ViewVC Help
View File | Revision Log | Show Annotations | Download File
/cvs/OpenCL/OpenCL.pm
(Generate patch)

Comparing OpenCL/OpenCL.pm (file contents):
Revision 1.30 by root, Thu Apr 5 10:08:59 2012 UTC vs.
Revision 1.58 by root, Wed Apr 25 20:29:03 2012 UTC

43 43
44OpenCL::Event objects are used to signal when something is complete. 44OpenCL::Event objects are used to signal when something is complete.
45 45
46=head2 HELPFUL RESOURCES 46=head2 HELPFUL RESOURCES
47 47
48The OpenCL spec used to develop this module (1.2 spec was available, but 48The OpenCL specs used to develop this module:
49no 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
53OpenCL manpages: 54OpenCL 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
57If you are into UML class diagrams, the following diagram might help - if 59If you are into UML class diagrams, the following diagram might help - if
58not, it will be mildly cobfusing: 60not, it will be mildly confusing (also, the class hierarchy of this module
61is 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
62Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it 65Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it
63is, but at least it's free of charge: 66is, 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
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
151functions. 154functions.
152 155
153 my $src = ' 156 my $src = '
154 __kernel void 157 kernel void
155 squareit (__global float *input, __global float *output) 158 squareit (global float *input, global float *output)
156 { 159 {
157 $id = get_global_id (0); 160 $id = get_global_id (0);
158 output [id] = input [id] * input [id]; 161 output [id] = input [id] * input [id];
159 } 162 }
160 '; 163 ';
161 164
162 my $prog = $ctx->program_with_source ($src); 165 my $prog = $ctx->build_program ($src);
163
164 # build croaks on compile errors, so catch it and print the compile errors
165 eval { $prog->build ($dev); 1 }
166 or die $prog->build_log;
167
168 my $kernel = $prog->kernel ("squareit"); 166 my $kernel = $prog->kernel ("squareit");
169 167
170=head2 Create some input and output float buffers, then call the 168=head2 Create some input and output float buffers, then call the
171'squareit' kernel on them. 169'squareit' kernel on them.
172 170
210 # enqueue an async read 208 # enqueue an async read
211 $ev = $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev); 209 $ev = $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev);
212 210
213 # wait for the last event to complete 211 # wait for the last event to complete
214 $ev->wait; 212 $ev->wait;
213
214=head2 Use the OpenGL module to share a texture between OpenCL and OpenGL and draw some julia
215set tunnel effect.
216
217This is quite a long example to get you going.
218
219 use OpenGL ":all";
220 use OpenCL;
221
222 # open a window and create a gl texture
223 OpenGL::glpOpenWindow width => 256, height => 256;
224 my $texid = glGenTextures_p 1;
225 glBindTexture GL_TEXTURE_2D, $texid;
226 glTexImage2D_c GL_TEXTURE_2D, 0, GL_RGBA8, 256, 256, 0, GL_RGBA, GL_UNSIGNED_BYTE, 0;
227
228 # find and use the first opencl device that let's us get a shared opengl context
229 my $platform;
230 my $dev;
231 my $ctx;
232
233 for (OpenCL::platforms) {
234 $platform = $_;
235 for ($platform->devices) {
236 $dev = $_;
237 $ctx = $platform->context ([OpenCL::GLX_DISPLAY_KHR, undef, OpenCL::GL_CONTEXT_KHR, undef], [$dev])
238 and last;
239 }
240 }
241
242 $ctx
243 or die "cannot find suitable OpenCL device\n";
244
245 my $queue = $ctx->queue ($dev);
246
247 # now attach an opencl image2d object to the opengl texture
248 my $tex = $ctx->gl_texture2d (OpenCL::MEM_WRITE_ONLY, GL_TEXTURE_2D, 0, $texid);
249
250 # now the boring opencl code
251 my $src = <<EOF;
252 kernel void
253 juliatunnel (write_only image2d_t img, float time)
254 {
255 float2 p = (float2)(get_global_id (0), get_global_id (1)) / 256.f * 2.f - 1.f;
256
257 float2 m = (float2)(1.f, p.y) / fabs (p.x);
258 m.x = fabs (fmod (m.x + time * 0.05f, 4.f)) - 2.f;
259
260 float2 z = m;
261 float2 c = (float2)(sin (time * 0.05005), cos (time * 0.06001));
262
263 for (int i = 0; i < 25 && dot (z, z) < 4.f; ++i)
264 z = (float2)(z.x * z.x - z.y * z.y, 2.f * z.x * z.y) + c;
265
266 float3 colour = (float3)(z.x, z.y, z.x * z.y);
267 write_imagef (img, (int2)(get_global_id (0), get_global_id (1)), (float4)(colour * p.x * p.x, 1.));
268 }
269 EOF
270
271 my $prog = $ctx->build_program ($src);
272 my $kernel = $prog->kernel ("juliatunnel");
273
