ViewVC Help
View File | Revision Log | Show Annotations | Download File
/cvs/OpenCL/OpenCL.pm
(Generate patch)

Comparing OpenCL/OpenCL.pm (file contents):
Revision 1.14 by root, Thu Nov 17 03:02:25 2011 UTC vs.
Revision 1.80 by root, Sat May 5 13:55:59 2012 UTC

27OpenCL::Program objects, which store source code and, after building for a 27OpenCL::Program objects, which store source code and, after building for a
28specific device ("compiling and linking"), also binary programs. For each 28specific device ("compiling and linking"), also binary programs. For each
29kernel function in a program you can then create an OpenCL::Kernel object 29kernel function in a program you can then create an OpenCL::Kernel object
30which represents basically a function call with argument values. 30which represents basically a function call with argument values.
31 31
32OpenCL::Memory objects of various flavours: OpenCL::Buffers objects (flat 32OpenCL::Memory objects of various flavours: OpenCL::Buffer objects (flat
33memory areas, think array) and OpenCL::Image objects (think 2d or 3d 33memory areas, think arrays or structs) and OpenCL::Image objects (think 2D
34array) for bulk data and input and output for kernels. 34or 3D array) for bulk data and input and output for kernels.
35 35
36OpenCL::Sampler objects, which are kind of like texture filter modes in 36OpenCL::Sampler objects, which are kind of like texture filter modes in
37OpenGL. 37OpenGL.
38 38
39OpenCL::Queue objects - command queues, which allow you to submit memory 39OpenCL::Queue objects - command queues, which allow you to submit memory
43 43
44OpenCL::Event objects are used to signal when something is complete. 44OpenCL::Event objects are used to signal when something is complete.
45 45
46=head2 HELPFUL RESOURCES 46=head2 HELPFUL RESOURCES
47 47
48The OpenCL spec used to develop this module (1.2 spec was available, but 48The OpenCL specs used to develop this module - download these and keept
49no implementation was available to me :). 49hema round, they are required reference material:
50 50
51 http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf 51 http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf
52 http://www.khronos.org/registry/cl/specs/opencl-1.2.pdf
53 http://www.khronos.org/registry/cl/specs/opencl-1.2-extensions.pdf
52 54
53OpenCL manpages: 55OpenCL manpages:
54 56
55 http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/ 57 http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/
58 http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/
59
60If you are into UML class diagrams, the following diagram might help - if
61not, it will be mildly confusing (also, the class hierarchy of this module
62is much more fine-grained):
63
64 http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/classDiagram.html
65
66Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it
67is, but at least it's free of charge:
68
69 http://developer.amd.com/zones/OpenCLZone/courses/Documents/Introduction_to_OpenCL_Programming%20Training_Guide%20%28201005%29.pdf
70
71And here's NVIDIA's OpenCL Best Practises Guide:
72
73 http://developer.download.nvidia.com/compute/cuda/3_2/toolkit/docs/OpenCL_Best_Practices_Guide.pdf
56 74
57=head1 BASIC WORKFLOW 75=head1 BASIC WORKFLOW
58 76
59To get something done, you basically have to do this once (refer to the 77To get something done, you basically have to do this once (refer to the
60examples below for actual code, this is just a high-level description): 78examples below for actual code, this is just a high-level description):
87 105
88Best run this once to get a feel for the platforms and devices in your 106Best run this once to get a feel for the platforms and devices in your
89system. 107system.
90 108
91 for my $platform (OpenCL::platforms) { 109 for my $platform (OpenCL::platforms) {
92 printf "platform: %s\n", $platform->info (OpenCL::PLATFORM_NAME); 110 printf "platform: %s\n", $platform->name;
93 printf "extensions: %s\n", $platform->info (OpenCL::PLATFORM_EXTENSIONS); 111 printf "extensions: %s\n", $platform->extensions;
94 for my $device ($platform->devices) { 112 for my $device ($platform->devices) {
95 printf "+ device: %s\n", $device->info (OpenCL::DEVICE_NAME); 113 printf "+ device: %s\n", $device->name;
96 my $ctx = $device->context; 114 my $ctx = $platform->context (undef, [$device]);
97 # do stuff 115 # do stuff
98 } 116 }
99 } 117 }
100 118
101=head2 Get a useful context and a command queue. 119=head2 Get a useful context and a command queue.
124=head2 Create a buffer with some predefined data, read it back synchronously, 142=head2 Create a buffer with some predefined data, read it back synchronously,
125then asynchronously. 143then asynchronously.
126 144
127 my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); 145 my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut");
128 146
129 $queue->enqueue_read_buffer ($buf, 1, 1, 3, my $data); 147 $queue->read_buffer ($buf, 1, 1, 3, my $data);
130 print "$data\n"; 148 print "$data\n";
131 149
132 my $ev = $queue->enqueue_read_buffer ($buf, 0, 1, 3, my $data); 150 my $ev = $queue->read_buffer ($buf, 0, 1, 3, my $data);
133 $ev->wait; 151 $ev->wait;
134 print "$data\n"; # prints "elm" 152 print "$data\n"; # prints "elm"
135 153
136=head2 Create and build a program, then create a kernel out of one of its 154=head2 Create and build a program, then create a kernel out of one of its
137functions. 155functions.
138 156
139 my $src = ' 157 my $src = '
140 __kernel void 158 kernel void
141 squareit (__global float *input, __global float *output) 159 squareit (global float *input, global float *output)
142 { 160 {
143 size_t id = get_global_id (0); 161 $id = get_global_id (0);
144 output [id] = input [id] * input [id]; 162 output [id] = input [id] * input [id];
145 } 163 }
146 '; 164 ';
147 165
148 my $prog = $ctx->program_with_source ($src); 166 my $prog = $ctx->build_program ($src);
149
150 # build croaks on compile errors, so catch it and print the compile errors
151 eval { $prog->build ($dev); 1 }
152 or die $prog->build_info ($dev, OpenCL::PROGRAM_BUILD_LOG);
153
154 my $kernel = $prog->kernel ("squareit"); 167 my $kernel = $prog->kernel ("squareit");
155 168
156=head2 Create some input and output float buffers, then call the 169=head2 Create some input and output float buffers, then call the
157'squareit' kernel on them. 170'squareit' kernel on them.
158 171
162 # set buffer 175 # set buffer
163 $kernel->set_buffer (0, $input); 176 $kernel->set_buffer (0, $input);
164 $kernel->set_buffer (1, $output); 177 $kernel->set_buffer (1, $output);
165 178
166 # execute it for all 4 numbers 179 # execute it for all 4 numbers
167 $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); 180 $queue->nd_range_kernel ($kernel, undef, [4], undef);
168 181
169 # enqueue a synchronous read 182 # enqueue a synchronous read
170 $queue->enqueue_read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); 183 $queue->read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data);
171 184
172 # print the results: 185 # print the results:
173 printf "%s\n", join ", ", unpack "f*", $data; 186 printf "%s\n", join ", ", unpack "f*", $data;
174 187
175=head2 The same enqueue operations as before, but assuming an out-of-order queue, 188=head2 The same enqueue operations as before, but assuming an out-of-order queue,
176showing off barriers. 189showing off barriers.
177 190
178 # execute it for all 4 numbers 191 # execute it for all 4 numbers
179 $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); 192 $queue->nd_range_kernel ($kernel, undef, [4], undef);
180 193
181 # enqueue a barrier to ensure in-order execution 194 # enqueue a barrier to ensure in-order execution
182 $queue->enqueue_barrier; 195 $queue->barrier;
183 196
184 # enqueue an async read 197 # enqueue an async read
185 $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); 198 $queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data);
186 199
187 # wait for all requests to finish 200 # wait for all requests to finish
188 $queue->finish; 201 $queue->finish;
189 202
190=head2 The same enqueue operations as before, but assuming an out-of-order queue, 203=head2 The same enqueue operations as before, but assuming an out-of-order queue,
191showing off event objects and wait lists. 204showing off event objects and wait lists.
192 205
193 # execute it for all 4 numbers 206 # execute it for all 4 numbers
194 my $ev = $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); 207 my $ev = $queue->nd_range_kernel ($kernel, undef, [4], undef);
195 208
196 # enqueue an async read 209 # enqueue an async read
197 $ev = $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev); 210 $ev = $queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev);
198 211
199 # wait for the last event to complete 212 # wait for the last event to complete
200 $ev->wait; 213 $ev->wait;
214
215=head2 Use the OpenGL module to share a texture between OpenCL and OpenGL and draw some julia
216set flight effect.
217
218This is quite a long example to get you going - you can download it from
219L<http://cvs.schmorp.de/OpenCL/examples/juliaflight>.
220
221 use OpenGL ":all";
222 use OpenCL;
223
224 my $S = $ARGV[0] || 256; # window/texture size, smaller is faster
225
226 # open a window and create a gl texture
227 OpenGL::glpOpenWindow width => $S, height => $S;
228 my $texid = glGenTextures_p 1;
229 glBindTexture GL_TEXTURE_2D, $texid;
230 glTexImage2D_c GL_TEXTURE_2D, 0, GL_RGBA8, $S, $S, 0, GL_RGBA, GL_UNSIGNED_BYTE, 0;
231
232 # find and use the first opencl device that let's us get a shared opengl context
233 my $platform;
234 my $dev;
235 my $ctx;
236
237 for (OpenCL::platforms) {
238 $platform = $_;
239 for ($platform->devices) {
240 $dev = $_;
241 $ctx = $platform->context ([OpenCL::GLX_DISPLAY_KHR, undef, OpenCL::GL_CONTEXT_KHR, undef], [$dev])
242 and last;
243 }
244 }
245
246 $ctx
247 or die "cannot find suitable OpenCL device\n";
248
249 my $queue = $ctx->queue ($dev);
250
251 # now attach an opencl image2d object to the opengl texture
252 my $tex = $ctx->gl_texture2d (OpenCL::MEM_WRITE_ONLY, GL_TEXTURE_2D, 0, $texid);
253
254 # now the boring opencl code
255 my $src = <<EOF;
256 kernel void
257 juliatunnel (write_only image2d_t img, float time)
258 {
259 int2 xy = (int2)(get_global_id (0), get_global_id (1));
260 float2 p = convert_float2 (xy) / $S.f * 2.f - 1.f;
261
262 float2 m = (float2)(1.f, p.y) / fabs (p.x); // tunnel
263 m.x = fabs (fmod (m.x + time * 0.05f, 4.f) - 2.f);
264
265 float2 z = m;
266 float2 c = (float2)(sin (time * 0.01133f), cos (time * 0.02521f));
267
268 for (int i = 0; i < 25 && dot (z, z) < 4.f; ++i) // standard julia
269 z = (float2)(z.x * z.x - z.y * z.y, 2.f * z.x * z.y) + c;
270
271 float3 colour = (float3)(z.x, z.y, atan2 (z.y, z.x));
272 write_imagef (img, xy, (float4)(colour * p.x * p.x, 1.));
273 }
274 EOF
275
276 my $prog = $ctx->build_program ($src);
277 my $kernel = $prog->kernel ("juliatunnel");
278
279 # program compiled, kernel ready, now draw and loop
280
281 for (my $time; ; ++$time) {
282 # acquire objects from opengl
283 $queue->acquire_gl_objects ([$tex]);
284
285 # configure and run our kernel
286 $kernel->setf ("mf", $tex, $time*2); # mf = memory object, float
287 $queue->nd_range_kernel ($kernel, undef, [$S, $S], undef);
288
289 # release objects to opengl again
290 $queue->release_gl_objects ([$tex]);
291
292 # wait
293 $queue->finish;
294
295 # now draw the texture, the defaults should be all right
296 glTexParameterf GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST;
297
298 glEnable GL_TEXTURE_2D;
299 glBegin GL_QUADS;
300 glTexCoord2f 0, 1; glVertex3i -1, -1, -1;
301 glTexCoord2f 0, 0; glVertex3i 1, -1, -1;
302 glTexCoord2f 1, 0; glVertex3i 1, 1, -1;
303 glTexCoord2f 1, 1; glVertex3i -1, 1, -1;
304 glEnd;
305
306 glXSwapBuffers;
307
308 select undef, undef, undef, 1/60;
309 }
310
311=head2 How to modify the previous example to not rely on GL sharing.
