… | |
… | |
43 | |
43 | |
44 | OpenCL::Event objects are used to signal when something is complete. |
44 | OpenCL::Event objects are used to signal when something is complete. |
45 | |
45 | |
46 | =head2 HELPFUL RESOURCES |
46 | =head2 HELPFUL RESOURCES |
47 | |
47 | |
48 | The OpenCL spec used to develop this module (1.2 spec was available, but |
48 | The OpenCL specs used to develop this module: |
49 | no implementation was available to me :). |
|
|
50 | |
49 | |
51 | http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf |
50 | http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf |
|
|
51 | http://www.khronos.org/registry/cl/specs/opencl-1.2.pdf |
|
|
52 | http://www.khronos.org/registry/cl/specs/opencl-1.2-extensions.pdf |
52 | |
53 | |
53 | OpenCL manpages: |
54 | OpenCL manpages: |
54 | |
55 | |
55 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/ |
56 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/ |
|
|
57 | http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/ |
56 | |
58 | |
57 | If you are into UML class diagrams, the following diagram might help - if |
59 | If you are into UML class diagrams, the following diagram might help - if |
58 | not, it will be mildly cobfusing: |
60 | not, it will be mildly confusing (also, the class hierarchy of this module |
|
|
61 | is much more fine-grained): |
59 | |
62 | |
60 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/classDiagram.html |
63 | http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/classDiagram.html |
61 | |
64 | |
62 | Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it |
65 | Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it |
63 | is, but at least it's free of charge: |
66 | is, but at least it's free of charge: |
64 | |
67 | |
65 | http://developer.amd.com/zones/OpenCLZone/courses/Documents/Introduction_to_OpenCL_Programming%20Training_Guide%20%28201005%29.pdf |
68 | http://developer.amd.com/zones/OpenCLZone/courses/Documents/Introduction_to_OpenCL_Programming%20Training_Guide%20%28201005%29.pdf |
… | |
… | |
138 | =head2 Create a buffer with some predefined data, read it back synchronously, |
141 | =head2 Create a buffer with some predefined data, read it back synchronously, |
139 | then asynchronously. |
142 | then asynchronously. |
140 | |
143 | |
141 | my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); |
144 | my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); |
142 | |
145 | |
143 | $queue->enqueue_read_buffer ($buf, 1, 1, 3, my $data); |
146 | $queue->read_buffer ($buf, 1, 1, 3, my $data); |
144 | print "$data\n"; |
147 | print "$data\n"; |
145 | |
148 | |
146 | my $ev = $queue->enqueue_read_buffer ($buf, 0, 1, 3, my $data); |
149 | my $ev = $queue->read_buffer ($buf, 0, 1, 3, my $data); |
147 | $ev->wait; |
150 | $ev->wait; |
148 | print "$data\n"; # prints "elm" |
151 | print "$data\n"; # prints "elm" |
149 | |
152 | |
150 | =head2 Create and build a program, then create a kernel out of one of its |
153 | =head2 Create and build a program, then create a kernel out of one of its |
151 | functions. |
154 | functions. |
… | |
… | |
157 | $id = get_global_id (0); |
160 | $id = get_global_id (0); |
158 | output [id] = input [id] * input [id]; |
161 | output [id] = input [id] * input [id]; |
159 | } |
162 | } |
160 | '; |
163 | '; |
161 | |
164 | |
162 | my $prog = $ctx->program_with_source ($src); |
165 | my $prog = $ctx->build_program ($src); |
163 | |
|
|
164 | # build croaks on compile errors, so catch it and print the compile errors |
|
|
165 | eval { $prog->build ($dev); 1 } |
|
|
166 | or die $prog->build_log; |
|
|
167 | |
|
|
168 | my $kernel = $prog->kernel ("squareit"); |
166 | my $kernel = $prog->kernel ("squareit"); |
169 | |
167 | |
170 | =head2 Create some input and output float buffers, then call the |
168 | =head2 Create some input and output float buffers, then call the |
171 | 'squareit' kernel on them. |
169 | 'squareit' kernel on them. |
172 | |
170 | |
… | |
… | |
176 | # set buffer |
174 | # set buffer |
177 | $kernel->set_buffer (0, $input); |
175 | $kernel->set_buffer (0, $input); |
178 | $kernel->set_buffer (1, $output); |
176 | $kernel->set_buffer (1, $output); |
179 | |
177 | |
180 | # execute it for all 4 numbers |
178 | # execute it for all 4 numbers |
181 | $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
179 | $queue->nd_range_kernel ($kernel, undef, [4], undef); |
182 | |
180 | |
183 | # enqueue a synchronous read |
181 | # enqueue a synchronous read |
184 | $queue->enqueue_read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
182 | $queue->read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
185 | |
183 | |
186 | # print the results: |
184 | # print the results: |
187 | printf "%s\n", join ", ", unpack "f*", $data; |
185 | printf "%s\n", join ", ", unpack "f*", $data; |
188 | |
186 | |
189 | =head2 The same enqueue operations as before, but assuming an out-of-order queue, |
187 | =head2 The same enqueue operations as before, but assuming an out-of-order queue, |
190 | showing off barriers. |
188 | showing off barriers. |
191 | |
189 | |
192 | # execute it for all 4 numbers |
190 | # execute it for all 4 numbers |
193 | $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
191 | $queue->nd_range_kernel ($kernel, undef, [4], undef); |
194 | |
192 | |
195 | # enqueue a barrier to ensure in-order execution |
193 | # enqueue a barrier to ensure in-order execution |
196 | $queue->enqueue_barrier; |
194 | $queue->barrier; |
197 | |
195 | |
198 | # enqueue an async read |
196 | # enqueue an async read |
199 | $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
197 | $queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
200 | |
198 | |
201 | # wait for all requests to finish |
199 | # wait for all requests to finish |
202 | $queue->finish; |
200 | $queue->finish; |
203 | |
201 | |
204 | =head2 The same enqueue operations as before, but assuming an out-of-order queue, |
202 | =head2 The same enqueue operations as before, but assuming an out-of-order queue, |
205 | showing off event objects and wait lists. |
203 | showing off event objects and wait lists. |
206 | |
204 | |
207 | # execute it for all 4 numbers |
205 | # execute it for all 4 numbers |
208 | my $ev = $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
206 | my $ev = $queue->nd_range_kernel ($kernel, undef, [4], undef); |