274 # program compiled, kernel ready, now draw and loop
275
276 for (my $time; ; ++$time) {
277 # acquire objects from opengl
278 $queue->enqueue_acquire_gl_objects ([$tex]);
279
280 # configure and run our kernel
281 $kernel->set_image2d (0, $tex);
282 $kernel->set_float (1, $time);
283 $queue->enqueue_nd_range_kernel ($kernel, undef, [256, 256], undef);
284
285 # release objects to opengl again
286 $queue->enqueue_release_gl_objects ([$tex]);
287
288 # wait
289 $queue->finish;
290
291 # now draw the texture, the defaults should be all right
292 glTexParameterf GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST;
293
294 glEnable GL_TEXTURE_2D;
295 glBegin GL_QUADS;
296 glTexCoord2f 0, 1; glVertex3i -1, -1, -1;
297 glTexCoord2f 0, 0; glVertex3i 1, -1, -1;
298 glTexCoord2f 1, 0; glVertex3i 1, 1, -1;
299 glTexCoord2f 1, 1; glVertex3i -1, 1, -1;
300 glEnd;
301
302 glXSwapBuffers;
303
304 select undef, undef, undef, 1/60;
305 }
215 306
216=head1 DOCUMENTATION 307=head1 DOCUMENTATION
217 308
218=head2 BASIC CONVENTIONS 309=head2 BASIC CONVENTIONS
219 310
241=item * Structures are often specified by flattening out their components 332=item * Structures are often specified by flattening out their components
242as with short vectors, and returned as arrayrefs. 333as with short vectors, and returned as arrayrefs.
243 334
244=item * When enqueuing commands, the wait list is specified by adding 335=item * When enqueuing commands, the wait list is specified by adding
245extra arguments to the function - anywhere a C<$wait_events...> argument 336extra arguments to the function - anywhere a C<$wait_events...> argument
246is documented this can be any number of event objects. 337is documented this can be any number of event objects. As an extsnion
338implemented by this module, C<undef> values will be ignored in the event
339list.
247 340
248=item * When enqueuing commands, if the enqueue method is called in void 341=item * When enqueuing commands, if the enqueue method is called in void
249context, no event is created. In all other contexts an event is returned 342context, no event is created. In all other contexts an event is returned
250by the method. 343by the method.
251 344
271 ulong IV - Q 364 ulong IV - Q
272 float NV float f 365 float NV float f
273 half IV ushort S 366 half IV ushort S
274 double NV double d 367 double NV double d
275 368
369=head2 GLX SUPPORT
370
371Due to the sad state that OpenGL support is in in Perl (mostly the OpenGL
372module, which has little to no documentation and has little to no support
373for glX), this module, as a special extension, treats context creation
374properties C<OpenCL::GLX_DISPLAY_KHR> and C<OpenCL::GL_CONTEXT_KHR>
375specially: If either or both of these are C<undef>, then the OpenCL
376module tries to dynamically resolve C<glXGetCurrentDisplay> and
377C<glXGetCurrentContext>, call these functions and use their return values
378instead.
379
380For this to work, the OpenGL library must be loaded, a GLX context must
381have been created and be made current, and C<dlsym> must be available and
382capable of finding the function via C<RTLD_DEFAULT>.
383
384=head2 EVENT SYSTEM
385
386OpenCL can generate a number of (potentially) asynchronous events, for
387example, after compiling a program, to signal a context-related error or,
388perhaps most important, to signal completion of queued jobs (by setting
389callbacks on OpenCL::Event objects).
390
391To facilitate this, this module maintains an event queue - each
392time an asynchronous event happens, it is queued, and perl will be
393interrupted. This is implemented via the L<Async::Interrupt> module. In
394addition, this module has L<AnyEvent> support, so it can seamlessly
395integrate itself into many event loops.
396
397Since this module is a bit hard to understand, here are some case examples:
398
399=head3 Don't use callbacks.
400
401When your program never uses any callbacks, then there will never be any
402notifications you need to take care of, and therefore no need to worry
403about all this.
404
405You can achieve a great deal by explicitly waiting for events, or using
406barriers and flush calls. In many programs, there is no need at all to
407tinker with asynchronous events.
408
409=head3 Use AnyEvent
410
411This module automatically registers a watcher that invokes all outstanding
412event callbacks when AnyEvent is initialised (and block asynchronous
413interruptions). Using this mode of operations is the safest and most
414recommended one.
