… | |
… | |
27 | OpenCL::Program objects, which store source code and, after building for a |
27 | OpenCL::Program objects, which store source code and, after building for a |
28 | specific device ("compiling and linking"), also binary programs. For each |
28 | specific device ("compiling and linking"), also binary programs. For each |
29 | kernel function in a program you can then create an OpenCL::Kernel object |
29 | kernel function in a program you can then create an OpenCL::Kernel object |
30 | which represents basically a function call with argument values. |
30 | which represents basically a function call with argument values. |
31 | |
31 | |
32 | OpenCL::Memory objects of various flavours: OpenCL::Buffers objects (flat |
32 | OpenCL::Memory objects of various flavours: OpenCL::Buffer objects (flat |
33 | memory areas, think array) and OpenCL::Image objects (think 2d or 3d |
33 | memory areas, think arrays or structs) and OpenCL::Image objects (think 2d |
34 | array) for bulk data and input and output for kernels. |
34 | or 3d array) for bulk data and input and output for kernels. |
35 | |
35 | |
36 | OpenCL::Sampler objects, which are kind of like texture filter modes in |
36 | OpenCL::Sampler objects, which are kind of like texture filter modes in |
37 | OpenGL. |
37 | OpenGL. |
38 | |
38 | |
39 | OpenCL::Queue objects - command queues, which allow you to submit memory |
39 | OpenCL::Queue objects - command queues, which allow you to submit memory |
… | |
… | |
43 | |
43 | |
44 | OpenCL::Event objects are used to signal when something is complete. |
44 | OpenCL::Event objects are used to signal when something is complete. |
45 | |
45 | |
46 | =head2 HELPFUL RESOURCES |
46 | =head2 HELPFUL RESOURCES |
47 | |
47 | |
48 | The OpenCL spec used to develop this module (1.2 spec was available, but |
48 | The OpenCL specs used to develop this module: |
49 | no implementation was available to me :). |
|
|
50 | |
49 | |
51 | http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf |
50 | http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf |
|
|
51 | http://www.khronos.org/registry/cl/specs/opencl-1.2.pdf |
|
|
52 | http://www.khronos.org/registry/cl/specs/opencl-1.2-extensions.pdf |
52 | |
53 | |
53 | OpenCL manpages: |
54 | OpenCL manpages: |
54 | |
55 | |
55 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/ |
56 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/ |
|
|
57 | http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/ |
|
|
58 | |
|
|
59 | If you are into UML class diagrams, the following diagram might help - if |
|
|
60 | not, it will be mildly confusing (also, the class hierarchy of this module |
|
|
61 | is much more fine-grained): |
|
|
62 | |
|
|
63 | http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/classDiagram.html |
|
|
64 | |
|
|
65 | Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it |
|
|
66 | is, 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 | |
|
|
70 | And 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 | |
59 | To get something done, you basically have to do this once (refer to the |
76 | To get something done, you basically have to do this once (refer to the |
60 | examples below for actual code, this is just a high-level description): |
77 | examples below for actual code, this is just a high-level description): |
… | |
… | |
87 | |
104 | |
88 | Best run this once to get a feel for the platforms and devices in your |
105 | Best run this once to get a feel for the platforms and devices in your |