209 | |
207 | |
210 | # enqueue an async read |
208 | # enqueue an async read |
211 | $ev = $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev); |
209 | $ev = $queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev); |
212 | |
210 | |
213 | # wait for the last event to complete |
211 | # wait for the last event to complete |
214 | $ev->wait; |
212 | $ev->wait; |
215 | |
213 | |
216 | =head2 Use the OpenGL module to share a texture between OpenCL and OpenGL and draw some julia |
214 | =head2 Use the OpenGL module to share a texture between OpenCL and OpenGL and draw some julia |
… | |
… | |
260 | m.x = fabs (fmod (m.x + time * 0.05f, 4.f)) - 2.f; |
258 | m.x = fabs (fmod (m.x + time * 0.05f, 4.f)) - 2.f; |
261 | |
259 | |
262 | float2 z = m; |
260 | float2 z = m; |
263 | float2 c = (float2)(sin (time * 0.05005), cos (time * 0.06001)); |
261 | float2 c = (float2)(sin (time * 0.05005), cos (time * 0.06001)); |
264 | |
262 | |
265 | for (int i = 0; i < 100 && dot (z, z) < 4.f; ++i) |
263 | for (int i = 0; i < 25 && dot (z, z) < 4.f; ++i) |
266 | z = (float2)(z.x * z.x - z.y * z.y, 2.f * z.x * z.y) + c; |
264 | z = (float2)(z.x * z.x - z.y * z.y, 2.f * z.x * z.y) + c; |
267 | |
265 | |
268 | float3 colour = (float3)(z.x, z.y, z.x * z.y); |
266 | float3 colour = (float3)(z.x, z.y, z.x * z.y); |
269 | write_imagef (img, (int2)(get_global_id (0), get_global_id (1)), (float4)(colour * p.x * p.x, 1.)); |
267 | write_imagef (img, (int2)(get_global_id (0), get_global_id (1)), (float4)(colour * p.x * p.x, 1.)); |
270 | } |
268 | } |
271 | EOF |
269 | EOF |
|
|
270 | |
272 | my $prog = $ctx->program_with_source ($src); |
271 | my $prog = $ctx->build_program ($src); |
273 | eval { $prog->build ($dev); 1 } |
|
|
274 | or die $prog->build_log ($dev); |
|
|
275 | |
|
|
276 | my $kernel = $prog->kernel ("juliatunnel"); |
272 | my $kernel = $prog->kernel ("juliatunnel"); |
277 | |
273 | |
278 | # program compiled, kernel ready, now draw and loop |
274 | # program compiled, kernel ready, now draw and loop |
279 | |
275 | |
280 | for (my $time; ; ++$time) { |
276 | for (my $time; ; ++$time) { |
281 | # acquire objects from opengl |
277 | # acquire objects from opengl |
282 | $queue->enqueue_acquire_gl_objects ([$tex]); |
278 | $queue->acquire_gl_objects ([$tex]); |
283 | |
279 | |
284 | # configure and run our kernel |
280 | # configure and run our kernel |
285 | $kernel->set_image2d (0, $tex); |
281 | $kernel->set_image2d (0, $tex); |
286 | $kernel->set_float (1, $time); |
282 | $kernel->set_float (1, $time); |
287 | $queue->enqueue_nd_range_kernel ($kernel, undef, [256, 256], undef); |
283 | $queue->nd_range_kernel ($kernel, undef, [256, 256], undef); |
288 | |
284 | |
289 | # release objects to opengl again |
285 | # release objects to opengl again |
290 | $queue->enqueue_release_gl_objects ([$tex]); |
286 | $queue->release_gl_objects ([$tex]); |
291 | |
287 | |
292 | # wait |
288 | # wait |
293 | $queue->flush; |
289 | $queue->finish; |
294 | |
290 | |
295 | # now draw the texture, the defaults should be all right |
291 | # now draw the texture, the defaults should be all right |
296 | glTexParameterf GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST; |
292 | glTexParameterf GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST; |
297 | |
293 | |
298 | glEnable GL_TEXTURE_2D; |
294 | glEnable GL_TEXTURE_2D; |
… | |
… | |
336 | =item * Structures are often specified by flattening out their components |
332 | =item * Structures are often specified by flattening out their components |
337 | as with short vectors, and returned as arrayrefs. |
333 | as with short vectors, and returned as arrayrefs. |
338 | |
334 | |
339 | =item * When enqueuing commands, the wait list is specified by adding |
335 | =item * When enqueuing commands, the wait list is specified by adding |
340 | extra arguments to the function - anywhere a C<$wait_events...> argument |
336 | extra arguments to the function - anywhere a C<$wait_events...> argument |
341 | is documented this can be any number of event objects. |
337 | is documented this can be any number of event objects. As an extsnion |
|
|
338 | implemented by this module, C<undef> values will be ignored in the event |
|
|
339 | list. |
342 | |
340 | |
343 | =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 |
344 | context, no event is created. In all other contexts an event is returned |
342 | context, no event is created. In all other contexts an event is returned |
345 | by the method. |
343 | by the method. |
346 | |
344 | |
… | |
… | |
381 | |
379 | |
382 | For this to work, the OpenGL library must be loaded, a GLX context must |
380 | For this to work, the OpenGL library must be loaded, a GLX context must |
383 | have been created and be made current, and C<dlsym> must be available and |
381 | have been created and be made current, and C<dlsym> must be available and |
384 | capable of finding the function via C<RTLD_DEFAULT>. |
382 | capable of finding the function via C<RTLD_DEFAULT>. |
385 | |
383 | |
|
|
384 | =head2 EVENT SYSTEM |
|
|
385 | |
|
|
386 | OpenCL can generate a number of (potentially) asynchronous events, for |
|
|
387 | example, after compiling a program, to signal a context-related error or, |
|
|
388 | perhaps most important, to signal completion of queued jobs (by setting |
|
|
389 | callbacks on OpenCL::Event objects). |
|
|
390 | |
|
|
391 | To facilitate this, this module maintains an event queue - each |
|
|
392 | time an asynchronous event happens, it is queued, and perl will be |
|
|
393 | interrupted. This is implemented via the L<Async::Interrupt> module. In |
|
|
394 | addition, this module has L<AnyEvent> support, so it can seamlessly |
|
|
395 | integrate itself into many event loops. |
|
|
396 | |
|
|
397 | Since this module is a bit hard to understand, here are some case examples: |
|
|
398 | |
|
|
399 | =head3 Don't use callbacks. |
|
|
400 | |
|
|
401 | When your program never uses any callbacks, then there will never be any |
|
|
402 | notifications you need to take care of, and therefore no need to worry |
|
|
403 | about all this. |
|
|
404 | |
|
|
405 | You can achieve a great deal by explicitly waiting for events, or using |
|
|
406 | barriers and flush calls. In many programs, there is no need at all to |
|
|
407 | tinker with asynchronous events. |
|
|
408 | |
|
|
