… | |
… | |
43 | |
43 | |
44 | OpenCL::Event objects are used to signal when something is complete. |
44 | OpenCL::Event objects are used to signal when something is complete. |
45 | |
45 | |
46 | =head2 HELPFUL RESOURCES |
46 | =head2 HELPFUL RESOURCES |
47 | |
47 | |
48 | The OpenCL spec used to develop this module (1.2 spec was available, but |
48 | The OpenCL specs used to develop this module: |
49 | no implementation was available to me :). |
|
|
50 | |
49 | |
51 | http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf |
50 | http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf |
|
|
51 | http://www.khronos.org/registry/cl/specs/opencl-1.2.pdf |
|
|
52 | http://www.khronos.org/registry/cl/specs/opencl-1.2-extensions.pdf |
52 | |
53 | |
53 | OpenCL manpages: |
54 | OpenCL manpages: |
54 | |
55 | |
55 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/ |
56 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/ |
|
|
57 | http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/ |
56 | |
58 | |
57 | If you are into UML class diagrams, the following diagram might help - if |
59 | If you are into UML class diagrams, the following diagram might help - if |
58 | not, it will be mildly cobfusing: |
60 | not, it will be mildly confusing (also, the class hierarchy of this module |
|
|
61 | is much more fine-grained): |
59 | |
62 | |
60 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/classDiagram.html |
63 | http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/classDiagram.html |
61 | |
64 | |
62 | Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it |
65 | Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it |
63 | is, but at least it's free of charge: |
66 | is, but at least it's free of charge: |
64 | |
67 | |
65 | http://developer.amd.com/zones/OpenCLZone/courses/Documents/Introduction_to_OpenCL_Programming%20Training_Guide%20%28201005%29.pdf |
68 | http://developer.amd.com/zones/OpenCLZone/courses/Documents/Introduction_to_OpenCL_Programming%20Training_Guide%20%28201005%29.pdf |
… | |
… | |
138 | =head2 Create a buffer with some predefined data, read it back synchronously, |
141 | =head2 Create a buffer with some predefined data, read it back synchronously, |
139 | then asynchronously. |
142 | then asynchronously. |
140 | |
143 | |
141 | my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); |
144 | my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); |
142 | |
145 | |
143 | $queue->enqueue_read_buffer ($buf, 1, 1, 3, my $data); |
146 | $queue->read_buffer ($buf, 1, 1, 3, my $data); |
144 | print "$data\n"; |
147 | print "$data\n"; |
145 | |
148 | |
146 | my $ev = $queue->enqueue_read_buffer ($buf, 0, 1, 3, my $data); |
149 | my $ev = $queue->read_buffer ($buf, 0, 1, 3, my $data); |
147 | $ev->wait; |
150 | $ev->wait; |
148 | print "$data\n"; # prints "elm" |
151 | print "$data\n"; # prints "elm" |
149 | |
152 | |
150 | =head2 Create and build a program, then create a kernel out of one of its |
153 | =head2 Create and build a program, then create a kernel out of one of its |
151 | functions. |
154 | functions. |
… | |
… | |
171 | # set buffer |
174 | # set buffer |
172 | $kernel->set_buffer (0, $input); |
175 | $kernel->set_buffer (0, $input); |
173 | $kernel->set_buffer (1, $output); |
176 | $kernel->set_buffer (1, $output); |
174 | |
177 | |
175 | # execute it for all 4 numbers |
178 | # execute it for all 4 numbers |
176 | $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
179 | $queue->nd_range_kernel ($kernel, undef, [4], undef); |
177 | |
180 | |
178 | # enqueue a synchronous read |
181 | # enqueue a synchronous read |
179 | $queue->enqueue_read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
182 | $queue->read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
180 | |
183 | |
181 | # print the results: |
184 | # print the results: |
182 | printf "%s\n", join ", ", unpack "f*", $data; |
185 | printf "%s\n", join ", ", unpack "f*", $data; |
183 | |
186 | |
184 | =head2 The same enqueue operations as before, but assuming an out-of-order queue, |
187 | =head2 The same enqueue operations as before, but assuming an out-of-order queue, |
185 | showing off barriers. |
188 | showing off barriers. |
186 | |
189 | |
187 | # execute it for all 4 numbers |
190 | # execute it for all 4 numbers |
188 | $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
191 | $queue->nd_range_kernel ($kernel, undef, [4], undef); |
189 | |
192 | |
190 | # enqueue a barrier to ensure in-order execution |
193 | # enqueue a barrier to ensure in-order execution |
191 | $queue->enqueue_barrier; |
194 | $queue->barrier; |
192 | |
195 | |
193 | # enqueue an async read |
196 | # enqueue an async read |
194 | $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
197 | $queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
195 | |
198 | |
196 | # wait for all requests to finish |
199 | # wait for all requests to finish |
197 | $queue->finish; |
200 | $queue->finish; |
198 | |
201 | |
199 | =head2 The same enqueue operations as before, but assuming an out-of-order queue, |
202 | =head2 The same enqueue operations as before, but assuming an out-of-order queue, |
200 | showing off event objects and wait lists. |
203 | showing off event objects and wait lists. |
201 | |
204 | |
202 | # execute it for all 4 numbers |
205 | # execute it for all 4 numbers |
203 | my $ev = $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
206 | my $ev = $queue->nd_range_kernel ($kernel, undef, [4], undef); |
204 | |
207 | |
205 | # enqueue an async read |
208 | # enqueue an async read |
206 | $ev = $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev); |
209 | $ev = $queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev); |
207 | |
210 | |
208 | # wait for the last event to complete |
211 | # wait for the last event to complete |
209 | $ev->wait; |
212 | $ev->wait; |
210 | |
213 | |
211 | =head2 Use the OpenGL module to share a texture between OpenCL and OpenGL and draw some julia |