89 | system. |
106 | system. |
90 | |
107 | |
91 | for my $platform (OpenCL::platforms) { |
108 | for my $platform (OpenCL::platforms) { |
92 | printf "platform: %s\n", $platform->info (OpenCL::PLATFORM_NAME); |
109 | printf "platform: %s\n", $platform->name; |
93 | printf "extensions: %s\n", $platform->info (OpenCL::PLATFORM_EXTENSIONS); |
110 | printf "extensions: %s\n", $platform->extensions; |
94 | for my $device ($platform->devices) { |
111 | for my $device ($platform->devices) { |
95 | printf "+ device: %s\n", $device->info (OpenCL::DEVICE_NAME); |
112 | printf "+ device: %s\n", $device->name; |
96 | my $ctx = $device->context; |
113 | my $ctx = $platform->context (undef, [$device]); |
97 | # do stuff |
114 | # do stuff |
98 | } |
115 | } |
99 | } |
116 | } |
100 | |
117 | |
101 | =head2 Get a useful context and a command queue. |
118 | =head2 Get a useful context and a command queue. |
… | |
… | |
124 | =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, |
125 | then asynchronously. |
142 | then asynchronously. |
126 | |
143 | |
127 | my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); |
144 | my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); |
128 | |
145 | |
129 | $queue->enqueue_read_buffer ($buf, 1, 1, 3, my $data); |
146 | $queue->read_buffer ($buf, 1, 1, 3, my $data); |
130 | print "$data\n"; |
147 | print "$data\n"; |
131 | |
148 | |
132 | my $ev = $queue->enqueue_read_buffer ($buf, 0, 1, 3, my $data); |
149 | my $ev = $queue->read_buffer ($buf, 0, 1, 3, my $data); |
133 | $ev->wait; |
150 | $ev->wait; |
134 | print "$data\n"; # prints "elm" |
151 | print "$data\n"; # prints "elm" |
135 | |
152 | |
136 | =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 |
137 | functions. |
154 | functions. |
138 | |
155 | |
139 | my $src = ' |
156 | my $src = ' |
140 | __kernel void |
157 | kernel void |
141 | squareit (__global float *input, __global float *output) |
158 | squareit (global float *input, global float *output) |
142 | { |
159 | { |
143 | $id = get_global_id (0); |
160 | $id = get_global_id (0); |
144 | output [id] = input [id] * input [id]; |
161 | output [id] = input [id] * input [id]; |
145 | } |
162 | } |
146 | '; |
163 | '; |
147 | |
164 | |
148 | my $prog = $ctx->program_with_source ($src); |
165 | 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"); |
166 | my $kernel = $prog->kernel ("squareit"); |
155 | |
167 | |
156 | =head2 Create some input and output float buffers, then call the |
168 | =head2 Create some input and output float buffers, then call the |
157 | 'squareit' kernel on them. |
169 | 'squareit' kernel on them. |
158 | |
170 | |
… | |
… | |
162 | # set buffer |
174 | # set buffer |
163 | $kernel->set_buffer (0, $input); |
175 | $kernel->set_buffer (0, $input); |
164 | $kernel->set_buffer (1, $output); |
176 | $kernel->set_buffer (1, $output); |
165 | |
177 | |
166 | # execute it for all 4 numbers |
178 | # execute it for all 4 numbers |
167 | $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
179 | $queue->nd_range_kernel ($kernel, undef, [4], undef); |
168 | |
180 | |
169 | # enqueue a synchronous read |
181 | # enqueue a synchronous read |
170 | $queue->enqueue_read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
182 | $queue->read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
171 | |
183 | |
172 | # print the results: |
184 | # print the results: |
173 | printf "%s\n", join ", ", unpack "f*", $data; |
185 | printf "%s\n", join ", ", unpack "f*", $data; |
174 | |
186 | |