409 | =head3 Use AnyEvent |
|
|
410 | |
|
|
411 | This module automatically registers a watcher that invokes all outstanding |
|
|
412 | event callbacks when AnyEvent is initialised (and block asynchronous |
|
|
413 | interruptions). Using this mode of operations is the safest and most |
|
|
414 | recommended one. |
|
|
415 | |
|
|
416 | To use this, simply use AnyEvent and this module normally, make sure you |
|
|
417 | have 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->marker; |
|
|
426 | $e->cb (sub { |
|
|
427 | warn "opencl is finished\n"; |
|
|
428 | }) |
|
|
429 | |
|
|
430 | main Gtk2; |
|
|
431 | |
|
|
432 | Note that this module will not initialise AnyEvent for you. Before |
|
|
433 | AnyEvent is initialised, the module will asynchronously interrupt perl |
|
|
434 | instead. To avoid any surprises, it's best to explicitly initialise |
|
|
435 | AnyEvent. |
|
|
436 | |
|
|
437 | You can temporarily enable asynchronous interruptions (see next paragraph) |
|
|
438 | by calling C<$OpenCL::INTERRUPT->unblock> and disable them again by |
|
|
439 | calling C<$OpenCL::INTERRUPT->block>. |
|
|
440 | |
|
|
441 | =head3 Let yourself be interrupted at any time |
|
|
442 | |
|
|
443 | This mode is the default unless AnyEvent is loaded and initialised. In |
|
|
444 | this mode, OpenCL asynchronously interrupts a running perl program. The |
|
|
445 | emphasis is on both I<asynchronously> and I<running> here. |
|
|
446 | |
|
|
447 | Asynchronously means that perl might execute your callbacks at any |
|
|
448 | time. For example, in the following code (I<THAT YOU SHOULD NOT COPY>), |
|
|
449 | the C<until> loop following the marker call will be interrupted by the |
|
|
450 | callback: |
|
|
451 | |
|
|
452 | my $e = $queue->marker; |
|
|
453 | my $flag; |
|
|
454 | $e->cb (sub { $flag = 1 }); |
|
|
455 | 1 until $flag; |
|
|
456 | # $flag is now 1 |
|
|
457 | |
|
|
458 | The reason why you shouldn't blindly copy the above code is that |
|
|
459 | busy waiting is a really really bad thing, and really really bad for |
|
|
460 | performance. |
|
|
461 | |
|
|
462 | While at first this asynchronous business might look exciting, it can be |
|
|
463 | really hard, because you need to be prepared for the callback code to be |
|
|
464 | executed at any time, which limits the amount of things the callback code |
|
|
465 | can do safely. |
|
|
466 | |
|
|
467 | This can be mitigated somewhat by using C<< |
|
|
468 | $OpenCL::INTERRUPT->scope_block >> (see the L<Async::Interrupt> |
|
|
469 | documentation for details). |
|
|
470 | |
|
|
471 | The other problem is that your program must be actively I<running> to be |
|
|
472 | interrupted. When you calculate stuff, your program is running. When you |
|
|
473 | hang in some C functions or other block execution (by calling C<sleep>, |
|
|
474 | C<select>, running an event loop and so on), your program is waiting, not |
|
|
475 | running. |
|
|
476 | |
|
|
477 | One way around that would be to attach a read watcher to your event loop, |
|
|
478 | listening for events on C<< $OpenCL::INTERRUPT->pipe_fileno >>, using a |
|
|
479 | dummy callback (C<sub { }>) to temporarily execute some perl code. |
|
|
480 | |
|
|
481 | That is then awfully close to using the built-in AnyEvent support above, |
|
|
482 | though, so consider that one instead. |
|
|
483 | |
|
|
484 | =head3 Be creative |
|
|
485 | |
|
|
486 | OpenCL exports the L<Async::Interrupt> object it uses in the global |
|
|
487 | variable C<$OpenCL::INTERRUPT>. You can configure it in any way you like. |
|
|
488 | |
|
|
489 | So if you want to feel like a real pro, err, wait, if you feel no risk |
|
|
490 | menas no fun, you can experiment by implementing your own mode of |
|
|
491 | operations. |
|
|
492 | |
|
|
493 | =cut |
|
|
494 | |
|
|
495 | package OpenCL; |
|
|
496 | |
|
|
497 | use common::sense; |
|
|
498 | use Async::Interrupt (); |
|
|
499 | |
|
|
500 | our $POLL_FUNC; # set by XS |
|
|
501 | |
|
|
502 | BEGIN { |
|
|
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 | |
386 | =head2 THE OpenCL PACKAGE |
533 | =head2 THE OpenCL PACKAGE |
387 | |
534 | |
388 | =over 4 |
535 | =over 4 |
389 | |
536 | |
390 | =item $int = OpenCL::errno |
537 | =item $int = OpenCL::errno |
… | |
… | |
408 | |
555 | |
409 | Returns all available OpenCL::Platform objects. |
556 | Returns all available OpenCL::Platform objects. |
410 | |
557 | |
411 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html> |
558 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html> |
412 | |
559 | |
413 | =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 |
414 | |
561 | |
415 | Tries to create a context from a default device and platform - never worked for me. |
562 | Tries to create a context from a default device and platform type - never worked for me. |
416 | |
563 | |
417 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
564 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
418 | |
565 | |
|
|
566 | =item $ctx = OpenCL::context $properties, \@devices, $callback->($err, $pvt) = $print_stderr) |
|
|
567 | |
|
|
568 | Create a new OpenCL::Context object using the given device object(s). This |
|
|
569 | function isn't implemented yet, use C<< $platform->context >> instead. |
|
|
570 | |
|
|
571 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> |
|
|
572 | |
419 | =item OpenCL::wait_for_events $wait_events... |
573 | =item OpenCL::wait_for_events $wait_events... |
420 | |
574 | |
421 | Waits for all events to complete. |
575 | Waits for all events to complete. |
422 | |
576 | |
423 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
577 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
424 | |
578 | |
|
|
579 | =item OpenCL::poll |
|
|
580 | |
|
|
581 | Checks if there are any outstanding events (see L<EVENT SYSTEM>) and |
|
|
582 | invokes their callbacks. |
|
|
583 | |
|
|
584 | =item $OpenCL::INTERRUPT |
|
|
585 | |
|
|
586 | The L<Async::Interrupt> object used to signal asynchronous events (see |
|
|
587 | L<EVENT SYSTEM>). |
|
|
588 | |
|
|
589 | =cut |
|
|
590 | |
|
|
591 | our $INTERRUPT = new Async::Interrupt c_cb => [$POLL_FUNC, 0]; |
|
|
592 | |
|
|
593 | &_eq_initialise ($INTERRUPT->signal_func); |
|
|
594 | |
|
|
595 | =item $OpenCL::WATCHER |
|
|
596 | |
|
|
597 | The L<AnyEvent> watcher object used to watch for asynchronous events (see |
|
|
