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

Comparing OpenCL/OpenCL.pm (file contents):
Revision 1.10 by root, Thu Nov 17 02:10:39 2011 UTC vs.
Revision 1.61 by root, Sat Apr 28 13:31:40 2012 UTC

18vendors) - usually there is only one. 18vendors) - usually there is only one.
19 19
20Each platform gives you access to a number of OpenCL::Device objects, e.g. 20Each platform gives you access to a number of OpenCL::Device objects, e.g.
21your graphics card. 21your graphics card.
22 22
23From a platform and some devices, you create an OpenCL::Context, which is 23From a platform and some device(s), you create an OpenCL::Context, which is
24a very central object in OpenCL: Once you have a context you can create 24a very central object in OpenCL: Once you have a context you can create
25most other objects: 25most other objects:
26 26
27OpenCL::Program objects, which store source code and, after building 27OpenCL::Program objects, which store source code and, after building for a
28("compiling and linking"), also binary programs. For each kernel function 28specific device ("compiling and linking"), also binary programs. For each
29in a program you can then create an OpenCL::Kernel object which represents 29kernel function in a program you can then create an OpenCL::Kernel object
30basically 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:
49no implementation was available to me :).
50 49
51 http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf 50 http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf
51 http://www.khronos.org/registry/cl/specs/opencl-1.2.pdf
52 http://www.khronos.org/registry/cl/specs/opencl-1.2-extensions.pdf
52 53
53OpenCL manpages: 54OpenCL manpages:
54 55
55 http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/ 56 http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/
57 http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/
58
59If you are into UML class diagrams, the following diagram might help - if
60not, it will be mildly confusing (also, the class hierarchy of this module
61is much more fine-grained):
62
63 http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/classDiagram.html
64
65Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it
66is, but at least it's free of charge:
67
68 http://developer.amd.com/zones/OpenCLZone/courses/Documents/Introduction_to_OpenCL_Programming%20Training_Guide%20%28201005%29.pdf
69
70And here's NVIDIA's OpenCL Best Practises Guide:
71
72 http://developer.download.nvidia.com/compute/cuda/3_2/toolkit/docs/OpenCL_Best_Practices_Guide.pdf
56 73
57=head1 BASIC WORKFLOW 74=head1 BASIC WORKFLOW
58 75
59To get something done, you basically have to do this once: 76To get something done, you basically have to do this once (refer to the
77examples below for actual code, this is just a high-level description):
60 78
61Find some platform (e.g. the first one) and some device (e.g. the first 79Find some platform (e.g. the first one) and some device(s) (e.g. the first
62device you can find), and create a context from those. 80device of the platform), and create a context from those.
63 81
64Create a command queue from your context, and program objects from your 82Create program objects from your OpenCL source code, then build (compile)
65OpenCL source code, build the programs. 83the programs for each device you want to run them on.
66 84
67Create kernel objects for all kernels you want to use. 85Create kernel objects for all kernels you want to use (surprisingly, these
86are not device-specific).
68 87
69Then, to execute stuff, you repeat this: 88Then, to execute stuff, you repeat these steps, possibly resuing or
89sharing some buffers:
70 90
71Create some input and output buffers from your context. Initialise the 91Create some input and output buffers from your context. Set these as
72input buffers with data. Set these as arguments to your kernel. 92arguments to your kernel.
93
94Enqueue buffer writes to initialise your input buffers (when not
95initialised at creation time).
73 96
74Enqueue the kernel execution. 97Enqueue the kernel execution.
75 98
76Enqueue buffer reads for your output buffer to read results. 99Enqueue buffer reads for your output buffer to read results.
77 100
78The next section shows how this can be done.
79
80=head1 EXAMPLES 101=head1 EXAMPLES
81 102
82=head2 Enumerate all devices and get contexts for them. 103=head2 Enumerate all devices and get contexts for them.
83 104
105Best run this once to get a feel for the platforms and devices in your
106system.
107
84 for my $platform (OpenCL::platforms) { 108 for my $platform (OpenCL::platforms) {
85 printf "platform: %s\n", $platform->info (OpenCL::PLATFORM_NAME); 109 printf "platform: %s\n", $platform->name;
86 printf "extensions: %s\n", $platform->info (OpenCL::PLATFORM_EXTENSIONS); 110 printf "extensions: %s\n", $platform->extensions;
87 for my $device ($platform->devices) { 111 for my $device ($platform->devices) {
88 printf "+ device: %s\n", $device->info (OpenCL::DEVICE_NAME); 112 printf "+ device: %s\n", $device->name;
89 my $ctx = $device->context; 113 my $ctx = $platform->context (undef, [$device]);
90 # do stuff 114 # do stuff
91 } 115 }
92 } 116 }
93 117
94=head2 Get a useful context and a command queue. 118=head2 Get a useful context and a command queue.
95 119
96 my $dev = ((OpenCL::platforms)[0]->devices)[0]; 120This is a useful boilerplate for any OpenCL program that only wants to use
97 my $ctx = $dev->context; 121one device,
98 my $queue = $ctx->queue ($dev); 122
123 my ($platform) = OpenCL::platforms; # find first platform
124 my ($dev) = $platform->devices; # find first device of platform
125 my $ctx = $platform->context (undef, [$dev]); # create context out of those
126 my $queue = $ctx->queue ($dev); # create a command queue for the device
99 127
100=head2 Print all supported image formats of a context. 128=head2 Print all supported image formats of a context.
129
130Best run this once for your context, to see whats available and how to
131gather information.
101 132
102 for my $type (OpenCL::MEM_OBJECT_IMAGE2D, OpenCL::MEM_OBJECT_IMAGE3D) { 133 for my $type (OpenCL::MEM_OBJECT_IMAGE2D, OpenCL::MEM_OBJECT_IMAGE3D) {
103 print "supported image formats for ", OpenCL::enum2str $type, "\n"; 134 print "supported image formats for ", OpenCL::enum2str $type, "\n";
104 135
105 for my $f ($ctx->supported_image_formats (0, $type)) { 136 for my $f ($ctx->supported_image_formats (0, $type)) {
110=head2 Create a buffer with some predefined data, read it back synchronously, 141=head2 Create a buffer with some predefined data, read it back synchronously,
111then asynchronously. 142then asynchronously.
112 143
113 my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); 144 my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut");
114 145
115 $queue->enqueue_read_buffer ($buf, 1, 1, 3, my $data); 146 $queue->read_buffer ($buf, 1, 1, 3, my $data);
116 print "$data\n"; 147 print "$data\n";
117 148
118 my $ev = $queue->enqueue_read_buffer ($buf, 0, 1, 3, my $data); 149 my $ev = $queue->read_buffer ($buf, 0, 1, 3, my $data);
119 $ev->wait; 150 $ev->wait;
120 print "$data\n"; # prints "elm" 151 print "$data\n"; # prints "elm"
121 152
122=head2 Create and build a program, then create a kernel out of one of its 153=head2 Create and build a program, then create a kernel out of one of its
123functions. 154functions.
124 155
125 my $src = ' 156 my $src = '
126 __kernel void 157 kernel void
127 squareit (__global float *input, __global float *output) 158 squareit (global float *input, global float *output)
128 { 159 {
129 size_t id = get_global_id (0); 160 $id = get_global_id (0);
130 output [id] = input [id] * input [id]; 161 output [id] = input [id] * input [id];
131 } 162 }
132 '; 163 ';
133 164
134 my $prog = $ctx->program_with_source ($src); 165 my $prog = $ctx->build_program ($src);
135
136 eval { $prog->build ($dev); 1 }
137 or die $prog->build_info ($dev, OpenCL::PROGRAM_BUILD_LOG);
138
139 my $kernel = $prog->kernel ("squareit"); 166 my $kernel = $prog->kernel ("squareit");
140 167
141=head2 Create some input and output float buffers, then call squareit on them. 168=head2 Create some input and output float buffers, then call the
169'squareit' kernel on them.
142 170
143 my $input = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, pack "f*", 1, 2, 3, 4.5); 171 my $input = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, pack "f*", 1, 2, 3, 4.5);
144 my $output = $ctx->buffer (0, OpenCL::SIZEOF_FLOAT * 5); 172 my $output = $ctx->buffer (0, OpenCL::SIZEOF_FLOAT * 5);
145 173
146 # set buffer 174 # set buffer
147 $kernel->set_buffer (0, $input); 175 $kernel->set_buffer (0, $input);
148 $kernel->set_buffer (1, $output); 176 $kernel->set_buffer (1, $output);
149 177
150 # execute it for all 4 numbers 178 # execute it for all 4 numbers
151 $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); 179 $queue->nd_range_kernel ($kernel, undef, [4], undef);
152 180
153 # enqueue a synchronous read 181 # enqueue a synchronous read
154 $queue->enqueue_read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); 182 $queue->read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data);
155 183
156 # print the results: 184 # print the results:
157 printf "%s\n", join ", ", unpack "f*", $data; 185 printf "%s\n", join ", ", unpack "f*", $data;
158 186
159=head2 The same enqueue operations as before, but assuming an out-of-order queue, 187=head2 The same enqueue operations as before, but assuming an out-of-order queue,
160showing off barriers. 188showing off barriers.
