… | |
… | |
105 | for my $platform (OpenCL::platforms) { |
105 | for my $platform (OpenCL::platforms) { |
106 | printf "platform: %s\n", $platform->name; |
106 | printf "platform: %s\n", $platform->name; |
107 | printf "extensions: %s\n", $platform->extensions; |
107 | printf "extensions: %s\n", $platform->extensions; |
108 | for my $device ($platform->devices) { |
108 | for my $device ($platform->devices) { |
109 | printf "+ device: %s\n", $device->name; |
109 | printf "+ device: %s\n", $device->name; |
110 | my $ctx = $device->context; |
110 | my $ctx = $platform->context (undef, [$device]); |
111 | # do stuff |
111 | # do stuff |
112 | } |
112 | } |
113 | } |
113 | } |
114 | |
114 | |
115 | =head2 Get a useful context and a command queue. |
115 | =head2 Get a useful context and a command queue. |
… | |
… | |
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 | |
276 | =head2 THE OpenCL PACKAGE |
381 | =head2 THE OpenCL PACKAGE |
277 | |
382 | |
278 | =over 4 |
383 | =over 4 |
279 | |
384 | |
280 | =item $int = OpenCL::errno |
385 | =item $int = OpenCL::errno |
… | |
… | |
286 | |
391 | |
287 | Comverts an error value into a human readable string. |
392 | Comverts an error value into a human readable string. |
288 | |
393 | |
289 | =item $str = OpenCL::enum2str $enum |
394 | =item $str = OpenCL::enum2str $enum |
290 | |
395 | |
291 | Converts most enum values (inof parameter names, image format constants, |
396 | Converts most enum values (of parameter names, image format constants, |
292 | object types, addressing and filter modes, command types etc.) into a |
397 | object types, addressing and filter modes, command types etc.) into a |
293 | human readbale string. When confronted with some random integer it can be |
398 | 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 |
399 | very helpful to pass it through this function to maybe get some readable |
295 | string out of it. |
400 | string out of it. |
296 | |
401 | |
297 | =item @platforms = OpenCL::platforms |
402 | =item @platforms = OpenCL::platforms |
298 | |
403 | |
… | |
… | |
326 | |
431 | |
327 | Tries to create a context. Never worked for me, and you need devices explicitly anyway. |
432 | Tries to create a context. Never worked for me, and you need devices explicitly anyway. |
328 | |
433 | |
329 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
434 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
330 | |
435 | |
331 | =item $ctx = $device->context ($properties = undef, @$devices, $notify = undef) |
436 | =item $ctx = $platform->context ($properties = undef, @$devices, $notify = undef) |
332 | |
437 | |
333 | Create a new OpenCL::Context object using the given device object(s)- a |
438 | Create a new OpenCL::Context object using the given device object(s)- a |
334 | CL_CONTEXT_PLATFORM property is supplied automatically. |
439 | CL_CONTEXT_PLATFORM property is supplied automatically. |
335 | |
440 | |
336 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> |
441 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> |
… | |
… | |
344 | It's best to avoid this method and use one of the following convenience |
449 | It's best to avoid this method and use one of the following convenience |
345 | wrappers. |
450 | wrappers. |
346 | |
451 | |
347 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html> |
452 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html> |
348 | |
453 | |
|
|
454 | =item $platform->unload_compiler |
|
|
455 | |
|
|
456 | Attempts to unload the compiler for this platform, for endless |
|
|
457 | profit. Does nothing on OpenCL 1.1. |
|
|
458 | |
|
|
459 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clUnloadPlatformCompiler.html> |
|
|
460 | |
349 | =for gengetinfo begin platform |
461 | =for gengetinfo begin platform |
350 | |
462 | |
351 | =item $string = $platform->profile |
463 | =item $string = $platform->profile |
352 | |
464 | |
353 | Calls C<clGetPlatformInfo> with C<CL_PLATFORM_PROFILE> and returns the result. |
465 | Calls C<clGetPlatformInfo> with C<CL_PLATFORM_PROFILE> and returns the result. |
… | |
… | |
638 | |
750 | |
639 | =item @device_partition_property_exts = $device->affinity_domains_ext |
751 | =item @device_partition_property_exts = $device->affinity_domains_ext |
640 | |
752 | |
641 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_AFFINITY_DOMAINS_EXT> and returns the result. |
753 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_AFFINITY_DOMAINS_EXT> and returns the result. |