598 | L<EVENT SYSTEM>). This variable is C<undef> until L<AnyEvent> has been |
|
|
599 | loaded I<and> initialised (e.g. by calling C<AnyEvent::detect>). |
|
|
600 | |
|
|
601 | =cut |
|
|
602 | |
|
|
603 | our $WATCHER; |
|
|
604 | |
|
|
605 | sub _init_anyevent { |
|
|
606 | $INTERRUPT->block; |
|
|
607 | $WATCHER = AE::io ($INTERRUPT->pipe_fileno, 0, sub { $INTERRUPT->handle }); |
|
|
608 | } |
|
|
609 | |
|
|
610 | if (defined $AnyEvent::MODEL) { |
|
|
611 | _init_anyevent; |
|
|
612 | } else { |
|
|
613 | push @AnyEvent::post_detect, \&_init_anyevent; |
|
|
614 | } |
|
|
615 | |
425 | =back |
616 | =back |
426 | |
617 | |
|
|
618 | =head2 THE OpenCL::Object CLASS |
|
|
619 | |
|
|
620 | This is the base class for all objects in the OpenCL module. The only |
|
|
621 | method it implements is the C<id> method, which is only useful if you want |
|
|
622 | to interface to OpenCL on the C level. |
|
|
623 | |
|
|
624 | =over 4 |
|
|
625 | |
|
|
626 | =item $iv = $obj->id |
|
|
627 | |
|
|
628 | OpenCL objects are represented by pointers or integers on the C level. If |
|
|
629 | you want to interface to an OpenCL object directly on the C level, then |
|
|
630 | you need this value, which is returned by this method. You should use an |
|
|
631 | C<IV> type in your code and cast that to the correct type. |
|
|
632 | |
|
|
633 | =cut |
|
|
634 | |
|
|
635 | sub OpenCL::Object::id { |
|
|
636 | ref $_[0] eq "SCALAR" |
|
|
637 | ? ${ $_[0] } |
|
|
638 | : $_[0][0] |
|
|
639 | } |
|
|
640 | |
|
|
641 | =back |
|
|
642 | |
427 | =head2 THE OpenCL::Platform CLASS |
643 | =head2 THE OpenCL::Platform CLASS |
428 | |
644 | |
429 | =over 4 |
645 | =over 4 |
430 | |
646 | |
431 | =item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL) |
647 | =item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL) |
432 | |
648 | |
433 | Returns a list of matching OpenCL::Device objects. |
649 | Returns a list of matching OpenCL::Device objects. |
434 | |
650 | |
435 | =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) |
436 | |
652 | |
437 | Tries to create a context. Never worked for me, and you need devices explicitly anyway. |
653 | Tries to create a context. Never worked for me, and you need devices explicitly anyway. |
438 | |
654 | |
439 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
655 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
440 | |
656 | |
441 | =item $ctx = $platform->context ($properties = undef, @$devices, $notify = undef) |
657 | =item $ctx = $platform->context ($properties, \@devices, $callback->($err, $pvt) = $print_stderr) |
442 | |
658 | |
443 | Create a new OpenCL::Context object using the given device object(s)- a |
659 | Create a new OpenCL::Context object using the given device object(s)- a |
444 | CL_CONTEXT_PLATFORM property is supplied automatically. |
660 | CL_CONTEXT_PLATFORM property is supplied automatically. |
445 | |
661 | |
446 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> |
662 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> |
… | |
… | |
454 | It's best to avoid this method and use one of the following convenience |
670 | It's best to avoid this method and use one of the following convenience |
455 | wrappers. |
671 | wrappers. |
456 | |
672 | |
457 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html> |
673 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html> |
458 | |
674 | |
|
|
675 | =item $platform->unload_compiler |
|
|
676 | |
|
|
677 | Attempts to unload the compiler for this platform, for endless |
|
|
678 | profit. Does nothing on OpenCL 1.1. |
|
|
679 | |
|
|
680 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clUnloadPlatformCompiler.html> |
|
|
681 | |
459 | =for gengetinfo begin platform |
682 | =for gengetinfo begin platform |
460 | |
683 | |
461 | =item $string = $platform->profile |
684 | =item $string = $platform->profile |
462 | |
685 | |
463 | Calls C<clGetPlatformInfo> with C<CL_PLATFORM_PROFILE> and returns the result. |
686 | Calls C<clGetPlatformInfo> with C<CL_PLATFORM_PROFILE> and returns the result. |
… | |
… | |
748 | |
971 | |
749 | =item @device_partition_property_exts = $device->affinity_domains_ext |
972 | =item @device_partition_property_exts = $device->affinity_domains_ext |
750 | |
973 | |
751 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_AFFINITY_DOMAINS_EXT> and returns the result. |
974 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_AFFINITY_DOMAINS_EXT> and returns the result. |
752 | |
975 | |
753 | =item $uint = $device->reference_count_ext |
976 | =item $uint = $device->reference_count_ext |
754 | |
977 | |
755 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_REFERENCE_COUNT_EXT > and returns the result. |
978 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_REFERENCE_COUNT_EXT> and returns the result. |
756 | |
979 | |
757 | =item @device_partition_property_exts = $device->partition_style_ext |
980 | =item @device_partition_property_exts = $device->partition_style_ext |
758 | |
981 | |
759 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_STYLE_EXT> and returns the result. |
982 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_STYLE_EXT> and returns the result. |
760 | |
983 | |
… | |
… | |
764 | |
987 | |
765 | =head2 THE OpenCL::Context CLASS |
988 | =head2 THE OpenCL::Context CLASS |
766 | |
989 | |
767 | =over 4 |
990 | =over 4 |
768 | |
991 | |
|
|
992 | =item $prog = $ctx->build_program ($program, $options = "") |
|
|
993 | |
|
|
994 | This convenience function tries to build the program on all devices in |
|
|
995 | the context. If the build fails, then the function will C<croak> with the |
|
|
996 | build log. Otherwise ti returns the program object. |
|
|
997 | |
|
|
998 | The C<$program> can either be a C<OpenCL::Program> object or a string |
|
|
999 | containing the program. In the latter case, a program objetc will be |
|
|
1000 | created automatically. |
|
|
1001 | |
|
|
1002 | =cut |
|
|
1003 | |
|
|
1004 | sub 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 | |
769 | =item $queue = $ctx->queue ($device, $properties) |
1022 | =item $queue = $ctx->queue ($device, $properties) |
770 | |
1023 | |
771 | Create a new OpenCL::Queue object from the context and the given device. |
1024 | Create a new OpenCL::Queue object from the context and the given device. |
772 | |
1025 | |