161 189
162 # execute it for all 4 numbers 190 # execute it for all 4 numbers
163 $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); 191 $queue->nd_range_kernel ($kernel, undef, [4], undef);
164 192
165 # enqueue a barrier to ensure in-order execution 193 # enqueue a barrier to ensure in-order execution
166 $queue->enqueue_barrier; 194 $queue->barrier;
167 195
168 # enqueue an async read 196 # enqueue an async read
169 $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); 197 $queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data);
170 198
171 # wait for all requests to finish 199 # wait for all requests to finish
172 $queue->finish; 200 $queue->finish;
173 201
174=head2 The same enqueue operations as before, but assuming an out-of-order queue, 202=head2 The same enqueue operations as before, but assuming an out-of-order queue,
175showing off event objects and wait lists. 203showing off event objects and wait lists.
176 204
177 # execute it for all 4 numbers 205 # execute it for all 4 numbers
178 my $ev = $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); 206 my $ev = $queue->nd_range_kernel ($kernel, undef, [4], undef);
179 207
180 # enqueue an async read 208 # enqueue an async read
181 $ev = $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev); 209 $ev = $queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev);
182 210
183 # wait for the last event to complete 211 # wait for the last event to complete
184 $ev->wait; 212 $ev->wait;
185 213
214=head2 Use the OpenGL module to share a texture between OpenCL and OpenGL and draw some julia
215set tunnel effect.
216
217This is quite a long example to get you going.
218
219 use OpenGL ":all";
220 use OpenCL;
221
222 # open a window and create a gl texture
223 OpenGL::glpOpenWindow width => 256, height => 256;
224 my $texid = glGenTextures_p 1;
225 glBindTexture GL_TEXTURE_2D, $texid;
226 glTexImage2D_c GL_TEXTURE_2D, 0, GL_RGBA8, 256, 256, 0, GL_RGBA, GL_UNSIGNED_BYTE, 0;
227
228 # find and use the first opencl device that let's us get a shared opengl context
229 my $platform;
230 my $dev;
231 my $ctx;
232
233 for (OpenCL::platforms) {
234 $platform = $_;
235 for ($platform->devices) {
236 $dev = $_;
237 $ctx = $platform->context ([OpenCL::GLX_DISPLAY_KHR, undef, OpenCL::GL_CONTEXT_KHR, undef], [$dev])
238 and last;
239 }
240 }
241
242 $ctx
243 or die "cannot find suitable OpenCL device\n";
244
245 my $queue = $ctx->queue ($dev);
246
247 # now attach an opencl image2d object to the opengl texture
248 my $tex = $ctx->gl_texture2d (OpenCL::MEM_WRITE_ONLY, GL_TEXTURE_2D, 0, $texid);
249
250 # now the boring opencl code
251 my $src = <<EOF;
252 kernel void
253 juliatunnel (write_only image2d_t img, float time)
254 {
255 float2 p = (float2)(get_global_id (0), get_global_id (1)) / 256.f * 2.f - 1.f;
256
257 float2 m = (float2)(1.f, p.y) / fabs (p.x);
258 m.x = fabs (fmod (m.x + time * 0.05f, 4.f)) - 2.f;
259
260 float2 z = m;
261 float2 c = (float2)(sin (time * 0.05005), cos (time * 0.06001));
262
263 for (int i = 0; i < 25 && dot (z, z) < 4.f; ++i)
264 z = (float2)(z.x * z.x - z.y * z.y, 2.f * z.x * z.y) + c;
265
266 float3 colour = (float3)(z.x, z.y, z.x * z.y);
267 write_imagef (img, (int2)(get_global_id (0), get_global_id (1)), (float4)(colour * p.x * p.x, 1.));
268 }
269 EOF
270
271 my $prog = $ctx->build_program ($src);
272 my $kernel = $prog->kernel ("juliatunnel");
273
274 # program compiled, kernel ready, now draw and loop
275
276 for (my $time; ; ++$time) {
277 # acquire objects from opengl
278 $queue->acquire_gl_objects ([$tex]);
279
280 # configure and run our kernel
281 $kernel->set_image2d (0, $tex);
282 $kernel->set_float (1, $time);
283 $queue->nd_range_kernel ($kernel, undef, [256, 256], undef);
284
285 # release objects to opengl again
286 $queue->release_gl_objects ([$tex]);
287
288 # wait
289 $queue->finish;
290
291 # now draw the texture, the defaults should be all right
292 glTexParameterf GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST;
293
294 glEnable GL_TEXTURE_2D;
295 glBegin GL_QUADS;
296 glTexCoord2f 0, 1; glVertex3i -1, -1, -1;
297 glTexCoord2f 0, 0; glVertex3i 1, -1, -1;
298 glTexCoord2f 1, 0; glVertex3i 1, 1, -1;
299 glTexCoord2f 1, 1; glVertex3i -1, 1, -1;
300 glEnd;
301
302 glXSwapBuffers;
303
304 select undef, undef, undef, 1/60;
305 }
306
186=head1 DOCUMENTATION 307=head1 DOCUMENTATION
187 308
188=head2 BASIC CONVENTIONS 309=head2 BASIC CONVENTIONS
189 310
190This is not a 1:1 C-style translation of OpenCL to Perl - instead I 311This is not a one-to-one C-style translation of OpenCL to Perl - instead
191attempted to make the interface as type-safe as possible and introducing 312I attempted to make the interface as type-safe as possible by introducing
192object syntax where it makes sense. There are a number of important 313object syntax where it makes sense. There are a number of important
193differences between the OpenCL C API and this module: 314differences between the OpenCL C API and this module:
194 315
195=over 4 316=over 4
196 317
197=item * Object lifetime managament is automatic - there is no need 318=item * Object lifetime managament is automatic - there is no need
198to free objects explicitly (C<clReleaseXXX>), the release function 319to free objects explicitly (C<clReleaseXXX>), the release function
199is called automatically once all Perl references to it go away. 320is called automatically once all Perl references to it go away.
200 321
201=item * OpenCL uses CamelCase for function names (C<clGetPlatformInfo>), 322=item * OpenCL uses CamelCase for function names
323(e.g. C<clGetPlatformIDs>, C<clGetPlatformInfo>), while this module
202while this module uses underscores as word separator and often leaves out 324uses underscores as word separator and often leaves out prefixes
203prefixes (C<< $platform->info >>). 325(C<OpenCL::platforms>, C<< $platform->info >>).
204 326
205=item * OpenCL often specifies fixed vector function arguments as short 327=item * OpenCL often specifies fixed vector function arguments as short
206arrays (C<size_t origin[3]>), while this module explicitly expects the 328arrays (C<size_t origin[3]>), while this module explicitly expects the
207components as separate arguments- 329components as separate arguments (C<$orig_x, $orig_y, $orig_z>) in
330function calls.
208 331
209=item * Where possible, one of the pitch values is calculated from the 332=item * Structures are often specified by flattening out their components
210perl scalar length and need not be specified. 333as with short vectors, and returned as arrayrefs.
211 334
212=item * When enqueuing commands, the wait list is specified by adding 335=item * When enqueuing commands, the wait list is specified by adding
213extra arguments to the function - anywhere a C<$wait_events...> argument 336extra arguments to the function - anywhere a C<$wait_events...> argument
214is documented this can be any number of event objects. 337is documented this can be any number of event objects. As an extsnion
338implemented by this module, C<undef> values will be ignored in the event
339list.
215 340
216=item * When enqueuing commands, if the enqueue method is called in void 341=item * When enqueuing commands, if the enqueue method is called in void
217context, no event is created. In all other contexts an event is returned 342context, no event is created. In all other contexts an event is returned
218by the method. 343by the method.
219 344
239 ulong IV - Q 364 ulong IV - Q
240 float NV float f 365 float NV float f
241 half IV ushort S 366 half IV ushort S
242 double NV double d 367 double NV double d
243 368
369=head2 GLX SUPPORT
370
371Due to the sad state that OpenGL support is in in Perl (mostly the OpenGL
372module, which has little to no documentation and has little to no support
373for glX), this module, as a special extension, treats context creation
374properties C<OpenCL::GLX_DISPLAY_KHR> and C<OpenCL::GL_CONTEXT_KHR>
375specially: If either or both of these are C<undef>, then the OpenCL
376module tries to dynamically resolve C<glXGetCurrentDisplay> and
377C<glXGetCurrentContext>, call these functions and use their return values
378instead.
379
380For this to work, the OpenGL library must be loaded, a GLX context must
381have been created and be made current, and C<dlsym> must be available and
382capable of finding the function via C<RTLD_DEFAULT>.
383
384=head2 EVENT SYSTEM
385
386OpenCL can generate a number of (potentially) asynchronous events, for
387example, after compiling a program, to signal a context-related error or,
388perhaps most important, to signal completion of queued jobs (by setting
389callbacks on OpenCL::Event objects).
390
391To facilitate this, this module maintains an event queue - each
392time an asynchronous event happens, it is queued, and perl will be
393interrupted. This is implemented via the L<Async::Interrupt> module. In
394addition, this module has L<AnyEvent> support, so it can seamlessly
395integrate itself into many event loops.
396
397Since this module is a bit hard to understand, here are some case examples:
398
399=head3 Don't use callbacks.
400
401When your program never uses any callbacks, then there will never be any
402notifications you need to take care of, and therefore no need to worry
403about all this.
404
405You can achieve a great deal by explicitly waiting for events, or using
406barriers and flush calls. In many programs, there is no need at all to
407tinker with asynchronous events.