415
416To use this, simply use AnyEvent and this module normally, make sure you
417have an event loop running:
418
419 use Gtk2 -init;
420 use AnyEvent;
421
422 # initialise AnyEvent, by creating a watcher, or:
423 AnyEvent::detect;
424
425 my $e = $queue->enqueue_marker;
426 $e->cb (sub {
427 warn "opencl is finished\n";
428 })
429
430 main Gtk2;
431
432Note that this module will not initialise AnyEvent for you. Before
433AnyEvent is initialised, the module will asynchronously interrupt perl
434instead. To avoid any surprises, it's best to explicitly initialise
435AnyEvent.
436
437You can temporarily enable asynchronous interruptions (see next paragraph)
438by calling C<$OpenCL::INTERRUPT->unblock> and disable them again by
439calling C<$OpenCL::INTERRUPT->block>.
440
441=head3 Let yourself be interrupted at any time
442
443This mode is the default unless AnyEvent is loaded and initialised. In
444this mode, OpenCL asynchronously interrupts a running perl program. The
445emphasis is on both I<asynchronously> and I<running> here.
446
447Asynchronously means that perl might execute your callbacks at any
448time. For example, in the following code (I<THAT YOU SHOULD NOT COPY>),
449the C<until> loop following the marker call will be interrupted by the
450callback:
451
452 my $e = $queue->enqueue_marker;
453 my $flag;
454 $e->cb (sub { $flag = 1 });
455 1 until $flag;
456 # $flag is now 1
457
458The reason why you shouldn't blindly copy the above code is that
459busy waiting is a really really bad thing, and really really bad for
460performance.
461
462While at first this asynchronous business might look exciting, it can be
463really hard, because you need to be prepared for the callback code to be
464executed at any time, which limits the amount of things the callback code
465can do safely.
466
467This can be mitigated somewhat by using C<<
468$OpenCL::INTERRUPT->scope_block >> (see the L<Async::Interrupt>
469documentation for details).
470
471The other problem is that your program must be actively I<running> to be
472interrupted. When you calculate stuff, your program is running. When you
473hang in some C functions or other block execution (by calling C<sleep>,
474C<select>, running an event loop and so on), your program is waiting, not
475running.
476
477One way around that would be to attach a read watcher to your event loop,
478listening for events on C<< $OpenCL::INTERRUPT->pipe_fileno >>, using a
479dummy callback (C<sub { }>) to temporarily execute some perl code.
480
481That is then awfully close to using the built-in AnyEvent support above,
482though, so consider that one instead.
483
484=head3 Be creative
485
486OpenCL exports the L<Async::Interrupt> object it uses in the global
487variable C<$OpenCL::INTERRUPT>. You can configure it in any way you like.
488
489So if you want to feel like a real pro, err, wait, if you feel no risk
490menas no fun, you can experiment by implementing your own mode of
491operations.
492
493=cut
494
495package OpenCL;
496
497use common::sense;
498use Async::Interrupt ();
499
500our $POLL_FUNC; # set by XS
501
502BEGIN {
503 our $VERSION = '0.97';
504
505 require XSLoader;
506 XSLoader::load (__PACKAGE__, $VERSION);
507
508 @OpenCL::Platform::ISA =
509 @OpenCL::Device::ISA =
510 @OpenCL::Context::ISA =
511 @OpenCL::Queue::ISA =
512 @OpenCL::Memory::ISA =
513 @OpenCL::Sampler::ISA =
514 @OpenCL::Program::ISA =
515 @OpenCL::Kernel::ISA =
516 @OpenCL::Event::ISA = OpenCL::Object::;
517
518 @OpenCL::Buffer::ISA =
519 @OpenCL::Image::ISA = OpenCL::Memory::;
520
521 @OpenCL::BufferObj::ISA = OpenCL::Buffer::;
522
523 @OpenCL::Image2D::ISA =
524 @OpenCL::Image3D::ISA =
525 @OpenCL::Image2DArray::ISA =
526 @OpenCL::Image1D::ISA =
527 @OpenCL::Image1DArray::ISA =
528 @OpenCL::Image1DBuffer::ISA = OpenCL::Image::;
529
530 @OpenCL::UserEvent::ISA = OpenCL::Event::;
531}
532
276=head2 THE OpenCL PACKAGE 533=head2 THE OpenCL PACKAGE
277 534
278=over 4 535=over 4
279 536
280=item $int = OpenCL::errno 537=item $int = OpenCL::errno
298 555
299Returns all available OpenCL::Platform objects. 556Returns all available OpenCL::Platform objects.
300 557
301L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html> 558L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html>
302 559
303=item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef 560=item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr
304 561
305Tries to create a context from a default device and platform - never worked for me. 562Tries to create a context from a default device and platform type - never worked for me.
306 563
307L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> 564L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>
308 565
566=item $ctx = OpenCL::context $properties, \@devices, $callback->($err, $pvt) = $print_stderr)
567
568Create a new OpenCL::Context object using the given device object(s). This
569function isn't implemented yet, use C<< $platform->context >> instead.