214 | =head2 Use the OpenGL module to share a texture between OpenCL and OpenGL and draw some julia |
212 | set tunnel effect. |
215 | set tunnel effect. |
213 | |
216 | |
214 | This is quite a long example to get you going. |
217 | This is quite a long example to get you going - you can download it from |
|
|
218 | L<http://cvs.schmorp.de/OpenCL/examples/juliaflight>. |
215 | |
219 | |
216 | use OpenGL ":all"; |
220 | use OpenGL ":all"; |
217 | use OpenCL; |
221 | use OpenCL; |
218 | |
222 | |
|
|
223 | my $S = $ARGV[0] || 256; # window/texture size, smaller is faster |
|
|
224 | |
219 | # open a window and create a gl texture |
225 | # open a window and create a gl texture |
220 | OpenGL::glpOpenWindow width => 256, height => 256; |
226 | OpenGL::glpOpenWindow width => $S, height => $S; |
221 | my $texid = glGenTextures_p 1; |
227 | my $texid = glGenTextures_p 1; |
222 | glBindTexture GL_TEXTURE_2D, $texid; |
228 | glBindTexture GL_TEXTURE_2D, $texid; |
223 | glTexImage2D_c GL_TEXTURE_2D, 0, GL_RGBA8, 256, 256, 0, GL_RGBA, GL_UNSIGNED_BYTE, 0; |
229 | glTexImage2D_c GL_TEXTURE_2D, 0, GL_RGBA8, $S, $S, 0, GL_RGBA, GL_UNSIGNED_BYTE, 0; |
224 | |
230 | |
225 | # find and use the first opencl device that let's us get a shared opengl context |
231 | # find and use the first opencl device that let's us get a shared opengl context |
226 | my $platform; |
232 | my $platform; |
227 | my $dev; |
233 | my $dev; |
228 | my $ctx; |
234 | my $ctx; |
… | |
… | |
247 | # now the boring opencl code |
253 | # now the boring opencl code |
248 | my $src = <<EOF; |
254 | my $src = <<EOF; |
249 | kernel void |
255 | kernel void |
250 | juliatunnel (write_only image2d_t img, float time) |
256 | juliatunnel (write_only image2d_t img, float time) |
251 | { |
257 | { |
252 | float2 p = (float2)(get_global_id (0), get_global_id (1)) / 256.f * 2.f - 1.f; |
258 | int2 xy = (int2)(get_global_id (0), get_global_id (1)); |
|
|
259 | float2 p = convert_float2 (xy) / $S.f * 2.f - 1.f; |
253 | |
260 | |
254 | float2 m = (float2)(1.f, p.y) / fabs (p.x); |
261 | float2 m = (float2)(1.f, p.y) / fabs (p.x); // tunnel |
255 | m.x = fabs (fmod (m.x + time * 0.05f, 4.f)) - 2.f; |
262 | m.x = fabs (fmod (m.x + time * 0.05f, 4.f) - 2.f); |
256 | |
263 | |
257 | float2 z = m; |
264 | float2 z = m; |
258 | float2 c = (float2)(sin (time * 0.05005), cos (time * 0.06001)); |
265 | float2 c = (float2)(sin (time * 0.01133f), cos (time * 0.02521f)); |
259 | |
266 | |
260 | for (int i = 0; i < 25 && dot (z, z) < 4.f; ++i) |
267 | for (int i = 0; i < 25 && dot (z, z) < 4.f; ++i) // standard julia |
261 | z = (float2)(z.x * z.x - z.y * z.y, 2.f * z.x * z.y) + c; |
268 | z = (float2)(z.x * z.x - z.y * z.y, 2.f * z.x * z.y) + c; |
262 | |
269 | |
263 | float3 colour = (float3)(z.x, z.y, z.x * z.y); |
270 | float3 colour = (float3)(z.x, z.y, atan2 (z.y, z.x)); |
264 | write_imagef (img, (int2)(get_global_id (0), get_global_id (1)), (float4)(colour * p.x * p.x, 1.)); |
271 | write_imagef (img, xy, (float4)(colour * p.x * p.x, 1.)); |
265 | } |
272 | } |
266 | EOF |
273 | EOF |
267 | |
274 | |
268 | my $prog = $ctx->build_program ($src); |
275 | my $prog = $ctx->build_program ($src); |
269 | my $kernel = $prog->kernel ("juliatunnel"); |
276 | my $kernel = $prog->kernel ("juliatunnel"); |
270 | |
277 | |
271 | # program compiled, kernel ready, now draw and loop |
278 | # program compiled, kernel ready, now draw and loop |
272 | |
279 | |
273 | for (my $time; ; ++$time) { |
280 | for (my $time; ; ++$time) { |
274 | # acquire objects from opengl |
281 | # acquire objects from opengl |
275 | $queue->enqueue_acquire_gl_objects ([$tex]); |
282 | $queue->acquire_gl_objects ([$tex]); |
276 | |
283 | |
277 | # configure and run our kernel |
284 | # configure and run our kernel |
278 | $kernel->set_image2d (0, $tex); |
285 | $kernel->setf ("mf", $tex, $time*2); # mf = memory object, float |
279 | $kernel->set_float (1, $time); |
|
|
280 | $queue->enqueue_nd_range_kernel ($kernel, undef, [256, 256], undef); |
286 | $queue->nd_range_kernel ($kernel, undef, [$S, $S], undef); |
281 | |
287 | |
282 | # release objects to opengl again |
288 | # release objects to opengl again |
283 | $queue->enqueue_release_gl_objects ([$tex]); |
289 | $queue->release_gl_objects ([$tex]); |
284 | |
290 | |
285 | # wait |
291 | # wait |
286 | $queue->finish; |
292 | $queue->finish; |
287 | |
293 | |
288 | # now draw the texture, the defaults should be all right |
294 | # now draw the texture, the defaults should be all right |
… | |
… | |
376 | |
382 | |
377 | For this to work, the OpenGL library must be loaded, a GLX context must |
383 | For this to work, the OpenGL library must be loaded, a GLX context must |
378 | have been created and be made current, and C<dlsym> must be available and |
384 | have been created and be made current, and C<dlsym> must be available and |
379 | capable of finding the function via C<RTLD_DEFAULT>. |
385 | capable of finding the function via C<RTLD_DEFAULT>. |
380 | |
386 | |
|
|
387 | =head2 EVENT SYSTEM |
|
|
388 | |
|
|
389 | OpenCL can generate a number of (potentially) asynchronous events, for |
|
|
390 | example, after compiling a program, to signal a context-related error or, |
|
|
391 | perhaps most important, to signal completion of queued jobs (by setting |
|
|
392 | callbacks on OpenCL::Event objects). |
|
|
393 | |
|
|
394 | To facilitate this, this module maintains an event queue - each |
|
|
395 | time an asynchronous event happens, it is queued, and perl will be |
|
|
396 | interrupted. This is implemented via the L<Async::Interrupt> module. In |
|
|
397 | addition, this module has L<AnyEvent> support, so it can seamlessly |
|
|
398 | integrate itself into many event loops. |
|
|
399 | |
|
|
400 | Since this module is a bit hard to understand, here are some case examples: |
|
|
401 | |
|
|
402 | =head3 Don't use callbacks. |
|
|
403 | |
|
|
404 | When your program never uses any callbacks, then there will never be any |
|
|