408
409=head3 Use AnyEvent
410
411This module automatically registers a watcher that invokes all outstanding
412event callbacks when AnyEvent is initialised (and block asynchronous
413interruptions). Using this mode of operations is the safest and most
414recommended one.
415
416To use this, simply use AnyEvent and this module normally, make sure you
417have an event loop running:
418
419 use Gtk2 -init;
420 use AnyEvent;
421
422 # initialise AnyEvent, by creating a watcher, or:
423 AnyEvent::detect;
424
425 my $e = $queue->marker;
426 $e->cb (sub {
427 warn "opencl is finished\n";
428 })
429
430 main Gtk2;
431
432Note that this module will not initialise AnyEvent for you. Before
433AnyEvent is initialised, the module will asynchronously interrupt perl
434instead. To avoid any surprises, it's best to explicitly initialise
435AnyEvent.
436
437You can temporarily enable asynchronous interruptions (see next paragraph)
438by calling C<$OpenCL::INTERRUPT->unblock> and disable them again by
439calling C<$OpenCL::INTERRUPT->block>.
440
441=head3 Let yourself be interrupted at any time
442
443This mode is the default unless AnyEvent is loaded and initialised. In
444this mode, OpenCL asynchronously interrupts a running perl program. The
445emphasis is on both I<asynchronously> and I<running> here.
446
447Asynchronously means that perl might execute your callbacks at any
448time. For example, in the following code (I<THAT YOU SHOULD NOT COPY>),
449the C<until> loop following the marker call will be interrupted by the
450callback:
451
452 my $e = $queue->marker;
453 my $flag;
454 $e->cb (sub { $flag = 1 });
455 1 until $flag;
456 # $flag is now 1
457
458The reason why you shouldn't blindly copy the above code is that
459busy waiting is a really really bad thing, and really really bad for
460performance.
461
462While at first this asynchronous business might look exciting, it can be
463really hard, because you need to be prepared for the callback code to be
464executed at any time, which limits the amount of things the callback code
465can do safely.
466
467This can be mitigated somewhat by using C<<
468$OpenCL::INTERRUPT->scope_block >> (see the L<Async::Interrupt>
469documentation for details).
470
471The other problem is that your program must be actively I<running> to be
472interrupted. When you calculate stuff, your program is running. When you
473hang in some C functions or other block execution (by calling C<sleep>,
474C<select>, running an event loop and so on), your program is waiting, not
475running.
476
477One way around that would be to attach a read watcher to your event loop,
478listening for events on C<< $OpenCL::INTERRUPT->pipe_fileno >>, using a
479dummy callback (C<sub { }>) to temporarily execute some perl code.
480
481That is then awfully close to using the built-in AnyEvent support above,
482though, so consider that one instead.
483
484=head3 Be creative
485
486OpenCL exports the L<Async::Interrupt> object it uses in the global
487variable C<$OpenCL::INTERRUPT>. You can configure it in any way you like.
488
489So if you want to feel like a real pro, err, wait, if you feel no risk
490menas no fun, you can experiment by implementing your own mode of
491operations.
492
493=cut
494
495package OpenCL;
496
497use common::sense;
498use Async::Interrupt ();
499
500our $POLL_FUNC; # set by XS
501
502BEGIN {
503 our $VERSION = '0.97';
504
505 require XSLoader;
506 XSLoader::load (__PACKAGE__, $VERSION);
507
508 @OpenCL::Platform::ISA =
509 @OpenCL::Device::ISA =
510 @OpenCL::Context::ISA =
511 @OpenCL::Queue::ISA =
512 @OpenCL::Memory::ISA =
513 @OpenCL::Sampler::ISA =
514 @OpenCL::Program::ISA =
515 @OpenCL::Kernel::ISA =
516 @OpenCL::Event::ISA = OpenCL::Object::;
517
518 @OpenCL::Buffer::ISA =
519 @OpenCL::Image::ISA = OpenCL::Memory::;
520
521 @OpenCL::BufferObj::ISA = OpenCL::Buffer::;
522
523 @OpenCL::Image2D::ISA =
524 @OpenCL::Image3D::ISA =
525 @OpenCL::Image2DArray::ISA =
526 @OpenCL::Image1D::ISA =
527 @OpenCL::Image1DArray::ISA =
528 @OpenCL::Image1DBuffer::ISA = OpenCL::Image::;
529
530 @OpenCL::UserEvent::ISA = OpenCL::Event::;
531}
532
244=head2 THE OpenCL PACKAGE 533=head2 THE OpenCL PACKAGE
245 534
246=over 4 535=over 4
247 536
248=item $int = OpenCL::errno 537=item $int = OpenCL::errno
249 538
250The last error returned by a function - it's only changed on errors. 539The last error returned by a function - it's only valid after an error occured
540and before calling another OpenCL function.
251 541
252=item $str = OpenCL::err2str $errval 542=item $str = OpenCL::err2str [$errval]
253 543
254Comverts an error value into a human readable string. 544Converts an error value into a human readable string. IF no error value is
545given, then the last error will be used (as returned by OpenCL::errno).
255 546
256=item $str = OpenCL::enum2str $enum 547=item $str = OpenCL::enum2str $enum
257 548
258Converts most enum values (inof parameter names, image format constants, 549Converts most enum values (of parameter names, image format constants,
259object types, addressing and filter modes, command types etc.) into a 550object types, addressing and filter modes, command types etc.) into a
260human readbale string. When confronted with some random integer it can be 551human readable string. When confronted with some random integer it can be
261very helpful to pass it through this function to maybe get some readable 552very helpful to pass it through this function to maybe get some readable
262string out of it. 553string out of it.
263 554
264=item @platforms = OpenCL::platforms 555=item @platforms = OpenCL::platforms
265 556
266Returns all available OpenCL::Platform objects. 557Returns all available OpenCL::Platform objects.
267 558
268L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html> 559L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html>
269 560
270=item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef 561=item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr
271 562
272Tries to create a context from a default device and platform - never worked for me. 563Tries to create a context from a default device and platform type - never worked for me.
273 564
274L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> 565L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>
275 566
567=item $ctx = OpenCL::context $properties, \@devices, $callback->($err, $pvt) = $print_stderr)
568
569Create a new OpenCL::Context object using the given device object(s). This
570function isn't implemented yet, use C<< $platform->context >> instead.
571
572L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>
573
276=item OpenCL::wait_for_events $wait_events... 574=item OpenCL::wait_for_events $wait_events...
277 575
278Waits for all events to complete. 576Waits for all events to complete.
279 577
280L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> 578L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>
281 579
580=item OpenCL::poll
581
582Checks if there are any outstanding events (see L<EVENT SYSTEM>) and
583invokes their callbacks.
584
585=item $OpenCL::INTERRUPT
586
587The L<Async::Interrupt> object used to signal asynchronous events (see
588L<EVENT SYSTEM>).
589
590=cut
591
592our $INTERRUPT = new Async::Interrupt c_cb => [$POLL_FUNC, 0];
593
594&_eq_initialise ($INTERRUPT->signal_func);
595
596=item $OpenCL::WATCHER
597
598The L<AnyEvent> watcher object used to watch for asynchronous events (see
599L<EVENT SYSTEM>). This variable is C<undef> until L<AnyEvent> has been
600loaded I<and> initialised (e.g. by calling C<AnyEvent::detect>).
601
602=cut
603
604our $WATCHER;
605
606sub _init_anyevent {
607 $INTERRUPT->block;
608 $WATCHER = AE::io ($INTERRUPT->pipe_fileno, 0, sub { $INTERRUPT->handle });
609}
610
611if (defined $AnyEvent::MODEL) {
612 _init_anyevent;
613} else {
614 push @AnyEvent::post_detect, \&_init_anyevent;
615}
616
282=back 617=back
283 618
619=head2 THE OpenCL::Object CLASS
620
621This is the base class for all objects in the OpenCL module. The only
622method it implements is the C<id> method, which is only useful if you want
623to interface to OpenCL on the C level.
624
625=over 4
626
627=item $iv = $obj->id
628
629OpenCL objects are represented by pointers or integers on the C level. If
630you want to interface to an OpenCL object directly on the C level, then
631you need this value, which is returned by this method. You should use an
632C<IV> type in your code and cast that to the correct type.
633
634=cut
635
636sub OpenCL::Object::id {
637 ref $_[0] eq "SCALAR"
638 ? ${ $_[0] }
639 : $_[0][0]
640}
641
642=back
643
284=head2 THE OpenCL::Platform CLASS 644=head2 THE OpenCL::Platform CLASS
285 645
286=over 4 646=over 4
287 647
648=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL)
649
650Returns a list of matching OpenCL::Device objects.
651
652=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr)
653
654Tries to create a context. Never worked for me, and you need devices explicitly anyway.
655
656L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html>
657
658=item $ctx = $platform->context ($properties, \@devices, $callback->($err, $pvt) = $print_stderr)
659
660Create a new OpenCL::Context object using the given device object(s)- a
661CL_CONTEXT_PLATFORM property is supplied automatically.
662
663L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html>
664
288=item $packed_value = $platform->info ($name) 665=item $packed_value = $platform->info ($name)
289 666
290Calls C<clGetPlatformInfo> and returns the packed, raw value - for 667Calls C<clGetPlatformInfo> and returns the packed, raw value - for
291strings, this will be the string, for other values you probably need to 668strings, this will be the string (possibly including terminating \0), for
292use the correct C<unpack>. This might get improved in the future. Hopefully. 669other values you probably need to use the correct C<unpack>.