570
571L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>
572
309=item OpenCL::wait_for_events $wait_events... 573=item OpenCL::wait_for_events $wait_events...
310 574
311Waits for all events to complete. 575Waits for all events to complete.
312 576
313L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> 577L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>
314 578
579=item OpenCL::poll
580
581Checks if there are any outstanding events (see L<EVENT SYSTEM>) and
582invokes their callbacks.
583
584=item $OpenCL::INTERRUPT
585
586The L<Async::Interrupt> object used to signal asynchronous events (see
587L<EVENT SYSTEM>).
588
589=cut
590
591our $INTERRUPT = new Async::Interrupt c_cb => [$POLL_FUNC, 0];
592
593&_eq_initialise ($INTERRUPT->signal_func);
594
595=item $OpenCL::WATCHER
596
597The L<AnyEvent> watcher object used to watch for asynchronous events (see
598L<EVENT SYSTEM>). This variable is C<undef> until L<AnyEvent> has been
599loaded I<and> initialised (e.g. by calling C<AnyEvent::detect>).
600
601=cut
602
603our $WATCHER;
604
605sub _init_anyevent {
606 $INTERRUPT->block;
607 $WATCHER = AE::io ($INTERRUPT->pipe_fileno, 0, sub { $INTERRUPT->handle });
608}
609
610if (defined $AnyEvent::MODEL) {
611 _init_anyevent;
612} else {
613 push @AnyEvent::post_detect, \&_init_anyevent;
614}
615
315=back 616=back
316 617
618=head2 THE OpenCL::Object CLASS
619
620This is the base class for all objects in the OpenCL module. The only
621method it implements is the C<id> method, which is only useful if you want
622to interface to OpenCL on the C level.
623
624=over 4
625
626=item $iv = $obj->id
627
628OpenCL objects are represented by pointers or integers on the C level. If
629you want to interface to an OpenCL object directly on the C level, then
630you need this value, which is returned by this method. You should use an
631C<IV> type in your code and cast that to the correct type.
632
633=cut
634
635sub OpenCL::Object::id {
636 ref $_[0] eq "SCALAR"
637 ? ${ $_[0] }
638 : $_[0][0]
639}
640
641=back
642
317=head2 THE OpenCL::Platform CLASS 643=head2 THE OpenCL::Platform CLASS
318 644
319=over 4 645=over 4
320 646
321=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL) 647=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL)
322 648
323Returns a list of matching OpenCL::Device objects. 649Returns a list of matching OpenCL::Device objects.
324 650
325=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef) 651=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr)
326 652
327Tries to create a context. Never worked for me, and you need devices explicitly anyway. 653Tries to create a context. Never worked for me, and you need devices explicitly anyway.
328 654
329L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> 655L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>
330 656
331=item $ctx = $platform->context ($properties = undef, @$devices, $notify = undef) 657=item $ctx = $platform->context ($properties, \@devices, $callback->($err, $pvt) = $print_stderr)
332 658
333Create a new OpenCL::Context object using the given device object(s)- a 659Create a new OpenCL::Context object using the given device object(s)- a
334CL_CONTEXT_PLATFORM property is supplied automatically. 660CL_CONTEXT_PLATFORM property is supplied automatically.
335 661
336L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> 662L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>
344It's best to avoid this method and use one of the following convenience 670It's best to avoid this method and use one of the following convenience
345wrappers. 671wrappers.
346 672
347L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html> 673L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html>
348 674
675=item $platform->unload_compiler
676
677Attempts to unload the compiler for this platform, for endless
678profit. Does nothing on OpenCL 1.1.
679
680L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clUnloadPlatformCompiler.html>
681
349=for gengetinfo begin platform 682=for gengetinfo begin platform
350 683
351=item $string = $platform->profile 684=item $string = $platform->profile
352 685
353Calls C<clGetPlatformInfo> with C<CL_PLATFORM_PROFILE> and returns the result. 686Calls C<clGetPlatformInfo> with C<CL_PLATFORM_PROFILE> and returns the result.
638 971
639=item @device_partition_property_exts = $device->affinity_domains_ext 972=item @device_partition_property_exts = $device->affinity_domains_ext
640 973
641Calls C<clGetDeviceInfo> with C<CL_DEVICE_AFFINITY_DOMAINS_EXT> and returns the result. 974Calls C<clGetDeviceInfo> with C<CL_DEVICE_AFFINITY_DOMAINS_EXT> and returns the result.
642 975
643=item $uint = $device->reference_count_ext 976=item $uint = $device->reference_count_ext
644 977
645Calls C<clGetDeviceInfo> with C<CL_DEVICE_REFERENCE_COUNT_EXT > and returns the result. 978Calls C<clGetDeviceInfo> with C<CL_DEVICE_REFERENCE_COUNT_EXT> and returns the result.