312
313For those poor souls with only a sucky CPU OpenCL implementation, you
314currently have to read the image into some perl scalar, and then modify a
315texture or use glDrawPixels or so).
316
317First, when you don't need gl sharing, you can create the context much simpler:
318
319 $ctx = $platform->context (undef, [$dev])
320
321To use a texture, you would modify the above example by creating an
322OpenCL::Image manually instead of deriving it from a texture:
323
324 my $tex = $ctx->image2d (OpenCL::MEM_WRITE_ONLY, OpenCL::RGBA, OpenCL::UNORM_INT8, $S, $S);
325
326And in the draw loop, intead of acquire_gl_objects/release_gl_objects, you
327would read the image2d after the kernel has written it:
328
329 $queue->read_image ($tex, 0, 0, 0, 0, $S, $S, 1, 0, 0, my $data);
330
331And then you would upload the pixel data to the texture (or use glDrawPixels):
332
333 glTexSubImage2D_s GL_TEXTURE_2D, 0, 0, 0, $S, $S, GL_RGBA, GL_UNSIGNED_BYTE, $data;
334
335The fully modified example can be found at
336L<http://cvs.schmorp.de/OpenCL/examples/juliaflight-nosharing>.
337
338=head2 Julia sets look soooo 80ies.
339
340Then colour them differently, e.g. using orbit traps! Replace the loop and
341colour calculation from the previous examples by this:
342
343 float2 dm = (float2)(1.f, 1.f);
344
345 for (int i = 0; i < 25; ++i)
346 {
347 z = (float2)(z.x * z.x - z.y * z.y, 2.f * z.x * z.y) + c;
348 dm = fmin (dm, (float2)(fabs (dot (z, z) - 1.f), fabs (z.x - 1.f)));
349 }
350
351 float3 colour = (float3)(dm.x * dm.y, dm.x * dm.y, dm.x);
352
353Also try C<-10.f> instead of C<-1.f>.
201 354
202=head1 DOCUMENTATION 355=head1 DOCUMENTATION
203 356
204=head2 BASIC CONVENTIONS 357=head2 BASIC CONVENTIONS
205 358
212 365
213=item * Object lifetime managament is automatic - there is no need 366=item * Object lifetime managament is automatic - there is no need
214to free objects explicitly (C<clReleaseXXX>), the release function 367to free objects explicitly (C<clReleaseXXX>), the release function
215is called automatically once all Perl references to it go away. 368is called automatically once all Perl references to it go away.
216 369
217=item * OpenCL uses CamelCase for function names (C<clGetPlatformInfo>), 370=item * OpenCL uses CamelCase for function names
371(e.g. C<clGetPlatformIDs>, C<clGetPlatformInfo>), while this module
218while this module uses underscores as word separator and often leaves out 372uses underscores as word separator and often leaves out prefixes
219prefixes (C<< $platform->info >>). 373(C<OpenCL::platforms>, C<< $platform->info >>).
220 374
221=item * OpenCL often specifies fixed vector function arguments as short 375=item * OpenCL often specifies fixed vector function arguments as short
222arrays (C<size_t origin[3]>), while this module explicitly expects the 376arrays (C<size_t origin[3]>), while this module explicitly expects the
223components as separate arguments- 377components as separate arguments (C<$orig_x, $orig_y, $orig_z>) in
378function calls.
224 379
225=item * Structures are often specified with their components, and returned 380=item * Structures are often specified by flattening out their components
226as arrayrefs. 381as with short vectors, and returned as arrayrefs.
227
228=item * Where possible, one of the pitch values is calculated from the
229perl scalar length and need not be specified.
230 382
231=item * When enqueuing commands, the wait list is specified by adding 383=item * When enqueuing commands, the wait list is specified by adding
232extra arguments to the function - anywhere a C<$wait_events...> argument 384extra arguments to the function - anywhere a C<$wait_events...> argument
233is documented this can be any number of event objects. 385is documented this can be any number of event objects. As an extsnion
386implemented by this module, C<undef> values will be ignored in the event
387list.
234 388
235=item * When enqueuing commands, if the enqueue method is called in void 389=item * When enqueuing commands, if the enqueue method is called in void
236context, no event is created. In all other contexts an event is returned 390context, no event is created. In all other contexts an event is returned
237by the method. 391by the method.
238 392
239=item * This module expects all functions to return C<CL_SUCCESS>. If any 393=item * This module expects all functions to return C<OpenCL::SUCCESS>. If any
240other status is returned the function will throw an exception, so you 394other status is returned the function will throw an exception, so you
241don't normally have to to any error checking. 395don't normally have to to any error checking.
242 396
243=back 397=back
398
399=head2 CONSTANTS
400
401All C<CL_xxx> constants that this module supports are always available
402in the C<OpenCL> namespace as C<OpenCL::xxx> (i.e. without the C<CL_>
403prefix). Constants which are not defined in the heaer files used during
404compilation, or otherwise are not available, will have the value C<-1>.
405
406=head2 OPENCL 1.1 VS. OPENCL 1.2
407
408This module supports both OpenCL version 1.1 and 1.2, although the OpenCL
4091.2 interface hasn't been tested much for lack of availability of an
410actual implementation.
411
412Every function or method in this manual page that interfaces to a
413particular OpenCL function has a link to the its C manual page.
414
415If the link contains a F<1.1>, then this function is an OpenCL 1.1
416function. Most but not all also exist in OpenCL 1.2, and this module
417tries to emulate the missing ones for you, when told to do so at
418compiletime. You cna check whether a function was removed in OpenCL 1.2 by
419replacing the F<1.1> component in the URL by F<1.2>.
420
421If the link contains a F<1.2>, then this is a OpenCL 1.2-only
422function. Even if the module was compiled with OpenCL 1.2 header files
423and has an 1.2 OpenCL library, calling such a function on a platform that
424doesn't implement 1.2 causes undefined behaviour, usually a crash (But
425this is not guaranteed).
426
427You can find out whether this module was compiled to prefer 1.1
428functionality by ooking at C<OpenCL::PREFER_1_1> - if it is true, then
4291.1 functions generally are implemented using 1.1 OpenCL functions. If it
430is false, then 1.1 functions missing from 1.2 are emulated by calling 1.2
431fucntions.
432
433This is a somewhat sorry state of affairs, but the Khronos group choose to
434make every release of OpenCL source and binary incompatible with previous
435releases.
244 436
245=head2 PERL AND OPENCL TYPES 437=head2 PERL AND OPENCL TYPES
246 438
247This handy(?) table lists OpenCL types and their perl, PDL and pack/unpack 439This handy(?) table lists OpenCL types and their perl, PDL and pack/unpack
248format equivalents: 440format equivalents:
258 ulong IV - Q 450 ulong IV - Q
259 float NV float f 451 float NV float f
260 half IV ushort S 452 half IV ushort S
261 double NV double d 453 double NV double d
262 454
455=head2 GLX SUPPORT
456
457Due to the sad state that OpenGL support is in in Perl (mostly the OpenGL
458module, which has little to no documentation and has little to no support
459for glX), this module, as a special extension, treats context creation
460properties C<OpenCL::GLX_DISPLAY_KHR> and C<OpenCL::GL_CONTEXT_KHR>
461specially: If either or both of these are C<undef>, then the OpenCL
462module tries to dynamically resolve C<glXGetCurrentDisplay> and
463C<glXGetCurrentContext>, call these functions and use their return values
464instead.
465
466For this to work, the OpenGL library must be loaded, a GLX context must
467have been created and be made current, and C<dlsym> must be available and
468capable of finding the function via C<RTLD_DEFAULT>.
469
470=head2 EVENT SYSTEM
471
472OpenCL can generate a number of (potentially) asynchronous events, for
473example, after compiling a program, to signal a context-related error or,
474perhaps most important, to signal completion of queued jobs (by setting
475callbacks on OpenCL::Event objects).
476
477The OpenCL module converts all these callbacks into events - you can
478still register callbacks, but they are not executed when your OpenCL
479implementation calls the actual callback, but only later. Therefore, none
480of the limitations of OpenCL callbacks apply to the perl implementation:
481it is perfectly safe to make blocking operations from event callbacks, and
482enqueued operations don't need to be flushed.
483
484To facilitate this, this module maintains an event queue - each
485time an asynchronous event happens, it is queued, and perl will be
486interrupted. This is implemented via the L<Async::Interrupt> module. In
487addition, this module has L<AnyEvent> support, so it can seamlessly
488integrate itself into many event loops.
489
490Since L<Async::Interrupt> is a bit hard to understand, here are some case examples:
491
492=head3 Don't use callbacks.
493
494When your program never uses any callbacks, then there will never be any
495notifications you need to take care of, and therefore no need to worry
496about all this.
497
498You can achieve a great deal by explicitly waiting for events, or using
499barriers and flush calls. In many programs, there is no need at all to
500tinker with asynchronous events.
501
502=head3 Use AnyEvent
503
504This module automatically registers a watcher that invokes all outstanding
505event callbacks when AnyEvent is initialised (and block asynchronous
506interruptions). Using this mode of operations is the safest and most
507recommended one.
508
509To use this, simply use AnyEvent and this module normally, make sure you
510have an event loop running:
511
512 use Gtk2 -init;
513 use AnyEvent;
514
515 # initialise AnyEvent, by creating a watcher, or:
516 AnyEvent::detect;
517
518 my $e = $queue->marker;
519 $e->cb (sub {
520 warn "opencl is finished\n";
521 })
522
523 main Gtk2;
524
525Note that this module will not initialise AnyEvent for you. Before
526AnyEvent is initialised, the module will asynchronously interrupt perl
527instead. To avoid any surprises, it's best to explicitly initialise
528AnyEvent.
529
530You can temporarily enable asynchronous interruptions (see next paragraph)
531by calling C<$OpenCL::INTERRUPT->unblock> and disable them again by
532calling C<$OpenCL::INTERRUPT->block>.
533
534=head3 Let yourself be interrupted at any time
535
536This mode is the default unless AnyEvent is loaded and initialised. In
537this mode, OpenCL asynchronously interrupts a running perl program. The
538emphasis is on both I<asynchronously> and I<running> here.
539
540Asynchronously means that perl might execute your callbacks at any
541time. For example, in the following code (I<THAT YOU SHOULD NOT COPY>),
542the C<until> loop following the marker call will be interrupted by the
543callback:
544
545 my $e = $queue->marker;
546 my $flag;
547 $e->cb (sub { $flag = 1 });
548 1 until $flag;
549 # $flag is now 1
550
551The reason why you shouldn't blindly copy the above code is that
552busy waiting is a really really bad thing, and really really bad for
553performance.
554
555While at first this asynchronous business might look exciting, it can be
556really hard, because you need to be prepared for the callback code to be
557executed at any time, which limits the amount of things the callback code
558can do safely.
559
560This can be mitigated somewhat by using C<<
561$OpenCL::INTERRUPT->scope_block >> (see the L<Async::Interrupt>
562documentation for details).
563
564The other problem is that your program must be actively I<running> to be
565interrupted. When you calculate stuff, your program is running. When you
566hang in some C functions or other block execution (by calling C<sleep>,
567C<select>, running an event loop and so on), your program is waiting, not
568running.
569
570One way around that would be to attach a read watcher to your event loop,
571listening for events on C<< $OpenCL::INTERRUPT->pipe_fileno >>, using a
572dummy callback (C<sub { }>) to temporarily execute some perl code.
573
574That is then awfully close to using the built-in AnyEvent support above,
575though, so consider that one instead.
576
577=head3 Be creative
578
579OpenCL exports the L<Async::Interrupt> object it uses in the global
580variable C<$OpenCL::INTERRUPT>. You can configure it in any way you like.
581
582So if you want to feel like a real pro, err, wait, if you feel no risk
583menas no fun, you can experiment by implementing your own mode of
584operations.