773 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html> |
1026 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html> |
|
|
1027 | |
|
|
1028 | Example: create an out-of-order queue. |
|
|
1029 | |
|
|
1030 | $queue = $ctx->queue ($device, OpenCL::QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE); |
774 | |
1031 | |
775 | =item $ev = $ctx->user_event |
1032 | =item $ev = $ctx->user_event |
776 | |
1033 | |
777 | Creates a new OpenCL::UserEvent object. |
1034 | Creates a new OpenCL::UserEvent object. |
778 | |
1035 | |
… | |
… | |
788 | =item $buf = $ctx->buffer_sv ($flags, $data) |
1045 | =item $buf = $ctx->buffer_sv ($flags, $data) |
789 | |
1046 | |
790 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and |
1047 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and |
791 | initialise it with the given data values. |
1048 | initialise it with the given data values. |
792 | |
1049 | |
|
|
1050 | =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) |
|
|
1051 | |
|
|
1052 | Creates a new OpenCL::Image object and optionally initialises it with |
|
|
1053 | the given data values. |
|
|
1054 | |
|
|
1055 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html> |
|
|
1056 | |
793 | =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) |
794 | |
1058 | |
795 | Creates a new OpenCL::Image2D object and optionally initialises it with |
1059 | Creates a new OpenCL::Image2D object and optionally initialises it with |
796 | the given data values. |
1060 | the given data values. |
797 | |
1061 | |
… | |
… | |
809 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object that refers to the given |
1073 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object that refers to the given |
810 | OpenGL buffer object. |
1074 | OpenGL buffer object. |
811 | |
1075 | |
812 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLBuffer.html |
1076 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLBuffer.html |
813 | |
1077 | |
|
|
1078 | =item $img = $ctx->gl_texture ($flags, $target, $miplevel, $texture) |
|
|
1079 | |
|
|
1080 | Creates a new OpenCL::Image object that refers to the given OpenGL |
|
|
1081 | texture object or buffer. |
|
|
1082 | |
|
|
1083 | http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateFromGLTexture.html |
|
|
1084 | |
814 | =item $ctx->gl_texture2d ($flags, $target, $miplevel, $texture) |
1085 | =item $img = $ctx->gl_texture2d ($flags, $target, $miplevel, $texture) |
815 | |
1086 | |
816 | Creates a new OpenCL::Image2D object that refers to the given OpenGL |
1087 | Creates a new OpenCL::Image2D object that refers to the given OpenGL |
817 | 2D texture object. |
1088 | 2D texture object. |
818 | |
1089 | |
819 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture2D.html |
1090 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture2D.html |
820 | |
1091 | |
821 | =item $ctx->gl_texture3d ($flags, $target, $miplevel, $texture) |
1092 | =item $img = $ctx->gl_texture3d ($flags, $target, $miplevel, $texture) |
822 | |
1093 | |
823 | Creates a new OpenCL::Image3D object that refers to the given OpenGL |
1094 | Creates a new OpenCL::Image3D object that refers to the given OpenGL |
824 | 3D texture object. |
1095 | 3D texture object. |
825 | |
1096 | |
826 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture3D.html |
1097 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture3D.html |
… | |
… | |
880 | =back |
1151 | =back |
881 | |
1152 | |
882 | =head2 THE OpenCL::Queue CLASS |
1153 | =head2 THE OpenCL::Queue CLASS |
883 | |
1154 | |
884 | An OpenCL::Queue represents an execution queue for OpenCL. You execute |
1155 | An OpenCL::Queue represents an execution queue for OpenCL. You execute |
885 | requests by calling their respective C<enqueue_xxx> method and waitinf for |
1156 | requests by calling their respective method and waiting for it to complete |
886 | it to complete in some way. |
1157 | in some way. |
887 | |
1158 | |
888 | All the enqueue methods return an event object that can be used to wait |
1159 | Most methods that enqueue some request return an event object that can |
889 | for completion, unless the method is called in void context, in which case |
1160 | be used to wait for completion (optionally using a callback), unless |
890 | no event object is created. |
1161 | the method is called in void context, in which case no event object is |
|
|
1162 | created. |
891 | |
1163 | |
892 | They also allow you to specify any number of other event objects that this |
1164 | They also allow you to specify any number of other event objects that this |
893 | request has to wait for before it starts executing, by simply passing the |
1165 | request has to wait for before it starts executing, by simply passing the |
894 | event objects as extra parameters to the enqueue methods. |
1166 | event objects as extra parameters to the enqueue methods. To simplify |
|
|
1167 | program design, this module ignores any C<undef> values in the list of |
|
|
1168 | events. This makes it possible to code operations such as this, without |
|
|
1169 | having to put a valid event object into C<$event> first: |
|
|
1170 | |
|
|
1171 | $event = $queue->xxx (..., $event); |
895 | |
1172 | |
896 | Queues execute in-order by default, without any parallelism, so in most |
1173 | Queues execute in-order by default, without any parallelism, so in most |
897 | cases (i.e. you use only one queue) it's not necessary to wait for or |
1174 | cases (i.e. you use only one queue) it's not necessary to wait for or |
898 | create event objects. |
1175 | create event objects, althoguh an our of order queue is often a bit |
|
|
1176 | faster. |
899 | |
1177 | |
900 | =over 4 |
1178 | =over 4 |
901 | |
1179 | |
902 | =item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) |
1180 | =item $ev = $queue->read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) |
903 | |
1181 | |
904 | Reads data from buffer into the given string. |
1182 | Reads data from buffer into the given string. |
905 | |
1183 | |
906 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html> |
1184 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html> |
907 | |
1185 | |
908 | =item $ev = $queue->enqueue_write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) |
1186 | =item $ev = $queue->write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) |
909 | |
1187 | |