405 | notifications you need to take care of, and therefore no need to worry |
|
|
406 | about all this. |
|
|
407 | |
|
|
408 | You can achieve a great deal by explicitly waiting for events, or using |
|
|
409 | barriers and flush calls. In many programs, there is no need at all to |
|
|
410 | tinker with asynchronous events. |
|
|
411 | |
|
|
412 | =head3 Use AnyEvent |
|
|
413 | |
|
|
414 | This module automatically registers a watcher that invokes all outstanding |
|
|
415 | event callbacks when AnyEvent is initialised (and block asynchronous |
|
|
416 | interruptions). Using this mode of operations is the safest and most |
|
|
417 | recommended one. |
|
|
418 | |
|
|
419 | To use this, simply use AnyEvent and this module normally, make sure you |
|
|
420 | have an event loop running: |
|
|
421 | |
|
|
422 | use Gtk2 -init; |
|
|
423 | use AnyEvent; |
|
|
424 | |
|
|
425 | # initialise AnyEvent, by creating a watcher, or: |
|
|
426 | AnyEvent::detect; |
|
|
427 | |
|
|
428 | my $e = $queue->marker; |
|
|
429 | $e->cb (sub { |
|
|
430 | warn "opencl is finished\n"; |
|
|
431 | }) |
|
|
432 | |
|
|
433 | main Gtk2; |
|
|
434 | |
|
|
435 | Note that this module will not initialise AnyEvent for you. Before |
|
|
436 | AnyEvent is initialised, the module will asynchronously interrupt perl |
|
|
437 | instead. To avoid any surprises, it's best to explicitly initialise |
|
|
438 | AnyEvent. |
|
|
439 | |
|
|
440 | You can temporarily enable asynchronous interruptions (see next paragraph) |
|
|
441 | by calling C<$OpenCL::INTERRUPT->unblock> and disable them again by |
|
|
442 | calling C<$OpenCL::INTERRUPT->block>. |
|
|
443 | |
|
|
444 | =head3 Let yourself be interrupted at any time |
|
|
445 | |
|
|
446 | This mode is the default unless AnyEvent is loaded and initialised. In |
|
|
447 | this mode, OpenCL asynchronously interrupts a running perl program. The |
|
|
448 | emphasis is on both I<asynchronously> and I<running> here. |
|
|
449 | |
|
|
450 | Asynchronously means that perl might execute your callbacks at any |
|
|
451 | time. For example, in the following code (I<THAT YOU SHOULD NOT COPY>), |
|
|
452 | the C<until> loop following the marker call will be interrupted by the |
|
|
453 | callback: |
|
|
454 | |
|
|
455 | my $e = $queue->marker; |
|
|
456 | my $flag; |
|
|
457 | $e->cb (sub { $flag = 1 }); |
|
|
458 | 1 until $flag; |
|
|
459 | # $flag is now 1 |
|
|
460 | |
|
|
461 | The reason why you shouldn't blindly copy the above code is that |
|
|
462 | busy waiting is a really really bad thing, and really really bad for |
|
|
463 | performance. |
|
|
464 | |
|
|
465 | While at first this asynchronous business might look exciting, it can be |
|
|
466 | really hard, because you need to be prepared for the callback code to be |
|
|
467 | executed at any time, which limits the amount of things the callback code |
|
|
468 | can do safely. |
|
|
469 | |
|
|
470 | This can be mitigated somewhat by using C<< |
|
|
471 | $OpenCL::INTERRUPT->scope_block >> (see the L<Async::Interrupt> |
|
|
472 | documentation for details). |
|
|
473 | |
|
|
474 | The other problem is that your program must be actively I<running> to be |
|
|
475 | interrupted. When you calculate stuff, your program is running. When you |
|
|
476 | hang in some C functions or other block execution (by calling C<sleep>, |
|
|
477 | C<select>, running an event loop and so on), your program is waiting, not |
|
|
478 | running. |
|
|
479 | |
|
|
480 | One way around that would be to attach a read watcher to your event loop, |
|
|
481 | listening for events on C<< $OpenCL::INTERRUPT->pipe_fileno >>, using a |
|
|
482 | dummy callback (C<sub { }>) to temporarily execute some perl code. |
|
|
483 | |
|
|
484 | That is then awfully close to using the built-in AnyEvent support above, |
|
|
485 | though, so consider that one instead. |
|
|
486 | |
|
|
487 | =head3 Be creative |
|
|
488 | |
|
|
489 | OpenCL exports the L<Async::Interrupt> object it uses in the global |
|
|
490 | variable C<$OpenCL::INTERRUPT>. You can configure it in any way you like. |
|
|
491 | |
|
|
492 | So if you want to feel like a real pro, err, wait, if you feel no risk |
|
|
493 | menas no fun, you can experiment by implementing your own mode of |
|
|
494 | operations. |
|
|
495 | |
381 | =cut |
496 | =cut |
382 | |
497 | |
383 | package OpenCL; |
498 | package OpenCL; |
384 | |
499 | |
385 | use common::sense; |
500 | use common::sense; |
|
|
501 | use Carp (); |
|
|
502 | use Async::Interrupt (); |
|
|
503 | |
|
|
504 | our $POLL_FUNC; # set by XS |
386 | |
505 | |
387 | BEGIN { |
506 | BEGIN { |
388 | our $VERSION = '0.96'; |
507 | our $VERSION = '0.98'; |
389 | |
508 | |
390 | require XSLoader; |
509 | require XSLoader; |
391 | XSLoader::load (__PACKAGE__, $VERSION); |
510 | XSLoader::load (__PACKAGE__, $VERSION); |
392 | |
511 | |
393 | @OpenCL::Platform::ISA = |
512 | @OpenCL::Platform::ISA = |
… | |
… | |
422 | =item $int = OpenCL::errno |
541 | =item $int = OpenCL::errno |
423 | |
542 | |
424 | The last error returned by a function - it's only valid after an error occured |
543 | The last error returned by a function - it's only valid after an error occured |
425 | and before calling another OpenCL function. |
544 | and before calling another OpenCL function. |
426 | |
545 | |
427 | =item $str = OpenCL::err2str $errval |
546 | =item $str = OpenCL::err2str [$errval] |
428 | |
547 | |
429 | Comverts an error value into a human readable string. |
548 | Converts an error value into a human readable string. IF no error value is |
|
|
549 | given, then the last error will be used (as returned by OpenCL::errno). |
430 | |
550 | |
431 | =item $str = OpenCL::enum2str $enum |
551 | =item $str = OpenCL::enum2str $enum |
432 | |
552 | |
433 | Converts most enum values (of parameter names, image format constants, |
553 | Converts most enum values (of parameter names, image format constants, |
434 | object types, addressing and filter modes, command types etc.) into a |
