… | |
… | |
141 | =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, |
142 | then asynchronously. |
142 | then asynchronously. |
143 | |
143 | |
144 | my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); |
144 | my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); |
145 | |
145 | |
146 | $queue->enqueue_read_buffer ($buf, 1, 1, 3, my $data); |
146 | $queue->read_buffer ($buf, 1, 1, 3, my $data); |
147 | print "$data\n"; |
147 | print "$data\n"; |
148 | |
148 | |
149 | my $ev = $queue->enqueue_read_buffer ($buf, 0, 1, 3, my $data); |
149 | my $ev = $queue->read_buffer ($buf, 0, 1, 3, my $data); |
150 | $ev->wait; |
150 | $ev->wait; |
151 | print "$data\n"; # prints "elm" |
151 | print "$data\n"; # prints "elm" |
152 | |
152 | |
153 | =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 |
154 | functions. |
154 | functions. |
… | |
… | |
174 | # set buffer |
174 | # set buffer |
175 | $kernel->set_buffer (0, $input); |
175 | $kernel->set_buffer (0, $input); |
176 | $kernel->set_buffer (1, $output); |
176 | $kernel->set_buffer (1, $output); |
177 | |
177 | |
178 | # execute it for all 4 numbers |
178 | # execute it for all 4 numbers |
179 | $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
179 | $queue->nd_range_kernel ($kernel, undef, [4], undef); |
180 | |
180 | |
181 | # enqueue a synchronous read |
181 | # enqueue a synchronous read |
182 | $queue->enqueue_read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
182 | $queue->read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
183 | |
183 | |
184 | # print the results: |
184 | # print the results: |
185 | printf "%s\n", join ", ", unpack "f*", $data; |
185 | printf "%s\n", join ", ", unpack "f*", $data; |
186 | |
186 | |
187 | =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, |
188 | showing off barriers. |
188 | showing off barriers. |
189 | |
189 | |
190 | # execute it for all 4 numbers |
190 | # execute it for all 4 numbers |
191 | $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
191 | $queue->nd_range_kernel ($kernel, undef, [4], undef); |
192 | |
192 | |
193 | # enqueue a barrier to ensure in-order execution |
193 | # enqueue a barrier to ensure in-order execution |
194 | $queue->enqueue_barrier; |
194 | $queue->barrier; |
195 | |
195 | |
196 | # enqueue an async read |
196 | # enqueue an async read |
197 | $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
197 | $queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
198 | |
198 | |
199 | # wait for all requests to finish |
199 | # wait for all requests to finish |
200 | $queue->finish; |
200 | $queue->finish; |
201 | |
201 | |
202 | =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, |
203 | showing off event objects and wait lists. |
203 | showing off event objects and wait lists. |
204 | |
204 | |
205 | # execute it for all 4 numbers |
205 | # execute it for all 4 numbers |
206 | my $ev = $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
206 | my $ev = $queue->nd_range_kernel ($kernel, undef, [4], undef); |
207 | |
207 | |
208 | # enqueue an async read |
208 | # enqueue an async read |
209 | $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); |
210 | |
210 | |
211 | # wait for the last event to complete |
211 | # wait for the last event to complete |
212 | $ev->wait; |
212 | $ev->wait; |
213 | |
213 | |
214 | =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 |
215 | set tunnel effect. |
215 | set tunnel effect. |
216 | |
216 | |
217 | This is quite a long example to get you going. |
217 | This is quite a long example to get you going - you can download it from |
|
|
218 | L<http://cvs.schmorp.de/OpenCL/examples/juliaflight>. |
218 | |
219 | |
219 | use OpenGL ":all"; |
220 | use OpenGL ":all"; |
220 | use OpenCL; |
221 | use OpenCL; |
221 | |
222 | |
|
|
223 | my $S = $ARGV[0] || 256; # window/texture size, smaller is faster |
