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>.	1851	This is a family of methods to set the kernel argument with the number
1433		1852	C<$index> to the give C<$value>.
1434	TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>,
1435	C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>,
1436	C<image2d>, C<image3d>, C<sampler>, C<local> or C<event>.
1437		1853
1438	Chars and integers (including the half type) are specified as integers,	1854	Chars and integers (including the half type) are specified as integers,
1439	float and double as floating point values, memory/buffer/image2d/image3d	1855	float and double as floating point values, memory/buffer/image must be
1440	must be an object of that type or C<undef>, local-memory arguments are	1856	an object of that type or C<undef>, local-memory arguments are set by
1441	set by specifying the size, and sampler and event must be objects of that	1857	specifying the size, and sampler and event must be objects of that type.
1442	type.	1858
		1859	Note that C<set_memory> works for all memory objects (all types of buffers
		1860	and images) - the main purpose of the more specific C<set_TYPE> functions
		1861	is type checking.
1443		1862
1444	Setting an argument for a kernel does NOT keep a reference to the object -	1863	Setting an argument for a kernel does NOT keep a reference to the object -
1445	for example, if you set an argument to some image object, free the image,	1864	for example, if you set an argument to some image object, free the image,
1446	and call the kernel, you will run into undefined behaviour.	1865	and call the kernel, you will run into undefined behaviour.
1447		1866
…		…
1460		1879
1461	Waits for the event to complete.	1880	Waits for the event to complete.
1462		1881
1463	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>	1882	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>
1464		1883
		1884	=item $ev->cb ($exec_callback_type, $callback->($event, $event_command_exec_status))
		1885
		1886	Adds a callback to the callback stack for the given event type. There is
		1887	no way to remove a callback again.
		1888
		1889	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetEventCallback.html>
		1890
1465	=item $packed_value = $ev->info ($name)	1891	=item $packed_value = $ev->info ($name)
1466		1892
1467	See C<< $platform->info >> for details.	1893	See C<< $platform->info >> for details.
1468		1894
1469	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html>	1895	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html>
…		…
1529		1955
1530	=over 4	1956	=over 4
1531		1957
1532	=item $ev->set_status ($execution_status)	1958	=item $ev->set_status ($execution_status)
1533		1959
		1960	Sets the execution status of the user event. Can only be called once,
		1961	either with OpenCL::COMPLETE or a negative number as status.
		1962
1534	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html>	1963	L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html>
1535		1964
1536	=back	1965	=back
1537		1966
		1967	=head2 THE OpenCL::Mapped CLASS
		1968
		1969	This class represents objects mapped into host memory. They are
		1970	represented by a blessed string scalar. The string data is the mapped
		1971	memory area, that is, if you read or write it, then the mapped object is
		1972	accessed directly.
		1973
		1974	You must only ever use operations that modify the string in-place - for
		1975	example, a C<substr> that doesn't change the length, or maybe a regex that
		1976	doesn't change the length. Any other operation might cause the data to be
		1977	copied.
		1978
		1979	When the object is destroyed it will enqueue an implicit unmap operation
		1980	on the queue that was used to create it.
		1981
		1982	Keep in mind that you I<need> to unmap (or destroy) mapped objects before
		1983	OpenCL sees the changes, even if some implementations don't need this