554 | object types, addressing and filter modes, command types etc.) into a |
… | |
… | |
440 | |
560 | |
441 | Returns all available OpenCL::Platform objects. |
561 | Returns all available OpenCL::Platform objects. |
442 | |
562 | |
443 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html> |
563 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html> |
444 | |
564 | |
445 | =item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef |
565 | =item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr |
446 | |
566 | |
447 | Tries to create a context from a default device and platform - never worked for me. |
567 | Tries to create a context from a default device and platform type - never worked for me. |
448 | |
568 | |
449 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
569 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
450 | |
570 | |
|
|
571 | =item $ctx = OpenCL::context $properties, \@devices, $callback->($err, $pvt) = $print_stderr) |
|
|
572 | |
|
|
573 | Create a new OpenCL::Context object using the given device object(s). This |
|
|
574 | function isn't implemented yet, use C<< $platform->context >> instead. |
|
|
575 | |
|
|
576 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> |
|
|
577 | |
451 | =item OpenCL::wait_for_events $wait_events... |
578 | =item OpenCL::wait_for_events $wait_events... |
452 | |
579 | |
453 | Waits for all events to complete. |
580 | Waits for all events to complete. |
454 | |
581 | |
455 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
582 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
|
|
583 | |
|
|
584 | =item OpenCL::poll |
|
|
585 | |
|
|
586 | Checks if there are any outstanding events (see L<EVENT SYSTEM>) and |
|
|
587 | invokes their callbacks. |
|
|
588 | |
|
|
589 | =item $OpenCL::INTERRUPT |
|
|
590 | |
|
|
591 | The L<Async::Interrupt> object used to signal asynchronous events (see |
|
|
592 | L<EVENT SYSTEM>). |
|
|
593 | |
|
|
594 | =cut |
|
|
595 | |
|
|
596 | our $INTERRUPT = new Async::Interrupt c_cb => [$POLL_FUNC, 0]; |
|
|
597 | |
|
|
598 | &_eq_initialise ($INTERRUPT->signal_func); |
|
|
599 | |
|
|
600 | =item $OpenCL::WATCHER |
|
|
601 | |
|
|
602 | The L<AnyEvent> watcher object used to watch for asynchronous events (see |
|
|
603 | L<EVENT SYSTEM>). This variable is C<undef> until L<AnyEvent> has been |
|
|
604 | loaded I<and> initialised (e.g. by calling C<AnyEvent::detect>). |
|
|
605 | |
|
|
606 | =cut |
|
|
607 | |
|
|
608 | our $WATCHER; |
|
|
609 | |
|
|
610 | sub _init_anyevent { |
|
|
611 | $INTERRUPT->block; |
|
|
612 | $WATCHER = AE::io ($INTERRUPT->pipe_fileno, 0, sub { $INTERRUPT->handle }); |
|
|
613 | } |
|
|
614 | |
|
|
615 | if (defined $AnyEvent::MODEL) { |
|
|
616 | _init_anyevent; |
|
|
617 | } else { |
|
|
618 | push @AnyEvent::post_detect, \&_init_anyevent; |
|
|
619 | } |
456 | |
620 | |
457 | =back |
621 | =back |
458 | |
622 | |
459 | =head2 THE OpenCL::Object CLASS |
623 | =head2 THE OpenCL::Object CLASS |
460 | |
624 | |
… | |
… | |
472 | C<IV> type in your code and cast that to the correct type. |
636 | C<IV> type in your code and cast that to the correct type. |
473 | |
637 | |
474 | =cut |
638 | =cut |
475 | |
639 | |
476 | sub OpenCL::Object::id { |
640 | sub OpenCL::Object::id { |
|
|
641 | ref $_[0] eq "SCALAR" |
477 | ${$_[0]} |
642 | ? ${ $_[0] } |
|
|
643 | : $_[0][0] |
478 | } |
644 | } |
479 | |
645 | |
480 | =back |
646 | =back |
481 | |
647 | |
482 | =head2 THE OpenCL::Platform CLASS |
648 | =head2 THE OpenCL::Platform CLASS |
… | |
… | |
485 | |
651 | |
486 | =item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL) |
652 | =item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL) |
487 | |
653 | |
488 | Returns a list of matching OpenCL::Device objects. |
654 | Returns a list of matching OpenCL::Device objects. |
489 | |
655 | |
490 | =item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef) |
656 | =item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr) |
491 | |
657 | |
492 | Tries to create a context. Never worked for me, and you need devices explicitly anyway. |
658 | Tries to create a context. Never worked for me, and you need devices explicitly anyway. |
493 | |
659 | |
494 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
660 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
495 | |
661 | |
496 | =item $ctx = $platform->context ($properties = undef, @$devices, $notify = undef) |
662 | =item $ctx = $platform->context ($properties, \@devices, $callback->($err, $pvt) = $print_stderr) |
497 | |
663 | |
498 | Create a new OpenCL::Context object using the given device object(s)- a |
664 | Create a new OpenCL::Context object using the given device object(s)- a |
499 | CL_CONTEXT_PLATFORM property is supplied automatically. |
665 | CL_CONTEXT_PLATFORM property is supplied automatically. |
500 | |
666 | |
501 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> |
667 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> |
… | |
… | |
844 | my ($self, $prog, $options) = @_; |
1010 | my ($self, $prog, $options) = @_; |
845 | |
1011 | |
846 | $prog = $self->program_with_source ($prog) |
1012 | $prog = $self->program_with_source ($prog) |
847 | unless ref $prog; |
1013 | unless ref $prog; |
848 | |
1014 | |
|
|
1015 | eval { $prog->build (undef, $options); 1 } |
|
|
1016 | or errno == BUILD_PROGRAM_FAILURE |
|
|
1017 | or errno == INVALID_BINARY # workaround nvidia bug |
|
|
1018 | or Carp::croak "OpenCL::Context->build_program: " . err2str; |
|
|
1019 | |
|
|
1020 | # we check status for all devices |
849 | for my $dev ($self->devices) { |
1021 | for my $dev ($self->devices) { |
850 | eval { $prog->build ($dev, $options); 1 } |
1022 | $prog->build_status ($dev) == BUILD_SUCCESS |
851 | or Carp::croak "Building OpenCL program for device '" . $dev->name . "' failed:\n" |
1023 | or Carp::croak "Building OpenCL program for device '" . $dev->name . "' failed:\n" |
852 | . $prog->build_log ($dev); |
1024 | . $prog->build_log ($dev); |
853 | } |
1025 | } |
854 | |
1026 | |