|
|
224 | |
222 | # open a window and create a gl texture |
225 | # open a window and create a gl texture |
223 | OpenGL::glpOpenWindow width => 256, height => 256; |
226 | OpenGL::glpOpenWindow width => $S, height => $S; |
224 | my $texid = glGenTextures_p 1; |
227 | my $texid = glGenTextures_p 1; |
225 | glBindTexture GL_TEXTURE_2D, $texid; |
228 | glBindTexture GL_TEXTURE_2D, $texid; |
226 | glTexImage2D_c GL_TEXTURE_2D, 0, GL_RGBA8, 256, 256, 0, GL_RGBA, GL_UNSIGNED_BYTE, 0; |
229 | glTexImage2D_c GL_TEXTURE_2D, 0, GL_RGBA8, $S, $S, 0, GL_RGBA, GL_UNSIGNED_BYTE, 0; |
227 | |
230 | |
228 | # find and use the first opencl device that let's us get a shared opengl context |
231 | # find and use the first opencl device that let's us get a shared opengl context |
229 | my $platform; |
232 | my $platform; |
230 | my $dev; |
233 | my $dev; |
231 | my $ctx; |
234 | my $ctx; |
… | |
… | |
250 | # now the boring opencl code |
253 | # now the boring opencl code |
251 | my $src = <<EOF; |
254 | my $src = <<EOF; |
252 | kernel void |
255 | kernel void |
253 | juliatunnel (write_only image2d_t img, float time) |
256 | juliatunnel (write_only image2d_t img, float time) |
254 | { |
257 | { |
255 | float2 p = (float2)(get_global_id (0), get_global_id (1)) / 256.f * 2.f - 1.f; |
258 | int2 xy = (int2)(get_global_id (0), get_global_id (1)); |
|
|
259 | float2 p = convert_float2 (xy) / $S.f * 2.f - 1.f; |
256 | |
260 | |
257 | float2 m = (float2)(1.f, p.y) / fabs (p.x); |
261 | float2 m = (float2)(1.f, p.y) / fabs (p.x); // tunnel |
258 | m.x = fabs (fmod (m.x + time * 0.05f, 4.f)) - 2.f; |
262 | m.x = fabs (fmod (m.x + time * 0.05f, 4.f) - 2.f); |
259 | |
263 | |
260 | float2 z = m; |
264 | float2 z = m; |
261 | float2 c = (float2)(sin (time * 0.05005), cos (time * 0.06001)); |
265 | float2 c = (float2)(sin (time * 0.01133f), cos (time * 0.02521f)); |
262 | |
266 | |
263 | for (int i = 0; i < 25 && dot (z, z) < 4.f; ++i) |
267 | for (int i = 0; i < 25 && dot (z, z) < 4.f; ++i) // standard julia |
264 | z = (float2)(z.x * z.x - z.y * z.y, 2.f * z.x * z.y) + c; |
268 | z = (float2)(z.x * z.x - z.y * z.y, 2.f * z.x * z.y) + c; |
265 | |
269 | |
266 | float3 colour = (float3)(z.x, z.y, z.x * z.y); |
270 | float3 colour = (float3)(z.x, z.y, atan2 (z.y, z.x)); |
267 | write_imagef (img, (int2)(get_global_id (0), get_global_id (1)), (float4)(colour * p.x * p.x, 1.)); |
271 | write_imagef (img, xy, (float4)(colour * p.x * p.x, 1.)); |
268 | } |
272 | } |
269 | EOF |
273 | EOF |
270 | |
274 | |
271 | my $prog = $ctx->build_program ($src); |
275 | my $prog = $ctx->build_program ($src); |
272 | my $kernel = $prog->kernel ("juliatunnel"); |
276 | my $kernel = $prog->kernel ("juliatunnel"); |
273 | |
277 | |
274 | # program compiled, kernel ready, now draw and loop |
278 | # program compiled, kernel ready, now draw and loop |
275 | |
279 | |
276 | for (my $time; ; ++$time) { |
280 | for (my $time; ; ++$time) { |
277 | # acquire objects from opengl |
281 | # acquire objects from opengl |
278 | $queue->enqueue_acquire_gl_objects ([$tex]); |
282 | $queue->acquire_gl_objects ([$tex]); |
279 | |
283 | |
280 | # configure and run our kernel |
284 | # configure and run our kernel |
281 | $kernel->set_image2d (0, $tex); |
285 | $kernel->setf ("mf", $tex, $time*2); # mf = memory object, float |
282 | $kernel->set_float (1, $time); |
|
|
283 | $queue->enqueue_nd_range_kernel ($kernel, undef, [256, 256], undef); |
286 | $queue->nd_range_kernel ($kernel, undef, [$S, $S], undef); |
284 | |
287 | |
285 | # release objects to opengl again |
288 | # release objects to opengl again |
286 | $queue->enqueue_release_gl_objects ([$tex]); |
289 | $queue->release_gl_objects ([$tex]); |
287 | |
290 | |
288 | # wait |
291 | # wait |
289 | $queue->finish; |
292 | $queue->finish; |
290 | |
293 | |