585
586=cut
587
588package OpenCL;
589
590use common::sense;
591use Carp ();
592use Async::Interrupt ();
593
594our $POLL_FUNC; # set by XS
595
596BEGIN {
597 our $VERSION = '0.99';
598
599 require XSLoader;
600 XSLoader::load (__PACKAGE__, $VERSION);
601
602 @OpenCL::Platform::ISA =
603 @OpenCL::Device::ISA =
604 @OpenCL::Context::ISA =
605 @OpenCL::Queue::ISA =
606 @OpenCL::Memory::ISA =
607 @OpenCL::Sampler::ISA =
608 @OpenCL::Program::ISA =
609 @OpenCL::Kernel::ISA =
610 @OpenCL::Event::ISA = OpenCL::Object::;
611
612 @OpenCL::SubDevice::ISA = OpenCL::Device::;
613
614 @OpenCL::Buffer::ISA =
615 @OpenCL::Image::ISA = OpenCL::Memory::;
616
617 @OpenCL::BufferObj::ISA = OpenCL::Buffer::;
618
619 @OpenCL::Image2D::ISA =
620 @OpenCL::Image3D::ISA =
621 @OpenCL::Image2DArray::ISA =
622 @OpenCL::Image1D::ISA =
623 @OpenCL::Image1DArray::ISA =
624 @OpenCL::Image1DBuffer::ISA = OpenCL::Image::;
625
626 @OpenCL::UserEvent::ISA = OpenCL::Event::;
627
628 @OpenCL::MappedBuffer::ISA =
629 @OpenCL::MappedImage::ISA = OpenCL::Mapped::;
630}
631
263=head2 THE OpenCL PACKAGE 632=head2 THE OpenCL PACKAGE
264 633
265=over 4 634=over 4
266 635
267=item $int = OpenCL::errno 636=item $int = OpenCL::errno
268 637
269The last error returned by a function - it's only valid after an error occured 638The last error returned by a function - it's only valid after an error occured
270and before calling another OpenCL function. 639and before calling another OpenCL function.
271 640
272=item $str = OpenCL::err2str $errval 641=item $str = OpenCL::err2str [$errval]
273 642
274Comverts an error value into a human readable string. 643Converts an error value into a human readable string. IF no error value is
644given, then the last error will be used (as returned by OpenCL::errno).
275 645
276=item $str = OpenCL::enum2str $enum 646=item $str = OpenCL::enum2str $enum
277 647
278Converts most enum values (inof parameter names, image format constants, 648Converts most enum values (of parameter names, image format constants,
279object types, addressing and filter modes, command types etc.) into a 649object types, addressing and filter modes, command types etc.) into a
280human readbale string. When confronted with some random integer it can be 650human readable string. When confronted with some random integer it can be
281very helpful to pass it through this function to maybe get some readable 651very helpful to pass it through this function to maybe get some readable
282string out of it. 652string out of it.
283 653
284=item @platforms = OpenCL::platforms 654=item @platforms = OpenCL::platforms
285 655
286Returns all available OpenCL::Platform objects. 656Returns all available OpenCL::Platform objects.
287 657
288L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html> 658L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html>
289 659
290=item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef 660=item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr
291 661
292Tries to create a context from a default device and platform - never worked for me. 662Tries to create a context from a default device and platform type - never worked for me.
663Consider using C<< $platform->context_from_type >> instead.
664
665type: OpenCL::DEVICE_TYPE_DEFAULT, OpenCL::DEVICE_TYPE_CPU, OpenCL::DEVICE_TYPE_GPU,
666OpenCL::DEVICE_TYPE_ACCELERATOR, OpenCL::DEVICE_TYPE_CUSTOM, OpenCL::DEVICE_TYPE_ALL.
293 667
294L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> 668L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>
295 669
670=item $ctx = OpenCL::context $properties, \@devices, $callback->($err, $pvt) = $print_stderr)
671
672Create a new OpenCL::Context object using the given device object(s).
673Consider using C<< $platform->context >> instead.
674
675L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>
676
296=item OpenCL::wait_for_events $wait_events... 677=item OpenCL::wait_for_events $wait_events...
297 678
298Waits for all events to complete. 679Waits for all events to complete.
299 680
300L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> 681L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>
301 682
683=item OpenCL::poll
684
685Checks if there are any outstanding events (see L<EVENT SYSTEM>) and
686invokes their callbacks.
687
688=item $OpenCL::INTERRUPT
689
690The L<Async::Interrupt> object used to signal asynchronous events (see
691L<EVENT SYSTEM>).
692
693=cut
694
695our $INTERRUPT = new Async::Interrupt c_cb => [$POLL_FUNC, 0];
696
697&_eq_initialise ($INTERRUPT->signal_func);
698
699=item $OpenCL::WATCHER
700
701The L<AnyEvent> watcher object used to watch for asynchronous events (see
702L<EVENT SYSTEM>). This variable is C<undef> until L<AnyEvent> has been
703loaded I<and> initialised (e.g. by calling C<AnyEvent::detect>).
704
705=cut
706
707our $WATCHER;
708
709sub _init_anyevent {
710 $INTERRUPT->block;
711 $WATCHER = AE::io ($INTERRUPT->pipe_fileno, 0, sub { $INTERRUPT->handle });
712}
713
714if (defined $AnyEvent::MODEL) {
715 _init_anyevent;
716} else {
717 push @AnyEvent::post_detect, \&_init_anyevent;
718}
719
302=back 720=back
303 721
722=head2 THE OpenCL::Object CLASS
723
724This is the base class for all objects in the OpenCL module. The only
725method it implements is the C<id> method, which is only useful if you want
726to interface to OpenCL on the C level.
727
728=over 4
729
730=item $iv = $obj->id
731
732OpenCL objects are represented by pointers or integers on the C level. If
733you want to interface to an OpenCL object directly on the C level, then
734you need this value, which is returned by this method. You should use an
735C<IV> type in your code and cast that to the correct type.
736
737=cut
738
739sub OpenCL::Object::id {
740 ref $_[0] eq "SCALAR"
741 ? ${ $_[0] }
742 : $_[0][0]
743}
744
745=back
746
304=head2 THE OpenCL::Platform CLASS 747=head2 THE OpenCL::Platform CLASS
305 748
306=over 4 749=over 4
307 750
751=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL)
752
753Returns a list of matching OpenCL::Device objects.
754
755=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr)
756
757Tries to create a context. Never worked for me, and you need devices explicitly anyway.
758
759L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>
760
761=item $ctx = $platform->context ($properties, \@devices, $callback->($err, $pvt) = $print_stderr)
762
763Create a new OpenCL::Context object using the given device object(s)- a
764OpenCL::CONTEXT_PLATFORM property is supplied automatically.
765
766L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>
767
308=item $packed_value = $platform->info ($name) 768=item $packed_value = $platform->info ($name)
309 769
310Calls C<clGetPlatformInfo> and returns the packed, raw value - for 770Calls C<clGetPlatformInfo> and returns the packed, raw value - for
311strings, this will be the string, for other values you probably need to 771strings, this will be the string (possibly including terminating \0), for
312use the correct C<unpack>. This might get improved in the future. Hopefully. 772other values you probably need to use the correct C<unpack>.
773
774It's best to avoid this method and use one of the following convenience
775wrappers.
313 776
314L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html> 777L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html>
315 778
316=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL) 779=item $platform->unload_compiler
317 780
318Returns a list of matching OpenCL::Device objects. 781Attempts to unload the compiler for this platform, for endless
782profit. Does nothing on OpenCL 1.1.
319 783
320=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef)
321
322Tries to create a context. Never worked for me, and you need devices explitly anyway.
323
324L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>
325
326=item $ctx = $device->context ($properties = undef, @$devices, $notify = undef)
327
328Create a new OpenCL::Context object using the given device object(s)- a
329CL_CONTEXT_PLATFORM property is supplied automatically.
330
331L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> 784L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clUnloadPlatformCompiler.html>
785
786=for gengetinfo begin platform
787
788=item $string = $platform->profile
789
790Calls C<clGetPlatformInfo> with C<OpenCL::PLATFORM_PROFILE> and returns the result.
791
792=item $string = $platform->version
793
794Calls C<clGetPlatformInfo> with C<OpenCL::PLATFORM_VERSION> and returns the result.
795
796=item $string = $platform->name
797
798Calls C<clGetPlatformInfo> with C<OpenCL::PLATFORM_NAME> and returns the result.
799
800=item $string = $platform->vendor
801
802Calls C<clGetPlatformInfo> with C<OpenCL::PLATFORM_VENDOR> and returns the result.
803
804=item $string = $platform->extensions
805
806Calls C<clGetPlatformInfo> with C<OpenCL::PLATFORM_EXTENSIONS> and returns the result.
807
808=for gengetinfo end platform
332 809
333=back 810=back
334 811
335=head2 THE OpenCL::Device CLASS 812=head2 THE OpenCL::Device CLASS
336 813
338 815
339=item $packed_value = $device->info ($name) 816=item $packed_value = $device->info ($name)
340 817
341See C<< $platform->info >> for details. 818See C<< $platform->info >> for details.
342 819
820type: OpenCL::DEVICE_TYPE_DEFAULT, OpenCL::DEVICE_TYPE_CPU,
821OpenCL::DEVICE_TYPE_GPU, OpenCL::DEVICE_TYPE_ACCELERATOR,
822OpenCL::DEVICE_TYPE_CUSTOM, OpenCL::DEVICE_TYPE_ALL.
823
824fp_config: OpenCL::FP_DENORM, OpenCL::FP_INF_NAN, OpenCL::FP_ROUND_TO_NEAREST,
825OpenCL::FP_ROUND_TO_ZERO, OpenCL::FP_ROUND_TO_INF, OpenCL::FP_FMA,
826OpenCL::FP_SOFT_FLOAT, OpenCL::FP_CORRECTLY_ROUNDED_DIVIDE_SQRT.
827
828mem_cache_type: OpenCL::NONE, OpenCL::READ_ONLY_CACHE, OpenCL::READ_WRITE_CACHE.
829
830local_mem_type: OpenCL::LOCAL, OpenCL::GLOBAL.
831
832exec_capabilities: OpenCL::EXEC_KERNEL, OpenCL::EXEC_NATIVE_KERNEL.
833
834command_queue_properties: OpenCL::QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE,
835OpenCL::QUEUE_PROFILING_ENABLE.
836
837partition_properties: OpenCL::DEVICE_PARTITION_EQUALLY,
838OpenCL::DEVICE_PARTITION_BY_COUNTS, OpenCL::DEVICE_PARTITION_BY_COUNTS_LIST_END,
839OpenCL::DEVICE_PARTITION_BY_AFFINITY_DOMAIN.
840
841affinity_domain: OpenCL::DEVICE_AFFINITY_DOMAIN_NUMA,
842OpenCL::DEVICE_AFFINITY_DOMAIN_L4_CACHE, OpenCL::DEVICE_AFFINITY_DOMAIN_L3_CACHE,
843OpenCL::DEVICE_AFFINITY_DOMAIN_L2_CACHE, OpenCL::DEVICE_AFFINITY_DOMAIN_L1_CACHE,
844OpenCL::DEVICE_AFFINITY_DOMAIN_NEXT_PARTITIONABLE.
845
343L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetDeviceInfo.html> 846L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetDeviceInfo.html>
344 847
848=item @devices = $device->sub_devices (\@properties)
849
850Creates OpencL::SubDevice objects by partitioning an existing device.
851
852L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateSubDevices.html>
853
854=for gengetinfo begin device
855
856=item $device_type = $device->type
857
858Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_TYPE> and returns the result.
859
860=item $uint = $device->vendor_id
861
862Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_VENDOR_ID> and returns the result.
863
864=item $uint = $device->max_compute_units
865
866Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_MAX_COMPUTE_UNITS> and returns the result.
867
868=item $uint = $device->max_work_item_dimensions
869
870Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_MAX_WORK_ITEM_DIMENSIONS> and returns the result.
871
872=item $int = $device->max_work_group_size
873
874Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_MAX_WORK_GROUP_SIZE> and returns the result.
875
876=item @ints = $device->max_work_item_sizes
877
878Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_MAX_WORK_ITEM_SIZES> and returns the result.
879
880=item $uint = $device->preferred_vector_width_char
881
882Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_PREFERRED_VECTOR_WIDTH_CHAR> and returns the result.
883
884=item $uint = $device->preferred_vector_width_short
885
886Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_PREFERRED_VECTOR_WIDTH_SHORT> and returns the result.