646 979
647=item @device_partition_property_exts = $device->partition_style_ext 980=item @device_partition_property_exts = $device->partition_style_ext
648 981
649Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_STYLE_EXT> and returns the result. 982Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_STYLE_EXT> and returns the result.
650 983
654 987
655=head2 THE OpenCL::Context CLASS 988=head2 THE OpenCL::Context CLASS
656 989
657=over 4 990=over 4
658 991
992=item $prog = $ctx->build_program ($program, $options = "")
993
994This convenience function tries to build the program on all devices in
995the context. If the build fails, then the function will C<croak> with the
996build log. Otherwise ti returns the program object.
997
998The C<$program> can either be a C<OpenCL::Program> object or a string
999containing the program. In the latter case, a program objetc will be
1000created automatically.
1001
1002=cut
1003
1004sub OpenCL::Context::build_program {
1005 my ($self, $prog, $options) = @_;
1006
1007 require Carp;
1008
1009 $prog = $self->program_with_source ($prog)
1010 unless ref $prog;
1011
1012 # we build separately per device so we instantly know which one failed
1013 for my $dev ($self->devices) {
1014 eval { $prog->build ([$dev], $options); 1 }
1015 or Carp::croak ("Building OpenCL program for device '" . $dev->name . "' failed:\n"
1016 . $prog->build_log ($dev));
1017 }
1018
1019 $prog
1020}
1021
659=item $queue = $ctx->queue ($device, $properties) 1022=item $queue = $ctx->queue ($device, $properties)
660 1023
661Create a new OpenCL::Queue object from the context and the given device. 1024Create a new OpenCL::Queue object from the context and the given device.
662 1025
663L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html> 1026L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html>
1027
1028Example: create an out-of-order queue.
1029
1030 $queue = $ctx->queue ($device, OpenCL::QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE);
664 1031
665=item $ev = $ctx->user_event 1032=item $ev = $ctx->user_event
666 1033
667Creates a new OpenCL::UserEvent object. 1034Creates a new OpenCL::UserEvent object.
668 1035
678=item $buf = $ctx->buffer_sv ($flags, $data) 1045=item $buf = $ctx->buffer_sv ($flags, $data)
679 1046
680Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and 1047Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and
681initialise it with the given data values. 1048initialise it with the given data values.
682 1049
1050=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)
1051
1052Creates a new OpenCL::Image object and optionally initialises it with
1053the given data values.
1054
1055L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html>
1056
683=item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $row_pitch = 0, $data = undef) 1057=item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $row_pitch = 0, $data = undef)
684 1058
685Creates a new OpenCL::Image2D object and optionally initialises it with 1059Creates a new OpenCL::Image2D object and optionally initialises it with
686the given data values. 1060the given data values.
687 1061
691 1065
692Creates a new OpenCL::Image3D object and optionally initialises it with 1066Creates a new OpenCL::Image3D object and optionally initialises it with
693the given data values. 1067the given data values.
694 1068
695L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage3D.html> 1069L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage3D.html>
1070
1071=item $buffer = $ctx->gl_buffer ($flags, $bufobj)
1072
1073Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object that refers to the given
1074OpenGL buffer object.
1075
1076http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLBuffer.html
1077
1078=item $img = $ctx->gl_texture ($flags, $target, $miplevel, $texture)
1079
1080Creates a new OpenCL::Image object that refers to the given OpenGL
1081texture object or buffer.
1082
1083http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateFromGLTexture.html
1084
1085=item $img = $ctx->gl_texture2d ($flags, $target, $miplevel, $texture)
1086
1087Creates a new OpenCL::Image2D object that refers to the given OpenGL
10882D texture object.
1089
1090http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture2D.html
1091
1092=item $img = $ctx->gl_texture3d ($flags, $target, $miplevel, $texture)
1093
1094Creates a new OpenCL::Image3D object that refers to the given OpenGL
10953D texture object.
1096
1097http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture3D.html
1098
1099=item $ctx->gl_renderbuffer ($flags, $renderbuffer)
1100
1101Creates a new OpenCL::Image2D object that refers to the given OpenGL
1102render buffer.
1103
1104http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLRenderbuffer.html
696 1105
697=item @formats = $ctx->supported_image_formats ($flags, $image_type) 1106=item @formats = $ctx->supported_image_formats ($flags, $image_type)
698 1107
699Returns a list of matching image formats - each format is an arrayref with 1108Returns a list of matching image formats - each format is an arrayref with
700two values, $channel_order and $channel_type, in it. 1109two values, $channel_order and $channel_type, in it.
751for completion, unless the method is called in void context, in which case 1160for completion, unless the method is called in void context, in which case
752no event object is created. 1161no event object is created.