670
671It's best to avoid this method and use one of the following convenience
672wrappers.
293 673
294L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html> 674L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html>
295 675
296=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL) 676=item $platform->unload_compiler
297 677
298Returns a list of matching OpenCL::Device objects. 678Attempts to unload the compiler for this platform, for endless
679profit. Does nothing on OpenCL 1.1.
299 680
300=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef)
301
302Tries to create a context. Never worked for me.
303
304L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> 681L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clUnloadPlatformCompiler.html>
682
683=for gengetinfo begin platform
684
685=item $string = $platform->profile
686
687Calls C<clGetPlatformInfo> with C<CL_PLATFORM_PROFILE> and returns the result.
688
689=item $string = $platform->version
690
691Calls C<clGetPlatformInfo> with C<CL_PLATFORM_VERSION> and returns the result.
692
693=item $string = $platform->name
694
695Calls C<clGetPlatformInfo> with C<CL_PLATFORM_NAME> and returns the result.
696
697=item $string = $platform->vendor
698
699Calls C<clGetPlatformInfo> with C<CL_PLATFORM_VENDOR> and returns the result.
700
701=item $string = $platform->extensions
702
703Calls C<clGetPlatformInfo> with C<CL_PLATFORM_EXTENSIONS> and returns the result.
704
705=for gengetinfo end platform
305 706
306=back 707=back
307 708
308=head2 THE OpenCL::Device CLASS 709=head2 THE OpenCL::Device CLASS
309 710
313 714
314See C<< $platform->info >> for details. 715See C<< $platform->info >> for details.
315 716
316L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetDeviceInfo.html> 717L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetDeviceInfo.html>
317 718
318=item $ctx = $device->context ($properties = undef, $notify = undef) 719=for gengetinfo begin device
319 720
320Create a new OpenCL::Context object. 721=item $device_type = $device->type
321 722
322L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> 723Calls C<clGetDeviceInfo> with C<CL_DEVICE_TYPE> and returns the result.
724
725=item $uint = $device->vendor_id
726
727Calls C<clGetDeviceInfo> with C<CL_DEVICE_VENDOR_ID> and returns the result.
728
729=item $uint = $device->max_compute_units
730
731Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_COMPUTE_UNITS> and returns the result.
732
733=item $uint = $device->max_work_item_dimensions
734
735Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS> and returns the result.
736
737=item $int = $device->max_work_group_size
738
739Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_WORK_GROUP_SIZE> and returns the result.
740
741=item @ints = $device->max_work_item_sizes
742
743Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_WORK_ITEM_SIZES> and returns the result.
744
745=item $uint = $device->preferred_vector_width_char
746
747Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_CHAR> and returns the result.
748
749=item $uint = $device->preferred_vector_width_short
750
751Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_SHORT> and returns the result.
752
753=item $uint = $device->preferred_vector_width_int
754
755Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_INT> and returns the result.
756
757=item $uint = $device->preferred_vector_width_long
758
759Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_LONG> and returns the result.
760
761=item $uint = $device->preferred_vector_width_float
762
763Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_FLOAT> and returns the result.
764
765=item $uint = $device->preferred_vector_width_double
766
767Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_DOUBLE> and returns the result.
768
769=item $uint = $device->max_clock_frequency
770
771Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_CLOCK_FREQUENCY> and returns the result.
772
773=item $bitfield = $device->address_bits
774
775Calls C<clGetDeviceInfo> with C<CL_DEVICE_ADDRESS_BITS> and returns the result.
776
777=item $uint = $device->max_read_image_args
778
779Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_READ_IMAGE_ARGS> and returns the result.
780
781=item $uint = $device->max_write_image_args
782
783Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_WRITE_IMAGE_ARGS> and returns the result.
784
785=item $ulong = $device->max_mem_alloc_size
786
787Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_MEM_ALLOC_SIZE> and returns the result.
788
789=item $int = $device->image2d_max_width
790
791Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE2D_MAX_WIDTH> and returns the result.
792
793=item $int = $device->image2d_max_height
794
795Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE2D_MAX_HEIGHT> and returns the result.
796
797=item $int = $device->image3d_max_width
798
799Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE3D_MAX_WIDTH> and returns the result.
800
801=item $int = $device->image3d_max_height
802
803Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE3D_MAX_HEIGHT> and returns the result.
804
805=item $int = $device->image3d_max_depth
806
807Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE3D_MAX_DEPTH> and returns the result.
808
809=item $uint = $device->image_support
810
811Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE_SUPPORT> and returns the result.
812
813=item $int = $device->max_parameter_size
814
815Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_PARAMETER_SIZE> and returns the result.
816
817=item $uint = $device->max_samplers
818
819Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_SAMPLERS> and returns the result.
820
821=item $uint = $device->mem_base_addr_align
822
823Calls C<clGetDeviceInfo> with C<CL_DEVICE_MEM_BASE_ADDR_ALIGN> and returns the result.
824
825=item $uint = $device->min_data_type_align_size
826
827Calls C<clGetDeviceInfo> with C<CL_DEVICE_MIN_DATA_TYPE_ALIGN_SIZE> and returns the result.
828
829=item $device_fp_config = $device->single_fp_config
830
831Calls C<clGetDeviceInfo> with C<CL_DEVICE_SINGLE_FP_CONFIG> and returns the result.
832
833=item $device_mem_cache_type = $device->global_mem_cache_type
834
835Calls C<clGetDeviceInfo> with C<CL_DEVICE_GLOBAL_MEM_CACHE_TYPE> and returns the result.
836
837=item $uint = $device->global_mem_cacheline_size
838
839Calls C<clGetDeviceInfo> with C<CL_DEVICE_GLOBAL_MEM_CACHELINE_SIZE> and returns the result.
840
841=item $ulong = $device->global_mem_cache_size
842
843Calls C<clGetDeviceInfo> with C<CL_DEVICE_GLOBAL_MEM_CACHE_SIZE> and returns the result.
844
845=item $ulong = $device->global_mem_size
846
847Calls C<clGetDeviceInfo> with C<CL_DEVICE_GLOBAL_MEM_SIZE> and returns the result.
848
849=item $ulong = $device->max_constant_buffer_size
850
851Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_CONSTANT_BUFFER_SIZE> and returns the result.
852
853=item $uint = $device->max_constant_args
854
855Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_CONSTANT_ARGS> and returns the result.
856
857=item $device_local_mem_type = $device->local_mem_type
858
859Calls C<clGetDeviceInfo> with C<CL_DEVICE_LOCAL_MEM_TYPE> and returns the result.
860
861=item $ulong = $device->local_mem_size
862
863Calls C<clGetDeviceInfo> with C<CL_DEVICE_LOCAL_MEM_SIZE> and returns the result.
864
865=item $boolean = $device->error_correction_support
866
867Calls C<clGetDeviceInfo> with C<CL_DEVICE_ERROR_CORRECTION_SUPPORT> and returns the result.
868
869=item $int = $device->profiling_timer_resolution
870
871Calls C<clGetDeviceInfo> with C<CL_DEVICE_PROFILING_TIMER_RESOLUTION> and returns the result.
872
873=item $boolean = $device->endian_little
874
875Calls C<clGetDeviceInfo> with C<CL_DEVICE_ENDIAN_LITTLE> and returns the result.
876
877=item $boolean = $device->available
878
879Calls C<clGetDeviceInfo> with C<CL_DEVICE_AVAILABLE> and returns the result.
880
881=item $boolean = $device->compiler_available
882
883Calls C<clGetDeviceInfo> with C<CL_DEVICE_COMPILER_AVAILABLE> and returns the result.
884
885=item $device_exec_capabilities = $device->execution_capabilities
886
887Calls C<clGetDeviceInfo> with C<CL_DEVICE_EXECUTION_CAPABILITIES> and returns the result.
888
889=item $command_queue_properties = $device->properties
890
891Calls C<clGetDeviceInfo> with C<CL_DEVICE_QUEUE_PROPERTIES> and returns the result.
892
893=item $ = $device->platform
894
895Calls C<clGetDeviceInfo> with C<CL_DEVICE_PLATFORM> and returns the result.
896
897=item $string = $device->name
898
899Calls C<clGetDeviceInfo> with C<CL_DEVICE_NAME> and returns the result.
900
901=item $string = $device->vendor
902
903Calls C<clGetDeviceInfo> with C<CL_DEVICE_VENDOR> and returns the result.
904
905=item $string = $device->driver_version
906
907Calls C<clGetDeviceInfo> with C<CL_DRIVER_VERSION> and returns the result.
908
909=item $string = $device->profile
910
911Calls C<clGetDeviceInfo> with C<CL_DEVICE_PROFILE> and returns the result.
912
913=item $string = $device->version
914
915Calls C<clGetDeviceInfo> with C<CL_DEVICE_VERSION> and returns the result.
916
917=item $string = $device->extensions
918
919Calls C<clGetDeviceInfo> with C<CL_DEVICE_EXTENSIONS> and returns the result.
920
921=item $uint = $device->preferred_vector_width_half
922
923Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_HALF> and returns the result.
924
925=item $uint = $device->native_vector_width_char
926
927Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_CHAR> and returns the result.
928
929=item $uint = $device->native_vector_width_short
930
931Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_SHORT> and returns the result.
932
933=item $uint = $device->native_vector_width_int
934
935Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_INT> and returns the result.
936
937=item $uint = $device->native_vector_width_long
938
939Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_LONG> and returns the result.