175 | =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, |
176 | showing off barriers. |
188 | showing off barriers. |
177 | |
189 | |
178 | # execute it for all 4 numbers |
190 | # execute it for all 4 numbers |
179 | $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
191 | $queue->nd_range_kernel ($kernel, undef, [4], undef); |
180 | |
192 | |
181 | # enqueue a barrier to ensure in-order execution |
193 | # enqueue a barrier to ensure in-order execution |
182 | $queue->enqueue_barrier; |
194 | $queue->barrier; |
183 | |
195 | |
184 | # enqueue an async read |
196 | # enqueue an async read |
185 | $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
197 | $queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
186 | |
198 | |
187 | # wait for all requests to finish |
199 | # wait for all requests to finish |
188 | $queue->finish; |
200 | $queue->finish; |
189 | |
201 | |
190 | =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, |
191 | showing off event objects and wait lists. |
203 | showing off event objects and wait lists. |
192 | |
204 | |
193 | # execute it for all 4 numbers |
205 | # execute it for all 4 numbers |
194 | my $ev = $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
206 | my $ev = $queue->nd_range_kernel ($kernel, undef, [4], undef); |
195 | |
207 | |
196 | # enqueue an async read |
208 | # enqueue an async read |
197 | $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); |
198 | |
210 | |
199 | # wait for the last event to complete |
211 | # wait for the last event to complete |
200 | $ev->wait; |
212 | $ev->wait; |
|
|
213 | |
|
|
214 | =head2 Use the OpenGL module to share a texture between OpenCL and OpenGL and draw some julia |
|
|
215 | set tunnel effect. |
|
|
216 | |
|
|
217 | This is quite a long example to get you going - you can download it from |
|
|
218 | L<http://cvs.schmorp.de/OpenCL/examples/juliaflight>. |
|
|
219 | |
|
|
220 | use OpenGL ":all"; |
|
|
221 | use OpenCL; |
|
|
222 | |
|
|
223 | my $S = $ARGV[0] || 256; # window/texture size, smaller is faster |
|
|
224 | |
|
|
225 | # open a window and create a gl texture |
|
|
226 | OpenGL::glpOpenWindow width => $S, height => $S; |
|
|
227 | my $texid = glGenTextures_p 1; |
|
|
228 | glBindTexture GL_TEXTURE_2D, $texid; |
|
|
229 | glTexImage2D_c GL_TEXTURE_2D, 0, GL_RGBA8, $S, $S, 0, GL_RGBA, GL_UNSIGNED_BYTE, 0; |
|
|
230 | |
|
|
231 | # find and use the first opencl device that let's us get a shared opengl context |
|
|
232 | my $platform; |
|
|
233 | my $dev; |
|
|
234 | my $ctx; |
|
|
235 | |
|
|
236 | for (OpenCL::platforms) { |
|
|
237 | $platform = $_; |
|
|
238 | for ($platform->devices) { |
|
|
239 | $dev = $_; |
|
|
240 | $ctx = $platform->context ([OpenCL::GLX_DISPLAY_KHR, undef, OpenCL::GL_CONTEXT_KHR, undef], [$dev]) |
|
|
241 | and last; |
|
|
242 | } |
|
|
243 | } |
|
|
244 | |
|
|
245 | $ctx |
|
|
246 | or die "cannot find suitable OpenCL device\n"; |
|
|
247 | |
|
|
248 | my $queue = $ctx->queue ($dev); |
|
|
249 | |
|
|
250 | # now attach an opencl image2d object to the opengl texture |
|
|
251 | my $tex = $ctx->gl_texture2d (OpenCL::MEM_WRITE_ONLY, GL_TEXTURE_2D, 0, $texid); |
|
|
252 | |
|
|
253 | # now the boring opencl code |
|
|
254 | my $src = <<EOF; |
|
|
255 | kernel void |
|
|
256 | juliatunnel (write_only image2d_t img, float time) |
|
|
257 | { |
|
|
258 | int2 xy = (int2)(get_global_id (0), get_global_id (1)); |
|
|
259 | float2 p = convert_float2 (xy) / $S.f * 2.f - 1.f; |
|
|
260 | |
|
|
261 | float2 m = (float2)(1.f, p.y) / fabs (p.x); // tunnel |