753 1162
754They also allow you to specify any number of other event objects that this 1163They also allow you to specify any number of other event objects that this
755request has to wait for before it starts executing, by simply passing the 1164request has to wait for before it starts executing, by simply passing the
756event objects as extra parameters to the enqueue methods. 1165event objects as extra parameters to the enqueue methods. To simplify
1166program design, this module ignores any C<undef> values in the list of
1167events. This makes it possible to code operations such as this, without
1168having to put a valid event object into C<$event> first:
1169
1170 $event = $queue->enqueue_xxx (..., $event);
757 1171
758Queues execute in-order by default, without any parallelism, so in most 1172Queues execute in-order by default, without any parallelism, so in most
759cases (i.e. you use only one queue) it's not necessary to wait for or 1173cases (i.e. you use only one queue) it's not necessary to wait for or
760create event objects. 1174create event objects, althoguh an our of order queue is often a bit
1175faster.
761 1176
762=over 4 1177=over 4
763 1178
764=item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) 1179=item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...)
765 1180
809 1224
810Yeah. 1225Yeah.
811 1226
812L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. 1227L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>.
813 1228
1229=item $ev = $queue->enqueue_fill_buffer ($mem, $pattern, $offset, $size, ...)
1230
1231Fills the given buffer object with repeated applications of C<$pattern>,
1232starting at C<$offset> for C<$size> octets.
1233
1234L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html>
1235
1236=item $ev = $queue->enqueue_fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...)
1237
1238Fills the given image area with the given rgba colour components. The
1239components are normally floating point values between C<0> and C<1>,
1240except when the image channel data type is a signe dor unsigned
1241unnormalised format, in which case the range is determined by the format.
1242
1243L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html>
1244
814=item $ev = $queue->enqueue_task ($kernel, $wait_events...) 1245=item $ev = $queue->enqueue_task ($kernel, $wait_events...)
815 1246
816L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> 1247L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html>
817 1248
818=item $ev = $queue->enqueue_nd_range_kernel ($kernel, @$global_work_offset, @$global_work_size, @$local_work_size, $wait_events...) 1249=item $ev = $queue->enqueue_nd_range_kernel ($kernel, \@global_work_offset, \@global_work_size, \@local_work_size, $wait_events...)
819 1250
820Enqueues a kernel execution. 1251Enqueues a kernel execution.
821 1252
822@$global_work_size must be specified as a reference to an array of 1253\@global_work_size must be specified as a reference to an array of
823integers specifying the work sizes (element counts). 1254integers specifying the work sizes (element counts).
824 1255
825@$global_work_offset must be either C<undef> (in which case all offsets 1256\@global_work_offset must be either C<undef> (in which case all offsets
826are C<0>), or a reference to an array of work offsets, with the same number 1257are C<0>), or a reference to an array of work offsets, with the same number
827of elements as @$global_work_size. 1258of elements as \@global_work_size.
828 1259
829@$local_work_size must be either C<undef> (in which case the 1260\@local_work_size must be either C<undef> (in which case the
830implementation is supposed to choose good local work sizes), or a 1261implementation is supposed to choose good local work sizes), or a
831reference to an array of local work sizes, with the same number of 1262reference to an array of local work sizes, with the same number of
832elements as @$global_work_size. 1263elements as \@global_work_size.
833 1264
834L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> 1265L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html>
835 1266
836=item $ev = $queue->enqueue_marker 1267=item $ev = $queue->enqueue_acquire_gl_objects ([object, ...], $wait_events...)
837 1268
1269Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired
1270for subsequent OpenCL usage.
1271
838L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueMarker.html> 1272L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html>
1273
1274=item $ev = $queue->enqueue_release_gl_objects ([object, ...], $wait_events...)
1275
1276Enqueues a list (an array-ref of OpenCL::Memory objects) to be released
1277for subsequent OpenGL usage.
1278
1279L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html>
839 1280
840=item $ev = $queue->enqueue_wait_for_events ($wait_events...) 1281=item $ev = $queue->enqueue_wait_for_events ($wait_events...)
841 1282
842L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> 1283L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html>
843 1284
844=item $queue->enqueue_barrier 1285=item $ev = $queue->enqueue_marker ($wait_events...)
845 1286
1287L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html>
1288
1289=item $ev = $queue->enqueue_barrier ($wait_events...)
1290
846L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueBarrier.html> 1291L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html>
847 1292
848=item $queue->flush 1293=item $queue->flush
849 1294
850L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html> 1295L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html>
851 1296
931=item $int = $mem->offset 1376=item $int = $mem->offset
932 1377
933Calls C<clGetMemObjectInfo> with C<CL_MEM_OFFSET> and returns the result. 1378Calls C<clGetMemObjectInfo> with C<CL_MEM_OFFSET> and returns the result.
