| … | |
… | |
| 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 |
| … | |
… | |
| 270 | |
273 | |
| 271 | # program compiled, kernel ready, now draw and loop |
274 | # program compiled, kernel ready, now draw and loop |
| 272 | |
275 | |
| 273 | for (my $time; ; ++$time) { |
276 | for (my $time; ; ++$time) { |
| 274 | # acquire objects from opengl |
277 | # acquire objects from opengl |
| 275 | $queue->enqueue_acquire_gl_objects ([$tex]); |
278 | $queue->acquire_gl_objects ([$tex]); |
| 276 | |
279 | |
| 277 | # configure and run our kernel |
280 | # configure and run our kernel |
| 278 | $kernel->set_image2d (0, $tex); |
281 | $kernel->set_image2d (0, $tex); |
| 279 | $kernel->set_float (1, $time); |
282 | $kernel->set_float (1, $time); |
| 280 | $queue->enqueue_nd_range_kernel ($kernel, undef, [256, 256], undef); |
283 | $queue->nd_range_kernel ($kernel, undef, [256, 256], undef); |
| 281 | |
284 | |
| 282 | # release objects to opengl again |
285 | # release objects to opengl again |
| 283 | $queue->enqueue_release_gl_objects ([$tex]); |
286 | $queue->release_gl_objects ([$tex]); |
| 284 | |
287 | |
| 285 | # wait |
288 | # wait |
| 286 | $queue->finish; |
289 | $queue->finish; |
| 287 | |
290 | |
| 288 | # now draw the texture, the defaults should be all right |
291 | # now draw the texture, the defaults should be all right |
| … | |
… | |
| 417 | use AnyEvent; |
420 | use AnyEvent; |
| 418 | |
421 | |
| 419 | # initialise AnyEvent, by creating a watcher, or: |
422 | # initialise AnyEvent, by creating a watcher, or: |
| 420 | AnyEvent::detect; |
423 | AnyEvent::detect; |
| 421 | |
424 | |
| 422 | my $e = $queue->enqueue_marker; |
425 | my $e = $queue->marker; |
| 423 | $e->cb (sub { |
426 | $e->cb (sub { |
| 424 | warn "opencl is finished\n"; |
427 | warn "opencl is finished\n"; |
| 425 | }) |
428 | }) |
| 426 | |
429 | |
| 427 | main Gtk2; |
430 | main Gtk2; |
| … | |
… | |
| 444 | Asynchronously means that perl might execute your callbacks at any |
447 | Asynchronously means that perl might execute your callbacks at any |
| 445 | time. For example, in the following code (I<THAT YOU SHOULD NOT COPY>), |
448 | time. For example, in the following code (I<THAT YOU SHOULD NOT COPY>), |
| 446 | the C<until> loop following the marker call will be interrupted by the |
449 | the C<until> loop following the marker call will be interrupted by the |
| 447 | callback: |
450 | callback: |
| 448 | |
451 | |
| 449 | my $e = $queue->enqueue_marker; |
452 | my $e = $queue->marker; |
| 450 | my $flag; |
453 | my $flag; |
| 451 | $e->cb (sub { $flag = 1 }); |
454 | $e->cb (sub { $flag = 1 }); |
| 452 | 1 until $flag; |
455 | 1 until $flag; |
| 453 | # $flag is now 1 |
456 | # $flag is now 1 |
| 454 | |
457 | |
| … | |
… | |
| 490 | =cut |
493 | =cut |
| 491 | |
494 | |
| 492 | package OpenCL; |
495 | package OpenCL; |
| 493 | |
496 | |
| 494 | use common::sense; |
497 | use common::sense; |
|
|
498 | use Carp (); |
| 495 | use Async::Interrupt (); |
499 | use Async::Interrupt (); |
| 496 | |
500 | |
| 497 | our $POLL_FUNC; # set by XS |
501 | our $POLL_FUNC; # set by XS |
| 498 | |
502 | |
| 499 | BEGIN { |
503 | BEGIN { |
| 500 | our $VERSION = '0.97'; |
504 | our $VERSION = '0.98'; |
| 501 | |
505 | |
| 502 | require XSLoader; |
506 | require XSLoader; |
| 503 | XSLoader::load (__PACKAGE__, $VERSION); |
507 | XSLoader::load (__PACKAGE__, $VERSION); |
| 504 | |
508 | |
| 505 | @OpenCL::Platform::ISA = |
509 | @OpenCL::Platform::ISA = |
| … | |
… | |
| 534 | =item $int = OpenCL::errno |
538 | =item $int = OpenCL::errno |
| 535 | |
539 | |
| 536 | The last error returned by a function - it's only valid after an error occured |
540 | The last error returned by a function - it's only valid after an error occured |
| 537 | and before calling another OpenCL function. |
541 | and before calling another OpenCL function. |
| 538 | |
542 | |
| 539 | =item $str = OpenCL::err2str $errval |
543 | =item $str = OpenCL::err2str [$errval] |
| 540 | |
544 | |
| 541 | Comverts an error value into a human readable string. |
545 | Converts an error value into a human readable string. IF no error value is |
