| … | |
… | |
| 43 | |
43 | |
| 44 | OpenCL::Event objects are used to signal when something is complete. |
44 | OpenCL::Event objects are used to signal when something is complete. |
| 45 | |
45 | |
| 46 | =head2 HELPFUL RESOURCES |
46 | =head2 HELPFUL RESOURCES |
| 47 | |
47 | |
| 48 | The OpenCL spec used to develop this module (1.2 spec was available, but |
48 | The OpenCL specs used to develop this module: |
| 49 | no implementation was available to me :). |
|
|
| 50 | |
49 | |
| 51 | http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf |
50 | http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf |
|
|
51 | http://www.khronos.org/registry/cl/specs/opencl-1.2.pdf |
|
|
52 | http://www.khronos.org/registry/cl/specs/opencl-1.2-extensions.pdf |
| 52 | |
53 | |
| 53 | OpenCL manpages: |
54 | OpenCL manpages: |
| 54 | |
55 | |
| 55 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/ |
56 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/ |
|
|
57 | http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/ |
| 56 | |
58 | |
| 57 | If you are into UML class diagrams, the following diagram might help - if |
59 | If you are into UML class diagrams, the following diagram might help - if |
| 58 | not, it will be mildly cobfusing: |
60 | not, it will be mildly confusing (also, the class hierarchy of this module |
|
|
61 | is much more fine-grained): |
| 59 | |
62 | |
| 60 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/classDiagram.html |
63 | http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/classDiagram.html |
| 61 | |
64 | |
| 62 | Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it |
65 | Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it |
| 63 | is, but at least it's free of charge: |
66 | is, but at least it's free of charge: |
| 64 | |
67 | |
| 65 | http://developer.amd.com/zones/OpenCLZone/courses/Documents/Introduction_to_OpenCL_Programming%20Training_Guide%20%28201005%29.pdf |
68 | http://developer.amd.com/zones/OpenCLZone/courses/Documents/Introduction_to_OpenCL_Programming%20Training_Guide%20%28201005%29.pdf |
| … | |
… | |
| 138 | =head2 Create a buffer with some predefined data, read it back synchronously, |
141 | =head2 Create a buffer with some predefined data, read it back synchronously, |
| 139 | then asynchronously. |
142 | then asynchronously. |
| 140 | |
143 | |
| 141 | my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); |
144 | my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); |
| 142 | |
145 | |
| 143 | $queue->enqueue_read_buffer ($buf, 1, 1, 3, my $data); |
146 | $queue->read_buffer ($buf, 1, 1, 3, my $data); |
| 144 | print "$data\n"; |
147 | print "$data\n"; |
| 145 | |
148 | |
| 146 | my $ev = $queue->enqueue_read_buffer ($buf, 0, 1, 3, my $data); |
149 | my $ev = $queue->read_buffer ($buf, 0, 1, 3, my $data); |
| 147 | $ev->wait; |
150 | $ev->wait; |
| 148 | print "$data\n"; # prints "elm" |
151 | print "$data\n"; # prints "elm" |
| 149 | |
152 | |
| 150 | =head2 Create and build a program, then create a kernel out of one of its |
153 | =head2 Create and build a program, then create a kernel out of one of its |
| 151 | functions. |
154 | functions. |
| … | |
… | |
| 171 | # set buffer |
174 | # set buffer |
| 172 | $kernel->set_buffer (0, $input); |
175 | $kernel->set_buffer (0, $input); |
| 173 | $kernel->set_buffer (1, $output); |
176 | $kernel->set_buffer (1, $output); |
| 174 | |
177 | |
| 175 | # execute it for all 4 numbers |
178 | # execute it for all 4 numbers |
| 176 | $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
179 | $queue->nd_range_kernel ($kernel, undef, [4], undef); |
| 177 | |
180 | |
| 178 | # enqueue a synchronous read |
181 | # enqueue a synchronous read |
| 179 | $queue->enqueue_read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
182 | $queue->read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
| 180 | |
183 | |
| 181 | # print the results: |
184 | # print the results: |
| 182 | printf "%s\n", join ", ", unpack "f*", $data; |
185 | printf "%s\n", join ", ", unpack "f*", $data; |
| 183 | |
186 | |
| 184 | =head2 The same enqueue operations as before, but assuming an out-of-order queue, |
187 | =head2 The same enqueue operations as before, but assuming an out-of-order queue, |
| 185 | showing off barriers. |
188 | showing off barriers. |
| 186 | |
189 | |
| 187 | # execute it for all 4 numbers |
190 | # execute it for all 4 numbers |
| 188 | $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
191 | $queue->nd_range_kernel ($kernel, undef, [4], undef); |