642 | |
754 | |
643 | =item $uint = $device->reference_count_ext |
755 | =item $uint = $device->reference_count_ext |
644 | |
756 | |
645 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_REFERENCE_COUNT_EXT > and returns the result. |
757 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_REFERENCE_COUNT_EXT> and returns the result. |
646 | |
758 | |
647 | =item @device_partition_property_exts = $device->partition_style_ext |
759 | =item @device_partition_property_exts = $device->partition_style_ext |
648 | |
760 | |
649 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_STYLE_EXT> and returns the result. |
761 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_STYLE_EXT> and returns the result. |
650 | |
762 | |
… | |
… | |
654 | |
766 | |
655 | =head2 THE OpenCL::Context CLASS |
767 | =head2 THE OpenCL::Context CLASS |
656 | |
768 | |
657 | =over 4 |
769 | =over 4 |
658 | |
770 | |
|
|
771 | =item $prog = $ctx->build_program ($program, $options = "") |
|
|
772 | |
|
|
773 | This convenience function tries to build the program on all devices in |
|
|
774 | the context. If the build fails, then the function will C<croak> with the |
|
|
775 | build log. Otherwise ti returns the program object. |
|
|
776 | |
|
|
777 | The C<$program> can either be a C<OpenCL::Program> object or a string |
|
|
778 | containing the program. In the latter case, a program objetc will be |
|
|
779 | created automatically. |
|
|
780 | |
|
|
781 | =cut |
|
|
782 | |
|
|
783 | sub OpenCL::Context::build_program { |
|
|
784 | my ($self, $prog, $options) = @_; |
|
|
785 | |
|
|
786 | $prog = $self->program_with_source ($prog) |
|
|
787 | unless ref $prog; |
|
|
788 | |
|
|
789 | for my $dev ($self->devices) { |
|
|
790 | eval { $prog->build ($dev, $options); 1 } |
|
|
791 | or Carp::croak "Building OpenCL program for device '" . $dev->name . "' failed:\n" |
|
|
792 | . $prog->build_log ($dev); |
|
|
793 | } |
|
|
794 | |
|
|
795 | $prog |
|
|
796 | } |
|
|
797 | |
659 | =item $queue = $ctx->queue ($device, $properties) |
798 | =item $queue = $ctx->queue ($device, $properties) |
660 | |
799 | |
661 | Create a new OpenCL::Queue object from the context and the given device. |
800 | Create a new OpenCL::Queue object from the context and the given device. |
662 | |
801 | |
663 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html> |
802 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html> |
664 | |
803 | |
|
|
804 | Example: create an out-of-order queue. |
|
|
805 | |
|
|
806 | $queue = $ctx->queue ($device, OpenCL::QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE); |
|
|
807 | |
665 | =item $ev = $ctx->user_event |
808 | =item $ev = $ctx->user_event |
666 | |
809 | |
667 | Creates a new OpenCL::UserEvent object. |
810 | Creates a new OpenCL::UserEvent object. |
668 | |
811 | |
669 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateUserEvent.html> |
812 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateUserEvent.html> |
670 | |
813 | |
671 | =item $buf = $ctx->buffer ($flags, $len) |
814 | =item $buf = $ctx->buffer ($flags, $len) |
672 | |
815 | |
673 | Creates a new OpenCL::Buffer object with the given flags and octet-size. |
816 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object with the |
|
|
817 | given flags and octet-size. |
674 | |
818 | |
675 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateBuffer.html> |
819 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateBuffer.html> |
676 | |
820 | |
677 | =item $buf = $ctx->buffer_sv ($flags, $data) |
821 | =item $buf = $ctx->buffer_sv ($flags, $data) |
678 | |
822 | |
679 | Creates a new OpenCL::Buffer object and initialise it with the given data values. |
823 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and |
|
|
824 | initialise it with the given data values. |
|
|
825 | |
|
|
826 | =item $img = $ctx->image ($self, $flags, $channel_order, $channel_type, $type, $width, $height, $depth, $array_size = 0, $row_pitch = 0, $slice_pitch = 0, $num_mip_level = 0, $num_samples = 0, $*data = &PL_sv_undef) |
|
|
827 | |
|
|
828 | Creates a new OpenCL::Image object and optionally initialises it with |
|
|
829 | the given data values. |
|
|
830 | |
|
|
831 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html> |
680 | |
832 | |
681 | =item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $row_pitch = 0, $data = undef) |