855 | $prog |
1027 | $prog |
856 | } |
1028 | } |
857 | |
1029 | |
… | |
… | |
881 | =item $buf = $ctx->buffer_sv ($flags, $data) |
1053 | =item $buf = $ctx->buffer_sv ($flags, $data) |
882 | |
1054 | |
883 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and |
1055 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and |
884 | initialise it with the given data values. |
1056 | initialise it with the given data values. |
885 | |
1057 | |
886 | =item $img = $ctx->image ($self, $flags, $channel_order, $channel_type, $type, $width, $height, $depth, $array_size = 0, $row_pitch = 0, $slice_pitch = 0, $num_mip_level = 0, $num_samples = 0, $*data = &PL_sv_undef) |
1058 | =item $img = $ctx->image ($self, $flags, $channel_order, $channel_type, $type, $width, $height, $depth = 0, $array_size = 0, $row_pitch = 0, $slice_pitch = 0, $num_mip_level = 0, $num_samples = 0, $*data = &PL_sv_undef) |
887 | |
1059 | |
888 | Creates a new OpenCL::Image object and optionally initialises it with |
1060 | Creates a new OpenCL::Image object and optionally initialises it with |
889 | the given data values. |
1061 | the given data values. |
890 | |
1062 | |
891 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html> |
1063 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html> |
… | |
… | |
987 | =back |
1159 | =back |
988 | |
1160 | |
989 | =head2 THE OpenCL::Queue CLASS |
1161 | =head2 THE OpenCL::Queue CLASS |
990 | |
1162 | |
991 | An OpenCL::Queue represents an execution queue for OpenCL. You execute |
1163 | An OpenCL::Queue represents an execution queue for OpenCL. You execute |
992 | requests by calling their respective C<enqueue_xxx> method and waitinf for |
1164 | requests by calling their respective method and waiting for it to complete |
993 | it to complete in some way. |
1165 | in some way. |
994 | |
1166 | |
995 | All the enqueue methods return an event object that can be used to wait |
1167 | Most methods that enqueue some request return an event object that can |
996 | for completion, unless the method is called in void context, in which case |
1168 | be used to wait for completion (optionally using a callback), unless |
997 | no event object is created. |
1169 | the method is called in void context, in which case no event object is |
|
|
1170 | created. |
998 | |
1171 | |
999 | They also allow you to specify any number of other event objects that this |
1172 | They also allow you to specify any number of other event objects that this |
1000 | request has to wait for before it starts executing, by simply passing the |
1173 | request has to wait for before it starts executing, by simply passing the |
1001 | event objects as extra parameters to the enqueue methods. To simplify |
1174 | event objects as extra parameters to the enqueue methods. To simplify |
1002 | program design, this module ignores any C<undef> values in the list of |
1175 | program design, this module ignores any C<undef> values in the list of |
1003 | events. This makes it possible to code operations such as this, without |
1176 | events. This makes it possible to code operations such as this, without |
1004 | having to put a valid event object into C<$event> first: |
1177 | having to put a valid event object into C<$event> first: |
1005 | |
1178 | |
1006 | $event = $queue->enqueue_xxx (..., $event); |
1179 | $event = $queue->xxx (..., $event); |
1007 | |
1180 | |
1008 | Queues execute in-order by default, without any parallelism, so in most |
1181 | Queues execute in-order by default, without any parallelism, so in most |
1009 | cases (i.e. you use only one queue) it's not necessary to wait for or |
1182 | cases (i.e. you use only one queue) it's not necessary to wait for or |
1010 | create event objects, althoguh an our of order queue is often a bit |
1183 | create event objects, althoguh an our of order queue is often a bit |
1011 | faster. |
1184 | faster. |
1012 | |
1185 | |
1013 | =over 4 |
1186 | =over 4 |
1014 | |
1187 | |
1015 | =item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) |
1188 | =item $ev = $queue->read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) |
1016 | |
1189 | |
1017 | Reads data from buffer into the given string. |
1190 | Reads data from buffer into the given string. |
1018 | |
1191 | |
1019 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html> |
1192 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html> |
1020 | |
1193 | |
1021 | =item $ev = $queue->enqueue_write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) |
1194 | =item $ev = $queue->write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) |
1022 | |
1195 | |
1023 | Writes data to buffer from the given string. |
1196 | Writes data to buffer from the given string. |
1024 | |
1197 | |
1025 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html> |
1198 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html> |
1026 | |
1199 | |
1027 | =item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) |
1200 | =item $ev = $queue->copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) |
1028 | |
1201 | |
1029 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> |
1202 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> |
1030 | |
1203 | |
1031 | =item $ev = $queue->enqueue_read_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) |
1204 | =item $ev = $queue->read_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) |
1032 | |
1205 | |
1033 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html |
1206 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html |
1034 | |
1207 | |
1035 | =item $ev = $queue->enqueue_write_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) |
1208 | =item $ev = $queue->write_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) |
1036 | |
1209 | |
1037 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html |
1210 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html |
1038 | |
1211 | |
1039 | =item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