940
941=item $uint = $device->native_vector_width_float
942
943Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_FLOAT> and returns the result.
944
945=item $uint = $device->native_vector_width_double
946
947Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_DOUBLE> and returns the result.
948
949=item $uint = $device->native_vector_width_half
950
951Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_HALF> and returns the result.
952
953=item $device_fp_config = $device->double_fp_config
954
955Calls C<clGetDeviceInfo> with C<CL_DEVICE_DOUBLE_FP_CONFIG> and returns the result.
956
957=item $device_fp_config = $device->half_fp_config
958
959Calls C<clGetDeviceInfo> with C<CL_DEVICE_HALF_FP_CONFIG> and returns the result.
960
961=item $boolean = $device->host_unified_memory
962
963Calls C<clGetDeviceInfo> with C<CL_DEVICE_HOST_UNIFIED_MEMORY> and returns the result.
964
965=item $device = $device->parent_device_ext
966
967Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARENT_DEVICE_EXT> and returns the result.
968
969=item @device_partition_property_exts = $device->partition_types_ext
970
971Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_TYPES_EXT> and returns the result.
972
973=item @device_partition_property_exts = $device->affinity_domains_ext
974
975Calls C<clGetDeviceInfo> with C<CL_DEVICE_AFFINITY_DOMAINS_EXT> and returns the result.
976
977=item $uint = $device->reference_count_ext
978
979Calls C<clGetDeviceInfo> with C<CL_DEVICE_REFERENCE_COUNT_EXT> and returns the result.
980
981=item @device_partition_property_exts = $device->partition_style_ext
982
983Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_STYLE_EXT> and returns the result.
984
985=for gengetinfo end device
323 986
324=back 987=back
325 988
326=head2 THE OpenCL::Context CLASS 989=head2 THE OpenCL::Context CLASS
327 990
328=over 4 991=over 4
329 992
330=item $packed_value = $ctx->info ($name) 993=item $prog = $ctx->build_program ($program, $options = "")
331 994
332See C<< $platform->info >> for details. 995This convenience function tries to build the program on all devices in
996the context. If the build fails, then the function will C<croak> with the
997build log. Otherwise ti returns the program object.
333 998
334L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetContextInfo.html> 999The C<$program> can either be a C<OpenCL::Program> object or a string
1000containing the program. In the latter case, a program objetc will be
1001created automatically.
1002
1003=cut
1004
1005sub OpenCL::Context::build_program {
1006 my ($self, $prog, $options) = @_;
1007
1008 require Carp;
1009
1010 $prog = $self->program_with_source ($prog)
1011 unless ref $prog;
1012
1013 eval { $prog->build (undef, $options); 1 }
1014 or errno == BUILD_PROGRAM_FAILURE
1015 or Carp::croak "OpenCL::Context->build_program: " . err2str;
1016
1017 # we check status for all devices
1018 for my $dev ($self->devices) {
1019 $prog->build_status ($dev) == BUILD_SUCCESS
1020 or Carp::croak ("Building OpenCL program for device '" . $dev->name . "' failed:\n"
1021 . $prog->build_log ($dev));
1022 }
1023
1024 $prog
1025}
335 1026
336=item $queue = $ctx->queue ($device, $properties) 1027=item $queue = $ctx->queue ($device, $properties)
337 1028
338Create a new OpenCL::Queue object from the context and the given device. 1029Create a new OpenCL::Queue object from the context and the given device.
339 1030
340L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html> 1031L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html>
341 1032
1033Example: create an out-of-order queue.
1034
1035 $queue = $ctx->queue ($device, OpenCL::QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE);
1036
342=item $ev = $ctx->user_event 1037=item $ev = $ctx->user_event
343 1038
344Creates a new OpenCL::UserEvent object. 1039Creates a new OpenCL::UserEvent object.
345 1040
346L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateUserEvent.html> 1041L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateUserEvent.html>
347 1042
348=item $buf = $ctx->buffer ($flags, $len) 1043=item $buf = $ctx->buffer ($flags, $len)
349 1044
350Creates a new OpenCL::Buffer object with the given flags and octet-size. 1045Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object with the
1046given flags and octet-size.
351 1047
352L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateBuffer.html> 1048L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateBuffer.html>
353 1049
354=item $buf = $ctx->buffer_sv ($flags, $data) 1050=item $buf = $ctx->buffer_sv ($flags, $data)
355 1051
356Creates a new OpenCL::Buffer object and initialise it with the given data values. 1052Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and
1053initialise it with the given data values.
357 1054
1055=item $img = $ctx->image ($self, $flags, $channel_order, $channel_type, $type, $width, $height, $depth = 0, $array_size = 0, $row_pitch = 0, $slice_pitch = 0, $num_mip_level = 0, $num_samples = 0, $*data = &PL_sv_undef)
1056
1057Creates a new OpenCL::Image object and optionally initialises it with
1058the given data values.
1059
1060L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html>
1061
358=item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $data) 1062=item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $row_pitch = 0, $data = undef)
359 1063
360Creates a new OpenCL::Image2D object and optionally initialises it with the given data values. 1064Creates a new OpenCL::Image2D object and optionally initialises it with
1065the given data values.
361 1066
362L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage2D.html> 1067L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage2D.html>
363 1068
364=item $img = $ctx->image3d ($flags, $channel_order, $channel_type, $width, $height, $depth, $slice_pitch, $data) 1069=item $img = $ctx->image3d ($flags, $channel_order, $channel_type, $width, $height, $depth, $row_pitch = 0, $slice_pitch = 0, $data = undef)
365 1070
366Creates a new OpenCL::Image3D object and optionally initialises it with the given data values. 1071Creates a new OpenCL::Image3D object and optionally initialises it with
1072the given data values.
367 1073
368L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage3D.html> 1074L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage3D.html>
1075
1076=item $buffer = $ctx->gl_buffer ($flags, $bufobj)
1077
1078Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object that refers to the given
1079OpenGL buffer object.
1080
1081http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLBuffer.html
1082
1083=item $img = $ctx->gl_texture ($flags, $target, $miplevel, $texture)
1084
1085Creates a new OpenCL::Image object that refers to the given OpenGL
1086texture object or buffer.
1087
1088http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateFromGLTexture.html
1089
1090=item $img = $ctx->gl_texture2d ($flags, $target, $miplevel, $texture)
1091
1092Creates a new OpenCL::Image2D object that refers to the given OpenGL
10932D texture object.
1094
1095http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture2D.html
1096
1097=item $img = $ctx->gl_texture3d ($flags, $target, $miplevel, $texture)
1098
1099Creates a new OpenCL::Image3D object that refers to the given OpenGL
11003D texture object.
1101
1102http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture3D.html
1103
1104=item $ctx->gl_renderbuffer ($flags, $renderbuffer)
1105
1106Creates a new OpenCL::Image2D object that refers to the given OpenGL
1107render buffer.
1108
1109http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLRenderbuffer.html
369 1110
370=item @formats = $ctx->supported_image_formats ($flags, $image_type) 1111=item @formats = $ctx->supported_image_formats ($flags, $image_type)
371 1112
372Returns a list of matching image formats - each format is an arrayref with 1113Returns a list of matching image formats - each format is an arrayref with
373two values, $channel_order and $channel_type, in it. 1114two values, $channel_order and $channel_type, in it.
384 1125
385Creates a new OpenCL::Program object from the given source code. 1126Creates a new OpenCL::Program object from the given source code.
386 1127
387L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateProgramWithSource.html> 1128L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateProgramWithSource.html>
388 1129
1130=item $packed_value = $ctx->info ($name)
1131
1132See C<< $platform->info >> for details.
1133
1134L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetContextInfo.html>
1135
1136=for gengetinfo begin context
1137
1138=item $uint = $context->reference_count
1139
1140Calls C<clGetContextInfo> with C<CL_CONTEXT_REFERENCE_COUNT> and returns the result.
1141
1142=item @devices = $context->devices
1143
1144Calls C<clGetContextInfo> with C<CL_CONTEXT_DEVICES> and returns the result.
1145
1146=item @property_ints = $context->properties
1147
1148Calls C<clGetContextInfo> with C<CL_CONTEXT_PROPERTIES> and returns the result.
1149
1150=item $uint = $context->num_devices
1151
1152Calls C<clGetContextInfo> with C<CL_CONTEXT_NUM_DEVICES> and returns the result.
1153
1154=for gengetinfo end context
1155
389=back 1156=back
390 1157
391=head2 THE OpenCL::Queue CLASS 1158=head2 THE OpenCL::Queue CLASS
392 1159
393An OpenCL::Queue represents an execution queue for OpenCL. You execute 1160An OpenCL::Queue represents an execution queue for OpenCL. You execute
394requests by calling their respective C<enqueue_xxx> method and waitinf for 1161requests by calling their respective method and waiting for it to complete
395it to complete in some way. 1162in some way.
396 1163
397All the enqueue methods return an event object that can be used to wait 1164Most methods that enqueue some request return an event object that can
398for completion, unless the method is called in void context, in which case 1165be used to wait for completion (optionally using a callback), unless
399no event object is created. 1166the method is called in void context, in which case no event object is
1167created.