|
|
546 | given, then the last error will be used (as returned by OpenCL::errno). |
| 542 | |
547 | |
| 543 | =item $str = OpenCL::enum2str $enum |
548 | =item $str = OpenCL::enum2str $enum |
| 544 | |
549 | |
| 545 | Converts most enum values (of parameter names, image format constants, |
550 | Converts most enum values (of parameter names, image format constants, |
| 546 | object types, addressing and filter modes, command types etc.) into a |
551 | object types, addressing and filter modes, command types etc.) into a |
| … | |
… | |
| 552 | |
557 | |
| 553 | Returns all available OpenCL::Platform objects. |
558 | Returns all available OpenCL::Platform objects. |
| 554 | |
559 | |
| 555 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html> |
560 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html> |
| 556 | |
561 | |
| 557 | =item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = $print_stderr |
562 | =item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr |
| 558 | |
563 | |
| 559 | Tries to create a context from a default device and platform - never worked for me. |
564 | Tries to create a context from a default device and platform type - never worked for me. |
| 560 | |
565 | |
| 561 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
566 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
|
|
567 | |
|
|
568 | =item $ctx = OpenCL::context $properties, \@devices, $callback->($err, $pvt) = $print_stderr) |
|
|
569 | |
|
|
570 | Create a new OpenCL::Context object using the given device object(s). This |
|
|
571 | function isn't implemented yet, use C<< $platform->context >> instead. |
|
|
572 | |
|
|
573 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> |
| 562 | |
574 | |
| 563 | =item OpenCL::wait_for_events $wait_events... |
575 | =item OpenCL::wait_for_events $wait_events... |
| 564 | |
576 | |
| 565 | Waits for all events to complete. |
577 | Waits for all events to complete. |
| 566 | |
578 | |
| … | |
… | |
| 636 | |
648 | |
| 637 | =item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL) |
649 | =item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL) |
| 638 | |
650 | |
| 639 | Returns a list of matching OpenCL::Device objects. |
651 | Returns a list of matching OpenCL::Device objects. |
| 640 | |
652 | |
| 641 | =item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = $print_stderr) |
653 | =item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr) |
| 642 | |
654 | |
| 643 | Tries to create a context. Never worked for me, and you need devices explicitly anyway. |
655 | Tries to create a context. Never worked for me, and you need devices explicitly anyway. |
| 644 | |
656 | |
| 645 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
657 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
| 646 | |
658 | |
| 647 | =item $ctx = $platform->context ($properties, @$devices, $notify = $print_stderr) |
659 | =item $ctx = $platform->context ($properties, \@devices, $callback->($err, $pvt) = $print_stderr) |
| 648 | |
660 | |
| 649 | Create a new OpenCL::Context object using the given device object(s)- a |
661 | Create a new OpenCL::Context object using the given device object(s)- a |
| 650 | CL_CONTEXT_PLATFORM property is supplied automatically. |
662 | CL_CONTEXT_PLATFORM property is supplied automatically. |
| 651 | |
663 | |
| 652 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> |
664 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> |
| … | |
… | |
| 992 | =cut |
1004 | =cut |
| 993 | |
1005 | |
| 994 | sub OpenCL::Context::build_program { |
1006 | sub OpenCL::Context::build_program { |
| 995 | my ($self, $prog, $options) = @_; |
1007 | my ($self, $prog, $options) = @_; |
| 996 | |
1008 | |
| 997 | require Carp; |
|
|
| 998 | |
|
|
| 999 | $prog = $self->program_with_source ($prog) |
1009 | $prog = $self->program_with_source ($prog) |
| 1000 | unless ref $prog; |
1010 | unless ref $prog; |
| 1001 | |
1011 | |
| 1002 | # we build separately per device so we instantly know which one failed |
1012 | eval { $prog->build (undef, $options); 1 } |
|
|
1013 | or errno == BUILD_PROGRAM_FAILURE |
|
|