887
888=item $uint = $device->preferred_vector_width_int
889
890Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_PREFERRED_VECTOR_WIDTH_INT> and returns the result.
891
892=item $uint = $device->preferred_vector_width_long
893
894Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_PREFERRED_VECTOR_WIDTH_LONG> and returns the result.
895
896=item $uint = $device->preferred_vector_width_float
897
898Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_PREFERRED_VECTOR_WIDTH_FLOAT> and returns the result.
899
900=item $uint = $device->preferred_vector_width_double
901
902Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_PREFERRED_VECTOR_WIDTH_DOUBLE> and returns the result.
903
904=item $uint = $device->max_clock_frequency
905
906Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_MAX_CLOCK_FREQUENCY> and returns the result.
907
908=item $bitfield = $device->address_bits
909
910Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_ADDRESS_BITS> and returns the result.
911
912=item $uint = $device->max_read_image_args
913
914Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_MAX_READ_IMAGE_ARGS> and returns the result.
915
916=item $uint = $device->max_write_image_args
917
918Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_MAX_WRITE_IMAGE_ARGS> and returns the result.
919
920=item $ulong = $device->max_mem_alloc_size
921
922Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_MAX_MEM_ALLOC_SIZE> and returns the result.
923
924=item $int = $device->image2d_max_width
925
926Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_IMAGE2D_MAX_WIDTH> and returns the result.
927
928=item $int = $device->image2d_max_height
929
930Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_IMAGE2D_MAX_HEIGHT> and returns the result.
931
932=item $int = $device->image3d_max_width
933
934Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_IMAGE3D_MAX_WIDTH> and returns the result.
935
936=item $int = $device->image3d_max_height
937
938Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_IMAGE3D_MAX_HEIGHT> and returns the result.
939
940=item $int = $device->image3d_max_depth
941
942Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_IMAGE3D_MAX_DEPTH> and returns the result.
943
944=item $uint = $device->image_support
945
946Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_IMAGE_SUPPORT> and returns the result.
947
948=item $int = $device->max_parameter_size
949
950Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_MAX_PARAMETER_SIZE> and returns the result.
951
952=item $uint = $device->max_samplers
953
954Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_MAX_SAMPLERS> and returns the result.
955
956=item $uint = $device->mem_base_addr_align
957
958Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_MEM_BASE_ADDR_ALIGN> and returns the result.
959
960=item $uint = $device->min_data_type_align_size
961
962Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_MIN_DATA_TYPE_ALIGN_SIZE> and returns the result.
963
964=item $device_fp_config = $device->single_fp_config
965
966Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_SINGLE_FP_CONFIG> and returns the result.
967
968=item $device_mem_cache_type = $device->global_mem_cache_type
969
970Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_GLOBAL_MEM_CACHE_TYPE> and returns the result.
971
972=item $uint = $device->global_mem_cacheline_size
973
974Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_GLOBAL_MEM_CACHELINE_SIZE> and returns the result.
975
976=item $ulong = $device->global_mem_cache_size
977
978Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_GLOBAL_MEM_CACHE_SIZE> and returns the result.
979
980=item $ulong = $device->global_mem_size
981
982Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_GLOBAL_MEM_SIZE> and returns the result.
983
984=item $ulong = $device->max_constant_buffer_size
985
986Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_MAX_CONSTANT_BUFFER_SIZE> and returns the result.
987
988=item $uint = $device->max_constant_args
989
990Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_MAX_CONSTANT_ARGS> and returns the result.
991
992=item $device_local_mem_type = $device->local_mem_type
993
994Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_LOCAL_MEM_TYPE> and returns the result.
995
996=item $ulong = $device->local_mem_size
997
998Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_LOCAL_MEM_SIZE> and returns the result.
999
1000=item $boolean = $device->error_correction_support
1001
1002Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_ERROR_CORRECTION_SUPPORT> and returns the result.
1003
1004=item $int = $device->profiling_timer_resolution
1005
1006Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_PROFILING_TIMER_RESOLUTION> and returns the result.
1007
1008=item $boolean = $device->endian_little
1009
1010Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_ENDIAN_LITTLE> and returns the result.
1011
1012=item $boolean = $device->available
1013
1014Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_AVAILABLE> and returns the result.
1015
1016=item $boolean = $device->compiler_available
1017
1018Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_COMPILER_AVAILABLE> and returns the result.
1019
1020=item $device_exec_capabilities = $device->execution_capabilities
1021
1022Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_EXECUTION_CAPABILITIES> and returns the result.
1023
1024=item $command_queue_properties = $device->properties
1025
1026Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_QUEUE_PROPERTIES> and returns the result.
1027
1028=item $ = $device->platform
1029
1030Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_PLATFORM> and returns the result.
1031
1032=item $string = $device->name
1033
1034Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_NAME> and returns the result.
1035
1036=item $string = $device->vendor
1037
1038Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_VENDOR> and returns the result.
1039
1040=item $string = $device->driver_version
1041
1042Calls C<clGetDeviceInfo> with C<OpenCL::DRIVER_VERSION> and returns the result.
1043
1044=item $string = $device->profile
1045
1046Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_PROFILE> and returns the result.
1047
1048=item $string = $device->version
1049
1050Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_VERSION> and returns the result.
1051
1052=item $string = $device->extensions
1053
1054Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_EXTENSIONS> and returns the result.
1055
1056=item $uint = $device->preferred_vector_width_half
1057
1058Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_PREFERRED_VECTOR_WIDTH_HALF> and returns the result.
1059
1060=item $uint = $device->native_vector_width_char
1061
1062Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_NATIVE_VECTOR_WIDTH_CHAR> and returns the result.
1063
1064=item $uint = $device->native_vector_width_short
1065
1066Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_NATIVE_VECTOR_WIDTH_SHORT> and returns the result.
1067
1068=item $uint = $device->native_vector_width_int
1069
1070Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_NATIVE_VECTOR_WIDTH_INT> and returns the result.
1071
1072=item $uint = $device->native_vector_width_long
1073
1074Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_NATIVE_VECTOR_WIDTH_LONG> and returns the result.
1075
1076=item $uint = $device->native_vector_width_float
1077
1078Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_NATIVE_VECTOR_WIDTH_FLOAT> and returns the result.
1079
1080=item $uint = $device->native_vector_width_double
1081
1082Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_NATIVE_VECTOR_WIDTH_DOUBLE> and returns the result.
1083
1084=item $uint = $device->native_vector_width_half
1085
1086Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_NATIVE_VECTOR_WIDTH_HALF> and returns the result.
1087
1088=item $device_fp_config = $device->double_fp_config
1089
1090Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_DOUBLE_FP_CONFIG> and returns the result.
1091
1092=item $device_fp_config = $device->half_fp_config
1093
1094Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_HALF_FP_CONFIG> and returns the result.
1095
1096=item $boolean = $device->host_unified_memory
1097
1098Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_HOST_UNIFIED_MEMORY> and returns the result.
1099
1100=item $device = $device->parent_device_ext
1101
1102Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_PARENT_DEVICE_EXT> and returns the result.
1103
1104=item @device_partition_property_exts = $device->partition_types_ext
1105
1106Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_PARTITION_TYPES_EXT> and returns the result.
1107
1108=item @device_partition_property_exts = $device->affinity_domains_ext
1109
1110Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_AFFINITY_DOMAINS_EXT> and returns the result.
1111
1112=item $uint = $device->reference_count_ext
1113
1114Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_REFERENCE_COUNT_EXT> and returns the result.
1115
1116=item @device_partition_property_exts = $device->partition_style_ext
1117
1118Calls C<clGetDeviceInfo> with C<OpenCL::DEVICE_PARTITION_STYLE_EXT> and returns the result.
1119
1120=for gengetinfo end device
1121
345=back 1122=back
346 1123
347=head2 THE OpenCL::Context CLASS 1124=head2 THE OpenCL::Context CLASS
348 1125
1126An OpenCL::Context is basically a container, or manager, for a number of
1127devices of a platform. It is used to create all sorts of secondary objects
1128such as buffers, queues, programs and so on.
1129
1130All context creation functions and methods take a list of properties
1131(type-value pairs). All property values can be specified as integers -
1132some additionally support other types:
1133
349=over 4 1134=over 4
350 1135
351=item $packed_value = $ctx->info ($name) 1136=item OpenCL::CONTEXT_PLATFORM
352 1137
353See C<< $platform->info >> for details. 1138Also accepts OpenCL::Platform objects.
354 1139
355L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetContextInfo.html> 1140=item OpenCL::GLX_DISPLAY_KHR
1141
1142Also accepts C<undef>, in which case a deep and troubling hack is engaged
1143to find the current glx display (see L<GLX SUPPORT>).
1144
1145=item OpenCL::GL_CONTEXT_KHR
1146
1147Also accepts C<undef>, in which case a deep and troubling hack is engaged
1148to find the current glx context (see L<GLX SUPPORT>).
1149
1150=back
1151
1152=over 4
1153
1154=item $prog = $ctx->build_program ($program, $options = "")
1155
1156This convenience function tries to build the program on all devices in
1157the context. If the build fails, then the function will C<croak> with the
1158build log. Otherwise ti returns the program object.
1159
1160The C<$program> can either be a C<OpenCL::Program> object or a string
1161containing the program. In the latter case, a program objetc will be
1162created automatically.
1163
1164=cut
1165
1166sub OpenCL::Context::build_program {
1167 my ($self, $prog, $options) = @_;
1168
1169 $prog = $self->program_with_source ($prog)
1170 unless ref $prog;
1171
1172 eval { $prog->build (undef, $options); 1 }
1173 or errno == BUILD_PROGRAM_FAILURE
1174 or errno == INVALID_BINARY # workaround nvidia bug
1175 or Carp::croak "OpenCL::Context->build_program: " . err2str;
1176
1177 # we check status for all devices
1178 for my $dev ($self->devices) {
1179 $prog->build_status ($dev) == BUILD_SUCCESS
1180 or Carp::croak "Building OpenCL program for device '" . $dev->name . "' failed:\n"
1181 . $prog->build_log ($dev);
1182 }
1183
1184 $prog
1185}
356 1186
357=item $queue = $ctx->queue ($device, $properties) 1187=item $queue = $ctx->queue ($device, $properties)
358 1188
359Create a new OpenCL::Queue object from the context and the given device. 1189Create a new OpenCL::Queue object from the context and the given device.
360 1190
361L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html> 1191L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html>
362 1192
1193Example: create an out-of-order queue.
1194
1195 $queue = $ctx->queue ($device, OpenCL::QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE);
1196
363=item $ev = $ctx->user_event 1197=item $ev = $ctx->user_event
364 1198
365Creates a new OpenCL::UserEvent object. 1199Creates a new OpenCL::UserEvent object.
366 1200
367L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateUserEvent.html> 1201L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateUserEvent.html>
368 1202
369=item $buf = $ctx->buffer ($flags, $len) 1203=item $buf = $ctx->buffer ($flags, $len)
370 1204
371Creates a new OpenCL::Buffer object with the given flags and octet-size. 1205Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object with the
1206given flags and octet-size.
1207
1208flags: OpenCL::MEM_READ_WRITE, OpenCL::MEM_WRITE_ONLY, OpenCL::MEM_READ_ONLY,
1209OpenCL::MEM_USE_HOST_PTR, OpenCL::MEM_ALLOC_HOST_PTR, OpenCL::MEM_COPY_HOST_PTR,
1210OpenCL::MEM_HOST_WRITE_ONLY, OpenCL::MEM_HOST_READ_ONLY, OpenCL::MEM_HOST_NO_ACCESS.
372 1211
373L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateBuffer.html> 1212L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateBuffer.html>
374 1213
375=item $buf = $ctx->buffer_sv ($flags, $data) 1214=item $buf = $ctx->buffer_sv ($flags, $data)
376 1215
377Creates a new OpenCL::Buffer object and initialise it with the given data values. 1216Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and
1217initialise it with the given data values.
378 1218
1219=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)
1220
1221Creates a new OpenCL::Image object and optionally initialises it with
1222the given data values.
1223
1224channel_order: OpenCL::R, OpenCL::A, OpenCL::RG, OpenCL::RA, OpenCL::RGB,
1225OpenCL::RGBA, OpenCL::BGRA, OpenCL::ARGB, OpenCL::INTENSITY, OpenCL::LUMINANCE,
1226OpenCL::Rx, OpenCL::RGx, OpenCL::RGBx.