| 189 | |
192 | |
| 190 | # enqueue a barrier to ensure in-order execution |
193 | # enqueue a barrier to ensure in-order execution |
| 191 | $queue->enqueue_barrier; |
194 | $queue->barrier; |
| 192 | |
195 | |
| 193 | # enqueue an async read |
196 | # enqueue an async read |
| 194 | $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
197 | $queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
| 195 | |
198 | |
| 196 | # wait for all requests to finish |
199 | # wait for all requests to finish |
| 197 | $queue->finish; |
200 | $queue->finish; |
| 198 | |
201 | |
| 199 | =head2 The same enqueue operations as before, but assuming an out-of-order queue, |
202 | =head2 The same enqueue operations as before, but assuming an out-of-order queue, |
| 200 | showing off event objects and wait lists. |
203 | showing off event objects and wait lists. |
| 201 | |
204 | |
| 202 | # execute it for all 4 numbers |
205 | # execute it for all 4 numbers |
| 203 | my $ev = $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
206 | my $ev = $queue->nd_range_kernel ($kernel, undef, [4], undef); |
| 204 | |
207 | |
| 205 | # enqueue an async read |
208 | # enqueue an async read |
| 206 | $ev = $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev); |
209 | $ev = $queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev); |
| 207 | |
210 | |
| 208 | # wait for the last event to complete |
211 | # wait for the last event to complete |
| 209 | $ev->wait; |
212 | $ev->wait; |
| 210 | |
213 | |
| 211 | =head2 Use the OpenGL module to share a texture between OpenCL and OpenGL and draw some julia |
214 | =head2 Use the OpenGL module to share a texture between OpenCL and OpenGL and draw some julia |
| 212 | set tunnel effect. |
215 | set tunnel effect. |
| 213 | |
216 | |
| 214 | This is quite a long example to get you going. |
217 | This is quite a long example to get you going - you can download it from |
|
|
218 | L<http://cvs.schmorp.de/OpenCL/examples/juliaflight>. |
| 215 | |
219 | |
| 216 | use OpenGL ":all"; |
220 | use OpenGL ":all"; |
| 217 | use OpenCL; |
221 | use OpenCL; |
| 218 | |
222 | |
|
|
223 | my $S = $ARGV[0] || 256; # window/texture size, smaller is faster |
|
|
224 | |
| 219 | # open a window and create a gl texture |
225 | # open a window and create a gl texture |
| 220 | OpenGL::glpOpenWindow width => 256, height => 256; |
226 | OpenGL::glpOpenWindow width => $S, height => $S; |
| 221 | my $texid = glGenTextures_p 1; |
227 | my $texid = glGenTextures_p 1; |
| 222 | glBindTexture GL_TEXTURE_2D, $texid; |
228 | glBindTexture GL_TEXTURE_2D, $texid; |
| 223 | glTexImage2D_c GL_TEXTURE_2D, 0, GL_RGBA8, 256, 256, 0, GL_RGBA, GL_UNSIGNED_BYTE, 0; |
229 | glTexImage2D_c GL_TEXTURE_2D, 0, GL_RGBA8, $S, $S, 0, GL_RGBA, GL_UNSIGNED_BYTE, 0; |
| 224 | |
230 | |
| 225 | # find and use the first opencl device that let's us get a shared opengl context |
231 | # find and use the first opencl device that let's us get a shared opengl context |
| 226 | my $platform; |
232 | my $platform; |
| 227 | my $dev; |
233 | my $dev; |
| 228 | my $ctx; |
234 | my $ctx; |
| … | |
… | |
| 247 | # now the boring opencl code |
253 | # now the boring opencl code |
| 248 | my $src = <<EOF; |
254 | my $src = <<EOF; |
| 249 | kernel void |
255 | kernel void |
| 250 | juliatunnel (write_only image2d_t img, float time) |
256 | juliatunnel (write_only image2d_t img, float time) |
| 251 | { |
257 | { |
| 252 | float2 p = (float2)(get_global_id (0), get_global_id (1)) / 256.f * 2.f - 1.f; |
258 | int2 xy = (int2)(get_global_id (0), get_global_id (1)); |
|
|
259 | float2 p = convert_float2 (xy) / $S.f * 2.f - 1.f; |
| 253 | |
260 | |
| 254 | float2 m = (float2)(1.f, p.y) / fabs (p.x); |
261 | float2 m = (float2)(1.f, p.y) / fabs (p.x); // tunnel |
| 255 | m.x = fabs (fmod (m.x + time * 0.05f, 4.f)) - 2.f; |
262 | m.x = fabs (fmod (m.x + time * 0.05f, 4.f) - 2.f); |
| 256 | |
263 | |
| 257 | float2 z = m; |
264 | float2 z = m; |
| 258 | float2 c = (float2)(sin (time * 0.05005), cos (time * 0.06001)); |
265 | float2 c = (float2)(sin (time * 0.01133f), cos (time * 0.02521f)); |
| 259 | |
266 | |
| 260 | for (int i = 0; i < 25 && dot (z, z) < 4.f; ++i) |
267 | for (int i = 0; i < 25 && dot (z, z) < 4.f; ++i) // standard julia |
| 261 | z = (float2)(z.x * z.x - z.y * z.y, 2.f * z.x * z.y) + c; |
268 | z = (float2)(z.x * z.x - z.y * z.y, 2.f * z.x * z.y) + c; |
| 262 | |
269 | |
| 263 | float3 colour = (float3)(z.x, z.y, z.x * z.y); |
270 | float3 colour = (float3)(z.x, z.y, atan2 (z.y, z.x)); |