1014 | or errno == INVALID_BINARY # workaround nvidia bug |
|
|
1015 | or Carp::croak "OpenCL::Context->build_program: " . err2str; |
|
|
1016 | |
|
|
1017 | # we check status for all devices |
| 1003 | for my $dev ($self->devices) { |
1018 | for my $dev ($self->devices) { |
| 1004 | eval { $prog->build ([$dev], $options); 1 } |
1019 | $prog->build_status ($dev) == BUILD_SUCCESS |
| 1005 | or Carp::croak ("Building OpenCL program for device '" . $dev->name . "' failed:\n" |
1020 | or Carp::croak "Building OpenCL program for device '" . $dev->name . "' failed:\n" |
| 1006 | . $prog->build_log ($dev)); |
1021 | . $prog->build_log ($dev); |
| 1007 | } |
1022 | } |
| 1008 | |
1023 | |
| 1009 | $prog |
1024 | $prog |
| 1010 | } |
1025 | } |
| 1011 | |
1026 | |
| … | |
… | |
| 1035 | =item $buf = $ctx->buffer_sv ($flags, $data) |
1050 | =item $buf = $ctx->buffer_sv ($flags, $data) |
| 1036 | |
1051 | |
| 1037 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and |
1052 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and |
| 1038 | initialise it with the given data values. |
1053 | initialise it with the given data values. |
| 1039 | |
1054 | |
| 1040 | =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) |
1055 | =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) |
| 1041 | |
1056 | |
| 1042 | Creates a new OpenCL::Image object and optionally initialises it with |
1057 | Creates a new OpenCL::Image object and optionally initialises it with |
| 1043 | the given data values. |
1058 | the given data values. |
| 1044 | |
1059 | |
| 1045 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html> |
1060 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html> |
| … | |
… | |
| 1141 | =back |
1156 | =back |
| 1142 | |
1157 | |
| 1143 | =head2 THE OpenCL::Queue CLASS |
1158 | =head2 THE OpenCL::Queue CLASS |
| 1144 | |
1159 | |
| 1145 | An OpenCL::Queue represents an execution queue for OpenCL. You execute |
1160 | An OpenCL::Queue represents an execution queue for OpenCL. You execute |
| 1146 | requests by calling their respective C<enqueue_xxx> method and waitinf for |
1161 | requests by calling their respective method and waiting for it to complete |
| 1147 | it to complete in some way. |
1162 | in some way. |
| 1148 | |
1163 | |
| 1149 | All the enqueue methods return an event object that can be used to wait |
1164 | Most methods that enqueue some request return an event object that can |
| 1150 | for completion, unless the method is called in void context, in which case |
1165 | be used to wait for completion (optionally using a callback), unless |
| 1151 | no event object is created. |
1166 | the method is called in void context, in which case no event object is |
|
|
1167 | created. |
| 1152 | |
1168 | |
| 1153 | They also allow you to specify any number of other event objects that this |
1169 | They also allow you to specify any number of other event objects that this |
| 1154 | request has to wait for before it starts executing, by simply passing the |
1170 | request has to wait for before it starts executing, by simply passing the |
| 1155 | event objects as extra parameters to the enqueue methods. To simplify |
1171 | event objects as extra parameters to the enqueue methods. To simplify |
| 1156 | program design, this module ignores any C<undef> values in the list of |
1172 | program design, this module ignores any C<undef> values in the list of |
| 1157 | events. This makes it possible to code operations such as this, without |
1173 | events. This makes it possible to code operations such as this, without |
| 1158 | having to put a valid event object into C<$event> first: |
1174 | having to put a valid event object into C<$event> first: |
| 1159 | |
1175 | |
| 1160 | $event = $queue->enqueue_xxx (..., $event); |
1176 | $event = $queue->xxx (..., $event); |
| 1161 | |
1177 | |
| 1162 | Queues execute in-order by default, without any parallelism, so in most |
1178 | Queues execute in-order by default, without any parallelism, so in most |
| 1163 | cases (i.e. you use only one queue) it's not necessary to wait for or |
1179 | cases (i.e. you use only one queue) it's not necessary to wait for or |
