… | |
… | |
149 | |
149 | |
150 | =head2 Create and build a program, then create a kernel out of one of its |
150 | =head2 Create and build a program, then create a kernel out of one of its |
151 | functions. |
151 | functions. |
152 | |
152 | |
153 | my $src = ' |
153 | my $src = ' |
154 | __kernel void |
154 | kernel void |
155 | squareit (__global float *input, __global float *output) |
155 | squareit (global float *input, global float *output) |
156 | { |
156 | { |
157 | $id = get_global_id (0); |
157 | $id = get_global_id (0); |
158 | output [id] = input [id] * input [id]; |
158 | output [id] = input [id] * input [id]; |
159 | } |
159 | } |
160 | '; |
160 | '; |
161 | |
161 | |
162 | my $prog = $ctx->program_with_source ($src); |
162 | 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"); |
163 | my $kernel = $prog->kernel ("squareit"); |
169 | |
164 | |
170 | =head2 Create some input and output float buffers, then call the |
165 | =head2 Create some input and output float buffers, then call the |
171 | 'squareit' kernel on them. |
166 | 'squareit' kernel on them. |
172 | |
167 | |
… | |
… | |
210 | # enqueue an async read |
205 | # enqueue an async read |
211 | $ev = $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev); |
206 | $ev = $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev); |
212 | |
207 | |
213 | # wait for the last event to complete |
208 | # wait for the last event to complete |
214 | $ev->wait; |
209 | $ev->wait; |
|
|
210 | |
|
|
211 | =head2 Use the OpenGL module to share a texture between OpenCL and OpenGL and draw some julia |
|
|
212 | set tunnel effect. |
|
|
213 | |
|
|
214 | This is quite a long example to get you going. |
|
|
215 | |
|
|
216 | use OpenGL ":all"; |
|
|
217 | use OpenCL; |
|
|
218 | |
|
|
219 | # open a window and create a gl texture |
|
|
220 | OpenGL::glpOpenWindow width => 256, height => 256; |
|
|
221 | my $texid = glGenTextures_p 1; |
|
|
222 | glBindTexture GL_TEXTURE_2D, $texid; |
|
|
223 | glTexImage2D_c GL_TEXTURE_2D, 0, GL_RGBA8, 256, 256, 0, GL_RGBA, GL_UNSIGNED_BYTE, 0; |
|
|
224 | |
|
|
225 | # find and use the first opencl device that let's us get a shared opengl context |
|
|
226 | my $platform; |
|
|
227 | my $dev; |
|
|
228 | my $ctx; |
|
|
229 | |
|
|
230 | for (OpenCL::platforms) { |
|
|
231 | $platform = $_; |
|
|
232 | for ($platform->devices) { |
|
|
233 | $dev = $_; |
|
|
234 | $ctx = $platform->context ([OpenCL::GLX_DISPLAY_KHR, undef, OpenCL::GL_CONTEXT_KHR, undef], [$dev]) |
|
|
235 | and last; |
|
|
236 | } |
|
|
237 | } |
|
|
238 | |
|
|
239 | $ctx |
|
|
240 | or die "cannot find suitable OpenCL device\n"; |
|
|
241 | |
|
|
242 | my $queue = $ctx->queue ($dev); |
|
|
243 | |
|
|
244 | # now attach an opencl image2d object to the opengl texture |
|
|
245 | my $tex = $ctx->gl_texture2d (OpenCL::MEM_WRITE_ONLY, GL_TEXTURE_2D, 0, $texid); |
|
|
246 | |
|
|
247 | # now the boring opencl code |
|
|
248 | my $src = <<EOF; |
|
|
249 | kernel void |
|
|
250 | juliatunnel (write_only image2d_t img, float time) |
|
|
251 | { |
|
|
252 | float2 p = (float2)(get_global_id (0), get_global_id (1)) / 256.f * 2.f - 1.f; |
|
|
253 | |
|
|
254 | float2 m = (float2)(1.f, p.y) / fabs (p.x); |
|
|
255 | m.x = fabs (fmod (m.x + time * 0.05f, 4.f)) - 2.f; |
|
|
256 | |
|
|
257 | float2 z = m; |
|
|
258 | float2 c = (float2)(sin (time * 0.05005), cos (time * 0.06001)); |
|
|
259 | |
|
|
260 | for (int i = 0; i < 25 && dot (z, z) < 4.f; ++i) |
|
|
261 | z = (float2)(z.x * z.x - z.y * z.y, 2.f * z.x * z.y) + c; |
|
|
262 | |
|
|
263 | float3 colour = (float3)(z.x, z.y, z.x * z.y); |
|
|
264 | write_imagef (img, (int2)(get_global_id (0), get_global_id (1)), (float4)(colour * p.x * p.x, 1.)); |
|
|
265 | } |
|
|
266 | EOF |
|
|
267 | |
|
|
268 | my $prog = $ctx->build_program ($src); |
|
|
269 | my $kernel = $prog->kernel ("juliatunnel"); |
|
|
270 | |
|
|
271 | # program compiled, kernel ready, now draw and loop |
|
|
272 | |
|
|
273 | for (my $time; ; ++$time) { |
|
|