|
|
262 | m.x = fabs (fmod (m.x + time * 0.05f, 4.f) - 2.f); |
|
|
263 | |
|
|
264 | float2 z = m; |
|
|
265 | float2 c = (float2)(sin (time * 0.01133f), cos (time * 0.02521f)); |
|
|
266 | |
|
|
267 | for (int i = 0; i < 25 && dot (z, z) < 4.f; ++i) // standard julia |
|
|
268 | z = (float2)(z.x * z.x - z.y * z.y, 2.f * z.x * z.y) + c; |
|
|
269 | |
|
|
270 | float3 colour = (float3)(z.x, z.y, atan2 (z.y, z.x)); |
|
|
271 | write_imagef (img, xy, (float4)(colour * p.x * p.x, 1.)); |
|
|
272 | } |
|
|
273 | EOF |
|
|
274 | |
|
|
275 | my $prog = $ctx->build_program ($src); |
|
|
276 | my $kernel = $prog->kernel ("juliatunnel"); |
|
|
277 | |
|
|
278 | # program compiled, kernel ready, now draw and loop |
|
|
279 | |
|
|
280 | for (my $time; ; ++$time) { |
|
|
281 | # acquire objects from opengl |
|
|
282 | $queue->acquire_gl_objects ([$tex]); |
|
|
283 | |
|
|
284 | # configure and run our kernel |
|
|
285 | $kernel->setf ("mf", $tex, $time*2); # mf = memory object, float |
|
|
286 | $queue->nd_range_kernel ($kernel, undef, [$S, $S], undef); |
|
|
287 | |
|
|
288 | # release objects to opengl again |
|
|
289 | $queue->release_gl_objects ([$tex]); |
|
|
290 | |
|
|
291 | # wait |
|
|
292 | $queue->finish; |
|
|
293 | |
|
|
294 | # now draw the texture, the defaults should be all right |
|
|
295 | glTexParameterf GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST; |
|
|
296 | |
|
|
297 | glEnable GL_TEXTURE_2D; |
|
|
298 | glBegin GL_QUADS; |
|
|
299 | glTexCoord2f 0, 1; glVertex3i -1, -1, -1; |
|
|
300 | glTexCoord2f 0, 0; glVertex3i 1, -1, -1; |
|
|
301 | glTexCoord2f 1, 0; glVertex3i 1, 1, -1; |
|
|
302 | glTexCoord2f 1, 1; glVertex3i -1, 1, -1; |
|
|
303 | glEnd; |
|
|
304 | |
|
|
305 | glXSwapBuffers; |
|
|
306 | |
|
|
307 | select undef, undef, undef, 1/60; |
|
|
308 | } |
201 | |
309 | |
202 | =head1 DOCUMENTATION |
310 | =head1 DOCUMENTATION |
203 | |
311 | |
204 | =head2 BASIC CONVENTIONS |
312 | =head2 BASIC CONVENTIONS |
205 | |
313 | |
… | |
… | |
212 | |
320 | |
213 | =item * Object lifetime managament is automatic - there is no need |
321 | =item * Object lifetime managament is automatic - there is no need |
214 | to free objects explicitly (C<clReleaseXXX>), the release function |
322 | to free objects explicitly (C<clReleaseXXX>), the release function |
215 | is called automatically once all Perl references to it go away. |
323 | is called automatically once all Perl references to it go away. |
216 | |
324 | |
217 | =item * OpenCL uses CamelCase for function names (C<clGetPlatformInfo>), |
325 | =item * OpenCL uses CamelCase for function names |
|
|
326 | (e.g. C<clGetPlatformIDs>, C<clGetPlatformInfo>), while this module |
218 | while this module uses underscores as word separator and often leaves out |
327 | uses underscores as word separator and often leaves out prefixes |
219 | prefixes (C<< $platform->info >>). |
328 | (C<OpenCL::platforms>, C<< $platform->info >>). |
220 | |
329 | |
221 | =item * OpenCL often specifies fixed vector function arguments as short |
330 | =item * OpenCL often specifies fixed vector function arguments as short |
222 | arrays (C<$origin[3]>), while this module explicitly expects the |
331 | arrays (C<size_t origin[3]>), while this module explicitly expects the |
223 | components as separate arguments- |
332 | components as separate arguments (C<$orig_x, $orig_y, $orig_z>) in |
|
|
333 | function calls. |
224 | |
334 | |
225 | =item * Structures are often specified with their components, and returned |