833 | =item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $row_pitch = 0, $data = undef) |
682 | |
834 | |
683 | Creates a new OpenCL::Image2D object and optionally initialises it with the given data values. |
835 | Creates a new OpenCL::Image2D object and optionally initialises it with |
|
|
836 | the given data values. |
684 | |
837 | |
685 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage2D.html> |
838 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage2D.html> |
686 | |
839 | |
687 | =item $img = $ctx->image3d ($flags, $channel_order, $channel_type, $width, $height, $depth, $row_pitch = 0, $slice_pitch = 0, $data = undef) |
840 | =item $img = $ctx->image3d ($flags, $channel_order, $channel_type, $width, $height, $depth, $row_pitch = 0, $slice_pitch = 0, $data = undef) |
688 | |
841 | |
689 | Creates a new OpenCL::Image3D object and optionally initialises it with the given data values. |
842 | Creates a new OpenCL::Image3D object and optionally initialises it with |
|
|
843 | the given data values. |
690 | |
844 | |
691 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage3D.html> |
845 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage3D.html> |
|
|
846 | |
|
|
847 | =item $buffer = $ctx->gl_buffer ($flags, $bufobj) |
|
|
848 | |
|
|
849 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object that refers to the given |
|
|
850 | OpenGL buffer object. |
|
|
851 | |
|
|
852 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLBuffer.html |
|
|
853 | |
|
|
854 | =item $img = $ctx->gl_texture ($flags, $target, $miplevel, $texture) |
|
|
855 | |
|
|
856 | Creates a new OpenCL::Image object that refers to the given OpenGL |
|
|
857 | texture object or buffer. |
|
|
858 | |
|
|
859 | http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateFromGLTexture.html |
|
|
860 | |
|
|
861 | =item $img = $ctx->gl_texture2d ($flags, $target, $miplevel, $texture) |
|
|
862 | |
|
|
863 | Creates a new OpenCL::Image2D object that refers to the given OpenGL |
|
|
864 | 2D texture object. |
|
|
865 | |
|
|
866 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture2D.html |
|
|
867 | |
|
|
868 | =item $img = $ctx->gl_texture3d ($flags, $target, $miplevel, $texture) |
|
|
869 | |
|
|
870 | Creates a new OpenCL::Image3D object that refers to the given OpenGL |
|
|
871 | 3D texture object. |
|
|
872 | |
|
|
873 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture3D.html |
|
|
874 | |
|
|
875 | =item $ctx->gl_renderbuffer ($flags, $renderbuffer) |
|
|
876 | |
|
|
877 | Creates a new OpenCL::Image2D object that refers to the given OpenGL |
|
|
878 | render buffer. |
|
|
879 | |
|
|
880 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLRenderbuffer.html |
692 | |
881 | |
693 | =item @formats = $ctx->supported_image_formats ($flags, $image_type) |
882 | =item @formats = $ctx->supported_image_formats ($flags, $image_type) |
694 | |
883 | |
695 | Returns a list of matching image formats - each format is an arrayref with |
884 | Returns a list of matching image formats - each format is an arrayref with |
696 | two values, $channel_order and $channel_type, in it. |
885 | two values, $channel_order and $channel_type, in it. |
… | |
… | |
747 | for completion, unless the method is called in void context, in which case |
936 | for completion, unless the method is called in void context, in which case |
748 | no event object is created. |
937 | no event object is created. |
749 | |
938 | |
750 | They also allow you to specify any number of other event objects that this |
939 | They also allow you to specify any number of other event objects that this |
751 | request has to wait for before it starts executing, by simply passing the |
940 | request has to wait for before it starts executing, by simply passing the |
752 | event objects as extra parameters to the enqueue methods. |
941 | event objects as extra parameters to the enqueue methods. To simplify |
|
|
942 | program design, this module ignores any C<undef> values in the list of |
|
|
943 | events. This makes it possible to code operations such as this, without |
|
|
944 | having to put a valid event object into C<$event> first: |
|
|
945 | |
|
|
946 | $event = $queue->enqueue_xxx (..., $event); |
753 | |
947 | |
754 | Queues execute in-order by default, without any parallelism, so in most |
948 | Queues execute in-order by default, without any parallelism, so in most |
755 | cases (i.e. you use only one queue) it's not necessary to wait for or |