274 | # acquire objects from opengl |
|
|
275 | $queue->enqueue_acquire_gl_objects ([$tex]); |
|
|
276 | |
|
|
277 | # configure and run our kernel |
|
|
278 | $kernel->set_image2d (0, $tex); |
|
|
279 | $kernel->set_float (1, $time); |
|
|
280 | $queue->enqueue_nd_range_kernel ($kernel, undef, [256, 256], undef); |
|
|
281 | |
|
|
282 | # release objects to opengl again |
|
|
283 | $queue->enqueue_release_gl_objects ([$tex]); |
|
|
284 | |
|
|
285 | # wait |
|
|
286 | $queue->finish; |
|
|
287 | |
|
|
288 | # now draw the texture, the defaults should be all right |
|
|
289 | glTexParameterf GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST; |
|
|
290 | |
|
|
291 | glEnable GL_TEXTURE_2D; |
|
|
292 | glBegin GL_QUADS; |
|
|
293 | glTexCoord2f 0, 1; glVertex3i -1, -1, -1; |
|
|
294 | glTexCoord2f 0, 0; glVertex3i 1, -1, -1; |
|
|
295 | glTexCoord2f 1, 0; glVertex3i 1, 1, -1; |
|
|
296 | glTexCoord2f 1, 1; glVertex3i -1, 1, -1; |
|
|
297 | glEnd; |
|
|
298 | |
|
|
299 | glXSwapBuffers; |
|
|
300 | |
|
|
301 | select undef, undef, undef, 1/60; |
|
|
302 | } |
215 | |
303 | |
216 | =head1 DOCUMENTATION |
304 | =head1 DOCUMENTATION |
217 | |
305 | |
218 | =head2 BASIC CONVENTIONS |
306 | =head2 BASIC CONVENTIONS |
219 | |
307 | |
… | |
… | |
241 | =item * Structures are often specified by flattening out their components |
329 | =item * Structures are often specified by flattening out their components |
242 | as with short vectors, and returned as arrayrefs. |
330 | as with short vectors, and returned as arrayrefs. |
243 | |
331 | |
244 | =item * When enqueuing commands, the wait list is specified by adding |
332 | =item * When enqueuing commands, the wait list is specified by adding |
245 | extra arguments to the function - anywhere a C<$wait_events...> argument |
333 | extra arguments to the function - anywhere a C<$wait_events...> argument |
246 | is documented this can be any number of event objects. |
334 | is documented this can be any number of event objects. As an extsnion |
|
|
335 | implemented by this module, C<undef> values will be ignored in the event |
|
|
336 | list. |
247 | |
337 | |
248 | =item * When enqueuing commands, if the enqueue method is called in void |
338 | =item * When enqueuing commands, if the enqueue method is called in void |
249 | context, no event is created. In all other contexts an event is returned |
339 | context, no event is created. In all other contexts an event is returned |
250 | by the method. |
340 | by the method. |
251 | |
341 | |
… | |
… | |
271 | ulong IV - Q |
361 | ulong IV - Q |
272 | float NV float f |
362 | float NV float f |
273 | half IV ushort S |
363 | half IV ushort S |
274 | double NV double d |
364 | double NV double d |
275 | |
365 | |
|
|
366 | =head2 GLX SUPPORT |
|
|
367 | |
|
|
368 | Due to the sad state that OpenGL support is in in Perl (mostly the OpenGL |
|
|
369 | module, which has little to no documentation and has little to no support |
|
|
370 | for glX), this module, as a special extension, treats context creation |
|
|
371 | properties C<OpenCL::GLX_DISPLAY_KHR> and C<OpenCL::GL_CONTEXT_KHR> |
|
|
372 | specially: If either or both of these are C<undef>, then the OpenCL |
|
|
373 | module tries to dynamically resolve C<glXGetCurrentDisplay> and |
|
|
374 | C<glXGetCurrentContext>, call these functions and use their return values |
|
|
375 | instead. |
|
|
376 | |
|
|
377 | 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 |
|
|
379 | capable of finding the function via C<RTLD_DEFAULT>. |
|
|
380 | |
|
|
381 | =cut |
|
|
382 | |
|
|
383 | package OpenCL; |
|
|
384 | |
|
|
385 | use common::sense; |
|
|
386 | |
|
|
387 | BEGIN { |
|
|
388 | our $VERSION = '0.96'; |
|
|
389 | |
|
|
390 | require XSLoader; |
|
|
391 | XSLoader::load (__PACKAGE__, $VERSION); |
|
|
392 | |
|
|
393 | @OpenCL::Platform::ISA = |
|
|
394 | @OpenCL::Device::ISA = |
|
|
395 | @OpenCL::Context::ISA = |
|
|
396 | @OpenCL::Queue::ISA = |
|
|
397 | @OpenCL::Memory::ISA = |
|
|
398 | @OpenCL::Sampler::ISA = |