1227
1228channel_type: OpenCL::SNORM_INT8, OpenCL::SNORM_INT16, OpenCL::UNORM_INT8,
1229OpenCL::UNORM_INT16, OpenCL::UNORM_SHORT_565, OpenCL::UNORM_SHORT_555,
1230OpenCL::UNORM_INT_101010, OpenCL::SIGNED_INT8, OpenCL::SIGNED_INT16,
1231OpenCL::SIGNED_INT32, OpenCL::UNSIGNED_INT8, OpenCL::UNSIGNED_INT16,
1232OpenCL::UNSIGNED_INT32, OpenCL::HALF_FLOAT, OpenCL::FLOAT.
1233
1234type: OpenCL::MEM_OBJECT_BUFFER, OpenCL::MEM_OBJECT_IMAGE2D,
1235OpenCL::MEM_OBJECT_IMAGE3D, OpenCL::MEM_OBJECT_IMAGE2D_ARRAY,
1236OpenCL::MEM_OBJECT_IMAGE1D, OpenCL::MEM_OBJECT_IMAGE1D_ARRAY,
1237OpenCL::MEM_OBJECT_IMAGE1D_BUFFER.
1238
1239L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html>
1240
379=item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $data) 1241=item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $row_pitch = 0, $data = undef)
380 1242
381Creates a new OpenCL::Image2D object and optionally initialises it with the given data values. 1243Creates a new OpenCL::Image2D object and optionally initialises it with
1244the given data values.
382 1245
383L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage2D.html> 1246L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage2D.html>
384 1247
385=item $img = $ctx->image3d ($flags, $channel_order, $channel_type, $width, $height, $depth, $slice_pitch, $data) 1248=item $img = $ctx->image3d ($flags, $channel_order, $channel_type, $width, $height, $depth, $row_pitch = 0, $slice_pitch = 0, $data = undef)
386 1249
387Creates a new OpenCL::Image3D object and optionally initialises it with the given data values. 1250Creates a new OpenCL::Image3D object and optionally initialises it with
1251the given data values.
388 1252
389L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage3D.html> 1253L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage3D.html>
1254
1255=item $buffer = $ctx->gl_buffer ($flags, $bufobj)
1256
1257Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object that refers to the given
1258OpenGL buffer object.
1259
1260flags: OpenCL::MEM_READ_WRITE, OpenCL::MEM_READ_ONLY, OpenCL::MEM_WRITE_ONLY.
1261
1262http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLBuffer.html
1263
1264=item $img = $ctx->gl_texture ($flags, $target, $miplevel, $texture)
1265
1266Creates a new OpenCL::Image object that refers to the given OpenGL
1267texture object or buffer.
1268
1269target: GL_TEXTURE_1D, GL_TEXTURE_1D_ARRAY, GL_TEXTURE_BUFFER,
1270GL_TEXTURE_2D, GL_TEXTURE_2D_ARRAY, GL_TEXTURE_3D,
1271GL_TEXTURE_CUBE_MAP_POSITIVE_X, GL_TEXTURE_CUBE_MAP_POSITIVE_Y,
1272GL_TEXTURE_CUBE_MAP_POSITIVE_Z, GL_TEXTURE_CUBE_MAP_NEGATIVE_X,
1273GL_TEXTURE_CUBE_MAP_NEGATIVE_Y, GL_TEXTURE_CUBE_MAP_NEGATIVE_Z,
1274GL_TEXTURE_RECTANGLE/GL_TEXTURE_RECTANGLE_ARB.
1275
1276http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateFromGLTexture.html
1277
1278=item $img = $ctx->gl_texture2d ($flags, $target, $miplevel, $texture)
1279
1280Creates a new OpenCL::Image2D object that refers to the given OpenGL
12812D texture object.
1282
1283http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture2D.html
1284
1285=item $img = $ctx->gl_texture3d ($flags, $target, $miplevel, $texture)
1286
1287Creates a new OpenCL::Image3D object that refers to the given OpenGL
12883D texture object.
1289
1290http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture3D.html
1291
1292=item $ctx->gl_renderbuffer ($flags, $renderbuffer)
1293
1294Creates a new OpenCL::Image2D object that refers to the given OpenGL
1295render buffer.
1296
1297http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLRenderbuffer.html
390 1298
391=item @formats = $ctx->supported_image_formats ($flags, $image_type) 1299=item @formats = $ctx->supported_image_formats ($flags, $image_type)
392 1300
393Returns a list of matching image formats - each format is an arrayref with 1301Returns a list of matching image formats - each format is an arrayref with
394two values, $channel_order and $channel_type, in it. 1302two values, $channel_order and $channel_type, in it.
397 1305
398=item $sampler = $ctx->sampler ($normalized_coords, $addressing_mode, $filter_mode) 1306=item $sampler = $ctx->sampler ($normalized_coords, $addressing_mode, $filter_mode)
399 1307
400Creates a new OpenCL::Sampler object. 1308Creates a new OpenCL::Sampler object.
401 1309
1310addressing_mode: OpenCL::ADDRESS_NONE, OpenCL::ADDRESS_CLAMP_TO_EDGE,
1311OpenCL::ADDRESS_CLAMP, OpenCL::ADDRESS_REPEAT, OpenCL::ADDRESS_MIRRORED_REPEAT.
1312
1313filter_mode: OpenCL::FILTER_NEAREST, OpenCL::FILTER_LINEAR.
1314
402L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateSampler.html> 1315L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateSampler.html>
403 1316
404=item $program = $ctx->program_with_source ($string) 1317=item $program = $ctx->program_with_source ($string)
405 1318
406Creates a new OpenCL::Program object from the given source code. 1319Creates a new OpenCL::Program object from the given source code.
407 1320
408L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateProgramWithSource.html> 1321L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateProgramWithSource.html>
409 1322
1323=item ($program, \@status) = $ctx->program_with_binary (\@devices, \@binaries)
1324
1325Creates a new OpenCL::Program object from the given binaries.
1326
1327L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateProgramWithBinary.html>
1328
1329Example: clone an existing program object that contains a successfully
1330compiled program, no matter how useless this is.
1331
1332 my $clone = $ctx->program_with_binary ([$prog->devices], [$prog->binaries]);
1333
1334=item $program = $ctx->program_with_built_in_kernels (\@devices, $kernel_names)
1335
1336Creates a new OpenCL::Program object from the given built-in kernel names.
1337
1338L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateProgramWithBuiltInKernels.html>
1339
1340=item $program = $ctx->link_program (\@devices, $options, \@programs, $cb->($program) = undef)
1341
1342Links all (already compiled) program objects specified in C<@programs>
1343together and returns a new OpenCL::Program object with the result.
1344
1345L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clLinkProgram.html>
1346
1347=item $packed_value = $ctx->info ($name)
1348
1349See C<< $platform->info >> for details.
1350
1351L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetContextInfo.html>
1352
1353=for gengetinfo begin context
1354
1355=item $uint = $context->reference_count
1356
1357Calls C<clGetContextInfo> with C<OpenCL::CONTEXT_REFERENCE_COUNT> and returns the result.
1358
1359=item @devices = $context->devices
1360
1361Calls C<clGetContextInfo> with C<OpenCL::CONTEXT_DEVICES> and returns the result.
1362
1363=item @property_ints = $context->properties
1364
1365Calls C<clGetContextInfo> with C<OpenCL::CONTEXT_PROPERTIES> and returns the result.
1366
1367=item $uint = $context->num_devices
1368
1369Calls C<clGetContextInfo> with C<OpenCL::CONTEXT_NUM_DEVICES> and returns the result.
1370
1371=for gengetinfo end context
1372
410=back 1373=back
411 1374
412=head2 THE OpenCL::Queue CLASS 1375=head2 THE OpenCL::Queue CLASS
413 1376
414An OpenCL::Queue represents an execution queue for OpenCL. You execute 1377An OpenCL::Queue represents an execution queue for OpenCL. You execute
415requests by calling their respective C<enqueue_xxx> method and waitinf for 1378requests by calling their respective method and waiting for it to complete
416it to complete in some way. 1379in some way.
417 1380
418All the enqueue methods return an event object that can be used to wait 1381Most methods that enqueue some request return an event object that can
419for completion, unless the method is called in void context, in which case 1382be used to wait for completion (optionally using a callback), unless
420no event object is created. 1383the method is called in void context, in which case no event object is
1384created.
421 1385
422They also allow you to specify any number of other event objects that this 1386They also allow you to specify any number of other event objects that this
423request has to wait for before it starts executing, by simply passing the 1387request has to wait for before it starts executing, by simply passing the
424event objects as extra parameters to the enqueue methods. 1388event objects as extra parameters to the enqueue methods. To simplify
1389program design, this module ignores any C<undef> values in the list of
1390events. This makes it possible to code operations such as this, without
1391having to put a valid event object into C<$event> first:
1392
1393 $event = $queue->xxx (..., $event);
425 1394
426Queues execute in-order by default, without any parallelism, so in most 1395Queues execute in-order by default, without any parallelism, so in most
427cases (i.e. you use only one queue) it's not necessary to wait for or 1396cases (i.e. you use only one queue) it's not necessary to wait for or
428create event objects. 1397create event objects, althoguh an our of order queue is often a bit
1398faster.
429 1399
430=over 4 1400=over 4
431 1401
432=item $packed_value = $ctx->info ($name)
433
434See C<< $platform->info >> for details.
435
436L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetCommandQueueInfo.html>
437
438=item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) 1402=item $ev = $queue->read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...)
439 1403
440Reads data from buffer into the given string. 1404Reads data from buffer into the given string.
441 1405
442L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html> 1406L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html>
443 1407
444=item $ev = $queue->enqueue_write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) 1408=item $ev = $queue->write_buffer ($buffer, $blocking, $offset, $data, $wait_events...)
445 1409
446Writes data to buffer from the given string. 1410Writes data to buffer from the given string.
447 1411
448L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html> 1412L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html>
449 1413
450=item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) 1414=item $ev = $queue->copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...)
451 1415
452L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> 1416L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html>
453 1417
1418=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...)
1419
1420http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html
1421
1422=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...)
1423
1424http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html
1425
1426=item $ev = $queue->copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...)
1427
1428L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>
1429
454=item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) 1430=item $ev = $queue->read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
1431
1432C<$row_pitch> (and C<$slice_pitch>) can be C<0>, in which case the OpenCL
1433module uses the image width (and height) to supply default values.
455 1434
456L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> 1435L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html>
457 1436
458=item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $data, $wait_events...) 1437=item $ev = $queue->write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
459 1438
1439C<$row_pitch> (and C<$slice_pitch>) can be C<0>, in which case the OpenCL
1440module uses the image width (and height) to supply default values.
460L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> 1441L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html>
461 1442
1443=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...)
1444
1445L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html>
1446
1447=item $ev = $queue->copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...)
1448
1449L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html>
1450
462=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, 4dst_row_pitch, $dst_slice_pitch, $ait_event...) 1451=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...)
463 1452
464Yeah. 1453Yeah.
465 1454
466L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html>
467
468=item $ev = $queue->enqueue_copy_buffer_to_image (OpenCL::Buffer src, OpenCL::Image dst, size_t src_offset, size_t dst_x, size_t dst_y, size_t dst_z, size_t width, size_t height, size_t depth, ...)
469
470L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. 1455L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>.
471 1456
472=item $ev = $queue->enqueue_copy_image (OpenCL::Image src, OpenCL::Buffer dst, size_t src_x, size_t src_y, size_t src_z, size_t dst_x, size_t dst_y, size_t dst_z, size_t width, size_t height, size_t depth, ...) 1457=item $ev = $queue->fill_buffer ($mem, $pattern, $offset, $size, ...)
473 1458
1459Fills the given buffer object with repeated applications of C<$pattern>,
1460starting at C<$offset> for C<$size> octets.
1461
1462L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html>
1463
1464=item $ev = $queue->fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...)
1465
1466Fills the given image area with the given rgba colour components. The
1467components are normally floating point values between C<0> and C<1>,
1468except when the image channel data type is a signe dor unsigned
1469unnormalised format, in which case the range is determined by the format.