291 | # now draw the texture, the defaults should be all right |
294 | # now draw the texture, the defaults should be all right |
… | |
… | |
301 | |
304 | |
302 | glXSwapBuffers; |
305 | glXSwapBuffers; |
303 | |
306 | |
304 | select undef, undef, undef, 1/60; |
307 | select undef, undef, undef, 1/60; |
305 | } |
308 | } |
|
|
309 | |
|
|
310 | =item How to modify the previous example to not rely on GL sharing. |
|
|
311 | |
|
|
312 | For those poor souls with only a sucky CPU OpenCL implementation, you |
|
|
313 | currently have to read the image into some perl scalar, and then modify a |
|
|
314 | texture or use glDrawPixels or so). |
|
|
315 | |
|
|
316 | First, when you don't need gl sharing, you can create the context much simpler: |
|
|
317 | |
|
|
318 | $ctx = $platform->context (undef, [$dev]) |
|
|
319 | |
|
|
320 | To use a texture, you would modify the above example by creating an |
|
|
321 | OpenCL::Image manually instead of deriving it from a texture: |
|
|
322 | |
|
|
323 | my $tex = $ctx->image2d (OpenCL::MEM_WRITE_ONLY, OpenCL::RGBA, OpenCL::UNORM_INT8, $S, $S); |
|
|
324 | |
|
|
325 | And in the darw loop, intead of acquire_gl_objects/release_gl_objects, you |
|
|
326 | would read the image2d after the kernel has written it: |
|
|
327 | |
|
|
328 | $queue->read_image ($tex, 0, 0, 0, 0, $S, $S, 1, 0, 0, my $data); |
|
|
329 | |
|
|
330 | And then you would upload the pixel data to the texture (or use glDrawPixels): |
|
|
331 | |
|
|
332 | glTexSubImage2D_s GL_TEXTURE_2D, 0, 0, 0, $S, $S, GL_RGBA, GL_UNSIGNED_BYTE, $data; |
|
|
333 | |
|
|
334 | The fully modified example can be found at |
|
|
335 | L<http://cvs.schmorp.de/OpenCL/examples/juliaflight-nosharing>. |
306 | |
336 | |
307 | =head1 DOCUMENTATION |
337 | =head1 DOCUMENTATION |
308 | |
338 | |
309 | =head2 BASIC CONVENTIONS |
339 | =head2 BASIC CONVENTIONS |
310 | |
340 | |
… | |
… | |
420 | use AnyEvent; |
450 | use AnyEvent; |
421 | |
451 | |
422 | # initialise AnyEvent, by creating a watcher, or: |
452 | # initialise AnyEvent, by creating a watcher, or: |
423 | AnyEvent::detect; |
453 | AnyEvent::detect; |
424 | |
454 | |
425 | my $e = $queue->enqueue_marker; |
455 | my $e = $queue->marker; |
426 | $e->cb (sub { |
456 | $e->cb (sub { |
427 | warn "opencl is finished\n"; |
457 | warn "opencl is finished\n"; |
428 | }) |
458 | }) |
429 | |
459 | |
430 | main Gtk2; |
460 | main Gtk2; |
… | |
… | |
447 | Asynchronously means that perl might execute your callbacks at any |
477 | Asynchronously means that perl might execute your callbacks at any |
448 | time. For example, in the following code (I<THAT YOU SHOULD NOT COPY>), |
478 | time. For example, in the following code (I<THAT YOU SHOULD NOT COPY>), |
449 | the C<until> loop following the marker call will be interrupted by the |
479 | the C<until> loop following the marker call will be interrupted by the |
450 | callback: |
480 | callback: |
451 | |
481 | |
452 | my $e = $queue->enqueue_marker; |
482 | my $e = $queue->marker; |
453 | my $flag; |
483 | my $flag; |
454 | $e->cb (sub { $flag = 1 }); |
484 | $e->cb (sub { $flag = 1 }); |
455 | 1 until $flag; |
485 | 1 until $flag; |
456 | # $flag is now 1 |
486 | # $flag is now 1 |
457 | |
487 | |
… | |
… | |
493 | =cut |
523 | =cut |
494 | |
524 | |
495 | package OpenCL; |
525 | package OpenCL; |
496 | |
526 | |
497 | use common::sense; |
527 | use common::sense; |
|
|
528 | use Carp (); |
498 | use Async::Interrupt (); |
529 | use Async::Interrupt (); |
499 | |
530 | |
500 | our $POLL_FUNC; # set by XS |
531 | our $POLL_FUNC; # set by XS |
501 | |
532 | |
502 | BEGIN { |
533 | BEGIN { |
503 | our $VERSION = '0.97'; |
534 | our $VERSION = '0.98'; |
504 | |
535 | |
505 | require XSLoader; |
536 | require XSLoader; |
506 | XSLoader::load (__PACKAGE__, $VERSION); |
537 | XSLoader::load (__PACKAGE__, $VERSION); |
507 | |
538 | |
508 | @OpenCL::Platform::ISA = |