| 264 | write_imagef (img, (int2)(get_global_id (0), get_global_id (1)), (float4)(colour * p.x * p.x, 1.)); |
271 | write_imagef (img, xy, (float4)(colour * p.x * p.x, 1.)); |
| 265 | } |
272 | } |
| 266 | EOF |
273 | EOF |
| 267 | |
274 | |
| 268 | my $prog = $ctx->build_program ($src); |
275 | my $prog = $ctx->build_program ($src); |
| 269 | my $kernel = $prog->kernel ("juliatunnel"); |
276 | my $kernel = $prog->kernel ("juliatunnel"); |
| 270 | |
277 | |
| 271 | # program compiled, kernel ready, now draw and loop |
278 | # program compiled, kernel ready, now draw and loop |
| 272 | |
279 | |
| 273 | for (my $time; ; ++$time) { |
280 | for (my $time; ; ++$time) { |
| 274 | # acquire objects from opengl |
281 | # acquire objects from opengl |
| 275 | $queue->enqueue_acquire_gl_objects ([$tex]); |
282 | $queue->acquire_gl_objects ([$tex]); |
| 276 | |
283 | |
| 277 | # configure and run our kernel |
284 | # configure and run our kernel |
| 278 | $kernel->set_image2d (0, $tex); |
285 | $kernel->setf ("mf", $tex, $time*2); # mf = memory object, float |
| 279 | $kernel->set_float (1, $time); |
|
|
| 280 | $queue->enqueue_nd_range_kernel ($kernel, undef, [256, 256], undef); |
286 | $queue->nd_range_kernel ($kernel, undef, [$S, $S], undef); |
| 281 | |
287 | |
| 282 | # release objects to opengl again |
288 | # release objects to opengl again |
| 283 | $queue->enqueue_release_gl_objects ([$tex]); |
289 | $queue->release_gl_objects ([$tex]); |
| 284 | |
290 | |
| 285 | # wait |
291 | # wait |
| 286 | $queue->finish; |
292 | $queue->finish; |
| 287 | |
293 | |
| 288 | # now draw the texture, the defaults should be all right |
294 | # now draw the texture, the defaults should be all right |
| … | |
… | |
| 417 | use AnyEvent; |
423 | use AnyEvent; |
| 418 | |
424 | |
| 419 | # initialise AnyEvent, by creating a watcher, or: |
425 | # initialise AnyEvent, by creating a watcher, or: |
| 420 | AnyEvent::detect; |
426 | AnyEvent::detect; |
| 421 | |
427 | |
| 422 | my $e = $queue->enqueue_marker; |
428 | my $e = $queue->marker; |
| 423 | $e->cb (sub { |
429 | $e->cb (sub { |
| 424 | warn "opencl is finished\n"; |
430 | warn "opencl is finished\n"; |
| 425 | }) |
431 | }) |
| 426 | |
432 | |
| 427 | main Gtk2; |
433 | main Gtk2; |
| … | |
… | |
| 444 | Asynchronously means that perl might execute your callbacks at any |
450 | Asynchronously means that perl might execute your callbacks at any |
| 445 | time. For example, in the following code (I<THAT YOU SHOULD NOT COPY>), |
451 | 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 |
452 | the C<until> loop following the marker call will be interrupted by the |
| 447 | callback: |
453 | callback: |
| 448 | |
454 | |
| 449 | my $e = $queue->enqueue_marker; |
455 | my $e = $queue->marker; |
| 450 | my $flag; |
456 | my $flag; |
| 451 | $e->cb (sub { $flag = 1 }); |
457 | $e->cb (sub { $flag = 1 }); |
| 452 | 1 until $flag; |
458 | 1 until $flag; |
| 453 | # $flag is now 1 |
459 | # $flag is now 1 |
| 454 | |
460 | |
| … | |
… | |
| 490 | =cut |
496 | =cut |
| 491 | |
497 | |
| 492 | package OpenCL; |
498 | package OpenCL; |
| 493 | |
499 | |
| 494 | use common::sense; |
500 | use common::sense; |
|
|
501 | use Carp (); |
| 495 | use Async::Interrupt (); |
502 | use Async::Interrupt (); |
| 496 | |
503 | |
| 497 | our $POLL_FUNC; # set by XS |
504 | our $POLL_FUNC; # set by XS |
| 498 | |
505 | |
| 499 | BEGIN { |
506 | BEGIN { |
| 500 | our $VERSION = '0.97'; |
507 | our $VERSION = '0.98'; |
| 501 | |
508 | |
| 502 | require XSLoader; |
509 | require XSLoader; |
| 503 | XSLoader::load (__PACKAGE__, $VERSION); |
510 | XSLoader::load (__PACKAGE__, $VERSION); |
| 504 | |
511 | |
| 505 | @OpenCL::Platform::ISA = |
512 | @OpenCL::Platform::ISA = |
| … | |
… | |
| 534 | =item $int = OpenCL::errno |
541 | =item $int = OpenCL::errno |
| 535 | |
542 | |
| 536 | The last error returned by a function - it's only valid after an error occured |
543 | The last error returned by a function - it's only valid after an error occured |
| 537 | and before calling another OpenCL function. |
544 | and before calling another OpenCL function. |
| 538 | |
545 | |
| 539 | =item $str = OpenCL::err2str $errval |
546 | =item $str = OpenCL::err2str [$errval] |
| 540 | |
547 | |
| 541 | Comverts an error value into a human readable string. |
548 | Converts an error value into a human readable string. IF no error value is |
|
|
549 | given, then the last error will be used (as returned by OpenCL::errno). |
| 542 | |
550 | |