335 | =item * Structures are often specified by flattening out their components |
226 | as arrayrefs. |
336 | as with short vectors, and returned as arrayrefs. |
227 | |
|
|
228 | =item * Where possible, one of the pitch values is calculated from the |
|
|
229 | perl scalar length and need not be specified. |
|
|
230 | |
337 | |
231 | =item * When enqueuing commands, the wait list is specified by adding |
338 | =item * When enqueuing commands, the wait list is specified by adding |
232 | extra arguments to the function - anywhere a C<$wait_events...> argument |
339 | extra arguments to the function - anywhere a C<$wait_events...> argument |
233 | is documented this can be any number of event objects. |
340 | is documented this can be any number of event objects. As an extsnion |
|
|
341 | implemented by this module, C<undef> values will be ignored in the event |
|
|
342 | list. |
234 | |
343 | |
235 | =item * When enqueuing commands, if the enqueue method is called in void |
344 | =item * When enqueuing commands, if the enqueue method is called in void |
236 | context, no event is created. In all other contexts an event is returned |
345 | context, no event is created. In all other contexts an event is returned |
237 | by the method. |
346 | by the method. |
238 | |
347 | |
… | |
… | |
258 | ulong IV - Q |
367 | ulong IV - Q |
259 | float NV float f |
368 | float NV float f |
260 | half IV ushort S |
369 | half IV ushort S |
261 | double NV double d |
370 | double NV double d |
262 | |
371 | |
|
|
372 | =head2 GLX SUPPORT |
|
|
373 | |
|
|
374 | Due to the sad state that OpenGL support is in in Perl (mostly the OpenGL |
|
|
375 | module, which has little to no documentation and has little to no support |
|
|
376 | for glX), this module, as a special extension, treats context creation |
|
|
377 | properties C<OpenCL::GLX_DISPLAY_KHR> and C<OpenCL::GL_CONTEXT_KHR> |
|
|
378 | specially: If either or both of these are C<undef>, then the OpenCL |
|
|
379 | module tries to dynamically resolve C<glXGetCurrentDisplay> and |
|
|
380 | C<glXGetCurrentContext>, call these functions and use their return values |
|
|
381 | instead. |
|
|
382 | |
|
|
383 | For this to work, the OpenGL library must be loaded, a GLX context must |
|
|
384 | have been created and be made current, and C<dlsym> must be available and |
|
|
385 | capable of finding the function via C<RTLD_DEFAULT>. |
|
|
386 | |
|
|
387 | =head2 EVENT SYSTEM |
|
|
388 | |
|
|
389 | OpenCL can generate a number of (potentially) asynchronous events, for |
|
|
390 | example, after compiling a program, to signal a context-related error or, |
|
|
391 | perhaps most important, to signal completion of queued jobs (by setting |
|
|
392 | callbacks on OpenCL::Event objects). |
|
|
393 | |
|
|
394 | To facilitate this, this module maintains an event queue - each |
|
|
395 | time an asynchronous event happens, it is queued, and perl will be |
|
|
396 | interrupted. This is implemented via the L<Async::Interrupt> module. In |
|
|
397 | addition, this module has L<AnyEvent> support, so it can seamlessly |
|
|
398 | integrate itself into many event loops. |
|
|
399 | |
|
|
400 | Since this module is a bit hard to understand, here are some case examples: |
|
|
401 | |
|
|
402 | =head3 Don't use callbacks. |
|
|
403 | |
|
|
404 | When your program never uses any callbacks, then there will never be any |
|
|
405 | notifications you need to take care of, and therefore no need to worry |
|
|
406 | about all this. |
|
|
407 | |
|
|