539 | @OpenCL::Platform::ISA = |
… | |
… | |
537 | =item $int = OpenCL::errno |
568 | =item $int = OpenCL::errno |
538 | |
569 | |
539 | The last error returned by a function - it's only valid after an error occured |
570 | The last error returned by a function - it's only valid after an error occured |
540 | and before calling another OpenCL function. |
571 | and before calling another OpenCL function. |
541 | |
572 | |
542 | =item $str = OpenCL::err2str $errval |
573 | =item $str = OpenCL::err2str [$errval] |
543 | |
574 | |
544 | Comverts an error value into a human readable string. |
575 | Converts an error value into a human readable string. IF no error value is |
|
|
576 | given, then the last error will be used (as returned by OpenCL::errno). |
545 | |
577 | |
546 | =item $str = OpenCL::enum2str $enum |
578 | =item $str = OpenCL::enum2str $enum |
547 | |
579 | |
548 | Converts most enum values (of parameter names, image format constants, |
580 | Converts most enum values (of parameter names, image format constants, |
549 | object types, addressing and filter modes, command types etc.) into a |
581 | object types, addressing and filter modes, command types etc.) into a |
… | |
… | |
1002 | =cut |
1034 | =cut |
1003 | |
1035 | |
1004 | sub OpenCL::Context::build_program { |
1036 | sub OpenCL::Context::build_program { |
1005 | my ($self, $prog, $options) = @_; |
1037 | my ($self, $prog, $options) = @_; |
1006 | |
1038 | |
1007 | require Carp; |
|
|
1008 | |
|
|
1009 | $prog = $self->program_with_source ($prog) |
1039 | $prog = $self->program_with_source ($prog) |
1010 | unless ref $prog; |
1040 | unless ref $prog; |
1011 | |
1041 | |
1012 | # we build separately per device so we instantly know which one failed |
1042 | eval { $prog->build (undef, $options); 1 } |
|
|
1043 | or errno == BUILD_PROGRAM_FAILURE |
|
|
1044 | or errno == INVALID_BINARY # workaround nvidia bug |
|
|
1045 | or Carp::croak "OpenCL::Context->build_program: " . err2str; |
|
|
1046 | |
|
|
1047 | # we check status for all devices |
1013 | for my $dev ($self->devices) { |
1048 | for my $dev ($self->devices) { |
1014 | eval { $prog->build ([$dev], $options); 1 } |
1049 | $prog->build_status ($dev) == BUILD_SUCCESS |
1015 | or Carp::croak ("Building OpenCL program for device '" . $dev->name . "' failed:\n" |
1050 | or Carp::croak "Building OpenCL program for device '" . $dev->name . "' failed:\n" |
1016 | . $prog->build_log ($dev)); |
1051 | . $prog->build_log ($dev); |
1017 | } |
1052 | } |
1018 | |
1053 | |
1019 | $prog |
1054 | $prog |
1020 | } |
1055 | } |
1021 | |
1056 | |
… | |
… | |
1045 | =item $buf = $ctx->buffer_sv ($flags, $data) |
1080 | =item $buf = $ctx->buffer_sv ($flags, $data) |
1046 | |
1081 | |
1047 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and |
1082 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and |
1048 | initialise it with the given data values. |
1083 | initialise it with the given data values. |
1049 | |
1084 | |
1050 | =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) |
1085 | =item $img = $ctx->image ($self, $flags, $channel_order, $channel_type, $type, $width, $height, $depth = 0, $array_size = 0, $row_pitch = 0, $slice_pitch = 0, $num_mip_level = 0, $num_samples = 0, $*data = &PL_sv_undef) |
1051 | |
1086 | |
1052 | Creates a new OpenCL::Image object and optionally initialises it with |
1087 | Creates a new OpenCL::Image object and optionally initialises it with |
1053 | the given data values. |
1088 | the given data values. |
1054 | |
1089 | |
1055 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html> |
1090 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html> |
… | |
… | |
1151 | =back |
1186 | =back |
1152 | |
1187 | |
1153 | =head2 THE OpenCL::Queue CLASS |
1188 | =head2 THE OpenCL::Queue CLASS |
1154 | |
1189 | |