1470
474L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> 1471L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html>
475 1472
476=item $ev = $queue->enqueue_copy_image_to_buffer (OpenCL::Image src, OpenCL::Buffer dst, size_t src_x, size_t src_y, size_t src_z, size_t width, size_t height, size_t depth, size_t dst_offset, ...)
477
478L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html>
479
480=item $ev = $queue->enqueue_task ($kernel, $wait_events...) 1473=item $ev = $queue->task ($kernel, $wait_events...)
481 1474
482L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> 1475L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html>
483 1476
484=item $ev = $queue->enqueue_nd_range_kernel ($kernel, @$global_work_offset, @$global_work_size, @$local_work_size, $wait_events...) 1477=item $ev = $queue->nd_range_kernel ($kernel, \@global_work_offset, \@global_work_size, \@local_work_size, $wait_events...)
485 1478
486Enqueues a kernel execution. 1479Enqueues a kernel execution.
487 1480
488@$global_work_size must be specified as a reference to an array of 1481\@global_work_size must be specified as a reference to an array of
489integers specifying the work sizes (element counts). 1482integers specifying the work sizes (element counts).
490 1483
491@$global_work_offset must be either C<undef> (in which case all offsets 1484\@global_work_offset must be either C<undef> (in which case all offsets
492are C<0>), or a reference to an array of work offsets, with the same number 1485are C<0>), or a reference to an array of work offsets, with the same number
493of elements as @$global_work_size. 1486of elements as \@global_work_size.
494 1487
495@$local_work_size must be either C<undef> (in which case the 1488\@local_work_size must be either C<undef> (in which case the
496implementation is supposed to choose good local work sizes), or a 1489implementation is supposed to choose good local work sizes), or a
497reference to an array of local work sizes, with the same number of 1490reference to an array of local work sizes, with the same number of
498elements as @$global_work_size. 1491elements as \@global_work_size.
499 1492
500L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> 1493L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html>
501 1494
502=item $ev = $queue->enqueue_marker 1495=item $ev = $queue->migrate_mem_objects (\@mem_objects, $flags, $wait_events...)
503 1496
1497Migrates a number of OpenCL::Memory objects to or from the device.
1498
1499flags: OpenCL::MIGRATE_MEM_OBJECT_HOST, OpenCL::MIGRATE_MEM_OBJECT_CONTENT_UNDEFINED
1500
1501L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMigrateMemObjects.html>
1502
1503=item $ev = $queue->acquire_gl_objects ([object, ...], $wait_events...)
1504
1505Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired
1506for subsequent OpenCL usage.
1507
504L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueMarker.html> 1508L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html>
505 1509
1510=item $ev = $queue->release_gl_objects ([object, ...], $wait_events...)
1511
1512Enqueues a list (an array-ref of OpenCL::Memory objects) to be released
1513for subsequent OpenGL usage.
1514
1515L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html>
1516
506=item $ev = $queue->enqueue_wait_for_events ($wait_events...) 1517=item $ev = $queue->wait_for_events ($wait_events...)
507 1518
508L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> 1519L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html>
509 1520
510=item $queue->enqueue_barrier 1521=item $ev = $queue->marker ($wait_events...)
511 1522
1523L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html>
1524
1525=item $ev = $queue->barrier ($wait_events...)
1526
512L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueBarrier.html> 1527L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html>
513 1528
514=item $queue->flush 1529=item $queue->flush
515 1530
516L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html> 1531L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html>
517 1532
518=item $queue->finish 1533=item $queue->finish
519 1534
520L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFinish.html> 1535L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFinish.html>
521 1536
1537=item $packed_value = $queue->info ($name)
1538
1539See C<< $platform->info >> for details.
1540
1541L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetCommandQueueInfo.html>
1542
1543=for gengetinfo begin command_queue
1544
1545=item $ctx = $command_queue->context
1546
1547Calls C<clGetCommandQueueInfo> with C<OpenCL::QUEUE_CONTEXT> and returns the result.
1548
1549=item $device = $command_queue->device
1550
1551Calls C<clGetCommandQueueInfo> with C<OpenCL::QUEUE_DEVICE> and returns the result.
1552
1553=item $uint = $command_queue->reference_count
1554
1555Calls C<clGetCommandQueueInfo> with C<OpenCL::QUEUE_REFERENCE_COUNT> and returns the result.
1556
1557=item $command_queue_properties = $command_queue->properties
1558
1559Calls C<clGetCommandQueueInfo> with C<OpenCL::QUEUE_PROPERTIES> and returns the result.
1560
1561=for gengetinfo end command_queue
1562
522=back 1563=back
523 1564
1565=head3 MEMORY MAPPED BUFFERS
1566
1567OpenCL allows you to map buffers and images to host memory (read: perl
1568scalars). This is done much like reading or copying a buffer, by enqueuing
1569a map or unmap operation on the command queue.
1570
1571The map operations return an C<OpenCL::Mapped> object - see L<THE
1572OpenCL::Mapped CLASS> section for details on what to do with these
1573objects.
1574
1575The object will be unmapped automatically when the mapped object is
1576destroyed (you can use a barrier to make sure the unmap has finished,
1577before using the buffer in a kernel), but you can also enqueue an unmap
1578operation manually.
1579
1580=over 4
1581
1582=item $mapped_buffer = $queue->map_buffer ($buf, $blocking=1, $map_flags=OpenCL::MAP_READ|OpenCL::MAP_WRITE, $offset=0, $size=undef, $wait_events...)
1583
1584Maps the given buffer into host memory and returns an
1585C<OpenCL::MappedBuffer> object. If C<$size> is specified as undef, then
1586the map will extend to the end of the buffer.
1587
1588map_flags: OpenCL::MAP_READ, OpenCL::MAP_WRITE, OpenCL::MAP_WRITE_INVALIDATE_REGION.
1589
1590L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueMapBuffer.html>
1591
1592Example: map the buffer $buf fully and replace the first 4 bytes by "abcd", then unmap.
1593
1594 {
1595 my $mapped = $queue->map_buffer ($buf, 1, OpenCL::MAP_WRITE);
1596 substr $$mapped, 0, 4, "abcd";
1597 } # asynchronously unmap because $mapped is destroyed
1598
1599=item $mapped_image = $queue->map_image ($img, $blocking=1, $map_flags=OpenCL::MAP_READ|OpenCL::MAP_WRITE, $x=0, $y=0, $z=0, $width=undef, $height=undef, $depth=undef, $wait_events...)
1600
1601Maps the given image area into host memory and return an
1602C<OpenCL::MappedImage> object.
1603
1604If any of C<$width>, C<$height> and/or C<$depth> are C<undef> then they
1605will be replaced by the maximum possible value.
1606
1607L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueMapImage.html>
1608
1609Example: map an image (with OpenCL::UNSIGNED_INT8 channel type) and set
1610the first channel of the leftmost column to 5, then explicitly unmap
1611it. You are not necessarily meant to do it this way, this example just
1612shows you the accessors to use :)
1613
1614 my $mapped = $queue->map_image ($image, 1, OpenCL::MAP_WRITE);
1615
1616 $mapped->set ($_ * $mapped->row_pitch, pack "C", 5)
1617 for 0..$image->height;
1618
1619 $mapped->unmap;.
1620 $mapped->wait; # only needed for out of order queues normally
1621
1622=item $ev = $queue->unmap ($mapped, $wait_events...)
1623
1624Unmaps the data from host memory. You must not call any methods that
1625modify the data, or modify the data scalar directly, after calling this
1626method.
1627
1628The mapped event object will always be passed as part of the
1629$wait_events. The mapped event object will be replaced by the new event
1630object that this request creates.
1631
1632=back
1633
524=head2 THE OpenCL::Memory CLASS 1634=head2 THE OpenCL::Memory CLASS
525 1635
526This the superclass of all memory objects - OpenCL::Buffer, OpenCL::Image, 1636This the superclass of all memory objects - OpenCL::Buffer, OpenCL::Image,
527OpenCL::Image2D and OpenCL::Image3D. The subclasses of this class 1637OpenCL::Image2D and OpenCL::Image3D.
528currently only exist to allow type-checking.
529 1638
530=over 4 1639=over 4
531 1640
532=item $packed_value = $memory->info ($name) 1641=item $packed_value = $memory->info ($name)
533 1642
534See C<< $platform->info >> for details. 1643See C<< $platform->info >> for details.
535 1644
536L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetMemObjectInfo.html> 1645L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetMemObjectInfo.html>
537 1646
1647=for gengetinfo begin mem
1648
1649=item $mem_object_type = $mem->type
1650
1651Calls C<clGetMemObjectInfo> with C<OpenCL::MEM_TYPE> and returns the result.
1652
1653=item $mem_flags = $mem->flags
1654
1655Calls C<clGetMemObjectInfo> with C<OpenCL::MEM_FLAGS> and returns the result.
1656
1657=item $int = $mem->size
1658
1659Calls C<clGetMemObjectInfo> with C<OpenCL::MEM_SIZE> and returns the result.
1660
1661=item $ptr_value = $mem->host_ptr
1662
1663Calls C<clGetMemObjectInfo> with C<OpenCL::MEM_HOST_PTR> and returns the result.
1664
1665=item $uint = $mem->map_count
1666
1667Calls C<clGetMemObjectInfo> with C<OpenCL::MEM_MAP_COUNT> and returns the result.
1668
1669=item $uint = $mem->reference_count
1670
1671Calls C<clGetMemObjectInfo> with C<OpenCL::MEM_REFERENCE_COUNT> and returns the result.
1672
1673=item $ctx = $mem->context
1674
1675Calls C<clGetMemObjectInfo> with C<OpenCL::MEM_CONTEXT> and returns the result.
1676
1677=item $mem = $mem->associated_memobject
1678
1679Calls C<clGetMemObjectInfo> with C<OpenCL::MEM_ASSOCIATED_MEMOBJECT> and returns the result.
1680
1681=item $int = $mem->offset
1682
1683Calls C<clGetMemObjectInfo> with C<OpenCL::MEM_OFFSET> and returns the result.
1684
1685=for gengetinfo end mem
1686
1687=item ($type, $name) = $mem->gl_object_info
1688
1689Returns the OpenGL object type (e.g. OpenCL::GL_OBJECT_TEXTURE2D) and the
1690object "name" (e.g. the texture name) used to create this memory object.
1691
1692L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetGLObjectInfo.html>
1693
538=back 1694=back
539 1695
1696=head2 THE OpenCL::Buffer CLASS
1697
1698This is a subclass of OpenCL::Memory, and the superclass of
1699OpenCL::BufferObj. Its purpose is simply to distinguish between buffers
1700and sub-buffers.
1701
1702=head2 THE OpenCL::BufferObj CLASS
1703
1704This is a subclass of OpenCL::Buffer and thus OpenCL::Memory. It exists
1705because one cna create sub buffers of OpenLC::BufferObj objects, but not
1706sub buffers from these sub buffers.
1707
1708=over 4
1709
1710=item $subbuf = $buf_obj->sub_buffer_region ($flags, $origin, $size)
1711
1712Creates an OpenCL::Buffer objects from this buffer and returns it. The
1713C<buffer_create_type> is assumed to be C<OpenCL::BUFFER_CREATE_TYPE_REGION>.
1714
1715L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateSubBuffer.html>
1716
1717=back
1718
1719=head2 THE OpenCL::Image CLASS
1720
1721This is the superclass of all image objects - OpenCL::Image1D,
1722OpenCL::Image1DArray, OpenCL::Image1DBuffer, OpenCL::Image2D,
1723OpenCL::Image2DArray and OpenCL::Image3D.
1724
1725=over 4
1726
1727=item $packed_value = $image->image_info ($name)
1728
1729See C<< $platform->info >> for details.
1730
1731The reason this method is not called C<info> is that there already is an
1732C<< ->info >> method inherited from C<OpenCL::Memory>.
1733
1734L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html>
1735
1736=item ($channel_order, $channel_data_type) = $image->format
1737
1738Returns the channel order and type used to create the image by calling
1739C<clGetImageInfo> with C<OpenCL::IMAGE_FORMAT>.
1740
1741=for gengetinfo begin image
1742
1743=item $int = $image->element_size
1744
1745Calls C<clGetImageInfo> with C<OpenCL::IMAGE_ELEMENT_SIZE> and returns the result.