934 1379
935=for gengetinfo end mem 1380=for gengetinfo end mem
1381
1382=item ($type, $name) = $mem->gl_object_info
1383
1384Returns the OpenGL object type (e.g. OpenCL::GL_OBJECT_TEXTURE2D) and the
1385object "name" (e.g. the texture name) used to create this memory object.
1386
1387L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetGLObjectInfo.html>
936 1388
937=back 1389=back
938 1390
939=head2 THE OpenCL::Buffer CLASS 1391=head2 THE OpenCL::Buffer CLASS
940 1392
959 1411
960=back 1412=back
961 1413
962=head2 THE OpenCL::Image CLASS 1414=head2 THE OpenCL::Image CLASS
963 1415
964This is the superclass of all image objects - OpenCL::Image2D and OpenCL::Image3D. 1416This is the superclass of all image objects - OpenCL::Image1D,
1417OpenCL::Image1DArray, OpenCL::Image1DBuffer, OpenCL::Image2D,
1418OpenCL::Image2DArray and OpenCL::Image3D.
965 1419
966=over 4 1420=over 4
967 1421
968=item $packed_value = $ev->image_info ($name) 1422=item $packed_value = $image->image_info ($name)
969 1423
970See C<< $platform->info >> for details. 1424See C<< $platform->info >> for details.
971 1425
972The reason this method is not called C<info> is that there already is an 1426The reason this method is not called C<info> is that there already is an
973C<< ->info >> method inherited from C<OpenCL::Memory>. 1427C<< ->info >> method inherited from C<OpenCL::Memory>.
974 1428
975L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html> 1429L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html>
976 1430
1431=item ($channel_order, $channel_data_type) = $image->format
1432
1433Returns the channel order and type used to create the image by calling
1434C<clGetImageInfo> with C<CL_IMAGE_FORMAT>.
1435
977=for gengetinfo begin image 1436=for gengetinfo begin image
978 1437
979=item $int = $image->element_size 1438=item $int = $image->element_size
980 1439
981Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result. 1440Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result.
1000 1459
1001Calls C<clGetImageInfo> with C<CL_IMAGE_DEPTH> and returns the result. 1460Calls C<clGetImageInfo> with C<CL_IMAGE_DEPTH> and returns the result.
1002 1461
1003=for gengetinfo end image 1462=for gengetinfo end image
1004 1463
1464=for gengetinfo begin gl_texture
1465
1466=item $GLenum = $gl_texture->target
1467
1468Calls C<clGetGLTextureInfo> with C<CL_GL_TEXTURE_TARGET> and returns the result.
1469
1470=item $GLint = $gl_texture->gl_mipmap_level
1471
1472Calls C<clGetGLTextureInfo> with C<CL_GL_MIPMAP_LEVEL> and returns the result.
1473
1474=for gengetinfo end gl_texture
1475
1005=back 1476=back
1006 1477
1007=head2 THE OpenCL::Sampler CLASS 1478=head2 THE OpenCL::Sampler CLASS
1008 1479
1009=over 4 1480=over 4
1042 1513
1043=head2 THE OpenCL::Program CLASS 1514=head2 THE OpenCL::Program CLASS
1044 1515
1045=over 4 1516=over 4
1046 1517
1047=item $program->build ($device, $options = "") 1518=item $program->build (\@devices = undef, $options = "", $cb->($program) = undef)
1048 1519
1049Tries to build the program with the givne options. 1520Tries to build the program with the given options. See also the
1521C<$ctx->build> convenience function.
1522
1523If a callback is specified, then it will be called when compilation is
1524finished. Note that many OpenCL implementations block your program while
1525compiling whether you use a callback or not. See C<build_async> if you
1526want to make sure the build is done in the background.
1527
1528Note that some OpenCL implementations atc up badly, and don't call the
1529callback in some error cases (but call it in others). This implementation
1530assumes the callback will always be called, and leaks memory if this is
1531not so. So best make sure you don't pass in invalid values.
1050 1532
1051L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> 1533L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html>
1534
1535=item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef)
1536
1537Similar to C<< ->build >>, except it starts a thread, and never fails (you
1538need to check the compilation status form the callback, or by polling).
1052 1539
1053=item $packed_value = $program->build_info ($device, $name) 1540=item $packed_value = $program->build_info ($device, $name)
1054 1541
1055Similar to C<< $platform->info >>, but returns build info for a previous 1542Similar to C<< $platform->info >>, but returns build info for a previous
1056build attempt for the given device. 1543build attempt for the given device.
1061 1548
1062Creates an OpenCL::Kernel object out of the named C<__kernel> function in 1549Creates an OpenCL::Kernel object out of the named C<__kernel> function in
1063the program. 1550the program.