400 1168
401They also allow you to specify any number of other event objects that this 1169They also allow you to specify any number of other event objects that this
402request has to wait for before it starts executing, by simply passing the 1170request has to wait for before it starts executing, by simply passing the
403event objects as extra parameters to the enqueue methods. 1171event objects as extra parameters to the enqueue methods. To simplify
1172program design, this module ignores any C<undef> values in the list of
1173events. This makes it possible to code operations such as this, without
1174having to put a valid event object into C<$event> first:
1175
1176 $event = $queue->xxx (..., $event);
404 1177
405Queues execute in-order by default, without any parallelism, so in most 1178Queues execute in-order by default, without any parallelism, so in most
406cases (i.e. you use only one queue) it's not necessary to wait for or 1179cases (i.e. you use only one queue) it's not necessary to wait for or
407create event objects. 1180create event objects, althoguh an our of order queue is often a bit
1181faster.
408 1182
409=over 4 1183=over 4
410 1184
411=item $packed_value = $ctx->info ($name)
412
413See C<< $platform->info >> for details.
414
415L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetCommandQueueInfo.html>
416
417=item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) 1185=item $ev = $queue->read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...)
418 1186
419Reads data from buffer into the given string. 1187Reads data from buffer into the given string.
420 1188
421L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html> 1189L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html>
422 1190
423=item $ev = $queue->enqueue_write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) 1191=item $ev = $queue->write_buffer ($buffer, $blocking, $offset, $data, $wait_events...)
424 1192
425Writes data to buffer from the given string. 1193Writes data to buffer from the given string.
426 1194
427L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html> 1195L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html>
428 1196
429=item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) 1197=item $ev = $queue->copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...)
430 1198
431L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> 1199L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html>
432 1200
1201=item $ev = $queue->read_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...)
1202
1203http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html
1204
1205=item $ev = $queue->write_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...)
1206
1207http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html
1208
433=item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) 1209=item $ev = $queue->read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
1210
1211L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html>
1212
1213=item $ev = $queue->copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...)
434 1214
435L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> 1215L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html>
436 1216
437=item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $data, $wait_events...) 1217=item $ev = $queue->write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...)
438 1218
439L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> 1219L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html>
440 1220
1221=item $ev = $queue->copy_image ($src_image, $dst_image, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...)
1222
1223L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html>
1224
1225=item $ev = $queue->copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...)
1226
1227L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html>
1228
441=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...) 1229=item $ev = $queue->copy_buffer_rect ($src, $dst, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $src_row_pitch, $src_slice_pitch, $dst_row_pitch, $dst_slice_pitch, $wait_event...)
442 1230
443Yeah. 1231Yeah.
444 1232
445L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html>
446
447=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, ...)
448
449L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. 1233L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>.
450 1234
451=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, ...) 1235=item $ev = $queue->fill_buffer ($mem, $pattern, $offset, $size, ...)
452 1236
1237Fills the given buffer object with repeated applications of C<$pattern>,
1238starting at C<$offset> for C<$size> octets.
1239
1240L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html>
1241
1242=item $ev = $queue->fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...)
1243
1244Fills the given image area with the given rgba colour components. The
1245components are normally floating point values between C<0> and C<1>,
1246except when the image channel data type is a signe dor unsigned
1247unnormalised format, in which case the range is determined by the format.
1248
453L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> 1249L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html>
454 1250
455=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, ...)
456
457L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html>
458
459=item $ev = $queue->enqueue_task ($kernel, $wait_events...) 1251=item $ev = $queue->task ($kernel, $wait_events...)
460 1252
461L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> 1253L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html>
462 1254
463=item $ev = $queue->enqueue_nd_range_kernel ($kernel, @$global_work_offset, @$global_work_size, @$local_work_size, $wait_events...) 1255=item $ev = $queue->nd_range_kernel ($kernel, \@global_work_offset, \@global_work_size, \@local_work_size, $wait_events...)
464 1256
465Enqueues a kernel execution. 1257Enqueues a kernel execution.
466 1258
467@$global_work_size must be specified as a reference to an array of 1259\@global_work_size must be specified as a reference to an array of
468integers specifying the work sizes (element counts). 1260integers specifying the work sizes (element counts).
469 1261
470@$global_work_offset must be either C<undef> (in which case all offsets 1262\@global_work_offset must be either C<undef> (in which case all offsets
471are C<0>), or a reference to an array of work offsets, with the same number 1263are C<0>), or a reference to an array of work offsets, with the same number
472of elements as @$global_work_size. 1264of elements as \@global_work_size.
473 1265
474@$local_work_size must be either C<undef> (in which case the 1266\@local_work_size must be either C<undef> (in which case the
475implementation is supposed to choose good local work sizes), or a 1267implementation is supposed to choose good local work sizes), or a
476reference to an array of local work sizes, with the same number of 1268reference to an array of local work sizes, with the same number of
477elements as @$global_work_size. 1269elements as \@global_work_size.
478 1270
479L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> 1271L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html>
480 1272
481=item $ev = $queue->enqueue_marker 1273=item $ev = $queue->acquire_gl_objects ([object, ...], $wait_events...)
482 1274
1275Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired
1276for subsequent OpenCL usage.
1277
483L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueMarker.html> 1278L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html>
484 1279
1280=item $ev = $queue->release_gl_objects ([object, ...], $wait_events...)
1281
1282Enqueues a list (an array-ref of OpenCL::Memory objects) to be released
1283for subsequent OpenGL usage.
1284
1285L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html>
1286
485=item $ev = $queue->enqueue_wait_for_events ($wait_events...) 1287=item $ev = $queue->wait_for_events ($wait_events...)
486 1288
487L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> 1289L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html>
488 1290
489=item $queue->enqueue_barrier 1291=item $ev = $queue->marker ($wait_events...)
490 1292
1293L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html>
1294
1295=item $ev = $queue->barrier ($wait_events...)
1296
491L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueBarrier.html> 1297L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html>
492 1298
493=item $queue->flush 1299=item $queue->flush
494 1300
495L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html> 1301L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html>
496 1302
497=item $queue->finish 1303=item $queue->finish
498 1304
499L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFinish.html> 1305L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFinish.html>
500 1306
1307=item $packed_value = $queue->info ($name)
1308
1309See C<< $platform->info >> for details.
1310
1311L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetCommandQueueInfo.html>
1312
1313=for gengetinfo begin command_queue
1314
1315=item $ctx = $command_queue->context
1316
1317Calls C<clGetCommandQueueInfo> with C<CL_QUEUE_CONTEXT> and returns the result.
1318
1319=item $device = $command_queue->device
1320
1321Calls C<clGetCommandQueueInfo> with C<CL_QUEUE_DEVICE> and returns the result.
1322
1323=item $uint = $command_queue->reference_count
1324
1325Calls C<clGetCommandQueueInfo> with C<CL_QUEUE_REFERENCE_COUNT> and returns the result.
1326
1327=item $command_queue_properties = $command_queue->properties
1328
1329Calls C<clGetCommandQueueInfo> with C<CL_QUEUE_PROPERTIES> and returns the result.
1330
1331=for gengetinfo end command_queue
1332
501=back 1333=back
502 1334
503=head2 THE OpenCL::Memory CLASS 1335=head2 THE OpenCL::Memory CLASS
504 1336
505This the superclass of all memory objects - OpenCL::Buffer, OpenCL::Image, 1337This the superclass of all memory objects - OpenCL::Buffer, OpenCL::Image,
506OpenCL::Image2D and OpenCL::Image3D. The subclasses of this class 1338OpenCL::Image2D and OpenCL::Image3D.
507currently only exist to allow type-checking.
508 1339
509=over 4 1340=over 4
510 1341
511=item $packed_value = $memory->info ($name) 1342=item $packed_value = $memory->info ($name)
512 1343
513See C<< $platform->info >> for details. 1344See C<< $platform->info >> for details.
514 1345
515L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetMemObjectInfo.html> 1346L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetMemObjectInfo.html>
516 1347
1348=for gengetinfo begin mem
1349
1350=item $mem_object_type = $mem->type
1351
1352Calls C<clGetMemObjectInfo> with C<CL_MEM_TYPE> and returns the result.
1353
1354=item $mem_flags = $mem->flags
1355
1356Calls C<clGetMemObjectInfo> with C<CL_MEM_FLAGS> and returns the result.
1357
1358=item $int = $mem->size
1359
1360Calls C<clGetMemObjectInfo> with C<CL_MEM_SIZE> and returns the result.
1361
1362=item $ptr_value = $mem->host_ptr
1363
1364Calls C<clGetMemObjectInfo> with C<CL_MEM_HOST_PTR> and returns the result.
1365
1366=item $uint = $mem->map_count
1367
1368Calls C<clGetMemObjectInfo> with C<CL_MEM_MAP_COUNT> and returns the result.
1369
1370=item $uint = $mem->reference_count
1371
1372Calls C<clGetMemObjectInfo> with C<CL_MEM_REFERENCE_COUNT> and returns the result.
1373
1374=item $ctx = $mem->context
1375
1376Calls C<clGetMemObjectInfo> with C<CL_MEM_CONTEXT> and returns the result.
1377
1378=item $mem = $mem->associated_memobject
1379
1380Calls C<clGetMemObjectInfo> with C<CL_MEM_ASSOCIATED_MEMOBJECT> and returns the result.
1381
1382=item $int = $mem->offset
1383
1384Calls C<clGetMemObjectInfo> with C<CL_MEM_OFFSET> and returns the result.