| 543 | =item $str = OpenCL::enum2str $enum |
551 | =item $str = OpenCL::enum2str $enum |
| 544 | |
552 | |
| 545 | Converts most enum values (of parameter names, image format constants, |
553 | Converts most enum values (of parameter names, image format constants, |
| 546 | object types, addressing and filter modes, command types etc.) into a |
554 | object types, addressing and filter modes, command types etc.) into a |
| … | |
… | |
| 999 | =cut |
1007 | =cut |
| 1000 | |
1008 | |
| 1001 | sub OpenCL::Context::build_program { |
1009 | sub OpenCL::Context::build_program { |
| 1002 | my ($self, $prog, $options) = @_; |
1010 | my ($self, $prog, $options) = @_; |
| 1003 | |
1011 | |
| 1004 | require Carp; |
|
|
| 1005 | |
|
|
| 1006 | $prog = $self->program_with_source ($prog) |
1012 | $prog = $self->program_with_source ($prog) |
| 1007 | unless ref $prog; |
1013 | unless ref $prog; |
| 1008 | |
1014 | |
| 1009 | # we build separately per device so we instantly know which one failed |
1015 | eval { $prog->build (undef, $options); 1 } |
|
|
1016 | or errno == BUILD_PROGRAM_FAILURE |
|
|
1017 | or errno == INVALID_BINARY # workaround nvidia bug |
|
|
1018 | or Carp::croak "OpenCL::Context->build_program: " . err2str; |
|
|
1019 | |
|
|
1020 | # we check status for all devices |
| 1010 | for my $dev ($self->devices) { |
1021 | for my $dev ($self->devices) { |
| 1011 | eval { $prog->build ([$dev], $options); 1 } |
1022 | $prog->build_status ($dev) == BUILD_SUCCESS |
| 1012 | or Carp::croak ("Building OpenCL program for device '" . $dev->name . "' failed:\n" |
1023 | or Carp::croak "Building OpenCL program for device '" . $dev->name . "' failed:\n" |
| 1013 | . $prog->build_log ($dev)); |
1024 | . $prog->build_log ($dev); |
| 1014 | } |
1025 | } |
| 1015 | |
1026 | |
| 1016 | $prog |
1027 | $prog |
| 1017 | } |
1028 | } |
| 1018 | |
1029 | |
| … | |
… | |
| 1042 | =item $buf = $ctx->buffer_sv ($flags, $data) |
1053 | =item $buf = $ctx->buffer_sv ($flags, $data) |
| 1043 | |
1054 | |
| 1044 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and |
1055 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and |
| 1045 | initialise it with the given data values. |
1056 | initialise it with the given data values. |
| 1046 | |
1057 | |
| 1047 | =item $img = $ctx->image ($self, $flags, $channel_order, $channel_type, $type, $width, $height, $depth, $array_size = 0, $row_pitch = 0, $slice_pitch = 0, $num_mip_level = 0, $num_samples = 0, $*data = &PL_sv_undef) |
1058 | =item $img = $ctx->image ($self, $flags, $channel_order, $channel_type, $type, $width, $height, $depth = 0, $array_size = 0, $row_pitch = 0, $slice_pitch = 0, $num_mip_level = 0, $num_samples = 0, $*data = &PL_sv_undef) |
| 1048 | |
1059 | |
| 1049 | Creates a new OpenCL::Image object and optionally initialises it with |
1060 | Creates a new OpenCL::Image object and optionally initialises it with |
| 1050 | the given data values. |
1061 | the given data values. |
| 1051 | |
1062 | |
| 1052 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html> |
1063 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html> |
| … | |
… | |
| 1148 | =back |
1159 | =back |
| 1149 | |
1160 | |
| 1150 | =head2 THE OpenCL::Queue CLASS |
1161 | =head2 THE OpenCL::Queue CLASS |
| 1151 | |
1162 | |
| 1152 | An OpenCL::Queue represents an execution queue for OpenCL. You execute |
1163 | An OpenCL::Queue represents an execution queue for OpenCL. You execute |
| 1153 | requests by calling their respective C<enqueue_xxx> method and waitinf for |
1164 | requests by calling their respective method and waiting for it to complete |
| 1154 | it to complete in some way. |
1165 | in some way. |
| 1155 | |
1166 | |
| 1156 | All the enqueue methods return an event object that can be used to wait |
1167 | Most methods that enqueue some request return an event object that can |
| 1157 | for completion, unless the method is called in void context, in which case |
1168 | be used to wait for completion (optionally using a callback), unless |
| 1158 | no event object is created. |
1169 | the method is called in void context, in which case no event object is |
|
|
1170 | created. |
| 1159 | |
1171 | |
| 1160 | They also allow you to specify any number of other event objects that this |
1172 | They also allow you to specify any number of other event objects that this |
| 1161 | request has to wait for before it starts executing, by simply passing the |
1173 | request has to wait for before it starts executing, by simply passing the |