|
|
399 | @OpenCL::Program::ISA = |
|
|
400 | @OpenCL::Kernel::ISA = |
|
|
401 | @OpenCL::Event::ISA = OpenCL::Object::; |
|
|
402 | |
|
|
403 | @OpenCL::Buffer::ISA = |
|
|
404 | @OpenCL::Image::ISA = OpenCL::Memory::; |
|
|
405 | |
|
|
406 | @OpenCL::BufferObj::ISA = OpenCL::Buffer::; |
|
|
407 | |
|
|
408 | @OpenCL::Image2D::ISA = |
|
|
409 | @OpenCL::Image3D::ISA = |
|
|
410 | @OpenCL::Image2DArray::ISA = |
|
|
411 | @OpenCL::Image1D::ISA = |
|
|
412 | @OpenCL::Image1DArray::ISA = |
|
|
413 | @OpenCL::Image1DBuffer::ISA = OpenCL::Image::; |
|
|
414 | |
|
|
415 | @OpenCL::UserEvent::ISA = OpenCL::Event::; |
|
|
416 | } |
|
|
417 | |
276 | =head2 THE OpenCL PACKAGE |
418 | =head2 THE OpenCL PACKAGE |
277 | |
419 | |
278 | =over 4 |
420 | =over 4 |
279 | |
421 | |
280 | =item $int = OpenCL::errno |
422 | =item $int = OpenCL::errno |
… | |
… | |
286 | |
428 | |
287 | Comverts an error value into a human readable string. |
429 | Comverts an error value into a human readable string. |
288 | |
430 | |
289 | =item $str = OpenCL::enum2str $enum |
431 | =item $str = OpenCL::enum2str $enum |
290 | |
432 | |
291 | Converts most enum values (inof parameter names, image format constants, |
433 | Converts most enum values (of parameter names, image format constants, |
292 | object types, addressing and filter modes, command types etc.) into a |
434 | object types, addressing and filter modes, command types etc.) into a |
293 | human readbale string. When confronted with some random integer it can be |
435 | human readable string. When confronted with some random integer it can be |
294 | very helpful to pass it through this function to maybe get some readable |
436 | very helpful to pass it through this function to maybe get some readable |
295 | string out of it. |
437 | string out of it. |
296 | |
438 | |
297 | =item @platforms = OpenCL::platforms |
439 | =item @platforms = OpenCL::platforms |
298 | |
440 | |
… | |
… | |
309 | =item OpenCL::wait_for_events $wait_events... |
451 | =item OpenCL::wait_for_events $wait_events... |
310 | |
452 | |
311 | Waits for all events to complete. |
453 | Waits for all events to complete. |
312 | |
454 | |
313 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
455 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
|
|
456 | |
|
|
457 | =back |
|
|
458 | |
|
|
459 | =head2 THE OpenCL::Object CLASS |
|
|
460 | |
|
|
461 | This is the base class for all objects in the OpenCL module. The only |
|
|
462 | method it implements is the C<id> method, which is only useful if you want |
|
|
463 | to interface to OpenCL on the C level. |
|
|
464 | |
|
|
465 | =over 4 |
|
|
466 | |
|
|
467 | =item $iv = $obj->id |
|
|
468 | |
|
|
469 | OpenCL objects are represented by pointers or integers on the C level. If |
|
|
470 | you want to interface to an OpenCL object directly on the C level, then |
|
|
471 | you need this value, which is returned by this method. You should use an |
|
|
472 | C<IV> type in your code and cast that to the correct type. |
|
|
473 | |
|
|
474 | =cut |
|
|
475 | |
|
|
476 | sub OpenCL::Object::id { |
|
|
477 | ${$_[0]} |
|
|
478 | } |
314 | |
479 | |
315 | =back |
480 | =back |
316 | |
481 | |
317 | =head2 THE OpenCL::Platform CLASS |
482 | =head2 THE OpenCL::Platform CLASS |
318 | |
483 | |
… | |
… | |
344 | It's best to avoid this method and use one of the following convenience |
509 | It's best to avoid this method and use one of the following convenience |
345 | wrappers. |
510 | wrappers. |
346 | |
511 | |
347 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html> |
512 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html> |
348 | |
513 | |
|
|
514 | =item $platform->unload_compiler |
|
|
515 | |
|
|
516 | Attempts to unload the compiler for this platform, for endless |
|
|
517 | profit. Does nothing on OpenCL 1.1. |
|
|
518 | |
|
|
519 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clUnloadPlatformCompiler.html> |
|
|
520 | |
349 | =for gengetinfo begin platform |