1385
1386=for gengetinfo end mem
1387
1388=item ($type, $name) = $mem->gl_object_info
1389
1390Returns the OpenGL object type (e.g. OpenCL::GL_OBJECT_TEXTURE2D) and the
1391object "name" (e.g. the texture name) used to create this memory object.
1392
1393L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetGLObjectInfo.html>
1394
517=back 1395=back
518 1396
1397=head2 THE OpenCL::Buffer CLASS
1398
1399This is a subclass of OpenCL::Memory, and the superclass of
1400OpenCL::BufferObj. Its purpose is simply to distinguish between buffers
1401and sub-buffers.
1402
1403=head2 THE OpenCL::BufferObj CLASS
1404
1405This is a subclass of OpenCL::Buffer and thus OpenCL::Memory. It exists
1406because one cna create sub buffers of OpenLC::BufferObj objects, but not
1407sub buffers from these sub buffers.
1408
1409=over 4
1410
1411=item $subbuf = $buf_obj->sub_buffer_region ($flags, $origin, $size)
1412
1413Creates an OpenCL::Buffer objects from this buffer and returns it. The
1414C<buffer_create_type> is assumed to be C<CL_BUFFER_CREATE_TYPE_REGION>.
1415
1416L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateSubBuffer.html>
1417
1418=back
1419
1420=head2 THE OpenCL::Image CLASS
1421
1422This is the superclass of all image objects - OpenCL::Image1D,
1423OpenCL::Image1DArray, OpenCL::Image1DBuffer, OpenCL::Image2D,
1424OpenCL::Image2DArray and OpenCL::Image3D.
1425
1426=over 4
1427
1428=item $packed_value = $image->image_info ($name)
1429
1430See C<< $platform->info >> for details.
1431
1432The reason this method is not called C<info> is that there already is an
1433C<< ->info >> method inherited from C<OpenCL::Memory>.
1434
1435L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html>
1436
1437=item ($channel_order, $channel_data_type) = $image->format
1438
1439Returns the channel order and type used to create the image by calling
1440C<clGetImageInfo> with C<CL_IMAGE_FORMAT>.
1441
1442=for gengetinfo begin image
1443
1444=item $int = $image->element_size
1445
1446Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result.
1447
1448=item $int = $image->row_pitch
1449
1450Calls C<clGetImageInfo> with C<CL_IMAGE_ROW_PITCH> and returns the result.
1451
1452=item $int = $image->slice_pitch
1453
1454Calls C<clGetImageInfo> with C<CL_IMAGE_SLICE_PITCH> and returns the result.
1455
1456=item $int = $image->width
1457
1458Calls C<clGetImageInfo> with C<CL_IMAGE_WIDTH> and returns the result.
1459
1460=item $int = $image->height
1461
1462Calls C<clGetImageInfo> with C<CL_IMAGE_HEIGHT> and returns the result.
1463
1464=item $int = $image->depth
1465
1466Calls C<clGetImageInfo> with C<CL_IMAGE_DEPTH> and returns the result.
1467
1468=for gengetinfo end image
1469
1470=for gengetinfo begin gl_texture
1471
1472=item $GLenum = $gl_texture->target
1473
1474Calls C<clGetGLTextureInfo> with C<CL_GL_TEXTURE_TARGET> and returns the result.
1475
1476=item $GLint = $gl_texture->gl_mipmap_level
1477
1478Calls C<clGetGLTextureInfo> with C<CL_GL_MIPMAP_LEVEL> and returns the result.
1479
1480=for gengetinfo end gl_texture
1481
1482=back
1483
519=head2 THE OpenCL::Sampler CLASS 1484=head2 THE OpenCL::Sampler CLASS
520 1485
521=over 4 1486=over 4
522 1487
523=item $packed_value = $sampler->info ($name) 1488=item $packed_value = $sampler->info ($name)
524 1489
525See C<< $platform->info >> for details. 1490See C<< $platform->info >> for details.
526 1491
527L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetSamplerInfo.html> 1492L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetSamplerInfo.html>
528 1493
1494=for gengetinfo begin sampler
1495
1496=item $uint = $sampler->reference_count
1497
1498Calls C<clGetSamplerInfo> with C<CL_SAMPLER_REFERENCE_COUNT> and returns the result.
1499
1500=item $ctx = $sampler->context
1501
1502Calls C<clGetSamplerInfo> with C<CL_SAMPLER_CONTEXT> and returns the result.
1503
1504=item $addressing_mode = $sampler->normalized_coords
1505
1506Calls C<clGetSamplerInfo> with C<CL_SAMPLER_NORMALIZED_COORDS> and returns the result.
1507
1508=item $filter_mode = $sampler->addressing_mode
1509
1510Calls C<clGetSamplerInfo> with C<CL_SAMPLER_ADDRESSING_MODE> and returns the result.
1511
1512=item $boolean = $sampler->filter_mode
1513
1514Calls C<clGetSamplerInfo> with C<CL_SAMPLER_FILTER_MODE> and returns the result.
1515
1516=for gengetinfo end sampler
1517
529=back 1518=back
530 1519
531=head2 THE OpenCL::Program CLASS 1520=head2 THE OpenCL::Program CLASS
532 1521
533=over 4 1522=over 4
534 1523
535=item $packed_value = $program->info ($name) 1524=item $program->build (\@devices = undef, $options = "", $cb->($program) = undef)
536 1525
537See C<< $platform->info >> for details.
538
539L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetProgramInfo.html>
540
541=item $program->build ($device, $options = "")
542
543Tries to build the program with the givne options. 1526Tries to build the program with the given options. See also the
1527C<$ctx->build> convenience function.
1528
1529If a callback is specified, then it will be called when compilation is
1530finished. Note that many OpenCL implementations block your program while
1531compiling whether you use a callback or not. See C<build_async> if you
1532want to make sure the build is done in the background.
1533
1534Note that some OpenCL implementations atc up badly, and don't call the
1535callback in some error cases (but call it in others). This implementation
1536assumes the callback will always be called, and leaks memory if this is
1537not so. So best make sure you don't pass in invalid values.
544 1538
545L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> 1539L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html>
1540
1541=item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef)
1542
1543Similar to C<< ->build >>, except it starts a thread, and never fails (you
1544need to check the compilation status form the callback, or by polling).
546 1545
547=item $packed_value = $program->build_info ($device, $name) 1546=item $packed_value = $program->build_info ($device, $name)
548 1547
549Similar to C<< $platform->info >>, but returns build info for a previous 1548Similar to C<< $platform->info >>, but returns build info for a previous
550build attempt for the given device. 1549build attempt for the given device.
556Creates an OpenCL::Kernel object out of the named C<__kernel> function in 1555Creates an OpenCL::Kernel object out of the named C<__kernel> function in
557the program. 1556the program.
558 1557
559L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html> 1558L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html>
560 1559
1560=item @kernels = $program->kernels_in_program
1561
1562Returns all kernels successfully compiled for all devices in program.
1563
1564http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernelsInProgram.html
1565
1566=for gengetinfo begin program_build
1567
1568=item $build_status = $program->build_status ($device)
1569
1570Calls C<clGetProgramBuildInfo> with C<CL_PROGRAM_BUILD_STATUS> and returns the result.
1571
1572=item $string = $program->build_options ($device)
1573
1574Calls C<clGetProgramBuildInfo> with C<CL_PROGRAM_BUILD_OPTIONS> and returns the result.
1575
1576=item $string = $program->build_log ($device)
1577
1578Calls C<clGetProgramBuildInfo> with C<CL_PROGRAM_BUILD_LOG> and returns the result.
1579
1580=for gengetinfo end program_build
1581
1582=item $packed_value = $program->info ($name)
1583
1584See C<< $platform->info >> for details.
1585
1586L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetProgramInfo.html>
1587
1588=for gengetinfo begin program
1589
1590=item $uint = $program->reference_count
1591
1592Calls C<clGetProgramInfo> with C<CL_PROGRAM_REFERENCE_COUNT> and returns the result.
1593
1594=item $ctx = $program->context
1595
1596Calls C<clGetProgramInfo> with C<CL_PROGRAM_CONTEXT> and returns the result.
1597
1598=item $uint = $program->num_devices
1599
1600Calls C<clGetProgramInfo> with C<CL_PROGRAM_NUM_DEVICES> and returns the result.
1601
1602=item @devices = $program->devices
1603
1604Calls C<clGetProgramInfo> with C<CL_PROGRAM_DEVICES> and returns the result.
1605
1606=item $string = $program->source
1607
1608Calls C<clGetProgramInfo> with C<CL_PROGRAM_SOURCE> and returns the result.
1609
1610=item @ints = $program->binary_sizes
1611
1612Calls C<clGetProgramInfo> with C<CL_PROGRAM_BINARY_SIZES> and returns the result.
1613
1614=for gengetinfo end program
1615
1616=item @blobs = $program->binaries
1617
1618Returns a string for the compiled binary for every device associated with
1619the program, empty strings indicate missing programs, and an empty result
1620means no program binaries are available.
1621
1622These "binaries" are often, in fact, informative low-level assembly
1623sources.
1624
1625L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetProgramInfo.html>
1626
561=back 1627=back
562 1628
563=head2 THE OpenCL::Kernel CLASS 1629=head2 THE OpenCL::Kernel CLASS
564 1630
565=over 4 1631=over 4
568 1634
569See C<< $platform->info >> for details. 1635See C<< $platform->info >> for details.