| 1162 | event objects as extra parameters to the enqueue methods. To simplify |
1174 | event objects as extra parameters to the enqueue methods. To simplify |
| 1163 | program design, this module ignores any C<undef> values in the list of |
1175 | program design, this module ignores any C<undef> values in the list of |
| 1164 | events. This makes it possible to code operations such as this, without |
1176 | events. This makes it possible to code operations such as this, without |
| 1165 | having to put a valid event object into C<$event> first: |
1177 | having to put a valid event object into C<$event> first: |
| 1166 | |
1178 | |
| 1167 | $event = $queue->enqueue_xxx (..., $event); |
1179 | $event = $queue->xxx (..., $event); |
| 1168 | |
1180 | |
| 1169 | Queues execute in-order by default, without any parallelism, so in most |
1181 | Queues execute in-order by default, without any parallelism, so in most |
| 1170 | cases (i.e. you use only one queue) it's not necessary to wait for or |
1182 | cases (i.e. you use only one queue) it's not necessary to wait for or |
| 1171 | create event objects, althoguh an our of order queue is often a bit |
1183 | create event objects, althoguh an our of order queue is often a bit |
| 1172 | faster. |
1184 | faster. |
| 1173 | |
1185 | |
| 1174 | =over 4 |
1186 | =over 4 |
| 1175 | |
1187 | |
| 1176 | =item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) |
1188 | =item $ev = $queue->read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) |
| 1177 | |
1189 | |
| 1178 | Reads data from buffer into the given string. |
1190 | Reads data from buffer into the given string. |
| 1179 | |
1191 | |
| 1180 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html> |
1192 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html> |
| 1181 | |
1193 | |
| 1182 | =item $ev = $queue->enqueue_write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) |
1194 | =item $ev = $queue->write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) |
| 1183 | |
1195 | |
| 1184 | Writes data to buffer from the given string. |
1196 | Writes data to buffer from the given string. |
| 1185 | |
1197 | |
| 1186 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html> |
1198 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html> |
| 1187 | |
1199 | |
| 1188 | =item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) |
1200 | =item $ev = $queue->copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) |
| 1189 | |
1201 | |
| 1190 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> |
1202 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> |
| 1191 | |
1203 | |
| 1192 | =item $ev = $queue->enqueue_read_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) |
1204 | =item $ev = $queue->read_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) |
| 1193 | |
1205 | |
| 1194 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html |
1206 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html |
| 1195 | |
1207 | |
| 1196 | =item $ev = $queue->enqueue_write_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) |
1208 | =item $ev = $queue->write_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) |
| 1197 | |
1209 | |
| 1198 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html |
1210 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html |
| 1199 | |
1211 | |
| 1200 | =item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
1212 | =item $ev = $queue->read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
| 1201 | |
1213 | |
| 1202 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html> |
1214 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html> |
| 1203 | |
1215 | |
| 1204 | =item $ev = $queue->enqueue_copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
1216 | =item $ev = $queue->copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
| 1205 | |
1217 | |
| 1206 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> |
1218 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> |
| 1207 | |
1219 | |
| 1208 | =item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
1220 | =item $ev = $queue->write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
| 1209 | |
1221 | |
| 1210 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> |
1222 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> |
| 1211 | |
1223 | |
| 1212 | =item $ev = $queue->enqueue_copy_image ($src_image, $dst_image, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
1224 | =item $ev = $queue->copy_image ($src_image, $dst_image, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