521 | =for gengetinfo begin platform |
350 | |
522 | |
351 | =item $string = $platform->profile |
523 | =item $string = $platform->profile |
352 | |
524 | |
353 | Calls C<clGetPlatformInfo> with C<CL_PLATFORM_PROFILE> and returns the result. |
525 | Calls C<clGetPlatformInfo> with C<CL_PLATFORM_PROFILE> and returns the result. |
… | |
… | |
638 | |
810 | |
639 | =item @device_partition_property_exts = $device->affinity_domains_ext |
811 | =item @device_partition_property_exts = $device->affinity_domains_ext |
640 | |
812 | |
641 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_AFFINITY_DOMAINS_EXT> and returns the result. |
813 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_AFFINITY_DOMAINS_EXT> and returns the result. |
642 | |
814 | |
643 | =item $uint = $device->reference_count_ext |
815 | =item $uint = $device->reference_count_ext |
644 | |
816 | |
645 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_REFERENCE_COUNT_EXT > and returns the result. |
817 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_REFERENCE_COUNT_EXT> and returns the result. |
646 | |
818 | |
647 | =item @device_partition_property_exts = $device->partition_style_ext |
819 | =item @device_partition_property_exts = $device->partition_style_ext |
648 | |
820 | |
649 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_STYLE_EXT> and returns the result. |
821 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_STYLE_EXT> and returns the result. |
650 | |
822 | |
… | |
… | |
654 | |
826 | |
655 | =head2 THE OpenCL::Context CLASS |
827 | =head2 THE OpenCL::Context CLASS |
656 | |
828 | |
657 | =over 4 |
829 | =over 4 |
658 | |
830 | |
|
|
831 | =item $prog = $ctx->build_program ($program, $options = "") |
|
|
832 | |
|
|
833 | This convenience function tries to build the program on all devices in |
|
|
834 | the context. If the build fails, then the function will C<croak> with the |
|
|
835 | build log. Otherwise ti returns the program object. |
|
|
836 | |
|
|
837 | The C<$program> can either be a C<OpenCL::Program> object or a string |
|
|
838 | containing the program. In the latter case, a program objetc will be |
|
|
839 | created automatically. |
|
|
840 | |
|
|
841 | =cut |
|
|
842 | |
|
|
843 | sub OpenCL::Context::build_program { |
|
|
844 | my ($self, $prog, $options) = @_; |
|
|
845 | |
|
|
846 | $prog = $self->program_with_source ($prog) |
|
|
847 | unless ref $prog; |
|
|
848 | |
|
|
849 | for my $dev ($self->devices) { |
|
|
850 | eval { $prog->build ($dev, $options); 1 } |
|
|
851 | or Carp::croak "Building OpenCL program for device '" . $dev->name . "' failed:\n" |
|
|
852 | . $prog->build_log ($dev); |
|
|
853 | } |
|
|
854 | |
|
|
855 | $prog |
|
|
856 | } |
|
|
857 | |
659 | =item $queue = $ctx->queue ($device, $properties) |
858 | =item $queue = $ctx->queue ($device, $properties) |
660 | |
859 | |
661 | Create a new OpenCL::Queue object from the context and the given device. |
860 | Create a new OpenCL::Queue object from the context and the given device. |
662 | |
861 | |
663 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html> |
862 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html> |
|
|
863 | |
|
|
864 | Example: create an out-of-order queue. |
|
|
865 | |
|
|
866 | $queue = $ctx->queue ($device, OpenCL::QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE); |
664 | |
867 | |
665 | =item $ev = $ctx->user_event |
868 | =item $ev = $ctx->user_event |
666 | |
869 | |
667 | Creates a new OpenCL::UserEvent object. |
870 | Creates a new OpenCL::UserEvent object. |
668 | |
871 | |
… | |
… | |
678 | =item $buf = $ctx->buffer_sv ($flags, $data) |
881 | =item $buf = $ctx->buffer_sv ($flags, $data) |
679 | |
882 | |
680 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and |
883 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and |
681 | initialise it with the given data values. |
884 | initialise it with the given data values. |
682 | |
885 | |
|
|
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) |
|
|
887 | |
|
|