910 | Writes data to buffer from the given string. |
1188 | Writes data to buffer from the given string. |
911 | |
1189 | |
912 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html> |
1190 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html> |
913 | |
1191 | |
914 | =item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) |
1192 | =item $ev = $queue->copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) |
915 | |
1193 | |
916 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> |
1194 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> |
917 | |
1195 | |
918 | =item $ev = $queue->enqueue_read_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) |
1196 | =item $ev = $queue->read_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) |
919 | |
1197 | |
920 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html |
1198 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html |
921 | |
1199 | |
922 | =item $ev = $queue->enqueue_write_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) |
1200 | =item $ev = $queue->write_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) |
923 | |
1201 | |
924 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html |
1202 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html |
925 | |
1203 | |
926 | =item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
1204 | =item $ev = $queue->read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
927 | |
1205 | |
928 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html> |
1206 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html> |
929 | |
1207 | |
930 | =item $ev = $queue->enqueue_copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
1208 | =item $ev = $queue->copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
931 | |
1209 | |
932 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> |
1210 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> |
933 | |
1211 | |
934 | =item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
1212 | =item $ev = $queue->write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
935 | |
1213 | |
936 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> |
1214 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> |
937 | |
1215 | |
938 | =item $ev = $queue->enqueue_copy_image ($src_image, $dst_image, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
1216 | =item $ev = $queue->copy_image ($src_image, $dst_image, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
939 | |
1217 | |
940 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> |
1218 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> |
941 | |
1219 | |
942 | =item $ev = $queue->enqueue_copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...) |
1220 | =item $ev = $queue->copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...) |
943 | |
1221 | |
944 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html> |
1222 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html> |
945 | |
1223 | |
946 | =item $ev = $queue->enqueue_copy_buffer_rect ($src, $dst, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $src_row_pitch, $src_slice_pitch, $dst_row_pitch, $dst_slice_pitch, $wait_event...) |
1224 | =item $ev = $queue->copy_buffer_rect ($src, $dst, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $src_row_pitch, $src_slice_pitch, $dst_row_pitch, $dst_slice_pitch, $wait_event...) |
947 | |
1225 | |
948 | Yeah. |
1226 | Yeah. |
949 | |
1227 | |
950 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
1228 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
951 | |
1229 | |
|
|
1230 | =item $ev = $queue->fill_buffer ($mem, $pattern, $offset, $size, ...) |
|
|
1231 | |
|
|
1232 | Fills the given buffer object with repeated applications of C<$pattern>, |
|
|
1233 | starting at C<$offset> for C<$size> octets. |
|
|
1234 | |
|
|
1235 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html> |
|
|
1236 | |
|
|
1237 | =item $ev = $queue->fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...) |
|
|
1238 | |
|
|
1239 | Fills the given image area with the given rgba colour components. The |
|
|
1240 | components are normally floating point values between C<0> and C<1>, |
|
|
1241 | except when the image channel data type is a signe dor unsigned |
|
|
1242 | unnormalised format, in which case the range is determined by the format. |
|
|
1243 | |
|
|
1244 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html> |
|
|
1245 | |
952 | =item $ev = $queue->enqueue_task ($kernel, $wait_events...) |
1246 | =item $ev = $queue->task ($kernel, $wait_events...) |
953 | |
1247 | |
954 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
1248 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
955 | |
1249 | |
956 | =item $ev = $queue->enqueue_nd_range_kernel ($kernel, @$global_work_offset, @$global_work_size, @$local_work_size, $wait_events...) |
1250 | =item $ev = $queue->nd_range_kernel ($kernel, \@global_work_offset, \@global_work_size, \@local_work_size, $wait_events...) |
957 | |
1251 | |
958 | Enqueues a kernel execution. |
1252 | Enqueues a kernel execution. |
959 | |
1253 | |
960 | @$global_work_size must be specified as a reference to an array of |
1254 | \@global_work_size must be specified as a reference to an array of |
961 | integers specifying the work sizes (element counts). |
1255 | integers specifying the work sizes (element counts). |
962 | |
1256 | |
963 | @$global_work_offset must be either C<undef> (in which case all offsets |
1257 | \@global_work_offset must be either C<undef> (in which case all offsets |
964 | are C<0>), or a reference to an array of work offsets, with the same number |
1258 | are C<0>), or a reference to an array of work offsets, with the same number |
965 | of elements as @$global_work_size. |
1259 | of elements as \@global_work_size. |
966 | |
1260 | |
967 | @$local_work_size must be either C<undef> (in which case the |
1261 | \@local_work_size must be either C<undef> (in which case the |
968 | implementation is supposed to choose good local work sizes), or a |
1262 | implementation is supposed to choose good local work sizes), or a |
969 | reference to an array of local work sizes, with the same number of |
1263 | reference to an array of local work sizes, with the same number of |
970 | elements as @$global_work_size. |
1264 | elements as \@global_work_size. |
971 | |
1265 | |