1155 | An OpenCL::Queue represents an execution queue for OpenCL. You execute |
1190 | An OpenCL::Queue represents an execution queue for OpenCL. You execute |
1156 | requests by calling their respective C<enqueue_xxx> method and waitinf for |
1191 | requests by calling their respective method and waiting for it to complete |
1157 | it to complete in some way. |
1192 | in some way. |
1158 | |
1193 | |
1159 | All the enqueue methods return an event object that can be used to wait |
1194 | Most methods that enqueue some request return an event object that can |
1160 | for completion, unless the method is called in void context, in which case |
1195 | be used to wait for completion (optionally using a callback), unless |
1161 | no event object is created. |
1196 | the method is called in void context, in which case no event object is |
|
|
1197 | created. |
1162 | |
1198 | |
1163 | They also allow you to specify any number of other event objects that this |
1199 | They also allow you to specify any number of other event objects that this |
1164 | request has to wait for before it starts executing, by simply passing the |
1200 | request has to wait for before it starts executing, by simply passing the |
1165 | event objects as extra parameters to the enqueue methods. To simplify |
1201 | event objects as extra parameters to the enqueue methods. To simplify |
1166 | program design, this module ignores any C<undef> values in the list of |
1202 | program design, this module ignores any C<undef> values in the list of |
1167 | events. This makes it possible to code operations such as this, without |
1203 | events. This makes it possible to code operations such as this, without |
1168 | having to put a valid event object into C<$event> first: |
1204 | having to put a valid event object into C<$event> first: |
1169 | |
1205 | |
1170 | $event = $queue->enqueue_xxx (..., $event); |
1206 | $event = $queue->xxx (..., $event); |
1171 | |
1207 | |
1172 | Queues execute in-order by default, without any parallelism, so in most |
1208 | Queues execute in-order by default, without any parallelism, so in most |
1173 | cases (i.e. you use only one queue) it's not necessary to wait for or |
1209 | cases (i.e. you use only one queue) it's not necessary to wait for or |
1174 | create event objects, althoguh an our of order queue is often a bit |
1210 | create event objects, althoguh an our of order queue is often a bit |
1175 | faster. |
1211 | faster. |
1176 | |
1212 | |
1177 | =over 4 |
1213 | =over 4 |
1178 | |
1214 | |
1179 | =item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) |
1215 | =item $ev = $queue->read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) |
1180 | |
1216 | |
1181 | Reads data from buffer into the given string. |
1217 | Reads data from buffer into the given string. |
1182 | |
1218 | |
1183 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html> |
1219 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html> |
1184 | |
1220 | |
1185 | =item $ev = $queue->enqueue_write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) |
1221 | =item $ev = $queue->write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) |
1186 | |
1222 | |
1187 | Writes data to buffer from the given string. |
1223 | Writes data to buffer from the given string. |
1188 | |
1224 | |
1189 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html> |
1225 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html> |
1190 | |
1226 | |
1191 | =item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) |
1227 | =item $ev = $queue->copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) |
1192 | |
1228 | |
1193 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> |
1229 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> |
1194 | |
1230 | |
1195 | =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...) |