| 1213 | |
1225 | |
| 1214 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> |
1226 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> |
| 1215 | |
1227 | |
| 1216 | =item $ev = $queue->enqueue_copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...) |
1228 | =item $ev = $queue->copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...) |
| 1217 | |
1229 | |
| 1218 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html> |
1230 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html> |
| 1219 | |
1231 | |
| 1220 | =item $ev = $queue->enqueue_copy_buffer_rect ($src, $dst, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $src_row_pitch, $src_slice_pitch, $dst_row_pitch, $dst_slice_pitch, $wait_event...) |
1232 | =item $ev = $queue->copy_buffer_rect ($src, $dst, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $src_row_pitch, $src_slice_pitch, $dst_row_pitch, $dst_slice_pitch, $wait_event...) |
| 1221 | |
1233 | |
| 1222 | Yeah. |
1234 | Yeah. |
| 1223 | |
1235 | |
| 1224 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
1236 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
| 1225 | |
1237 | |
| 1226 | =item $ev = $queue->enqueue_fill_buffer ($mem, $pattern, $offset, $size, ...) |
1238 | =item $ev = $queue->fill_buffer ($mem, $pattern, $offset, $size, ...) |
| 1227 | |
1239 | |
| 1228 | Fills the given buffer object with repeated applications of C<$pattern>, |
1240 | Fills the given buffer object with repeated applications of C<$pattern>, |
| 1229 | starting at C<$offset> for C<$size> octets. |
1241 | starting at C<$offset> for C<$size> octets. |
| 1230 | |
1242 | |
| 1231 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html> |
1243 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html> |
| 1232 | |
1244 | |
| 1233 | =item $ev = $queue->enqueue_fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...) |
1245 | =item $ev = $queue->fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...) |
| 1234 | |
1246 | |
| 1235 | Fills the given image area with the given rgba colour components. The |
1247 | Fills the given image area with the given rgba colour components. The |
| 1236 | components are normally floating point values between C<0> and C<1>, |
1248 | components are normally floating point values between C<0> and C<1>, |
| 1237 | except when the image channel data type is a signe dor unsigned |
1249 | except when the image channel data type is a signe dor unsigned |
| 1238 | unnormalised format, in which case the range is determined by the format. |
1250 | unnormalised format, in which case the range is determined by the format. |
| 1239 | |
1251 | |
| 1240 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html> |
1252 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html> |
| 1241 | |
1253 | |
| 1242 | =item $ev = $queue->enqueue_task ($kernel, $wait_events...) |
1254 | =item $ev = $queue->task ($kernel, $wait_events...) |
| 1243 | |
1255 | |
| 1244 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
1256 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
| 1245 | |
1257 | |
| 1246 | =item $ev = $queue->enqueue_nd_range_kernel ($kernel, @$global_work_offset, @$global_work_size, @$local_work_size, $wait_events...) |
1258 | =item $ev = $queue->nd_range_kernel ($kernel, \@global_work_offset, \@global_work_size, \@local_work_size, $wait_events...) |
| 1247 | |
1259 | |
| 1248 | Enqueues a kernel execution. |
1260 | Enqueues a kernel execution. |
| 1249 | |
1261 | |
| 1250 | @$global_work_size must be specified as a reference to an array of |
1262 | \@global_work_size must be specified as a reference to an array of |
| 1251 | integers specifying the work sizes (element counts). |
1263 | integers specifying the work sizes (element counts). |
| 1252 | |
1264 | |
| 1253 | @$global_work_offset must be either C<undef> (in which case all offsets |
1265 | \@global_work_offset must be either C<undef> (in which case all offsets |
| 1254 | are C<0>), or a reference to an array of work offsets, with the same number |
1266 | are C<0>), or a reference to an array of work offsets, with the same number |
| 1255 | of elements as @$global_work_size. |
1267 | of elements as \@global_work_size. |
| 1256 | |
1268 | |
| 1257 | @$local_work_size must be either C<undef> (in which case the |
1269 | \@local_work_size must be either C<undef> (in which case the |
| 1258 | implementation is supposed to choose good local work sizes), or a |
1270 | implementation is supposed to choose good local work sizes), or a |