949 | cases (i.e. you use only one queue) it's not necessary to wait for or |
756 | create event objects. |
950 | create event objects, althoguh an our of order queue is often a bit |
|
|
951 | faster. |
757 | |
952 | |
758 | =over 4 |
953 | =over 4 |
759 | |
954 | |
760 | =item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) |
955 | =item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) |
761 | |
956 | |
… | |
… | |
771 | |
966 | |
772 | =item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) |
967 | =item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) |
773 | |
968 | |
774 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> |
969 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> |
775 | |
970 | |
|
|
971 | =item $ev = $queue->enqueue_read_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) |
|
|
972 | |
|
|
973 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html |
|
|
974 | |
|
|
975 | =item $ev = $queue->enqueue_write_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) |
|
|
976 | |
|
|
977 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html |
|
|
978 | |
776 | =item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
979 | =item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
777 | |
980 | |
|
|
981 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html> |
|
|
982 | |
|
|
983 | =item $ev = $queue->enqueue_copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
|
|
984 | |
778 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> |
985 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> |
779 | |
986 | |
780 | =item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
987 | =item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
781 | |
988 | |
782 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> |
989 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> |
783 | |
990 | |
|
|
991 | =item $ev = $queue->enqueue_copy_image ($src_image, $dst_image, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
|
|
992 | |
|
|
993 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> |
|
|
994 | |
|
|
995 | =item $ev = $queue->enqueue_copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...) |
|
|
996 | |
|
|
997 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html> |
|
|
998 | |
784 | =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...) |
999 | =item $ev = $queue->enqueue_copy_buffer_rect ($src, $dst, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $src_row_pitch, $src_slice_pitch, $dst_row_pitch, $dst_slice_pitch, $wait_event...) |
785 | |
1000 | |
786 | Yeah. |
1001 | Yeah. |
787 | |
1002 | |
788 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html> |
|
|
789 | |
|
|
790 | =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...) |
|
|
791 | |
|
|
792 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
1003 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
793 | |
|
|
794 | =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...) |
|
|
795 | |
|
|
796 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> |
|
|
797 | |
|
|
798 | =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...) |
|
|
799 | |
|
|
800 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html> |
|
|
801 | |
1004 | |
802 | =item $ev = $queue->enqueue_task ($kernel, $wait_events...) |
1005 | =item $ev = $queue->enqueue_task ($kernel, $wait_events...) |
803 | |
1006 | |
804 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
1007 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
805 | |
1008 | |
… | |
… | |
819 | reference to an array of local work sizes, with the same number of |
1022 | reference to an array of local work sizes, with the same number of |
820 | elements as @$global_work_size. |
1023 | elements as @$global_work_size. |
821 | |
1024 | |
822 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
1025 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
823 | |
1026 | |
824 | =item $ev = $queue->enqueue_marker |
1027 | =item $ev = $queue->enqueue_acquire_gl_objects ([object, ...], $wait_events...) |
825 | |
1028 | |
|
|
1029 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired |
|
|
1030 | for subsequent OpenCL usage. |
|
|
1031 | |
826 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueMarker.html> |
1032 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html> |
|
|
1033 | |
|
|
1034 | =item $ev = $queue->enqueue_release_gl_objects ([object, ...], $wait_events...) |
|
|
1035 | |
|
|