1231 | =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...) |
1196 | |
1232 | |
1197 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html |
1233 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html |
1198 | |
1234 | |
1199 | =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...) |
1235 | =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...) |
1200 | |
1236 | |
1201 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html |
1237 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html |
1202 | |
1238 | |
1203 | =item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
|
|
1204 | |
|
|
1205 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html> |
|
|
1206 | |
|
|
1207 | =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...) |
1239 | =item $ev = $queue->copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
|
|
1240 | |
|
|
1241 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html> |
|
|
1242 | |
|
|
1243 | =item $ev = $queue->read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
|
|
1244 | |
|
|
1245 | C<$row_pitch> (and C<$slice_pitch>) can be C<0>, in which case the OpenCL |
|
|
1246 | module uses the image width (and height) to supply default values. |
1208 | |
1247 | |
1209 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> |
1248 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> |
1210 | |
1249 | |
1211 | =item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
1250 | =item $ev = $queue->write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
1212 | |
1251 | |
|
|
1252 | C<$row_pitch> (and C<$slice_pitch>) can be C<0>, in which case the OpenCL |
|
|
1253 | module uses the image width (and height) to supply default values. |
1213 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> |
1254 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> |
1214 | |
1255 | |
1215 | =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...) |
1256 | =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...) |
1216 | |
1257 | |
1217 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> |
1258 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> |
1218 | |
1259 | |
1219 | =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...) |
1260 | =item $ev = $queue->copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...) |
1220 | |
1261 | |
1221 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html> |
1262 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html> |
1222 | |
1263 | |
1223 | =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...) |
1264 | =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...) |
1224 | |
1265 | |
1225 | Yeah. |
1266 | Yeah. |
1226 | |
1267 | |
1227 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
1268 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
1228 | |
1269 | |
1229 | =item $ev = $queue->enqueue_fill_buffer ($mem, $pattern, $offset, $size, ...) |
1270 | =item $ev = $queue->fill_buffer ($mem, $pattern, $offset, $size, ...) |
1230 | |
1271 | |
1231 | Fills the given buffer object with repeated applications of C<$pattern>, |
1272 | Fills the given buffer object with repeated applications of C<$pattern>, |
1232 | starting at C<$offset> for C<$size> octets. |
1273 | starting at C<$offset> for C<$size> octets. |
1233 | |
1274 | |
1234 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html> |
1275 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html> |
1235 | |
1276 | |
1236 | =item $ev = $queue->enqueue_fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...) |
1277 | =item $ev = $queue->fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...) |
1237 | |
1278 | |
1238 | Fills the given image area with the given rgba colour components. The |
1279 | Fills the given image area with the given rgba colour components. The |
1239 | components are normally floating point values between C<0> and C<1>, |