888 | Creates a new OpenCL::Image object and optionally initialises it with |
|
|
889 | the given data values. |
|
|
890 | |
|
|
891 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html> |
|
|
892 | |
683 | =item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $row_pitch = 0, $data = undef) |
893 | =item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $row_pitch = 0, $data = undef) |
684 | |
894 | |
685 | Creates a new OpenCL::Image2D object and optionally initialises it with |
895 | Creates a new OpenCL::Image2D object and optionally initialises it with |
686 | the given data values. |
896 | the given data values. |
687 | |
897 | |
… | |
… | |
691 | |
901 | |
692 | Creates a new OpenCL::Image3D object and optionally initialises it with |
902 | Creates a new OpenCL::Image3D object and optionally initialises it with |
693 | the given data values. |
903 | the given data values. |
694 | |
904 | |
695 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage3D.html> |
905 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage3D.html> |
|
|
906 | |
|
|
907 | =item $buffer = $ctx->gl_buffer ($flags, $bufobj) |
|
|
908 | |
|
|
909 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object that refers to the given |
|
|
910 | OpenGL buffer object. |
|
|
911 | |
|
|
912 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLBuffer.html |
|
|
913 | |
|
|
914 | =item $img = $ctx->gl_texture ($flags, $target, $miplevel, $texture) |
|
|
915 | |
|
|
916 | Creates a new OpenCL::Image object that refers to the given OpenGL |
|
|
917 | texture object or buffer. |
|
|
918 | |
|
|
919 | http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateFromGLTexture.html |
|
|
920 | |
|
|
921 | =item $img = $ctx->gl_texture2d ($flags, $target, $miplevel, $texture) |
|
|
922 | |
|
|
923 | Creates a new OpenCL::Image2D object that refers to the given OpenGL |
|
|
924 | 2D texture object. |
|
|
925 | |
|
|
926 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture2D.html |
|
|
927 | |
|
|
928 | =item $img = $ctx->gl_texture3d ($flags, $target, $miplevel, $texture) |
|
|
929 | |
|
|
930 | Creates a new OpenCL::Image3D object that refers to the given OpenGL |
|
|
931 | 3D texture object. |
|
|
932 | |
|
|
933 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture3D.html |
|
|
934 | |
|
|
935 | =item $ctx->gl_renderbuffer ($flags, $renderbuffer) |
|
|
936 | |
|
|
937 | Creates a new OpenCL::Image2D object that refers to the given OpenGL |
|
|
938 | render buffer. |
|
|
939 | |
|
|
940 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLRenderbuffer.html |
696 | |
941 | |
697 | =item @formats = $ctx->supported_image_formats ($flags, $image_type) |
942 | =item @formats = $ctx->supported_image_formats ($flags, $image_type) |
698 | |
943 | |
699 | Returns a list of matching image formats - each format is an arrayref with |
944 | Returns a list of matching image formats - each format is an arrayref with |
700 | two values, $channel_order and $channel_type, in it. |
945 | two values, $channel_order and $channel_type, in it. |
… | |
… | |
751 | for completion, unless the method is called in void context, in which case |
996 | for completion, unless the method is called in void context, in which case |
752 | no event object is created. |
997 | no event object is created. |
753 | |
998 | |
754 | They also allow you to specify any number of other event objects that this |
999 | They also allow you to specify any number of other event objects that this |
755 | request has to wait for before it starts executing, by simply passing the |
1000 | request has to wait for before it starts executing, by simply passing the |
756 | event objects as extra parameters to the enqueue methods. |
1001 | event objects as extra parameters to the enqueue methods. To simplify |
|
|
1002 | program design, this module ignores any C<undef> values in the list of |
|
|
1003 | events. This makes it possible to code operations such as this, without |
|
|
1004 | having to put a valid event object into C<$event> first: |