| 1259 | reference to an array of local work sizes, with the same number of |
1271 | reference to an array of local work sizes, with the same number of |
| 1260 | elements as @$global_work_size. |
1272 | elements as \@global_work_size. |
| 1261 | |
1273 | |
| 1262 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
1274 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
| 1263 | |
1275 | |
| 1264 | =item $ev = $queue->enqueue_acquire_gl_objects ([object, ...], $wait_events...) |
1276 | =item $ev = $queue->acquire_gl_objects ([object, ...], $wait_events...) |
| 1265 | |
1277 | |
| 1266 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired |
1278 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired |
| 1267 | for subsequent OpenCL usage. |
1279 | for subsequent OpenCL usage. |
| 1268 | |
1280 | |
| 1269 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html> |
1281 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html> |
| 1270 | |
1282 | |
| 1271 | =item $ev = $queue->enqueue_release_gl_objects ([object, ...], $wait_events...) |
1283 | =item $ev = $queue->release_gl_objects ([object, ...], $wait_events...) |
| 1272 | |
1284 | |
| 1273 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be released |
1285 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be released |
| 1274 | for subsequent OpenGL usage. |
1286 | for subsequent OpenGL usage. |
| 1275 | |
1287 | |
| 1276 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html> |
1288 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html> |
| 1277 | |
1289 | |
| 1278 | =item $ev = $queue->enqueue_wait_for_events ($wait_events...) |
1290 | =item $ev = $queue->wait_for_events ($wait_events...) |
| 1279 | |
1291 | |
| 1280 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
1292 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
| 1281 | |
1293 | |
| 1282 | =item $ev = $queue->enqueue_marker ($wait_events...) |
1294 | =item $ev = $queue->marker ($wait_events...) |
| 1283 | |
1295 | |
| 1284 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html> |
1296 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html> |
| 1285 | |
1297 | |
| 1286 | =item $ev = $queue->enqueue_barrier ($wait_events...) |
1298 | =item $ev = $queue->barrier ($wait_events...) |
| 1287 | |
1299 | |
| 1288 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html> |
1300 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html> |
| 1289 | |
1301 | |
| 1290 | =item $queue->flush |
1302 | =item $queue->flush |
| 1291 | |
1303 | |
| … | |
… | |
| 1520 | If a callback is specified, then it will be called when compilation is |
1532 | If a callback is specified, then it will be called when compilation is |
| 1521 | finished. Note that many OpenCL implementations block your program while |
1533 | finished. Note that many OpenCL implementations block your program while |
| 1522 | compiling whether you use a callback or not. See C<build_async> if you |
1534 | compiling whether you use a callback or not. See C<build_async> if you |
| 1523 | want to make sure the build is done in the background. |
1535 | want to make sure the build is done in the background. |
| 1524 | |
1536 | |
| 1525 | Note that some OpenCL implementations atc up badly, and don't call the |
1537 | Note that some OpenCL implementations act up badly, and don't call the |
| 1526 | callback in some error cases (but call it in others). This implementation |
1538 | callback in some error cases (but call it in others). This implementation |
| 1527 | assumes the callback will always be called, and leaks memory if this is |
1539 | assumes the callback will always be called, and leaks memory if this is |
| 1528 | not so. So best make sure you don't pass in invalid values. |
1540 | not so. So best make sure you don't pass in invalid values. |
| 1529 | |
1541 | |
|
|
1542 | Some implementations fail with C<OpenCL::INVALID_BINARY> when the |
|
|
1543 | compilation state is successful but some later stage fails. |
|
|
1544 | |
| 1530 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
1545 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
| 1531 | |
1546 | |
| 1532 | =item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef) |
1547 | =item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef) |
| 1533 | |
1548 | |
| 1534 | Similar to C<< ->build >>, except it starts a thread, and never fails (you |
1549 | Similar to C<< ->build >>, except it starts a thread, and never fails (you |
| … | |
… | |
| 1682 | |
1697 | |