1036 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be released |
|
|
1037 | for subsequent OpenGL usage. |
|
|
1038 | |
|
|
1039 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html> |
827 | |
1040 | |
828 | =item $ev = $queue->enqueue_wait_for_events ($wait_events...) |
1041 | =item $ev = $queue->enqueue_wait_for_events ($wait_events...) |
829 | |
1042 | |
830 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
1043 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
831 | |
1044 | |
832 | =item $queue->enqueue_barrier |
1045 | =item $ev = $queue->enqueue_marker ($wait_events...) |
833 | |
1046 | |
|
|
1047 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html> |
|
|
1048 | |
|
|
1049 | =item $ev = $queue->enqueue_barrier ($wait_events...) |
|
|
1050 | |
834 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueBarrier.html> |
1051 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html> |
835 | |
1052 | |
836 | =item $queue->flush |
1053 | =item $queue->flush |
837 | |
1054 | |
838 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html> |
1055 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html> |
839 | |
1056 | |
… | |
… | |
920 | |
1137 | |
921 | Calls C<clGetMemObjectInfo> with C<CL_MEM_OFFSET> and returns the result. |
1138 | Calls C<clGetMemObjectInfo> with C<CL_MEM_OFFSET> and returns the result. |
922 | |
1139 | |
923 | =for gengetinfo end mem |
1140 | =for gengetinfo end mem |
924 | |
1141 | |
|
|
1142 | =item ($type, $name) = $mem->gl_object_info |
|
|
1143 | |
|
|
1144 | Returns the OpenGL object type (e.g. OpenCL::GL_OBJECT_TEXTURE2D) and the |
|
|
1145 | object "name" (e.g. the texture name) used to create this memory object. |
|
|
1146 | |
|
|
1147 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetGLObjectInfo.html> |
|
|
1148 | |
925 | =back |
1149 | =back |
926 | |
1150 | |
|
|
1151 | =head2 THE OpenCL::Buffer CLASS |
|
|
1152 | |
|
|
1153 | This is a subclass of OpenCL::Memory, and the superclass of |
|
|
1154 | OpenCL::BufferObj. Its purpose is simply to distinguish between buffers |
|
|
1155 | and sub-buffers. |
|
|
1156 | |
|
|
1157 | =head2 THE OpenCL::BufferObj CLASS |
|
|
1158 | |
|
|
1159 | This is a subclass of OpenCL::Buffer and thus OpenCL::Memory. It exists |
|
|
1160 | because one cna create sub buffers of OpenLC::BufferObj objects, but not |
|
|
1161 | sub buffers from these sub buffers. |
|
|
1162 | |
|
|
1163 | =over 4 |
|
|
1164 | |
|
|
1165 | =item $subbuf = $buf_obj->sub_buffer_region ($flags, $origin, $size) |
|
|
1166 | |
|
|
1167 | Creates an OpenCL::Buffer objects from this buffer and returns it. The |
|
|
1168 | C<buffer_create_type> is assumed to be C<CL_BUFFER_CREATE_TYPE_REGION>. |
|
|
1169 | |
|
|
1170 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateSubBuffer.html> |
|
|
1171 | |
|
|
1172 | =back |
|
|
1173 | |
927 | =head2 THE OpenCL::Image CLASS |
1174 | =head2 THE OpenCL::Image CLASS |
928 | |
1175 | |
929 | This is the superclass of all image objects - OpenCL::Image2D and OpenCL::Image3D. |
1176 | This is the superclass of all image objects - OpenCL::Image1D, |
|
|
1177 | OpenCL::Image1DArray, OpenCL::Image1DBuffer, OpenCL::Image2D, |
|
|
1178 | OpenCL::Image2DArray and OpenCL::Image3D. |
930 | |
1179 | |
931 | =over 4 |
1180 | =over 4 |
932 | |
1181 | |
933 | =item $packed_value = $ev->image_info ($name) |
1182 | =item $packed_value = $ev->image_info ($name) |
934 | |
1183 | |
… | |
… | |
965 | |
1214 | |
966 | Calls C<clGetImageInfo> with C<CL_IMAGE_DEPTH> and returns the result. |
1215 | Calls C<clGetImageInfo> with C<CL_IMAGE_DEPTH> and returns the result. |
967 | |
1216 | |
968 | =for gengetinfo end image |
1217 | =for gengetinfo end image |
969 | |
1218 | |
|
|
1219 | =for gengetinfo begin gl_texture |
|
|
1220 | |
|
|
1221 | =item $GLenum = $gl_texture->target |
|
|
1222 | |
|
|
1223 | Calls C<clGetGLTextureInfo> with C<CL_GL_TEXTURE_TARGET> and returns the result. |
|
|
1224 | |
|
|
1225 | =item $GLint = $gl_texture->gl_mipmap_level |
|
|
1226 | |
|
|
1227 | Calls C<clGetGLTextureInfo> with C<CL_GL_MIPMAP_LEVEL> and returns the result. |
|
|
1228 | |
|
|
1229 | =for gengetinfo end gl_texture |
|
|
1230 | |
970 | =back |
1231 | =back |
971 | |
1232 | |
972 | =head2 THE OpenCL::Sampler CLASS |
1233 | =head2 THE OpenCL::Sampler CLASS |
973 | |
1234 | |
974 | =over 4 |
1235 | =over 4 |
… | |
… | |
1009 | |
1270 | |
1010 | =over 4 |
1271 | =over 4 |
1011 | |
1272 | |
1012 | =item $program->build ($device, $options = "") |