408 | You can achieve a great deal by explicitly waiting for events, or using |
|
|
409 | barriers and flush calls. In many programs, there is no need at all to |
|
|
410 | tinker with asynchronous events. |
|
|
411 | |
|
|
412 | =head3 Use AnyEvent |
|
|
413 | |
|
|
414 | This module automatically registers a watcher that invokes all outstanding |
|
|
415 | event callbacks when AnyEvent is initialised (and block asynchronous |
|
|
416 | interruptions). Using this mode of operations is the safest and most |
|
|
417 | recommended one. |
|
|
418 | |
|
|
419 | To use this, simply use AnyEvent and this module normally, make sure you |
|
|
420 | have an event loop running: |
|
|
421 | |
|
|
422 | use Gtk2 -init; |
|
|
423 | use AnyEvent; |
|
|
424 | |
|
|
425 | # initialise AnyEvent, by creating a watcher, or: |
|
|
426 | AnyEvent::detect; |
|
|
427 | |
|
|
428 | my $e = $queue->marker; |
|
|
429 | $e->cb (sub { |
|
|
430 | warn "opencl is finished\n"; |
|
|
431 | }) |
|
|
432 | |
|
|
433 | main Gtk2; |
|
|
434 | |
|
|
435 | Note that this module will not initialise AnyEvent for you. Before |
|
|
436 | AnyEvent is initialised, the module will asynchronously interrupt perl |
|
|
437 | instead. To avoid any surprises, it's best to explicitly initialise |
|
|
438 | AnyEvent. |
|
|
439 | |
|
|
440 | You can temporarily enable asynchronous interruptions (see next paragraph) |
|
|
441 | by calling C<$OpenCL::INTERRUPT->unblock> and disable them again by |
|
|
442 | calling C<$OpenCL::INTERRUPT->block>. |
|
|
443 | |
|
|
444 | =head3 Let yourself be interrupted at any time |
|
|
445 | |
|
|
446 | This mode is the default unless AnyEvent is loaded and initialised. In |
|
|
447 | this mode, OpenCL asynchronously interrupts a running perl program. The |
|
|
448 | emphasis is on both I<asynchronously> and I<running> here. |
|
|
449 | |
|
|
450 | Asynchronously means that perl might execute your callbacks at any |
|
|
451 | time. For example, in the following code (I<THAT YOU SHOULD NOT COPY>), |
|
|
452 | the C<until> loop following the marker call will be interrupted by the |
|
|
453 | callback: |
|
|
454 | |
|
|
455 | my $e = $queue->marker; |
|
|
456 | my $flag; |
|
|
457 | $e->cb (sub { $flag = 1 }); |
|
|
458 | 1 until $flag; |
|
|
459 | # $flag is now 1 |
|
|
460 | |
|
|
461 | The reason why you shouldn't blindly copy the above code is that |
|
|
462 | busy waiting is a really really bad thing, and really really bad for |
|
|
463 | performance. |
|
|
464 | |
|
|
465 | While at first this asynchronous business might look exciting, it can be |
|
|
466 | really hard, because you need to be prepared for the callback code to be |
|
|
467 | executed at any time, which limits the amount of things the callback code |
|
|
468 | can do safely. |
|
|
469 | |
|
|
470 | This can be mitigated somewhat by using C<< |
|
|
471 | $OpenCL::INTERRUPT->scope_block >> (see the L<Async::Interrupt> |
|
|
472 | documentation for details). |
|
|
473 | |
|
|
474 | The other problem is that your program must be actively I<running> to be |
|
|
475 | interrupted. When you calculate stuff, your program is running. When you |
|
|
476 | hang in some C functions or other block execution (by calling C<sleep>, |
|
|
477 | C<select>, running an event loop and so on), your program is waiting, not |
|
|
478 | running. |
|
|
479 | |
|
|
480 | One way around that would be to attach a read watcher to your event loop, |
|
|
481 | listening for events on C<< $OpenCL::INTERRUPT->pipe_fileno >>, using a |
|
|