|
|
1005 | |
|
|
1006 | $event = $queue->enqueue_xxx (..., $event); |
757 | |
1007 | |
758 | Queues execute in-order by default, without any parallelism, so in most |
1008 | Queues execute in-order by default, without any parallelism, so in most |
759 | cases (i.e. you use only one queue) it's not necessary to wait for or |
1009 | cases (i.e. you use only one queue) it's not necessary to wait for or |
760 | create event objects. |
1010 | create event objects, althoguh an our of order queue is often a bit |
|
|
1011 | faster. |
761 | |
1012 | |
762 | =over 4 |
1013 | =over 4 |
763 | |
1014 | |
764 | =item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) |
1015 | =item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) |
765 | |
1016 | |
… | |
… | |
808 | =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...) |
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...) |
809 | |
1060 | |
810 | Yeah. |
1061 | Yeah. |
811 | |
1062 | |
812 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
1063 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
|
|
1064 | |
|
|
1065 | =item $ev = $queue->enqueue_fill_buffer ($mem, $pattern, $offset, $size, ...) |
|
|
1066 | |
|
|
1067 | Fills the given buffer object with repeated applications of C<$pattern>, |
|
|
1068 | starting at C<$offset> for C<$size> octets. |
|
|
1069 | |
|
|
1070 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html> |
|
|
1071 | |
|
|
1072 | =item $ev = $queue->enqueue_fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...) |
|
|
1073 | |
|
|
1074 | 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>, |
|
|
1076 | 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. |
|
|
1078 | |
|
|
1079 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html> |
813 | |
1080 | |
814 | =item $ev = $queue->enqueue_task ($kernel, $wait_events...) |
1081 | =item $ev = $queue->enqueue_task ($kernel, $wait_events...) |
815 | |
1082 | |
816 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
1083 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
817 | |
1084 | |
… | |
… | |
831 | reference to an array of local work sizes, with the same number of |
1098 | reference to an array of local work sizes, with the same number of |
832 | elements as @$global_work_size. |
1099 | elements as @$global_work_size. |
833 | |
1100 | |
834 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
1101 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
835 | |
1102 | |
836 | =item $ev = $queue->enqueue_marker |
1103 | =item $ev = $queue->enqueue_acquire_gl_objects ([object, ...], $wait_events...) |
837 | |
1104 | |
|
|
1105 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired |
|
|
1106 | for subsequent OpenCL usage. |
|
|
1107 | |
838 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueMarker.html> |
1108 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html> |
|
|
1109 | |
|
|
1110 | =item $ev = $queue->enqueue_release_gl_objects ([object, ...], $wait_events...) |
|
|
1111 | |
|
|
1112 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be released |
|
|
1113 | for subsequent OpenGL usage. |
|
|
1114 | |
|
|
1115 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html> |
839 | |
1116 | |
840 | =item $ev = $queue->enqueue_wait_for_events ($wait_events...) |
1117 | =item $ev = $queue->enqueue_wait_for_events ($wait_events...) |
841 | |
1118 | |
842 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
1119 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
843 | |
1120 | |
844 | =item $queue->enqueue_barrier |
1121 | =item $ev = $queue->enqueue_marker ($wait_events...) |
845 | |
1122 | |
|
|
1123 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html> |
|
|
1124 | |
|
|
1125 | =item $ev = $queue->enqueue_barrier ($wait_events...) |
|
|
1126 | |
846 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueBarrier.html> |
1127 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html> |
847 | |
1128 | |
848 | =item $queue->flush |
1129 | =item $queue->flush |