972 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
1266 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
973 | |
1267 | |
974 | =item $ev = $queue->enqueue_marker ($wait_events...) |
|
|
975 | |
|
|
976 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueMarker.html> |
|
|
977 | |
|
|
978 | =item $ev = $queue->enqueue_acquire_gl_objects ([object, ...], $wait_events...) |
1268 | =item $ev = $queue->acquire_gl_objects ([object, ...], $wait_events...) |
979 | |
1269 | |
980 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired |
1270 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired |
981 | for subsequent OpenCL usage. |
1271 | for subsequent OpenCL usage. |
982 | |
1272 | |
983 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html> |
1273 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html> |
984 | |
1274 | |
985 | =item $ev = $queue->enqueue_release_gl_objects ([object, ...], $wait_events...) |
1275 | =item $ev = $queue->release_gl_objects ([object, ...], $wait_events...) |
986 | |
1276 | |
987 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be released |
1277 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be released |
988 | for subsequent OpenGL usage. |
1278 | for subsequent OpenGL usage. |
989 | |
1279 | |
990 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html> |
1280 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html> |
991 | |
1281 | |
992 | =item $ev = $queue->enqueue_wait_for_events ($wait_events...) |
1282 | =item $ev = $queue->wait_for_events ($wait_events...) |
993 | |
1283 | |
994 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
1284 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
995 | |
1285 | |
996 | =item $queue->enqueue_barrier |
1286 | =item $ev = $queue->marker ($wait_events...) |
997 | |
1287 | |
|
|
1288 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html> |
|
|
1289 | |
|
|
1290 | =item $ev = $queue->barrier ($wait_events...) |
|
|
1291 | |
998 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueBarrier.html> |
1292 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html> |
999 | |
1293 | |
1000 | =item $queue->flush |
1294 | =item $queue->flush |
1001 | |
1295 | |
1002 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html> |
1296 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html> |
1003 | |
1297 | |
… | |
… | |
1118 | |
1412 | |
1119 | =back |
1413 | =back |
1120 | |
1414 | |
1121 | =head2 THE OpenCL::Image CLASS |
1415 | =head2 THE OpenCL::Image CLASS |
1122 | |
1416 | |
1123 | This is the superclass of all image objects - OpenCL::Image2D and OpenCL::Image3D. |
1417 | This is the superclass of all image objects - OpenCL::Image1D, |
|
|
1418 | OpenCL::Image1DArray, OpenCL::Image1DBuffer, OpenCL::Image2D, |
|
|
1419 | OpenCL::Image2DArray and OpenCL::Image3D. |
1124 | |
1420 | |
1125 | =over 4 |
1421 | =over 4 |
1126 | |
1422 | |
1127 | =item $packed_value = $ev->image_info ($name) |
1423 | =item $packed_value = $image->image_info ($name) |
1128 | |
1424 | |
1129 | See C<< $platform->info >> for details. |
1425 | See C<< $platform->info >> for details. |
1130 | |
1426 | |
1131 | The reason this method is not called C<info> is that there already is an |
1427 | The reason this method is not called C<info> is that there already is an |
1132 | C<< ->info >> method inherited from C<OpenCL::Memory>. |
1428 | C<< ->info >> method inherited from C<OpenCL::Memory>. |
1133 | |
1429 | |
1134 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html> |
1430 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html> |
1135 | |
1431 | |
|
|
1432 | =item ($channel_order, $channel_data_type) = $image->format |
|
|
1433 | |
|
|
1434 | Returns the channel order and type used to create the image by calling |
|
|
1435 | C<clGetImageInfo> with C<CL_IMAGE_FORMAT>. |
|
|
1436 | |
1136 | =for gengetinfo begin image |
1437 | =for gengetinfo begin image |
1137 | |
1438 | |
1138 | =item $int = $image->element_size |
1439 | =item $int = $image->element_size |
1139 | |
1440 | |
1140 | Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result. |
1441 | Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result. |
… | |
… | |
1213 | |
1514 | |
1214 | =head2 THE OpenCL::Program CLASS |
1515 | =head2 THE OpenCL::Program CLASS |
1215 | |
1516 | |
1216 | =over 4 |
1517 | =over 4 |
1217 | |
1518 | |
1218 | =item $program->build ($device, $options = "") |
1519 | =item $program->build (\@devices = undef, $options = "", $cb->($program) = undef) |
1219 | |
1520 | |
1220 | Tries to build the program with the givne options. |
1521 | Tries to build the program with the given options. See also the |
|
|
1522 | C<$ctx->build> convenience function. |
|
|
1523 | |
|
|
1524 | If a callback is specified, then it will be called when compilation is |
|
|
1525 | finished. Note that many OpenCL implementations block your program while |
|
|
1526 | compiling whether you use a callback or not. See C<build_async> if you |
|
|
1527 | want to make sure the build is done in the background. |
|
|
1528 | |
|
|
1529 | Note that some OpenCL implementations atc up badly, and don't call the |
|
|
1530 | callback in some error cases (but call it in others). This implementation |
|
|
1531 | assumes the callback will always be called, and leaks memory if this is |
|
|
1532 | not so. So best make sure you don't pass in invalid values. |
1221 | |
1533 | |
1222 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
1534 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
|
|
1535 | |
|
|
1536 | =item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef) |
|
|
1537 | |
|
|
1538 | Similar to C<< ->build >>, except it starts a thread, and never fails (you |
|
|
1539 | need to check the compilation status form the callback, or by polling). |
1223 | |
1540 | |
1224 | =item $packed_value = $program->build_info ($device, $name) |
1541 | =item $packed_value = $program->build_info ($device, $name) |
1225 | |
1542 | |
1226 | Similar to C<< $platform->info >>, but returns build info for a previous |
1543 | Similar to C<< $platform->info >>, but returns build info for a previous |
1227 | build attempt for the given device. |
1544 | build attempt for the given device. |
… | |
… | |
1232 | |
1549 | |
1233 | Creates an OpenCL::Kernel object out of the named C<__kernel> function in |
1550 | Creates an OpenCL::Kernel object out of the named C<__kernel> function in |