1280 | components are normally floating point values between C<0> and C<1>, |
1240 | except when the image channel data type is a signe dor unsigned |
1281 | except when the image channel data type is a signe dor unsigned |
1241 | unnormalised format, in which case the range is determined by the format. |
1282 | unnormalised format, in which case the range is determined by the format. |
1242 | |
1283 | |
1243 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html> |
1284 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html> |
1244 | |
1285 | |
1245 | =item $ev = $queue->enqueue_task ($kernel, $wait_events...) |
1286 | =item $ev = $queue->task ($kernel, $wait_events...) |
1246 | |
1287 | |
1247 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
1288 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
1248 | |
1289 | |
1249 | =item $ev = $queue->enqueue_nd_range_kernel ($kernel, \@global_work_offset, \@global_work_size, \@local_work_size, $wait_events...) |
1290 | =item $ev = $queue->nd_range_kernel ($kernel, \@global_work_offset, \@global_work_size, \@local_work_size, $wait_events...) |
1250 | |
1291 | |
1251 | Enqueues a kernel execution. |
1292 | Enqueues a kernel execution. |
1252 | |
1293 | |
1253 | \@global_work_size must be specified as a reference to an array of |
1294 | \@global_work_size must be specified as a reference to an array of |
1254 | integers specifying the work sizes (element counts). |
1295 | integers specifying the work sizes (element counts). |
… | |
… | |
1262 | reference to an array of local work sizes, with the same number of |
1303 | reference to an array of local work sizes, with the same number of |
1263 | elements as \@global_work_size. |
1304 | elements as \@global_work_size. |
1264 | |
1305 | |
1265 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
1306 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
1266 | |
1307 | |
1267 | =item $ev = $queue->enqueue_acquire_gl_objects ([object, ...], $wait_events...) |
1308 | =item $ev = $queue->acquire_gl_objects ([object, ...], $wait_events...) |
1268 | |
1309 | |
1269 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired |
1310 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired |
1270 | for subsequent OpenCL usage. |
1311 | for subsequent OpenCL usage. |
1271 | |
1312 | |
1272 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html> |
1313 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html> |
1273 | |
1314 | |
1274 | =item $ev = $queue->enqueue_release_gl_objects ([object, ...], $wait_events...) |
1315 | =item $ev = $queue->release_gl_objects ([object, ...], $wait_events...) |
1275 | |
1316 | |
1276 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be released |
1317 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be released |
1277 | for subsequent OpenGL usage. |
1318 | for subsequent OpenGL usage. |
1278 | |
1319 | |
1279 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html> |
1320 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html> |
1280 | |
1321 | |
1281 | =item $ev = $queue->enqueue_wait_for_events ($wait_events...) |
1322 | =item $ev = $queue->wait_for_events ($wait_events...) |
1282 | |
1323 | |
1283 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
1324 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
1284 | |
1325 | |
1285 | =item $ev = $queue->enqueue_marker ($wait_events...) |
1326 | =item $ev = $queue->marker ($wait_events...) |
1286 | |
1327 | |
1287 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html> |
1328 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html> |
1288 | |
1329 | |
1289 | =item $ev = $queue->enqueue_barrier ($wait_events...) |
1330 | =item $ev = $queue->barrier ($wait_events...) |
1290 | |
1331 | |
1291 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html> |
1332 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html> |