849 | |
1130 | |
850 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html> |
1131 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html> |
851 | |
1132 | |
… | |
… | |
931 | =item $int = $mem->offset |
1212 | =item $int = $mem->offset |
932 | |
1213 | |
933 | Calls C<clGetMemObjectInfo> with C<CL_MEM_OFFSET> and returns the result. |
1214 | Calls C<clGetMemObjectInfo> with C<CL_MEM_OFFSET> and returns the result. |
934 | |
1215 | |
935 | =for gengetinfo end mem |
1216 | =for gengetinfo end mem |
|
|
1217 | |
|
|
1218 | =item ($type, $name) = $mem->gl_object_info |
|
|
1219 | |
|
|
1220 | Returns the OpenGL object type (e.g. OpenCL::GL_OBJECT_TEXTURE2D) and the |
|
|
1221 | object "name" (e.g. the texture name) used to create this memory object. |
|
|
1222 | |
|
|
1223 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetGLObjectInfo.html> |
936 | |
1224 | |
937 | =back |
1225 | =back |
938 | |
1226 | |
939 | =head2 THE OpenCL::Buffer CLASS |
1227 | =head2 THE OpenCL::Buffer CLASS |
940 | |
1228 | |
… | |
… | |
959 | |
1247 | |
960 | =back |
1248 | =back |
961 | |
1249 | |
962 | =head2 THE OpenCL::Image CLASS |
1250 | =head2 THE OpenCL::Image CLASS |
963 | |
1251 | |
964 | This is the superclass of all image objects - OpenCL::Image2D and OpenCL::Image3D. |
1252 | This is the superclass of all image objects - OpenCL::Image1D, |
|
|
1253 | OpenCL::Image1DArray, OpenCL::Image1DBuffer, OpenCL::Image2D, |
|
|
1254 | OpenCL::Image2DArray and OpenCL::Image3D. |
965 | |
1255 | |
966 | =over 4 |
1256 | =over 4 |
967 | |
1257 | |
968 | =item $packed_value = $ev->image_info ($name) |
1258 | =item $packed_value = $image->image_info ($name) |
969 | |
1259 | |
970 | See C<< $platform->info >> for details. |
1260 | See C<< $platform->info >> for details. |
971 | |
1261 | |
972 | The reason this method is not called C<info> is that there already is an |
1262 | The reason this method is not called C<info> is that there already is an |
973 | C<< ->info >> method inherited from C<OpenCL::Memory>. |
1263 | C<< ->info >> method inherited from C<OpenCL::Memory>. |
974 | |
1264 | |
975 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html> |
1265 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html> |
976 | |
1266 | |
|
|
1267 | =item ($channel_order, $channel_data_type) = $image->format |
|
|
1268 | |
|
|
1269 | Returns the channel order and type used to create the image by calling |
|
|
1270 | C<clGetImageInfo> with C<CL_IMAGE_FORMAT>. |
|
|
1271 | |
977 | =for gengetinfo begin image |
1272 | =for gengetinfo begin image |
978 | |
1273 | |
979 | =item $int = $image->element_size |
1274 | =item $int = $image->element_size |
980 | |
1275 | |
981 | Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result. |
1276 | Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result. |
… | |
… | |
1000 | |
1295 | |
1001 | Calls C<clGetImageInfo> with C<CL_IMAGE_DEPTH> and returns the result. |
1296 | Calls C<clGetImageInfo> with C<CL_IMAGE_DEPTH> and returns the result. |
1002 | |
1297 | |
1003 | =for gengetinfo end image |
1298 | =for gengetinfo end image |
1004 | |
1299 | |
|
|
1300 | =for gengetinfo begin gl_texture |
|
|
1301 | |
|
|
1302 | =item $GLenum = $gl_texture->target |
|
|
1303 | |
|
|
1304 | Calls C<clGetGLTextureInfo> with C<CL_GL_TEXTURE_TARGET> and returns the result. |
|
|
1305 | |
|
|
1306 | =item $GLint = $gl_texture->gl_mipmap_level |
|
|
1307 | |
|
|
1308 | Calls C<clGetGLTextureInfo> with C<CL_GL_MIPMAP_LEVEL> and returns the result. |
|
|
1309 | |
|
|
1310 | =for gengetinfo end gl_texture |
|
|
1311 | |
1005 | =back |
1312 | =back |
1006 | |
1313 | |
1007 | =head2 THE OpenCL::Sampler CLASS |
1314 | =head2 THE OpenCL::Sampler CLASS |
1008 | |
1315 | |
1009 | =over 4 |
1316 | =over 4 |
… | |
… | |
1044 | |
1351 | |
1045 | =over 4 |
1352 | =over 4 |
1046 | |
1353 | |
1047 | =item $program->build ($device, $options = "") |
1354 | =item $program->build ($device, $options = "") |
1048 | |
1355 | |