1212 | =item $ev = $queue->read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
1040 | |
1213 | |
1041 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html> |
1214 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html> |
1042 | |
1215 | |
1043 | =item $ev = $queue->enqueue_copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
1216 | =item $ev = $queue->copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
1044 | |
1217 | |
1045 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> |
1218 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> |
1046 | |
1219 | |
1047 | =item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
1220 | =item $ev = $queue->write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
1048 | |
1221 | |
1049 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> |
1222 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> |
1050 | |
1223 | |
1051 | =item $ev = $queue->enqueue_copy_image ($src_image, $dst_image, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
1224 | =item $ev = $queue->copy_image ($src_image, $dst_image, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
1052 | |
1225 | |
1053 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> |
1226 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> |
1054 | |
1227 | |
1055 | =item $ev = $queue->enqueue_copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...) |
1228 | =item $ev = $queue->copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...) |
1056 | |
1229 | |
1057 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html> |
1230 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html> |
1058 | |
1231 | |
1059 | =item $ev = $queue->enqueue_copy_buffer_rect ($src, $dst, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $src_row_pitch, $src_slice_pitch, $dst_row_pitch, $dst_slice_pitch, $wait_event...) |
1232 | =item $ev = $queue->copy_buffer_rect ($src, $dst, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $src_row_pitch, $src_slice_pitch, $dst_row_pitch, $dst_slice_pitch, $wait_event...) |
1060 | |
1233 | |
1061 | Yeah. |
1234 | Yeah. |
1062 | |
1235 | |
1063 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
1236 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
1064 | |
1237 | |
1065 | =item $ev = $queue->enqueue_fill_buffer ($mem, $pattern, $offset, $size, ...) |
1238 | =item $ev = $queue->fill_buffer ($mem, $pattern, $offset, $size, ...) |
1066 | |
1239 | |
1067 | Fills the given buffer object with repeated applications of C<$pattern>, |
1240 | Fills the given buffer object with repeated applications of C<$pattern>, |
1068 | starting at C<$offset> for C<$size> octets. |
1241 | starting at C<$offset> for C<$size> octets. |
1069 | |
1242 | |
1070 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html> |
1243 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html> |
1071 | |
1244 | |
1072 | =item $ev = $queue->enqueue_fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...) |
1245 | =item $ev = $queue->fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...) |
1073 | |
1246 | |
1074 | Fills the given image area with the given rgba colour components. The |
1247 | Fills the given image area with the given rgba colour components. The |
1075 | components are normally floating point values between C<0> and C<1>, |
1248 | components are normally floating point values between C<0> and C<1>, |
1076 | except when the image channel data type is a signe dor unsigned |
1249 | except when the image channel data type is a signe dor unsigned |
1077 | unnormalised format, in which case the range is determined by the format. |
1250 | unnormalised format, in which case the range is determined by the format. |
1078 | |
1251 | |
1079 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html> |
1252 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html> |
1080 | |
1253 | |
1081 | =item $ev = $queue->enqueue_task ($kernel, $wait_events...) |
1254 | =item $ev = $queue->task ($kernel, $wait_events...) |
1082 | |
1255 | |
1083 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
1256 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
1084 | |
1257 | |
1085 | =item $ev = $queue->enqueue_nd_range_kernel ($kernel, @$global_work_offset, @$global_work_size, @$local_work_size, $wait_events...) |
1258 | =item $ev = $queue->nd_range_kernel ($kernel, \@global_work_offset, \@global_work_size, \@local_work_size, $wait_events...) |
1086 | |
1259 | |
1087 | Enqueues a kernel execution. |
1260 | Enqueues a kernel execution. |
1088 | |
1261 | |
1089 | @$global_work_size must be specified as a reference to an array of |
1262 | \@global_work_size must be specified as a reference to an array of |
1090 | integers specifying the work sizes (element counts). |
1263 | integers specifying the work sizes (element counts). |
1091 | |
1264 | |
1092 | @$global_work_offset must be either C<undef> (in which case all offsets |
1265 | \@global_work_offset must be either C<undef> (in which case all offsets |
1093 | are C<0>), or a reference to an array of work offsets, with the same number |
1266 | are C<0>), or a reference to an array of work offsets, with the same number |
1094 | of elements as @$global_work_size. |
1267 | of elements as \@global_work_size. |
1095 | |
1268 | |
1096 | @$local_work_size must be either C<undef> (in which case the |
1269 | \@local_work_size must be either C<undef> (in which case the |
1097 | implementation is supposed to choose good local work sizes), or a |
1270 | implementation is supposed to choose good local work sizes), or a |
1098 | reference to an array of local work sizes, with the same number of |
1271 | reference to an array of local work sizes, with the same number of |
1099 | elements as @$global_work_size. |
1272 | elements as \@global_work_size. |
1100 | |
1273 | |
1101 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
1274 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
1102 | |
1275 | |
1103 | =item $ev = $queue->enqueue_acquire_gl_objects ([object, ...], $wait_events...) |