1234 | the program. |
1551 | the program. |
1235 | |
1552 | |
1236 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html> |
1553 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html> |
|
|
1554 | |
|
|
1555 | =item @kernels = $program->kernels_in_program |
|
|
1556 | |
|
|
1557 | Returns all kernels successfully compiled for all devices in program. |
|
|
1558 | |
|
|
1559 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernelsInProgram.html |
1237 | |
1560 | |
1238 | =for gengetinfo begin program_build |
1561 | =for gengetinfo begin program_build |
1239 | |
1562 | |
1240 | =item $build_status = $program->build_status ($device) |
1563 | =item $build_status = $program->build_status ($device) |
1241 | |
1564 | |
… | |
… | |
1363 | |
1686 | |
1364 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result. |
1687 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result. |
1365 | |
1688 | |
1366 | =for gengetinfo end kernel_work_group |
1689 | =for gengetinfo end kernel_work_group |
1367 | |
1690 | |
1368 | =item $kernel->set_TYPE ($index, $value) |
1691 | =item $kernel->set_TYPE ($index, $value) |
1369 | |
1692 | |
|
|
1693 | =item $kernel->set_char ($index, $value) |
|
|
1694 | |
|
|
1695 | =item $kernel->set_uchar ($index, $value) |
|
|
1696 | |
|
|
1697 | =item $kernel->set_short ($index, $value) |
|
|
1698 | |
|
|
1699 | =item $kernel->set_ushort ($index, $value) |
|
|
1700 | |
|
|
1701 | =item $kernel->set_int ($index, $value) |
|
|
1702 | |
|
|
1703 | =item $kernel->set_uint ($index, $value) |
|
|
1704 | |
|
|
1705 | =item $kernel->set_long ($index, $value) |
|
|
1706 | |
|
|
1707 | =item $kernel->set_ulong ($index, $value) |
|
|
1708 | |
|
|
1709 | =item $kernel->set_half ($index, $value) |
|
|
1710 | |
|
|
1711 | =item $kernel->set_float ($index, $value) |
|
|
1712 | |
|
|
1713 | =item $kernel->set_double ($index, $value) |
|
|
1714 | |
|
|
1715 | =item $kernel->set_memory ($index, $value) |
|
|
1716 | |
|
|
1717 | =item $kernel->set_buffer ($index, $value) |
|
|
1718 | |
|
|
1719 | =item $kernel->set_image ($index, $value) |
|
|
1720 | |
|
|
1721 | =item $kernel->set_sampler ($index, $value) |
|
|
1722 | |
|
|
1723 | =item $kernel->set_local ($index, $value) |
|
|
1724 | |
|
|
1725 | =item $kernel->set_event ($index, $value) |
|
|
1726 | |
1370 | This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>. |
1727 | This is a family of methods to set the kernel argument with the number |
1371 | |
1728 | C<$index> to the give C<$value>. |
1372 | TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>, |
|
|
1373 | C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>, |
|
|
1374 | C<image2d>, C<image3d>, C<sampler> or C<event>. |
|
|
1375 | |
1729 | |
1376 | Chars and integers (including the half type) are specified as integers, |
1730 | Chars and integers (including the half type) are specified as integers, |
1377 | float and double as floating point values, memory/buffer/image2d/image3d |
1731 | float and double as floating point values, memory/buffer/image must be |
1378 | must be an object of that type or C<undef>, and sampler and event must be |
1732 | an object of that type or C<undef>, local-memory arguments are set by |
1379 | objects of that type. |
1733 | specifying the size, and sampler and event must be objects of that type. |
|
|
1734 | |
|
|
1735 | Note that C<set_memory> works for all memory objects (all types of buffers |
|
|
1736 | and images) - the main purpose of the more specific C<set_TYPE> functions |
|
|
1737 | is type checking. |
|
|
1738 | |
|
|
1739 | Setting an argument for a kernel does NOT keep a reference to the object - |
|
|
1740 | for example, if you set an argument to some image object, free the image, |
|
|
1741 | and call the kernel, you will run into undefined behaviour. |
1380 | |
1742 | |
1381 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html> |
1743 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html> |
1382 | |
1744 | |
1383 | =back |
1745 | =back |
1384 | |
1746 | |
… | |
… | |
1393 | |
1755 | |
1394 | Waits for the event to complete. |
1756 | Waits for the event to complete. |
1395 | |
1757 | |
1396 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
1758 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
1397 | |
1759 | |
|
|
1760 | =item $ev->cb ($exec_callback_type, $callback->($event, $event_command_exec_status)) |
|
|
1761 | |
|
|
1762 | Adds a callback to the callback stack for the given event type. There is |
|
|
1763 | no way to remove a callback again. |
|
|
1764 | |
|
|
1765 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetEventCallback.html> |
|
|
1766 | |
1398 | =item $packed_value = $ev->info ($name) |
1767 | =item $packed_value = $ev->info ($name) |
1399 | |
1768 | |
1400 | See C<< $platform->info >> for details. |
1769 | See C<< $platform->info >> for details. |
1401 | |
1770 | |
1402 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html> |
1771 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html> |
… | |
… | |
1462 | |
1831 | |
1463 | =over 4 |
1832 | =over 4 |
1464 | |
1833 | |
1465 | =item $ev->set_status ($execution_status) |
1834 | =item $ev->set_status ($execution_status) |
1466 | |
1835 | |
|
|
1836 | Sets the execution status of the user event. Can only be called once, |
|
|
1837 | either with OpenCL::COMPLETE or a negative number as status. |
|
|
1838 | |
1467 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html> |
1839 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html> |
1468 | |
1840 | |
1469 | =back |
1841 | =back |
1470 | |
1842 | |
1471 | =cut |
1843 | =cut |
1472 | |
|
|
1473 | package OpenCL; |
|
|
1474 | |
|
|
1475 | use common::sense; |
|
|
1476 | |
|
|
1477 | BEGIN { |
|
|
1478 | our $VERSION = '0.95'; |
|
|
1479 | |
|
|
1480 | require XSLoader; |
|
|
1481 | XSLoader::load (__PACKAGE__, $VERSION); |
|
|
1482 | |
|
|
1483 | @OpenCL::Buffer::ISA = |
|
|
1484 | @OpenCL::Image::ISA = OpenCL::Memory::; |
|
|
1485 | |
|
|
1486 | @OpenCL::BufferObj::ISA = OpenCL::Buffer::; |
|
|
1487 | |
|
|
1488 | @OpenCL::Image2D::ISA = |
|
|
1489 | @OpenCL::Image3D::ISA = OpenCL::Image::; |
|
|
1490 | |
|
|
1491 | @OpenCL::UserEvent::ISA = OpenCL::Event::; |
|
|
1492 | } |
|
|
1493 | |
1844 | |
1494 | 1; |
1845 | 1; |
1495 | |
1846 | |
1496 | =head1 AUTHOR |
1847 | =head1 AUTHOR |
1497 | |
1848 | |