| 1683 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result. |
1698 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result. |
| 1684 | |
1699 | |
| 1685 | =for gengetinfo end kernel_work_group |
1700 | =for gengetinfo end kernel_work_group |
| 1686 | |
1701 | |
|
|
1702 | =item $kernel->setf ($format, ...) |
|
|
1703 | |
|
|
1704 | Sets the arguments of a kernel. Since OpenCL 1.1 doesn't have a generic |
|
|
1705 | way to set arguments (and with OpenCL 1.2 it might be rather slow), you |
|
|
1706 | need to specify a format argument, much as with C<printf>, to tell OpenCL |
|
|
1707 | what type of argument it is. |
|
|
1708 | |
|
|
1709 | The format arguments are single letters: |
|
|
1710 | |
|
|
1711 | c char |
|
|
1712 | C unsigned char |
|
|
1713 | s short |
|
|
1714 | S unsigned short |
|
|
1715 | i int |
|
|
1716 | I unsigned int |
|
|
1717 | l long |
|
|
1718 | L unsigned long |
|
|
1719 | |
|
|
1720 | h half float (0..65535) |
|
|
1721 | f float |
|
|
1722 | d double |
|
|
1723 | |
|
|
1724 | z local (octet size) |
|
|
1725 | |
|
|
1726 | m memory object (buffer or image) |
|
|
1727 | a sampler |
|
|
1728 | e event |
|
|
1729 | |
|
|
1730 | Space characters in the format string are ignored. |
|
|
1731 | |
|
|
1732 | Example: set the arguments for a kernel that expects an int, two floats, a buffer and an image. |
|
|
1733 | |
|
|
1734 | $kernel->setf ("i ff mm", 5, 0.5, 3, $buffer, $image); |
|
|
1735 | |
| 1687 | =item $kernel->set_TYPE ($index, $value) |
1736 | =item $kernel->set_TYPE ($index, $value) |
| 1688 | |
1737 | |
|
|
1738 | =item $kernel->set_char ($index, $value) |
|
|
1739 | |
|
|
1740 | =item $kernel->set_uchar ($index, $value) |
|
|
1741 | |
|
|
1742 | =item $kernel->set_short ($index, $value) |
|
|
1743 | |
|
|
1744 | =item $kernel->set_ushort ($index, $value) |
|
|
1745 | |
|
|
1746 | =item $kernel->set_int ($index, $value) |
|
|
1747 | |
|
|
1748 | =item $kernel->set_uint ($index, $value) |
|
|
1749 | |
|
|
1750 | =item $kernel->set_long ($index, $value) |
|
|
1751 | |
|
|
1752 | =item $kernel->set_ulong ($index, $value) |
|
|
1753 | |
|
|
1754 | =item $kernel->set_half ($index, $value) |
|
|
1755 | |
|
|
1756 | =item $kernel->set_float ($index, $value) |
|
|
1757 | |
|
|
1758 | =item $kernel->set_double ($index, $value) |
|
|
1759 | |
|
|
1760 | =item $kernel->set_memory ($index, $value) |
|
|
1761 | |
|
|
1762 | =item $kernel->set_buffer ($index, $value) |
|
|
1763 | |
|
|
1764 | =item $kernel->set_image ($index, $value) |
|
|
1765 | |
|
|
1766 | =item $kernel->set_sampler ($index, $value) |
|
|
1767 | |
|
|
1768 | =item $kernel->set_local ($index, $value) |
|
|
1769 | |
|
|
1770 | =item $kernel->set_event ($index, $value) |
|
|
1771 | |
| 1689 | This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>. |
1772 | This is a family of methods to set the kernel argument with the number |
| 1690 | |
1773 | C<$index> to the give C<$value>. |
| 1691 | TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>, |
|
|
| 1692 | C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>, |
|
|
| 1693 | C<image2d>, C<image3d>, C<sampler>, C<local> or C<event>. |
|
|
| 1694 | |
1774 | |
| 1695 | Chars and integers (including the half type) are specified as integers, |
1775 | Chars and integers (including the half type) are specified as integers, |
| 1696 | float and double as floating point values, memory/buffer/image2d/image3d |
1776 | float and double as floating point values, memory/buffer/image must be |
| 1697 | must be an object of that type or C<undef>, local-memory arguments are |
1777 | an object of that type or C<undef>, local-memory arguments are set by |
| 1698 | set by specifying the size, and sampler and event must be objects of that |
1778 | specifying the size, and sampler and event must be objects of that type. |
| 1699 | type. |
1779 | |
|
|
1780 | Note that C<set_memory> works for all memory objects (all types of buffers |
|
|
1781 | and images) - the main purpose of the more specific C<set_TYPE> functions |
|
|
1782 | is type checking. |
| 1700 | |
1783 | |
| 1701 | Setting an argument for a kernel does NOT keep a reference to the object - |
1784 | Setting an argument for a kernel does NOT keep a reference to the object - |
| 1702 | for example, if you set an argument to some image object, free the image, |
1785 | for example, if you set an argument to some image object, free the image, |
| 1703 | and call the kernel, you will run into undefined behaviour. |
1786 | and call the kernel, you will run into undefined behaviour. |
| 1704 | |
1787 | |