1049 | Tries to build the program with the givne options. |
1356 | Tries to build the program with the given options. See also the |
|
|
1357 | C<$ctx->build> convenience function. |
1050 | |
1358 | |
1051 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
1359 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
1052 | |
1360 | |
1053 | =item $packed_value = $program->build_info ($device, $name) |
1361 | =item $packed_value = $program->build_info ($device, $name) |
1054 | |
1362 | |
… | |
… | |
1061 | |
1369 | |
1062 | Creates an OpenCL::Kernel object out of the named C<__kernel> function in |
1370 | Creates an OpenCL::Kernel object out of the named C<__kernel> function in |
1063 | the program. |
1371 | the program. |
1064 | |
1372 | |
1065 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html> |
1373 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html> |
|
|
1374 | |
|
|
1375 | =item @kernels = $program->kernels_in_program |
|
|
1376 | |
|
|
1377 | Returns all kernels successfully compiled for all devices in program. |
|
|
1378 | |
|
|
1379 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernelsInProgram.html |
1066 | |
1380 | |
1067 | =for gengetinfo begin program_build |
1381 | =for gengetinfo begin program_build |
1068 | |
1382 | |
1069 | =item $build_status = $program->build_status ($device) |
1383 | =item $build_status = $program->build_status ($device) |
1070 | |
1384 | |
… | |
… | |
1198 | |
1512 | |
1199 | This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>. |
1513 | This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>. |
1200 | |
1514 | |
1201 | TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>, |
1515 | TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>, |
1202 | C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>, |
1516 | C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>, |
1203 | C<image2d>, C<image3d>, C<sampler> or C<event>. |
1517 | C<image2d>, C<image3d>, C<sampler>, C<local> or C<event>. |
1204 | |
1518 | |
1205 | Chars and integers (including the half type) are specified as integers, |
1519 | Chars and integers (including the half type) are specified as integers, |
1206 | float and double as floating point values, memory/buffer/image2d/image3d |
1520 | float and double as floating point values, memory/buffer/image2d/image3d |
1207 | must be an object of that type or C<undef>, and sampler and event must be |
1521 | must be an object of that type or C<undef>, local-memory arguments are |
1208 | objects of that type. |
1522 | set by specifying the size, and sampler and event must be objects of that |
|
|
1523 | type. |
|
|
1524 | |
|
|
1525 | Setting an argument for a kernel does NOT keep a reference to the object - |
|
|
1526 | for example, if you set an argument to some image object, free the image, |
|
|
1527 | and call the kernel, you will run into undefined behaviour. |
1209 | |
1528 | |
1210 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html> |
1529 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html> |
1211 | |
1530 | |
1212 | =back |
1531 | =back |
1213 | |
1532 | |
… | |
… | |
1297 | |
1616 | |
1298 | =back |
1617 | =back |
1299 | |
1618 | |
1300 | =cut |
1619 | =cut |
1301 | |
1620 | |
1302 | package OpenCL; |
|
|
1303 | |
|
|
1304 | use common::sense; |
|
|
1305 | |
|
|
1306 | BEGIN { |
|
|
1307 | our $VERSION = '0.91'; |
|
|
1308 | |
|
|
1309 | require XSLoader; |
|
|
1310 | XSLoader::load (__PACKAGE__, $VERSION); |
|
|
1311 | |
|
|
1312 | @OpenCL::Buffer::ISA = |
|
|
1313 | @OpenCL::Image::ISA = OpenCL::Memory::; |
|
|
1314 | |
|
|
1315 | @OpenCL::BufferObj::ISA = OpenCL::Buffer::; |
|
|
1316 | |
|
|
1317 | @OpenCL::Image2D::ISA = |
|
|
1318 | @OpenCL::Image3D::ISA = OpenCL::Image::; |
|
|
1319 | |
|
|
1320 | @OpenCL::UserEvent::ISA = OpenCL::Event::; |
|
|
1321 | } |
|
|
1322 | |
|
|
1323 | 1; |
1621 | 1; |
1324 | |
1622 | |
1325 | =head1 AUTHOR |
1623 | =head1 AUTHOR |
1326 | |
1624 | |
1327 | Marc Lehmann <schmorp@schmorp.de> |
1625 | Marc Lehmann <schmorp@schmorp.de> |