1064 1551
1065L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html> 1552L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html>
1553
1554=item @kernels = $program->kernels_in_program
1555
1556Returns all kernels successfully compiled for all devices in program.
1557
1558http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernelsInProgram.html
1066 1559
1067=for gengetinfo begin program_build 1560=for gengetinfo begin program_build
1068 1561
1069=item $build_status = $program->build_status ($device) 1562=item $build_status = $program->build_status ($device)
1070 1563
1192 1685
1193Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result. 1686Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result.
1194 1687
1195=for gengetinfo end kernel_work_group 1688=for gengetinfo end kernel_work_group
1196 1689
1197=item $kernel->set_TYPE ($index, $value) 1690=item $kernel->set_TYPE ($index, $value)
1198 1691
1692=item $kernel->set_char ($index, $value)
1693
1694=item $kernel->set_uchar ($index, $value)
1695
1696=item $kernel->set_short ($index, $value)
1697
1698=item $kernel->set_ushort ($index, $value)
1699
1700=item $kernel->set_int ($index, $value)
1701
1702=item $kernel->set_uint ($index, $value)
1703
1704=item $kernel->set_long ($index, $value)
1705
1706=item $kernel->set_ulong ($index, $value)
1707
1708=item $kernel->set_half ($index, $value)
1709
1710=item $kernel->set_float ($index, $value)
1711
1712=item $kernel->set_double ($index, $value)
1713
1714=item $kernel->set_memory ($index, $value)
1715
1716=item $kernel->set_buffer ($index, $value)
1717
1718=item $kernel->set_image ($index, $value)
1719
1720=item $kernel->set_sampler ($index, $value)
1721
1722=item $kernel->set_local ($index, $value)
1723
1724=item $kernel->set_event ($index, $value)
1725
1199This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>. 1726This is a family of methods to set the kernel argument with the number
1200 1727C<$index> to the give C<$value>.
1201TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>,
1202C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>,
1203C<image2d>, C<image3d>, C<sampler> or C<event>.
1204 1728
1205Chars and integers (including the half type) are specified as integers, 1729Chars and integers (including the half type) are specified as integers,
1206float and double as floating point values, memory/buffer/image2d/image3d 1730float and double as floating point values, memory/buffer/image must be
1207must be an object of that type or C<undef>, and sampler and event must be 1731an object of that type or C<undef>, local-memory arguments are set by
1208objects of that type. 1732specifying the size, and sampler and event must be objects of that type.
1733
1734Note that C<set_memory> works for all memory objects (all types of buffers
1735and images) - the main purpose of the more specific C<set_TYPE> functions
1736is type checking.
1737
1738Setting an argument for a kernel does NOT keep a reference to the object -
1739for example, if you set an argument to some image object, free the image,
1740and call the kernel, you will run into undefined behaviour.
1209 1741
1210L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html> 1742L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html>
1211 1743
1212=back 1744=back
1213 1745
1222 1754
1223Waits for the event to complete. 1755Waits for the event to complete.
1224 1756
1225L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> 1757L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>
1226 1758
1759=item $ev->cb ($exec_callback_type, $callback->($event, $event_command_exec_status))
1760
1761Adds a callback to the callback stack for the given event type. There is
1762no way to remove a callback again.
1763
1764L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetEventCallback.html>
1765
1227=item $packed_value = $ev->info ($name) 1766=item $packed_value = $ev->info ($name)
1228 1767
1229See C<< $platform->info >> for details. 1768See C<< $platform->info >> for details.
1230 1769
1231L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html> 1770L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html>
1291 1830
1292=over 4 1831=over 4
1293 1832
1294=item $ev->set_status ($execution_status) 1833=item $ev->set_status ($execution_status)
1295 1834
1835Sets the execution status of the user event. Can only be called once,
1836either with OpenCL::COMPLETE or a negative number as status.
1837
1296L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html> 1838L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html>
1297 1839
1298=back 1840=back
1299 1841
1300=cut 1842=cut
1301
1302package OpenCL;
1303
1304use common::sense;
1305
1306BEGIN {
1307 our $VERSION = '0.91';
1308
1309 require XSLoader;
1310 XSLoader::load (__PACKAGE__, $VERSION);
1311
1312 @OpenCL::Buffer::ISA =
1313 @OpenCL::Image::ISA = OpenCL::Memory::;
1314
1315 @OpenCL::BufferObj::ISA = OpenCL::Buffer::;
1316
1317 @OpenCL::Image2D::ISA =
1318 @OpenCL::Image3D::ISA = OpenCL::Image::;
1319
1320 @OpenCL::UserEvent::ISA = OpenCL::Event::;
1321}
1322 1843
13231; 18441;
1324 1845
1325=head1 AUTHOR 1846=head1 AUTHOR
1326 1847

Diff Legend

Removed lines
+ Added lines
< Changed lines
> Changed lines