1746
1747=item $int = $image->row_pitch
1748
1749Calls C<clGetImageInfo> with C<OpenCL::IMAGE_ROW_PITCH> and returns the result.
1750
1751=item $int = $image->slice_pitch
1752
1753Calls C<clGetImageInfo> with C<OpenCL::IMAGE_SLICE_PITCH> and returns the result.
1754
1755=item $int = $image->width
1756
1757Calls C<clGetImageInfo> with C<OpenCL::IMAGE_WIDTH> and returns the result.
1758
1759=item $int = $image->height
1760
1761Calls C<clGetImageInfo> with C<OpenCL::IMAGE_HEIGHT> and returns the result.
1762
1763=item $int = $image->depth
1764
1765Calls C<clGetImageInfo> with C<OpenCL::IMAGE_DEPTH> and returns the result.
1766
1767=for gengetinfo end image
1768
1769=for gengetinfo begin gl_texture
1770
1771=item $GLenum = $gl_texture->target
1772
1773Calls C<clGetGLTextureInfo> with C<OpenCL::GL_TEXTURE_TARGET> and returns the result.
1774
1775=item $GLint = $gl_texture->gl_mipmap_level
1776
1777Calls C<clGetGLTextureInfo> with C<OpenCL::GL_MIPMAP_LEVEL> and returns the result.
1778
1779=for gengetinfo end gl_texture
1780
1781=back
1782
540=head2 THE OpenCL::Sampler CLASS 1783=head2 THE OpenCL::Sampler CLASS
541 1784
542=over 4 1785=over 4
543 1786
544=item $packed_value = $sampler->info ($name) 1787=item $packed_value = $sampler->info ($name)
545 1788
546See C<< $platform->info >> for details. 1789See C<< $platform->info >> for details.
547 1790
548L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetSamplerInfo.html> 1791L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetSamplerInfo.html>
549 1792
1793=for gengetinfo begin sampler
1794
1795=item $uint = $sampler->reference_count
1796
1797Calls C<clGetSamplerInfo> with C<OpenCL::SAMPLER_REFERENCE_COUNT> and returns the result.
1798
1799=item $ctx = $sampler->context
1800
1801Calls C<clGetSamplerInfo> with C<OpenCL::SAMPLER_CONTEXT> and returns the result.
1802
1803=item $addressing_mode = $sampler->normalized_coords
1804
1805Calls C<clGetSamplerInfo> with C<OpenCL::SAMPLER_NORMALIZED_COORDS> and returns the result.
1806
1807=item $filter_mode = $sampler->addressing_mode
1808
1809Calls C<clGetSamplerInfo> with C<OpenCL::SAMPLER_ADDRESSING_MODE> and returns the result.
1810
1811=item $boolean = $sampler->filter_mode
1812
1813Calls C<clGetSamplerInfo> with C<OpenCL::SAMPLER_FILTER_MODE> and returns the result.
1814
1815=for gengetinfo end sampler
1816
550=back 1817=back
551 1818
552=head2 THE OpenCL::Program CLASS 1819=head2 THE OpenCL::Program CLASS
553 1820
554=over 4 1821=over 4
555 1822
556=item $packed_value = $program->info ($name) 1823=item $program->build (\@devices = undef, $options = "", $cb->($program) = undef)
557 1824
558See C<< $platform->info >> for details.
559
560L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetProgramInfo.html>
561
562=item $program->build ($device, $options = "")
563
564Tries to build the program with the givne options. 1825Tries to build the program with the given options. See also the
1826C<$ctx->build> convenience function.
1827
1828If a callback is specified, then it will be called when compilation is
1829finished. Note that many OpenCL implementations block your program while
1830compiling whether you use a callback or not. See C<build_async> if you
1831want to make sure the build is done in the background.
1832
1833Note that some OpenCL implementations act up badly, and don't call the
1834callback in some error cases (but call it in others). This implementation
1835assumes the callback will always be called, and leaks memory if this is
1836not so. So best make sure you don't pass in invalid values.
1837
1838Some implementations fail with C<OpenCL::INVALID_BINARY> when the
1839compilation state is successful but some later stage fails.
1840
1841options: C<-D name>, C<-D name=definition>, C<-I dir>,
1842C<-cl-single-precision-constant>, C<-cl-denorms-are-zero>,
1843C<-cl-fp32-correctly-rounded-divide-sqrt>, C<-cl-opt-disable>,
1844C<-cl-mad-enable>, C<-cl-no-signed-zeros>, C<-cl-unsafe-math-optimizations>,
1845C<-cl-finite-math-only>, C<-cl-fast-relaxed-math>,
1846C<-w>, C<-Werror>, C<-cl-std=CL1.1/CL1.2>, C<-cl-kernel-arg-info>,
1847C<-create-library>, C<-enable-link-options>.
1848
1849build_status: OpenCL::BUILD_SUCCESS, OpenCL::BUILD_NONE,
1850OpenCL::BUILD_ERROR, OpenCL::BUILD_IN_PROGRESS.
565 1851
566L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> 1852L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html>
1853
1854=item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef)
1855
1856Similar to C<< ->build >>, except it starts a thread, and never fails (you
1857need to check the compilation status form the callback, or by polling).
1858
1859=item $program->compile (\@devices = undef, $options = "", \%headers = undef, $cb->($program) = undef)
1860
1861Compiles the given program for the given devices (or all devices if
1862undef). If C<$headers> is given, it must be a hashref with include name =>
1863OpenCL::Program pairs.
1864
1865L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCompileProgram.html>
567 1866
568=item $packed_value = $program->build_info ($device, $name) 1867=item $packed_value = $program->build_info ($device, $name)
569 1868
570Similar to C<< $platform->info >>, but returns build info for a previous 1869Similar to C<< $platform->info >>, but returns build info for a previous
571build attempt for the given device. 1870build attempt for the given device.
572 1871
1872binary_type: OpenCL::PROGRAM_BINARY_TYPE_NONE,
1873OpenCL::PROGRAM_BINARY_TYPE_COMPILED_OBJECT,
1874OpenCL::PROGRAM_BINARY_TYPE_LIBRARY,
1875OpenCL::PROGRAM_BINARY_TYPE_EXECUTABLE.
1876
573L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetBuildInfo.html> 1877L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetBuildInfo.html>
574 1878
575=item $kernel = $program->kernel ($function_name) 1879=item $kernel = $program->kernel ($function_name)
576 1880
577Creates an OpenCL::Kernel object out of the named C<__kernel> function in 1881Creates an OpenCL::Kernel object out of the named C<__kernel> function in
578the program. 1882the program.
579 1883
580L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html> 1884L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html>
581 1885
1886=item @kernels = $program->kernels_in_program
1887
1888Returns all kernels successfully compiled for all devices in program.
1889
1890http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernelsInProgram.html
1891
1892=for gengetinfo begin program_build
1893
1894=item $build_status = $program->build_status ($device)
1895
1896Calls C<clGetProgramBuildInfo> with C<OpenCL::PROGRAM_BUILD_STATUS> and returns the result.
1897
1898=item $string = $program->build_options ($device)
1899
1900Calls C<clGetProgramBuildInfo> with C<OpenCL::PROGRAM_BUILD_OPTIONS> and returns the result.
1901
1902=item $string = $program->build_log ($device)
1903
1904Calls C<clGetProgramBuildInfo> with C<OpenCL::PROGRAM_BUILD_LOG> and returns the result.
1905
1906=item $binary_type = $program->binary_type ($device)
1907
1908Calls C<clGetProgramBuildInfo> with C<OpenCL::PROGRAM_BINARY_TYPE> and returns the result.
1909
1910=for gengetinfo end program_build
1911
1912=item $packed_value = $program->info ($name)
1913
1914See C<< $platform->info >> for details.
1915
1916L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetProgramInfo.html>
1917
1918=for gengetinfo begin program
1919
1920=item $uint = $program->reference_count
1921
1922Calls C<clGetProgramInfo> with C<OpenCL::PROGRAM_REFERENCE_COUNT> and returns the result.
1923
1924=item $ctx = $program->context
1925
1926Calls C<clGetProgramInfo> with C<OpenCL::PROGRAM_CONTEXT> and returns the result.
1927
1928=item $uint = $program->num_devices
1929
1930Calls C<clGetProgramInfo> with C<OpenCL::PROGRAM_NUM_DEVICES> and returns the result.
1931
1932=item @devices = $program->devices
1933
1934Calls C<clGetProgramInfo> with C<OpenCL::PROGRAM_DEVICES> and returns the result.
1935
1936=item $string = $program->source
1937
1938Calls C<clGetProgramInfo> with C<OpenCL::PROGRAM_SOURCE> and returns the result.
1939
1940=item @ints = $program->binary_sizes
1941
1942Calls C<clGetProgramInfo> with C<OpenCL::PROGRAM_BINARY_SIZES> and returns the result.
1943
1944=for gengetinfo end program
1945
1946=item @blobs = $program->binaries
1947
1948Returns a string for the compiled binary for every device associated with
1949the program, empty strings indicate missing programs, and an empty result
1950means no program binaries are available.
1951
1952These "binaries" are often, in fact, informative low-level assembly
1953sources.
1954
1955L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetProgramInfo.html>
1956
582=back 1957=back
583 1958
584=head2 THE OpenCL::Kernel CLASS 1959=head2 THE OpenCL::Kernel CLASS
585 1960
586=over 4 1961=over 4
589 1964
590See C<< $platform->info >> for details. 1965See C<< $platform->info >> for details.
591 1966
592L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetKernelInfo.html> 1967L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetKernelInfo.html>
593 1968
1969=for gengetinfo begin kernel
1970
1971=item $string = $kernel->function_name
1972
1973Calls C<clGetKernelInfo> with C<OpenCL::KERNEL_FUNCTION_NAME> and returns the result.
1974
1975=item $uint = $kernel->num_args
1976
1977Calls C<clGetKernelInfo> with C<OpenCL::KERNEL_NUM_ARGS> and returns the result.
1978
1979=item $uint = $kernel->reference_count
1980
1981Calls C<clGetKernelInfo> with C<OpenCL::KERNEL_REFERENCE_COUNT> and returns the result.
1982
1983=item $ctx = $kernel->context
1984
1985Calls C<clGetKernelInfo> with C<OpenCL::KERNEL_CONTEXT> and returns the result.
1986
1987=item $program = $kernel->program
1988
1989Calls C<clGetKernelInfo> with C<OpenCL::KERNEL_PROGRAM> and returns the result.
1990
1991=for gengetinfo end kernel
1992
1993=item $packed_value = $kernel->work_group_info ($device, $name)
1994
1995See C<< $platform->info >> for details.
1996
1997L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetKernelWorkGroupInfo.html>
1998
1999=for gengetinfo begin kernel_work_group
2000
2001=item $int = $kernel->work_group_size ($device)
2002
2003Calls C<clGetKernelWorkGroupInfo> with C<OpenCL::KERNEL_WORK_GROUP_SIZE> and returns the result.
2004
2005=item @ints = $kernel->compile_work_group_size ($device)
2006
2007Calls C<clGetKernelWorkGroupInfo> with C<OpenCL::KERNEL_COMPILE_WORK_GROUP_SIZE> and returns the result.
2008
2009=item $ulong = $kernel->local_mem_size ($device)
2010
2011Calls C<clGetKernelWorkGroupInfo> with C<OpenCL::KERNEL_LOCAL_MEM_SIZE> and returns the result.
2012
2013=item $int = $kernel->preferred_work_group_size_multiple ($device)
2014
2015Calls C<clGetKernelWorkGroupInfo> with C<OpenCL::KERNEL_PREFERRED_WORK_GROUP_SIZE_MULTIPLE> and returns the result.
2016
2017=item $ulong = $kernel->private_mem_size ($device)
2018
2019Calls C<clGetKernelWorkGroupInfo> with C<OpenCL::KERNEL_PRIVATE_MEM_SIZE> and returns the result.
2020
2021=for gengetinfo end kernel_work_group
2022
2023=item $packed_value = $kernel->arg_info ($idx, $name)
2024
2025See C<< $platform->info >> for details.