1276 | =item $ev = $queue->acquire_gl_objects ([object, ...], $wait_events...) |
1104 | |
1277 | |
1105 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired |
1278 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired |
1106 | for subsequent OpenCL usage. |
1279 | for subsequent OpenCL usage. |
1107 | |
1280 | |
1108 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html> |
1281 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html> |
1109 | |
1282 | |
1110 | =item $ev = $queue->enqueue_release_gl_objects ([object, ...], $wait_events...) |
1283 | =item $ev = $queue->release_gl_objects ([object, ...], $wait_events...) |
1111 | |
1284 | |
1112 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be released |
1285 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be released |
1113 | for subsequent OpenGL usage. |
1286 | for subsequent OpenGL usage. |
1114 | |
1287 | |
1115 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html> |
1288 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html> |
1116 | |
1289 | |
1117 | =item $ev = $queue->enqueue_wait_for_events ($wait_events...) |
1290 | =item $ev = $queue->wait_for_events ($wait_events...) |
1118 | |
1291 | |
1119 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
1292 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
1120 | |
1293 | |
1121 | =item $ev = $queue->enqueue_marker ($wait_events...) |
1294 | =item $ev = $queue->marker ($wait_events...) |
1122 | |
1295 | |
1123 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html> |
1296 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html> |
1124 | |
1297 | |
1125 | =item $ev = $queue->enqueue_barrier ($wait_events...) |
1298 | =item $ev = $queue->barrier ($wait_events...) |
1126 | |
1299 | |
1127 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html> |
1300 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html> |
1128 | |
1301 | |
1129 | =item $queue->flush |
1302 | =item $queue->flush |
1130 | |
1303 | |
… | |
… | |
1253 | OpenCL::Image1DArray, OpenCL::Image1DBuffer, OpenCL::Image2D, |
1426 | OpenCL::Image1DArray, OpenCL::Image1DBuffer, OpenCL::Image2D, |
1254 | OpenCL::Image2DArray and OpenCL::Image3D. |
1427 | OpenCL::Image2DArray and OpenCL::Image3D. |
1255 | |
1428 | |
1256 | =over 4 |
1429 | =over 4 |
1257 | |
1430 | |
1258 | =item $packed_value = $ev->image_info ($name) |
1431 | =item $packed_value = $image->image_info ($name) |
1259 | |
1432 | |
1260 | See C<< $platform->info >> for details. |
1433 | See C<< $platform->info >> for details. |
1261 | |
1434 | |
1262 | The reason this method is not called C<info> is that there already is an |
1435 | The reason this method is not called C<info> is that there already is an |
1263 | C<< ->info >> method inherited from C<OpenCL::Memory>. |
1436 | C<< ->info >> method inherited from C<OpenCL::Memory>. |
1264 | |
1437 | |
1265 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html> |
1438 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html> |
1266 | |
1439 | |
|
|
1440 | =item ($channel_order, $channel_data_type) = $image->format |
|
|
1441 | |
|
|
1442 | Returns the channel order and type used to create the image by calling |
|
|
1443 | C<clGetImageInfo> with C<CL_IMAGE_FORMAT>. |
|
|
1444 | |
1267 | =for gengetinfo begin image |
1445 | =for gengetinfo begin image |
1268 | |
1446 | |
1269 | =item $int = $image->element_size |
1447 | =item $int = $image->element_size |
1270 | |
1448 | |
1271 | Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result. |
1449 | Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result. |
… | |
… | |
1344 | |
1522 | |
1345 | =head2 THE OpenCL::Program CLASS |
1523 | =head2 THE OpenCL::Program CLASS |
1346 | |
1524 | |
1347 | =over 4 |
1525 | =over 4 |
1348 | |
1526 | |
1349 | =item $program->build ($device, $options = "") |
1527 | =item $program->build (\@devices = undef, $options = "", $cb->($program) = undef) |
1350 | |
1528 | |
1351 | Tries to build the program with the given options. See also the |
1529 | Tries to build the program with the given options. See also the |
1352 | C<$ctx->build> convenience function. |
1530 | C<$ctx->build> convenience function. |
1353 | |
1531 | |
|
|
1532 | If a callback is specified, then it will be called when compilation is |
|
|
1533 | finished. Note that many OpenCL implementations block your program while |
|
|
1534 | compiling whether you use a callback or not. See C<build_async> if you |
|
|
1535 | want to make sure the build is done in the background. |
|
|
1536 | |
|
|
1537 | Note that some OpenCL implementations act up badly, and don't call the |
|
|
1538 | callback in some error cases (but call it in others). This implementation |
|
|
1539 | assumes the callback will always be called, and leaks memory if this is |
|
|
1540 | not so. So best make sure you don't pass in invalid values. |
|
|
1541 | |
|
|
1542 | Some implementations fail with C<OpenCL::INVALID_BINARY> when the |
|
|
1543 | compilation state is successful but some later stage fails. |
|
|
1544 | |
1354 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
1545 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
|
|
1546 | |
|
|
1547 | =item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef) |
|
|
1548 | |
|
|
1549 | Similar to C<< ->build >>, except it starts a thread, and never fails (you |
|
|
1550 | need to check the compilation status form the callback, or by polling). |
1355 | |
1551 | |
1356 | =item $packed_value = $program->build_info ($device, $name) |
1552 | =item $packed_value = $program->build_info ($device, $name) |
1357 | |
1553 | |
1358 | Similar to C<< $platform->info >>, but returns build info for a previous |
1554 | Similar to C<< $platform->info >>, but returns build info for a previous |
1359 | build attempt for the given device. |
1555 | build attempt for the given device. |
… | |
… | |
1501 | |
1697 | |
1502 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result. |
1698 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result. |