570 1636
571L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetKernelInfo.html> 1637L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetKernelInfo.html>
572 1638
1639=for gengetinfo begin kernel
1640
1641=item $string = $kernel->function_name
1642
1643Calls C<clGetKernelInfo> with C<CL_KERNEL_FUNCTION_NAME> and returns the result.
1644
1645=item $uint = $kernel->num_args
1646
1647Calls C<clGetKernelInfo> with C<CL_KERNEL_NUM_ARGS> and returns the result.
1648
1649=item $uint = $kernel->reference_count
1650
1651Calls C<clGetKernelInfo> with C<CL_KERNEL_REFERENCE_COUNT> and returns the result.
1652
1653=item $ctx = $kernel->context
1654
1655Calls C<clGetKernelInfo> with C<CL_KERNEL_CONTEXT> and returns the result.
1656
1657=item $program = $kernel->program
1658
1659Calls C<clGetKernelInfo> with C<CL_KERNEL_PROGRAM> and returns the result.
1660
1661=for gengetinfo end kernel
1662
1663=item $packed_value = $kernel->work_group_info ($device, $name)
1664
1665See C<< $platform->info >> for details.
1666
1667The reason this method is not called C<info> is that there already is an
1668C<< ->info >> method.
1669
1670L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetKernelWorkGroupInfo.html>
1671
1672=for gengetinfo begin kernel_work_group
1673
1674=item $int = $kernel->work_group_size ($device)
1675
1676Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_WORK_GROUP_SIZE> and returns the result.
1677
1678=item @ints = $kernel->compile_work_group_size ($device)
1679
1680Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_COMPILE_WORK_GROUP_SIZE> and returns the result.
1681
1682=item $ulong = $kernel->local_mem_size ($device)
1683
1684Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_LOCAL_MEM_SIZE> and returns the result.
1685
1686=item $int = $kernel->preferred_work_group_size_multiple ($device)
1687
1688Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PREFERRED_WORK_GROUP_SIZE_MULTIPLE> and returns the result.
1689
1690=item $ulong = $kernel->private_mem_size ($device)
1691
1692Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result.
1693
1694=for gengetinfo end kernel_work_group
1695
1696=item $kernel->setf ($format, ...)
1697
1698Sets the arguments of a kernel. Since OpenCL 1.1 doesn't have a generic
1699way to set arguments (and with OpenCL 1.2 it might be rather slow), you
1700need to specify a format argument, much as with C<printf>, to tell OpenCL
1701what type of argument it is.
1702
1703The format arguments are single letters:
1704
1705 c char
1706 C unsigned char
1707 s short
1708 S unsigned short
1709 i int
1710 I unsigned int
1711 l long
1712 L unsigned long
1713
1714 h half float (0..65535)
1715 f float
1716 d double
1717
1718 z local (octet size)
1719
1720 m memory object (buffer or image)
1721 a sampler
1722 e event
1723
1724Space characters in the format string are ignored.
1725
1726Example: set the arguments for a kernel that expects an int, two floats, a buffer and an image.
1727
1728 $kernel->setf ("i ff mm", 5, 0.5, 3, $buffer, $image);
1729
573=item $kernel->set_TYPE ($index, $value) 1730=item $kernel->set_TYPE ($index, $value)
574 1731
1732=item $kernel->set_char ($index, $value)
1733
1734=item $kernel->set_uchar ($index, $value)
1735
1736=item $kernel->set_short ($index, $value)
1737
1738=item $kernel->set_ushort ($index, $value)
1739
1740=item $kernel->set_int ($index, $value)
1741
1742=item $kernel->set_uint ($index, $value)
1743
1744=item $kernel->set_long ($index, $value)
1745
1746=item $kernel->set_ulong ($index, $value)
1747
1748=item $kernel->set_half ($index, $value)
1749
1750=item $kernel->set_float ($index, $value)
1751
1752=item $kernel->set_double ($index, $value)
1753
1754=item $kernel->set_memory ($index, $value)
1755
1756=item $kernel->set_buffer ($index, $value)
1757
1758=item $kernel->set_image ($index, $value)
1759
1760=item $kernel->set_sampler ($index, $value)
1761
1762=item $kernel->set_local ($index, $value)
1763
1764=item $kernel->set_event ($index, $value)
1765
575This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>. 1766This is a family of methods to set the kernel argument with the number
576 1767C<$index> to the give C<$value>.
577TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>,
578C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>,
579C<image2d>, C<image3d>, C<sampler> or C<event>.
580 1768
581Chars and integers (including the half type) are specified as integers, 1769Chars and integers (including the half type) are specified as integers,
582float and double as floating point values, memory/buffer/image2d/image3d 1770float and double as floating point values, memory/buffer/image must be
583must be an object of that type or C<undef>, and sampler and event must be 1771an object of that type or C<undef>, local-memory arguments are set by
584objects of that type. 1772specifying the size, and sampler and event must be objects of that type.
1773
1774Note that C<set_memory> works for all memory objects (all types of buffers
1775and images) - the main purpose of the more specific C<set_TYPE> functions
1776is type checking.
1777
1778Setting an argument for a kernel does NOT keep a reference to the object -
1779for example, if you set an argument to some image object, free the image,
1780and call the kernel, you will run into undefined behaviour.
585 1781
586L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html> 1782L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html>
587 1783
588=back 1784=back
589 1785
592This is the superclass for all event objects (including OpenCL::UserEvent 1788This is the superclass for all event objects (including OpenCL::UserEvent
593objects). 1789objects).
594 1790
595=over 4 1791=over 4
596 1792
1793=item $ev->wait
1794
1795Waits for the event to complete.
1796
1797L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html>
1798
1799=item $ev->cb ($exec_callback_type, $callback->($event, $event_command_exec_status))
1800
1801Adds a callback to the callback stack for the given event type. There is
1802no way to remove a callback again.
1803
1804L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetEventCallback.html>
1805
597=item $packed_value = $ev->info ($name) 1806=item $packed_value = $ev->info ($name)
598 1807
599See C<< $platform->info >> for details. 1808See C<< $platform->info >> for details.
600 1809
601L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html> 1810L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html>
602 1811
603=item $ev->wait 1812=for gengetinfo begin event
604 1813
605Waits for the event to complete. 1814=item $queue = $event->command_queue
606 1815
1816Calls C<clGetEventInfo> with C<CL_EVENT_COMMAND_QUEUE> and returns the result.
1817
1818=item $command_type = $event->command_type
1819
1820Calls C<clGetEventInfo> with C<CL_EVENT_COMMAND_TYPE> and returns the result.
1821
1822=item $uint = $event->reference_count
1823
1824Calls C<clGetEventInfo> with C<CL_EVENT_REFERENCE_COUNT> and returns the result.
1825
1826=item $uint = $event->command_execution_status
1827
1828Calls C<clGetEventInfo> with C<CL_EVENT_COMMAND_EXECUTION_STATUS> and returns the result.
1829
1830=item $ctx = $event->context
1831
1832Calls C<clGetEventInfo> with C<CL_EVENT_CONTEXT> and returns the result.
1833
1834=for gengetinfo end event
1835
1836=item $packed_value = $ev->profiling_info ($name)
1837
1838See C<< $platform->info >> for details.
1839
1840The reason this method is not called C<info> is that there already is an
1841C<< ->info >> method.
1842
607L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> 1843L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetProfilingInfo.html>
1844
1845=for gengetinfo begin profiling
1846
1847=item $ulong = $event->profiling_command_queued
1848
1849Calls C<clGetEventProfilingInfo> with C<CL_PROFILING_COMMAND_QUEUED> and returns the result.
1850
1851=item $ulong = $event->profiling_command_submit
1852
1853Calls C<clGetEventProfilingInfo> with C<CL_PROFILING_COMMAND_SUBMIT> and returns the result.
1854
1855=item $ulong = $event->profiling_command_start
1856
1857Calls C<clGetEventProfilingInfo> with C<CL_PROFILING_COMMAND_START> and returns the result.
1858
1859=item $ulong = $event->profiling_command_end
1860
1861Calls C<clGetEventProfilingInfo> with C<CL_PROFILING_COMMAND_END> and returns the result.
1862
1863=for gengetinfo end profiling
608 1864
609=back 1865=back
610 1866
611=head2 THE OpenCL::UserEvent CLASS 1867=head2 THE OpenCL::UserEvent CLASS
612 1868
614 1870
615=over 4 1871=over 4
616 1872
617=item $ev->set_status ($execution_status) 1873=item $ev->set_status ($execution_status)
618 1874
1875Sets the execution status of the user event. Can only be called once,
1876either with OpenCL::COMPLETE or a negative number as status.
1877
619L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html> 1878L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html>
620 1879
621=back 1880=back
622 1881
623=cut 1882=cut
624
625package OpenCL;
626
627use common::sense;
628
629BEGIN {
630 our $VERSION = '0.03';
631
632 require XSLoader;
633 XSLoader::load (__PACKAGE__, $VERSION);
634
635 @OpenCL::Buffer::ISA =
636 @OpenCL::Image::ISA = OpenCL::Memory::;
637
638 @OpenCL::Image2D::ISA =
639 @OpenCL::Image3D::ISA = OpenCL::Image::;
640
641 @OpenCL::UserEvent::ISA = OpenCL::Event::;
642}
643 1883
6441; 18841;
645 1885
646=head1 AUTHOR 1886=head1 AUTHOR
647 1887

Diff Legend

Removed lines
+ Added lines
< Changed lines
> Changed lines