| 1164 | create event objects, althoguh an our of order queue is often a bit |
1180 | create event objects, althoguh an our of order queue is often a bit |
| 1165 | faster. |
1181 | faster. |
| 1166 | |
1182 | |
| 1167 | =over 4 |
1183 | =over 4 |
| 1168 | |
1184 | |
| 1169 | =item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) |
1185 | =item $ev = $queue->read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) |
| 1170 | |
1186 | |
| 1171 | Reads data from buffer into the given string. |
1187 | Reads data from buffer into the given string. |
| 1172 | |
1188 | |
| 1173 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html> |
1189 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html> |
| 1174 | |
1190 | |
| 1175 | =item $ev = $queue->enqueue_write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) |
1191 | =item $ev = $queue->write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) |
| 1176 | |
1192 | |
| 1177 | Writes data to buffer from the given string. |
1193 | Writes data to buffer from the given string. |
| 1178 | |
1194 | |
| 1179 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html> |
1195 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html> |
| 1180 | |
1196 | |
| 1181 | =item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) |
1197 | =item $ev = $queue->copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) |
| 1182 | |
1198 | |
| 1183 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> |
1199 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> |
| 1184 | |
1200 | |
| 1185 | =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...) |
1201 | =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...) |
| 1186 | |
1202 | |
| 1187 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html |
1203 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html |
| 1188 | |
1204 | |
| 1189 | =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...) |
1205 | =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...) |
| 1190 | |
1206 | |
| 1191 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html |
1207 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html |
| 1192 | |
1208 | |
| 1193 | =item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
1209 | =item $ev = $queue->read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
| 1194 | |
1210 | |
| 1195 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html> |
1211 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html> |
| 1196 | |
1212 | |
| 1197 | =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...) |
1213 | =item $ev = $queue->copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
| 1198 | |
1214 | |
| 1199 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> |
1215 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> |
| 1200 | |
1216 | |
| 1201 | =item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
1217 | =item $ev = $queue->write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
| 1202 | |
1218 | |
| 1203 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> |
1219 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> |
| 1204 | |
1220 | |
| 1205 | =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...) |
1221 | =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...) |
| 1206 | |
1222 | |
| 1207 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> |
1223 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> |
| 1208 | |
1224 | |
| 1209 | =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...) |
1225 | =item $ev = $queue->copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...) |
| 1210 | |
1226 | |
| 1211 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html> |
1227 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html> |
| 1212 | |
1228 | |
| 1213 | =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...) |
1229 | =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...) |
| 1214 | |
1230 | |
| 1215 | Yeah. |
1231 | Yeah. |
| 1216 | |
1232 | |
| 1217 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
1233 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
| 1218 | |
1234 | |