1503 | |
1699 | |
1504 | =for gengetinfo end kernel_work_group |
1700 | =for gengetinfo end kernel_work_group |
1505 | |
1701 | |
|
|
1702 | =item $kernel->setf ($format, ...) |
|
|
1703 | |
|
|
1704 | Sets the arguments of a kernel. Since OpenCL 1.1 doesn't have a generic |
|
|
1705 | way to set arguments (and with OpenCL 1.2 it might be rather slow), you |
|
|
1706 | need to specify a format argument, much as with C<printf>, to tell OpenCL |
|
|
1707 | what type of argument it is. |
|
|
1708 | |
|
|
1709 | The format arguments are single letters: |
|
|
1710 | |
|
|
1711 | c char |
|
|
1712 | C unsigned char |
|
|
1713 | s short |
|
|
1714 | S unsigned short |
|
|
1715 | i int |
|
|
1716 | I unsigned int |
|
|
1717 | l long |
|
|
1718 | L unsigned long |
|
|
1719 | |
|
|
1720 | h half float (0..65535) |
|
|
1721 | f float |
|
|
1722 | d double |
|
|
1723 | |
|
|
1724 | z local (octet size) |
|
|
1725 | |
|
|
1726 | m memory object (buffer or image) |
|
|
1727 | a sampler |
|
|
1728 | e event |
|
|
1729 | |
|
|
1730 | Space characters in the format string are ignored. |
|
|
1731 | |
|
|
1732 | Example: set the arguments for a kernel that expects an int, two floats, a buffer and an image. |
|
|
1733 | |
|
|
1734 | $kernel->setf ("i ff mm", 5, 0.5, 3, $buffer, $image); |
|
|
1735 | |
1506 | =item $kernel->set_TYPE ($index, $value) |
1736 | =item $kernel->set_TYPE ($index, $value) |
1507 | |
1737 | |
|
|
1738 | =item $kernel->set_char ($index, $value) |
|
|
1739 | |
|
|
1740 | =item $kernel->set_uchar ($index, $value) |
|
|
1741 | |
|
|
1742 | =item $kernel->set_short ($index, $value) |
|
|
1743 | |
|
|
1744 | =item $kernel->set_ushort ($index, $value) |
|
|
1745 | |
|
|
1746 | =item $kernel->set_int ($index, $value) |
|
|
1747 | |
|
|
1748 | =item $kernel->set_uint ($index, $value) |
|
|
1749 | |
|
|
1750 | =item $kernel->set_long ($index, $value) |
|
|
1751 | |
|
|
1752 | =item $kernel->set_ulong ($index, $value) |
|
|
1753 | |
|
|
1754 | =item $kernel->set_half ($index, $value) |
|
|
1755 | |
|
|
1756 | =item $kernel->set_float ($index, $value) |
|
|
1757 | |
|
|
1758 | =item $kernel->set_double ($index, $value) |
|
|
1759 | |
|
|
1760 | =item $kernel->set_memory ($index, $value) |
|
|
1761 | |
|
|
1762 | =item $kernel->set_buffer ($index, $value) |
|
|
1763 | |
|
|
1764 | =item $kernel->set_image ($index, $value) |
|
|
1765 | |
|
|
1766 | =item $kernel->set_sampler ($index, $value) |
|
|
1767 | |
|
|
1768 | =item $kernel->set_local ($index, $value) |
|
|
1769 | |
|
|
1770 | =item $kernel->set_event ($index, $value) |
|
|
1771 | |
1508 | This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>. |
1772 | This is a family of methods to set the kernel argument with the number |
1509 | |
1773 | C<$index> to the give C<$value>. |
1510 | TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>, |
|
|
1511 | C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>, |
|
|
1512 | C<image2d>, C<image3d>, C<sampler>, C<local> or C<event>. |
|
|
1513 | |
1774 | |
1514 | Chars and integers (including the half type) are specified as integers, |
1775 | Chars and integers (including the half type) are specified as integers, |
1515 | float and double as floating point values, memory/buffer/image2d/image3d |
1776 | float and double as floating point values, memory/buffer/image must be |
1516 | must be an object of that type or C<undef>, local-memory arguments are |
1777 | an object of that type or C<undef>, local-memory arguments are set by |
1517 | set by specifying the size, and sampler and event must be objects of that |
1778 | specifying the size, and sampler and event must be objects of that type. |
1518 | type. |
1779 | |
|
|
1780 | Note that C<set_memory> works for all memory objects (all types of buffers |
|
|
1781 | and images) - the main purpose of the more specific C<set_TYPE> functions |
|
|
1782 | is type checking. |
1519 | |
1783 | |
1520 | Setting an argument for a kernel does NOT keep a reference to the object - |
1784 | Setting an argument for a kernel does NOT keep a reference to the object - |
1521 | for example, if you set an argument to some image object, free the image, |
1785 | for example, if you set an argument to some image object, free the image, |
1522 | and call the kernel, you will run into undefined behaviour. |
1786 | and call the kernel, you will run into undefined behaviour. |
1523 | |
1787 | |
… | |
… | |
1536 | |
1800 | |
1537 | Waits for the event to complete. |
1801 | Waits for the event to complete. |
1538 | |
1802 | |
1539 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
1803 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
1540 | |
1804 | |
|
|
1805 | =item $ev->cb ($exec_callback_type, $callback->($event, $event_command_exec_status)) |
|
|
1806 | |
|
|
1807 | Adds a callback to the callback stack for the given event type. There is |
|
|
1808 | no way to remove a callback again. |
|
|
1809 | |
|
|
1810 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetEventCallback.html> |
|
|
1811 | |
1541 | =item $packed_value = $ev->info ($name) |
1812 | =item $packed_value = $ev->info ($name) |
1542 | |
1813 | |
1543 | See C<< $platform->info >> for details. |
1814 | See C<< $platform->info >> for details. |
1544 | |
1815 | |
1545 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html> |
1816 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html> |
… | |
… | |
1605 | |
1876 | |
1606 | =over 4 |
1877 | =over 4 |
1607 | |
1878 | |
1608 | =item $ev->set_status ($execution_status) |
1879 | =item $ev->set_status ($execution_status) |
1609 | |
1880 | |
|
|
1881 | Sets the execution status of the user event. Can only be called once, |
|
|
1882 | either with OpenCL::COMPLETE or a negative number as status. |
|
|
1883 | |
1610 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html> |
1884 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html> |
1611 | |
1885 | |
1612 | =back |
1886 | =back |
1613 | |
1887 | |
1614 | =cut |
1888 | =cut |