2026
2027L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clGetKernelArgInfo.html>
2028
2029=for gengetinfo begin kernel_arg
2030
2031=item $kernel_arg_address_qualifier = $kernel->arg_address_qualifier ($idx)
2032
2033Calls C<clGetKernelArgInfo> with C<OpenCL::KERNEL_ARG_ADDRESS_QUALIFIER> and returns the result.
2034
2035=item $kernel_arg_access_qualifier = $kernel->arg_access_qualifier ($idx)
2036
2037Calls C<clGetKernelArgInfo> with C<OpenCL::KERNEL_ARG_ACCESS_QUALIFIER> and returns the result.
2038
2039=item $string = $kernel->arg_type_name ($idx)
2040
2041Calls C<clGetKernelArgInfo> with C<OpenCL::KERNEL_ARG_TYPE_NAME> and returns the result.
2042
2043=item $kernel_arg_type_qualifier = $kernel->arg_type_qualifier ($idx)
2044
2045Calls C<clGetKernelArgInfo> with C<OpenCL::KERNEL_ARG_TYPE_QUALIFIER> and returns the result.
2046
2047=item $string = $kernel->arg_name ($idx)
2048
2049Calls C<clGetKernelArgInfo> with C<OpenCL::KERNEL_ARG_NAME> and returns the result.
2050
2051=for gengetinfo end kernel_arg
2052
2053=item $kernel->setf ($format, ...)
2054
2055Sets the arguments of a kernel. Since OpenCL 1.1 doesn't have a generic
2056way to set arguments (and with OpenCL 1.2 it might be rather slow), you
2057need to specify a format argument, much as with C<printf>, to tell OpenCL
2058what type of argument it is.
2059
2060The format arguments are single letters:
2061
2062 c char
2063 C unsigned char
2064 s short
2065 S unsigned short
2066 i int
2067 I unsigned int
2068 l long
2069 L unsigned long
2070
2071 h half float (0..65535)
2072 f float
2073 d double
2074
2075 z local (octet size)
2076
2077 m memory object (buffer or image)
2078 a sampler
2079 e event
2080
2081Space characters in the format string are ignored.
2082
2083Example: set the arguments for a kernel that expects an int, two floats, a buffer and an image.
2084
2085 $kernel->setf ("i ff mm", 5, 0.5, 3, $buffer, $image);
2086
594=item $kernel->set_TYPE ($index, $value) 2087=item $kernel->set_TYPE ($index, $value)
595 2088
2089=item $kernel->set_char ($index, $value)
2090
2091=item $kernel->set_uchar ($index, $value)
2092
2093=item $kernel->set_short ($index, $value)
2094
2095=item $kernel->set_ushort ($index, $value)
2096
2097=item $kernel->set_int ($index, $value)
2098
2099=item $kernel->set_uint ($index, $value)
2100
2101=item $kernel->set_long ($index, $value)
2102
2103=item $kernel->set_ulong ($index, $value)
2104
2105=item $kernel->set_half ($index, $value)
2106
2107=item $kernel->set_float ($index, $value)
2108
2109=item $kernel->set_double ($index, $value)
2110
2111=item $kernel->set_memory ($index, $value)
2112
2113=item $kernel->set_buffer ($index, $value)
2114
2115=item $kernel->set_image ($index, $value)
2116
2117=item $kernel->set_sampler ($index, $value)
2118
2119=item $kernel->set_local ($index, $value)
2120
2121=item $kernel->set_event ($index, $value)
2122
596This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>. 2123This is a family of methods to set the kernel argument with the number
597 2124C<$index> to the give C<$value>.
598TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>,
599C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>,
600C<image2d>, C<image3d>, C<sampler> or C<event>.
601 2125
602Chars and integers (including the half type) are specified as integers, 2126Chars and integers (including the half type) are specified as integers,
603float and double as floating point values, memory/buffer/image2d/image3d 2127float and double as floating point values, memory/buffer/image must be
604must be an object of that type or C<undef>, and sampler and event must be 2128an object of that type or C<undef>, local-memory arguments are set by
605objects of that type. 2129specifying the size, and sampler and event must be objects of that type.
2130
2131Note that C<set_memory> works for all memory objects (all types of buffers
2132and images) - the main purpose of the more specific C<set_TYPE> functions
2133is type checking.
2134
2135Setting an argument for a kernel does NOT keep a reference to the object -
2136for example, if you set an argument to some image object, free the image,
2137and call the kernel, you will run into undefined behaviour.
606 2138
607L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html> 2139L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html>
608 2140
609=back 2141=back
610 2142
613This is the superclass for all event objects (including OpenCL::UserEvent 2145This is the superclass for all event objects (including OpenCL::UserEvent
614objects). 2146objects).
615 2147
616=over 4 2148=over 4
617 2149
2150=item $ev->wait
2151
2152Waits for the event to complete.
2153
2154L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>
2155
2156=item $ev->cb ($exec_callback_type, $callback->($event, $event_command_exec_status))
2157
2158Adds a callback to the callback stack for the given event type. There is
2159no way to remove a callback again.
2160
2161L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetEventCallback.html>
2162
618=item $packed_value = $ev->info ($name) 2163=item $packed_value = $ev->info ($name)
619 2164
620See C<< $platform->info >> for details. 2165See C<< $platform->info >> for details.
621 2166
622L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html> 2167L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html>
623 2168
624=item $ev->wait 2169=for gengetinfo begin event
625 2170
626Waits for the event to complete. 2171=item $queue = $event->command_queue
627 2172
2173Calls C<clGetEventInfo> with C<OpenCL::EVENT_COMMAND_QUEUE> and returns the result.
2174
2175=item $command_type = $event->command_type
2176
2177Calls C<clGetEventInfo> with C<OpenCL::EVENT_COMMAND_TYPE> and returns the result.
2178
2179=item $uint = $event->reference_count
2180
2181Calls C<clGetEventInfo> with C<OpenCL::EVENT_REFERENCE_COUNT> and returns the result.
2182
2183=item $uint = $event->command_execution_status
2184
2185Calls C<clGetEventInfo> with C<OpenCL::EVENT_COMMAND_EXECUTION_STATUS> and returns the result.
2186
2187=item $ctx = $event->context
2188
2189Calls C<clGetEventInfo> with C<OpenCL::EVENT_CONTEXT> and returns the result.
2190
2191=for gengetinfo end event
2192
2193=item $packed_value = $ev->profiling_info ($name)
2194
2195See C<< $platform->info >> for details.
2196
2197The reason this method is not called C<info> is that there already is an
2198C<< ->info >> method.
2199
628L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> 2200L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetProfilingInfo.html>
2201
2202=for gengetinfo begin profiling
2203
2204=item $ulong = $event->profiling_command_queued
2205
2206Calls C<clGetEventProfilingInfo> with C<OpenCL::PROFILING_COMMAND_QUEUED> and returns the result.
2207
2208=item $ulong = $event->profiling_command_submit
2209
2210Calls C<clGetEventProfilingInfo> with C<OpenCL::PROFILING_COMMAND_SUBMIT> and returns the result.
2211
2212=item $ulong = $event->profiling_command_start
2213
2214Calls C<clGetEventProfilingInfo> with C<OpenCL::PROFILING_COMMAND_START> and returns the result.
2215
2216=item $ulong = $event->profiling_command_end
2217
2218Calls C<clGetEventProfilingInfo> with C<OpenCL::PROFILING_COMMAND_END> and returns the result.
2219
2220=for gengetinfo end profiling
629 2221
630=back 2222=back
631 2223
632=head2 THE OpenCL::UserEvent CLASS 2224=head2 THE OpenCL::UserEvent CLASS
633 2225
635 2227
636=over 4 2228=over 4
637 2229
638=item $ev->set_status ($execution_status) 2230=item $ev->set_status ($execution_status)
639 2231
2232Sets the execution status of the user event. Can only be called once,
2233either with OpenCL::COMPLETE or a negative number as status.
2234
2235execution_status: OpenCL::COMPLETE or a negative integer.
2236
640L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html> 2237L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html>
641 2238
642=back 2239=back
643 2240
2241=head2 THE OpenCL::Mapped CLASS
2242
2243This class represents objects mapped into host memory. They are
2244represented by a blessed string scalar. The string data is the mapped
2245memory area, that is, if you read or write it, then the mapped object is
2246accessed directly.
2247
2248You must only ever use operations that modify the string in-place - for
2249example, a C<substr> that doesn't change the length, or maybe a regex that
2250doesn't change the length. Any other operation might cause the data to be
2251copied.
2252
2253When the object is destroyed it will enqueue an implicit unmap operation
2254on the queue that was used to create it.
2255
2256Keep in mind that you I<need> to unmap (or destroy) mapped objects before
2257OpenCL sees the changes, even if some implementations don't need this
2258sometimes.
2259
2260Example, replace the first two floats in the mapped buffer by 1 and 2.
2261
2262 my $mapped = $queue->map_buffer ($buf, ...
2263 $mapped->event->wait; # make sure it's there
2264
2265 # now replace first 8 bytes by new data, which is exactly 8 bytes long
2266 # we blindly assume device endianness to equal host endianness
2267 # (and of course, we assume iee 754 single precision floats :)
2268 substr $$mapped, 0, 8, pack "f*", 1, 2;
2269
2270=over 4
2271
2272=item $ev = $mapped->unmap ($wait_events...)
2273
2274Unmaps the mapped memory object, using the queue originally used to create
2275it, quite similarly to C<< $queue->unmap ($mapped, ...) >>.
2276
2277=item $bool = $mapped->mapped
2278
2279Returns whether the object is still mapped - true before an C<unmap> is
2280enqueued, false afterwards.
2281
2282=item $ev = $mapped->event
2283
2284Return the event object associated with the mapped object. Initially, this
2285will be the event object created when mapping the object, and after an
2286unmap, this will be the event object that the unmap operation created.
2287
2288=item $mapped->wait
2289
2290Same as C<< $mapped->event->wait >> - makes sure no operations on this
2291mapped object are outstanding.
2292
2293=item $bytes = $mapped->size
2294
2295Returns the size of the mapped area, in bytes. Same as C<length $$mapped>.
2296
2297=item $ptr = $mapped->ptr
2298
2299Returns the raw memory address of the mapped area.
2300
2301=item $mapped->set ($offset, $data)
2302
2303Replaces the data at the given C<$offset> in the memory area by the new
2304C<$data>. This method is safer than direct manipulation of C<$mapped>
2305because it does bounds-checking, but also slower.
2306
2307=item $data = $mapped->get ($offset, $length)
2308
2309Returns (without copying) a scalar representing the data at the given
2310C<$offset> and C<$length> in the mapped memory area. This is the same as
2311the following substr, except much slower;
2312
2313 $data = substr $$mapped, $offset, $length
2314
644=cut 2315=cut
645 2316
646package OpenCL; 2317sub OpenCL::Mapped::get {
647 2318 substr ${$_[0]}, $_[1], $_[2]
648use common::sense;
649
650BEGIN {
651 our $VERSION = '0.14';
652
653 require XSLoader;
654 XSLoader::load (__PACKAGE__, $VERSION);
655
656 @OpenCL::Buffer::ISA =
657 @OpenCL::Image::ISA = OpenCL::Memory::;
658
659 @OpenCL::Image2D::ISA =
660 @OpenCL::Image3D::ISA = OpenCL::Image::;
661
662 @OpenCL::UserEvent::ISA = OpenCL::Event::;
663} 2319}
2320
2321=back
2322
2323=head2 THE OpenCL::MappedBuffer CLASS
2324
2325This is a subclass of OpenCL::Mapped, representing mapped buffers.
2326
2327=head2 THE OpenCL::MappedImage CLASS
2328
2329This is a subclass of OpenCL::Mapped, representing mapped images.
2330
2331=over 4
2332
2333=item $bytes = $mapped->row_pitch
2334
2335=item $bytes = $mapped->slice_pitch
2336
2337Return the row or slice pitch of the image that has been mapped.
2338
2339=back
2340
2341
2342=cut
664 2343
6651; 23441;
666 2345
667=head1 AUTHOR 2346=head1 AUTHOR
668 2347

Diff Legend

Removed lines
+ Added lines
< Changed lines
> Changed lines