1273 | =item $program->build ($device, $options = "") |
1013 | |
1274 | |
1014 | Tries to build the program with the givne options. |
1275 | Tries to build the program with the given options. See also the |
|
|
1276 | C<$ctx->build> convenience function. |
1015 | |
1277 | |
1016 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
1278 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
1017 | |
1279 | |
1018 | =item $packed_value = $program->build_info ($device, $name) |
1280 | =item $packed_value = $program->build_info ($device, $name) |
1019 | |
1281 | |
… | |
… | |
1026 | |
1288 | |
1027 | Creates an OpenCL::Kernel object out of the named C<__kernel> function in |
1289 | Creates an OpenCL::Kernel object out of the named C<__kernel> function in |
1028 | the program. |
1290 | the program. |
1029 | |
1291 | |
1030 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html> |
1292 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html> |
|
|
1293 | |
|
|
1294 | =item @kernels = $program->kernels_in_program |
|
|
1295 | |
|
|
1296 | Returns all kernels successfully compiled for all devices in program. |
|
|
1297 | |
|
|
1298 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernelsInProgram.html |
1031 | |
1299 | |
1032 | =for gengetinfo begin program_build |
1300 | =for gengetinfo begin program_build |
1033 | |
1301 | |
1034 | =item $build_status = $program->build_status ($device) |
1302 | =item $build_status = $program->build_status ($device) |
1035 | |
1303 | |
… | |
… | |
1163 | |
1431 | |
1164 | This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>. |
1432 | This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>. |
1165 | |
1433 | |
1166 | TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>, |
1434 | TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>, |
1167 | C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>, |
1435 | C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>, |
1168 | C<image2d>, C<image3d>, C<sampler> or C<event>. |
1436 | C<image2d>, C<image3d>, C<sampler>, C<local> or C<event>. |
1169 | |
1437 | |
1170 | Chars and integers (including the half type) are specified as integers, |
1438 | Chars and integers (including the half type) are specified as integers, |
1171 | float and double as floating point values, memory/buffer/image2d/image3d |
1439 | float and double as floating point values, memory/buffer/image2d/image3d |
1172 | must be an object of that type or C<undef>, and sampler and event must be |
1440 | must be an object of that type or C<undef>, local-memory arguments are |
1173 | objects of that type. |
1441 | set by specifying the size, and sampler and event must be objects of that |
|
|
1442 | type. |
|
|
1443 | |
|
|
1444 | Setting an argument for a kernel does NOT keep a reference to the object - |
|
|
1445 | for example, if you set an argument to some image object, free the image, |
|
|
1446 | and call the kernel, you will run into undefined behaviour. |
1174 | |
1447 | |
1175 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html> |
1448 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html> |
1176 | |
1449 | |
1177 | =back |
1450 | =back |
1178 | |
1451 | |
… | |
… | |
1267 | package OpenCL; |
1540 | package OpenCL; |
1268 | |
1541 | |
1269 | use common::sense; |
1542 | use common::sense; |
1270 | |
1543 | |
1271 | BEGIN { |
1544 | BEGIN { |
1272 | our $VERSION = '0.55'; |
1545 | our $VERSION = '0.96'; |
1273 | |
1546 | |
1274 | require XSLoader; |
1547 | require XSLoader; |
1275 | XSLoader::load (__PACKAGE__, $VERSION); |
1548 | XSLoader::load (__PACKAGE__, $VERSION); |
1276 | |
1549 | |
1277 | @OpenCL::Buffer::ISA = |
1550 | @OpenCL::Buffer::ISA = |
1278 | @OpenCL::Image::ISA = OpenCL::Memory::; |
1551 | @OpenCL::Image::ISA = OpenCL::Memory::; |
1279 | |
1552 | |
|
|
1553 | @OpenCL::BufferObj::ISA = OpenCL::Buffer::; |
|
|
1554 | |
1280 | @OpenCL::Image2D::ISA = |
1555 | @OpenCL::Image2D::ISA = |
|
|
1556 | @OpenCL::Image3D::ISA = |
|
|
1557 | @OpenCL::Image2DArray::ISA = |
|
|
1558 | @OpenCL::Image1D::ISA = |
|
|
1559 | @OpenCL::Image1DArray::ISA = |
1281 | @OpenCL::Image3D::ISA = OpenCL::Image::; |
1560 | @OpenCL::Image1DBuffer::ISA = OpenCL::Image::; |
1282 | |
1561 | |
1283 | @OpenCL::UserEvent::ISA = OpenCL::Event::; |
1562 | @OpenCL::UserEvent::ISA = OpenCL::Event::; |
1284 | } |
1563 | } |
1285 | |
1564 | |
1286 | 1; |
1565 | 1; |
1287 | |
1566 | |
1288 | =head1 AUTHOR |
1567 | =head1 AUTHOR |