| 1219 | =item $ev = $queue->enqueue_fill_buffer ($mem, $pattern, $offset, $size, ...) |
1235 | =item $ev = $queue->fill_buffer ($mem, $pattern, $offset, $size, ...) |
| 1220 | |
1236 | |
| 1221 | Fills the given buffer object with repeated applications of C<$pattern>, |
1237 | Fills the given buffer object with repeated applications of C<$pattern>, |
| 1222 | starting at C<$offset> for C<$size> octets. |
1238 | starting at C<$offset> for C<$size> octets. |
| 1223 | |
1239 | |
| 1224 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html> |
1240 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html> |
| 1225 | |
1241 | |
| 1226 | =item $ev = $queue->enqueue_fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...) |
1242 | =item $ev = $queue->fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...) |
| 1227 | |
1243 | |
| 1228 | Fills the given image area with the given rgba colour components. The |
1244 | Fills the given image area with the given rgba colour components. The |
| 1229 | components are normally floating point values between C<0> and C<1>, |
1245 | components are normally floating point values between C<0> and C<1>, |
| 1230 | except when the image channel data type is a signe dor unsigned |
1246 | except when the image channel data type is a signe dor unsigned |
| 1231 | unnormalised format, in which case the range is determined by the format. |
1247 | unnormalised format, in which case the range is determined by the format. |
| 1232 | |
1248 | |
| 1233 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html> |
1249 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html> |
| 1234 | |
1250 | |
| 1235 | =item $ev = $queue->enqueue_task ($kernel, $wait_events...) |
1251 | =item $ev = $queue->task ($kernel, $wait_events...) |
| 1236 | |
1252 | |
| 1237 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
1253 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
| 1238 | |
1254 | |
| 1239 | =item $ev = $queue->enqueue_nd_range_kernel ($kernel, @$global_work_offset, @$global_work_size, @$local_work_size, $wait_events...) |
1255 | =item $ev = $queue->nd_range_kernel ($kernel, \@global_work_offset, \@global_work_size, \@local_work_size, $wait_events...) |
| 1240 | |
1256 | |
| 1241 | Enqueues a kernel execution. |
1257 | Enqueues a kernel execution. |
| 1242 | |
1258 | |
| 1243 | @$global_work_size must be specified as a reference to an array of |
1259 | \@global_work_size must be specified as a reference to an array of |
| 1244 | integers specifying the work sizes (element counts). |
1260 | integers specifying the work sizes (element counts). |
| 1245 | |
1261 | |
| 1246 | @$global_work_offset must be either C<undef> (in which case all offsets |
1262 | \@global_work_offset must be either C<undef> (in which case all offsets |
| 1247 | are C<0>), or a reference to an array of work offsets, with the same number |
1263 | are C<0>), or a reference to an array of work offsets, with the same number |
| 1248 | of elements as @$global_work_size. |
1264 | of elements as \@global_work_size. |
| 1249 | |
1265 | |
| 1250 | @$local_work_size must be either C<undef> (in which case the |
1266 | \@local_work_size must be either C<undef> (in which case the |
| 1251 | implementation is supposed to choose good local work sizes), or a |
1267 | implementation is supposed to choose good local work sizes), or a |
| 1252 | reference to an array of local work sizes, with the same number of |
1268 | reference to an array of local work sizes, with the same number of |
| 1253 | elements as @$global_work_size. |
1269 | elements as \@global_work_size. |
| 1254 | |
1270 | |
| 1255 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
1271 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
| 1256 | |
1272 | |
| 1257 | =item $ev = $queue->enqueue_acquire_gl_objects ([object, ...], $wait_events...) |
1273 | =item $ev = $queue->acquire_gl_objects ([object, ...], $wait_events...) |
| 1258 | |
1274 | |
| 1259 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired |
1275 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired |
| 1260 | for subsequent OpenCL usage. |