		1984	sometimes.
		1985
		1986	Example, replace the first two floats in the mapped buffer by 1 and 2.
		1987
		1988	my $mapped = $queue->map_buffer ($buf, ...
		1989	$mapped->event->wait; # make sure it's there
		1990
		1991	# now replace first 8 bytes by new data, which is exactly 8 bytes long
		1992	# we blindly assume device endianness to equal host endianness
		1993	# (and of course, we assume iee 754 single precision floats :)
		1994	substr $$mapped, 0, 8, pack "f*", 1, 2;
		1995
		1996	=over 4
		1997
		1998	=item $ev = $mapped->unmap ($wait_events...)
		1999
		2000	Unmaps the mapped memory object, using the queue originally used to create
		2001	it, quite similarly to C<< $queue->unmap ($mapped, ...) >>.
		2002
		2003	=item $bool = $mapped->mapped
		2004
		2005	Returns whether the object is still mapped - true before an C<unmap> is
		2006	enqueued, false afterwards.
		2007
		2008	=item $ev = $mapped->event
		2009
		2010	Return the event object associated with the mapped object. Initially, this
		2011	will be the event object created when mapping the object, and after an
		2012	unmap, this will be the event object that the unmap operation created.
		2013
		2014	=item $mapped->wait
		2015
		2016	Same as C<< $mapped->event->wait >> - makes sure no operations on this
		2017	mapped object are outstanding.
		2018
		2019	=item $bytes = $mapped->size
		2020
		2021	Returns the size of the mapped area, in bytes. Same as C<length $$mapped>.
		2022
		2023	=item $ptr = $mapped->ptr
		2024
		2025	Returns the raw memory address of the mapped area.
		2026
		2027	=item $mapped->set ($offset, $data)
		2028
		2029	Replaces the data at the given C<$offset> in the memory area by the new
		2030	C<$data>. This method is safer than direct manipulation of C<$mapped>
		2031	because it does bounds-checking, but also slower.
		2032
		2033	=item $data = $mapped->get ($offset, $length)
		2034
		2035	Returns (without copying) a scalar representing the data at the given
		2036	C<$offset> and C<$length> in the mapped memory area. This is the same as
		2037	the following substr, except much slower;
		2038
		2039	$data = substr $$mapped, $offset, $length
		2040
1538	=cut	2041	=cut
1539		2042
1540	package OpenCL;	2043	sub OpenCL::Mapped::get {
1541		2044	substr ${$_[0]}, $_[1], $_[2]
1542	use common::sense;
1543
1544	BEGIN {
1545	our $VERSION = '0.96';
1546
1547	require XSLoader;
1548	XSLoader::load (__PACKAGE__, $VERSION);
1549
1550	@OpenCL::Buffer::ISA =
1551	@OpenCL::Image::ISA = OpenCL::Memory::;
1552
1553	@OpenCL::BufferObj::ISA = OpenCL::Buffer::;
1554
1555	@OpenCL::Image2D::ISA =
1556	@OpenCL::Image3D::ISA =
1557	@OpenCL::Image2DArray::ISA =
1558	@OpenCL::Image1D::ISA =
1559	@OpenCL::Image1DArray::ISA =
1560	@OpenCL::Image1DBuffer::ISA = OpenCL::Image::;
1561
1562	@OpenCL::UserEvent::ISA = OpenCL::Event::;
1563	}	2045	}
		2046
		2047	=back
		2048
		2049	=head2 THE OpenCL::MappedBuffer CLASS
		2050
		2051	This is a subclass of OpenCL::Mapped, representing mapped buffers.
		2052
		2053	=head2 THE OpenCL::MappedImage CLASS
		2054
		2055	This is a subclass of OpenCL::Mapped, representing mapped images.
		2056
		2057	=over 4
		2058
		2059	=item $bytes = $mapped->row_pitch
		2060
		2061	=item $bytes = $mapped->slice_pitch
		2062
		2063	Return the row or slice pitch of the image that has been mapped.
		2064
		2065	=back
		2066
		2067
		2068	=cut
1564		2069
1565	1;	2070	1;
1566		2071
1567	=head1 AUTHOR	2072	=head1 AUTHOR
1568		2073

Diff Legend

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

Comparing OpenCL/OpenCL.pm (file contents): Revision 1.51 by root, Tue Apr 24 13:45:58 2012 UTC vs. Revision 1.68 by root, Tue May 1 22:25:13 2012 UTC

Diff Legend

Comparing OpenCL/OpenCL.pm (file contents):
Revision 1.51 by root, Tue Apr 24 13:45:58 2012 UTC vs.
Revision 1.68 by root, Tue May 1 22:25:13 2012 UTC