1292 | |
1333 | |
1293 | =item $queue->flush |
1334 | =item $queue->flush |
1294 | |
1335 | |
… | |
… | |
1523 | If a callback is specified, then it will be called when compilation is |
1564 | If a callback is specified, then it will be called when compilation is |
1524 | finished. Note that many OpenCL implementations block your program while |
1565 | finished. Note that many OpenCL implementations block your program while |
1525 | compiling whether you use a callback or not. See C<build_async> if you |
1566 | compiling whether you use a callback or not. See C<build_async> if you |
1526 | want to make sure the build is done in the background. |
1567 | want to make sure the build is done in the background. |
1527 | |
1568 | |
1528 | Note that some OpenCL implementations atc up badly, and don't call the |
1569 | Note that some OpenCL implementations act up badly, and don't call the |
1529 | callback in some error cases (but call it in others). This implementation |
1570 | callback in some error cases (but call it in others). This implementation |
1530 | assumes the callback will always be called, and leaks memory if this is |
1571 | assumes the callback will always be called, and leaks memory if this is |
1531 | not so. So best make sure you don't pass in invalid values. |
1572 | not so. So best make sure you don't pass in invalid values. |
1532 | |
1573 | |
|
|
1574 | Some implementations fail with C<OpenCL::INVALID_BINARY> when the |
|
|
1575 | compilation state is successful but some later stage fails. |
|
|
1576 | |
1533 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
1577 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
1534 | |
1578 | |
1535 | =item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef) |
1579 | =item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef) |
1536 | |
1580 | |
1537 | Similar to C<< ->build >>, except it starts a thread, and never fails (you |
1581 | Similar to C<< ->build >>, except it starts a thread, and never fails (you |
… | |
… | |
1684 | =item $ulong = $kernel->private_mem_size ($device) |
1728 | =item $ulong = $kernel->private_mem_size ($device) |
1685 | |
1729 | |
1686 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result. |
1730 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result. |
1687 | |
1731 | |
1688 | =for gengetinfo end kernel_work_group |
1732 | =for gengetinfo end kernel_work_group |
|
|
1733 | |
|
|
1734 | =item $kernel->setf ($format, ...) |
|
|
1735 | |
|
|
1736 | Sets the arguments of a kernel. Since OpenCL 1.1 doesn't have a generic |
|
|
1737 | way to set arguments (and with OpenCL 1.2 it might be rather slow), you |
|
|
1738 | need to specify a format argument, much as with C<printf>, to tell OpenCL |
|
|
1739 | what type of argument it is. |
|
|
1740 | |
|
|
1741 | The format arguments are single letters: |
|
|
1742 | |
|
|
1743 | c char |
|
|
1744 | C unsigned char |
|
|
1745 | s short |
|
|
1746 | S unsigned short |
|
|
1747 | i int |
|
|
1748 | I unsigned int |
|
|
1749 | l long |
|
|
1750 | L unsigned long |
|
|
1751 | |
|
|
1752 | h half float (0..65535) |
|
|
1753 | f float |
|
|
1754 | d double |
|
|
1755 | |
|
|
1756 | z local (octet size) |
|
|
1757 | |
|
|
1758 | m memory object (buffer or image) |
|
|
1759 | a sampler |
|
|
1760 | e event |
|
|
1761 | |
|
|
1762 | Space characters in the format string are ignored. |
|
|
1763 | |
|
|
1764 | Example: set the arguments for a kernel that expects an int, two floats, a buffer and an image. |
|
|
1765 | |
|
|
1766 | $kernel->setf ("i ff mm", 5, 0.5, 3, $buffer, $image); |
1689 | |
1767 | |
1690 | =item $kernel->set_TYPE ($index, $value) |
1768 | =item $kernel->set_TYPE ($index, $value) |
1691 | |
1769 | |
1692 | =item $kernel->set_char ($index, $value) |
1770 | =item $kernel->set_char ($index, $value) |
1693 | |
1771 | |