1276 | for subsequent OpenCL usage. |
| 1261 | |
1277 | |
| 1262 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html> |
1278 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html> |
| 1263 | |
1279 | |
| 1264 | =item $ev = $queue->enqueue_release_gl_objects ([object, ...], $wait_events...) |
1280 | =item $ev = $queue->release_gl_objects ([object, ...], $wait_events...) |
| 1265 | |
1281 | |
| 1266 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be released |
1282 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be released |
| 1267 | for subsequent OpenGL usage. |
1283 | for subsequent OpenGL usage. |
| 1268 | |
1284 | |
| 1269 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html> |
1285 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html> |
| 1270 | |
1286 | |
| 1271 | =item $ev = $queue->enqueue_wait_for_events ($wait_events...) |
1287 | =item $ev = $queue->wait_for_events ($wait_events...) |
| 1272 | |
1288 | |
| 1273 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
1289 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
| 1274 | |
1290 | |
| 1275 | =item $ev = $queue->enqueue_marker ($wait_events...) |
1291 | =item $ev = $queue->marker ($wait_events...) |
| 1276 | |
1292 | |
| 1277 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html> |
1293 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html> |
| 1278 | |
1294 | |
| 1279 | =item $ev = $queue->enqueue_barrier ($wait_events...) |
1295 | =item $ev = $queue->barrier ($wait_events...) |
| 1280 | |
1296 | |
| 1281 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html> |
1297 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html> |
| 1282 | |
1298 | |
| 1283 | =item $queue->flush |
1299 | =item $queue->flush |
| 1284 | |
1300 | |
| … | |
… | |
| 1513 | If a callback is specified, then it will be called when compilation is |
1529 | If a callback is specified, then it will be called when compilation is |
| 1514 | finished. Note that many OpenCL implementations block your program while |
1530 | finished. Note that many OpenCL implementations block your program while |
| 1515 | compiling whether you use a callback or not. See C<build_async> if you |
1531 | compiling whether you use a callback or not. See C<build_async> if you |
| 1516 | want to make sure the build is done in the background. |
1532 | want to make sure the build is done in the background. |
| 1517 | |
1533 | |
| 1518 | Note that some OpenCL implementations atc up badly, and don't call the |
1534 | Note that some OpenCL implementations act up badly, and don't call the |
| 1519 | callback in some error cases (but call it in others). This implementation |
1535 | callback in some error cases (but call it in others). This implementation |
| 1520 | assumes the callback will always be called, and leaks memory if this is |
1536 | assumes the callback will always be called, and leaks memory if this is |
| 1521 | not so. So best make sure you don't pass in invalid values. |
1537 | not so. So best make sure you don't pass in invalid values. |
| 1522 | |
1538 | |
|
|
1539 | Some implementations fail with C<OpenCL::INVALID_BINARY> when the |
|
|
1540 | compilation state is successful but some later stage fails. |
|
|
1541 | |
| 1523 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
1542 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
| 1524 | |
1543 | |
| 1525 | =item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef) |
1544 | =item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef) |
| 1526 | |
1545 | |
| 1527 | Similar to C<< ->build >>, except it starts a thread, and never fails (you |
1546 | Similar to C<< ->build >>, except it starts a thread, and never fails (you |
| … | |
… | |
| 1675 | |
1694 | |
| 1676 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result. |
1695 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result. |
| 1677 | |
1696 | |
| 1678 | =for gengetinfo end kernel_work_group |
1697 | =for gengetinfo end kernel_work_group |
| 1679 | |
1698 | |
|
|
1699 | =item $kernel->setf ($format, ...) |
|
|
1700 | |
|
|
1701 | Sets the arguments of a kernel. Since OpenCL 1.1 doesn't have a generic |
|
|
1702 | way to set arguments (and with OpenCL 1.2 it might be rather slow), you |
|
|
1703 | need to specify a format argument, much as with C<printf>, to tell OpenCL |
|
|
1704 | what type of argument it is. |
|
|
1705 | |
|
|
1706 | The format arguments are single letters: |
|
|
1707 | |
|
|
1708 | c char |
|
|
1709 | C unsigned char |
|
|
1710 | s short |
|
|
1711 | S unsigned short |
|
|
1712 | i int |
|
|
1713 | I unsigned int |
|
|
1714 | l long |
|
|
1715 | L unsigned long |
|
|
1716 | |
|
|
1717 | h half float (0..65535) |
|
|
1718 | f float |
|
|
1719 | d double |
|
|
1720 | |
|
|
1721 | z local (octet size) |
|
|
1722 | |
|
|
1723 | m memory object (buffer or image) |
|
|
1724 | a sampler |
|
|
1725 | e event |
|
|
1726 | |
|
|
1727 | Space characters in the format string are ignored. |
|
|
1728 | |
|
|
1729 | Example: set the arguments for a kernel that expects an int, two floats, a buffer and an image. |
|
|
1730 | |
|
|
1731 | $kernel->setf ("i ff mm", 5, 0.5, 3, $buffer, $image); |
|
|
1732 | |
| 1680 | =item $kernel->set_TYPE ($index, $value) |
1733 | =item $kernel->set_TYPE ($index, $value) |
| 1681 | |
1734 | |
|
|
1735 | =item $kernel->set_char ($index, $value) |
|
|
1736 | |
|
|
1737 | =item $kernel->set_uchar ($index, $value) |
|
|
1738 | |
|
|
1739 | =item $kernel->set_short ($index, $value) |
|
|
1740 | |
|
|
1741 | =item $kernel->set_ushort ($index, $value) |
|
|
1742 | |
|
|
1743 | =item $kernel->set_int ($index, $value) |
|
|
1744 | |
|
|
1745 | =item $kernel->set_uint ($index, $value) |
|
|
1746 | |
|
|
1747 | =item $kernel->set_long ($index, $value) |
|
|
1748 | |
|
|
1749 | =item $kernel->set_ulong ($index, $value) |
|
|
1750 | |
|
|
1751 | =item $kernel->set_half ($index, $value) |
|
|
1752 | |
|
|
1753 | =item $kernel->set_float ($index, $value) |
|
|
1754 | |
|
|
1755 | =item $kernel->set_double ($index, $value) |
|
|
1756 | |
|
|
1757 | =item $kernel->set_memory ($index, $value) |
|
|
1758 | |
|
|
1759 | =item $kernel->set_buffer ($index, $value) |
|
|
1760 | |
|
|
1761 | =item $kernel->set_image ($index, $value) |
|
|
1762 | |
|
|
1763 | =item $kernel->set_sampler ($index, $value) |
|
|
1764 | |
|
|
1765 | =item $kernel->set_local ($index, $value) |
|
|
1766 | |
|
|
1767 | =item $kernel->set_event ($index, $value) |
|
|
1768 | |
| 1682 | This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>. |
1769 | This is a family of methods to set the kernel argument with the number |
| 1683 | |
1770 | C<$index> to the give C<$value>. |
| 1684 | TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>, |
|
|
| 1685 | C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>, |
|
|
| 1686 | C<image2d>, C<image3d>, C<sampler>, C<local> or C<event>. |
|
|
| 1687 | |
1771 | |
| 1688 | Chars and integers (including the half type) are specified as integers, |
1772 | Chars and integers (including the half type) are specified as integers, |
| 1689 | float and double as floating point values, memory/buffer/image2d/image3d |
1773 | float and double as floating point values, memory/buffer/image must be |
| 1690 | must be an object of that type or C<undef>, local-memory arguments are |
1774 | an object of that type or C<undef>, local-memory arguments are set by |
| 1691 | set by specifying the size, and sampler and event must be objects of that |
1775 | specifying the size, and sampler and event must be objects of that type. |
| 1692 | type. |
1776 | |
|
|
1777 | Note that C<set_memory> works for all memory objects (all types of buffers |
|
|
1778 | and images) - the main purpose of the more specific C<set_TYPE> functions |
|
|
1779 | is type checking. |
| 1693 | |
1780 | |
| 1694 | Setting an argument for a kernel does NOT keep a reference to the object - |
1781 | Setting an argument for a kernel does NOT keep a reference to the object - |
| 1695 | for example, if you set an argument to some image object, free the image, |
1782 | for example, if you set an argument to some image object, free the image, |
| 1696 | and call the kernel, you will run into undefined behaviour. |
1783 | and call the kernel, you will run into undefined behaviour. |
| 1697 | |
1784 | |