482 | dummy callback (C<sub { }>) to temporarily execute some perl code. |
|
|
483 | |
|
|
484 | That is then awfully close to using the built-in AnyEvent support above, |
|
|
485 | though, so consider that one instead. |
|
|
486 | |
|
|
487 | =head3 Be creative |
|
|
488 | |
|
|
489 | OpenCL exports the L<Async::Interrupt> object it uses in the global |
|
|
490 | variable C<$OpenCL::INTERRUPT>. You can configure it in any way you like. |
|
|
491 | |
|
|
492 | So if you want to feel like a real pro, err, wait, if you feel no risk |
|
|
493 | menas no fun, you can experiment by implementing your own mode of |
|
|
494 | operations. |
|
|
495 | |
|
|
496 | =cut |
|
|
497 | |
|
|
498 | package OpenCL; |
|
|
499 | |
|
|
500 | use common::sense; |
|
|
501 | use Carp (); |
|
|
502 | use Async::Interrupt (); |
|
|
503 | |
|
|
504 | our $POLL_FUNC; # set by XS |
|
|
505 | |
|
|
506 | BEGIN { |
|
|
507 | our $VERSION = '0.98'; |
|
|
508 | |
|
|
509 | require XSLoader; |
|
|
510 | XSLoader::load (__PACKAGE__, $VERSION); |
|
|
511 | |
|
|
512 | @OpenCL::Platform::ISA = |
|
|
513 | @OpenCL::Device::ISA = |
|
|
514 | @OpenCL::Context::ISA = |
|
|
515 | @OpenCL::Queue::ISA = |
|
|
516 | @OpenCL::Memory::ISA = |
|
|
517 | @OpenCL::Sampler::ISA = |
|
|
518 | @OpenCL::Program::ISA = |
|
|
519 | @OpenCL::Kernel::ISA = |
|
|
520 | @OpenCL::Event::ISA = OpenCL::Object::; |
|
|
521 | |
|
|
522 | @OpenCL::Buffer::ISA = |
|
|
523 | @OpenCL::Image::ISA = OpenCL::Memory::; |
|
|
524 | |
|
|
525 | @OpenCL::BufferObj::ISA = OpenCL::Buffer::; |
|
|
526 | |
|
|
527 | @OpenCL::Image2D::ISA = |
|
|
528 | @OpenCL::Image3D::ISA = |
|
|
529 | @OpenCL::Image2DArray::ISA = |
|
|
530 | @OpenCL::Image1D::ISA = |
|
|
531 | @OpenCL::Image1DArray::ISA = |
|
|
532 | @OpenCL::Image1DBuffer::ISA = OpenCL::Image::; |
|
|
533 | |
|
|
534 | @OpenCL::UserEvent::ISA = OpenCL::Event::; |
|
|
535 | } |
|
|
536 | |
263 | =head2 THE OpenCL PACKAGE |
537 | =head2 THE OpenCL PACKAGE |
264 | |
538 | |
265 | =over 4 |
539 | =over 4 |
266 | |
540 | |
267 | =item $int = OpenCL::errno |
541 | =item $int = OpenCL::errno |
268 | |
542 | |
269 | The last error returned by a function - it's only valid after an error occured |
543 | The last error returned by a function - it's only valid after an error occured |
270 | and before calling another OpenCL function. |
544 | and before calling another OpenCL function. |
271 | |
545 | |
272 | =item $str = OpenCL::err2str $errval |
546 | =item $str = OpenCL::err2str [$errval] |
273 | |
547 | |
274 | Comverts an error value into a human readable string. |
548 | Converts an error value into a human readable string. IF no error value is |
|
|
549 | given, then the last error will be used (as returned by OpenCL::errno). |
275 | |
550 | |
276 | =item $str = OpenCL::enum2str $enum |
551 | =item $str = OpenCL::enum2str $enum |
277 | |
552 | |
278 | Converts most enum values (inof parameter names, image format constants, |
553 | Converts most enum values (of parameter names, image format constants, |
279 | object types, addressing and filter modes, command types etc.) into a |
554 | object types, addressing and filter modes, command types etc.) into a |
280 | human readbale string. When confronted with some random integer it can be |
555 | human readable string. When confronted with some random integer it can be |
281 | very helpful to pass it through this function to maybe get some readable |
556 | very helpful to pass it through this function to maybe get some readable |
282 | string out of it. |
557 | string out of it. |
283 | |
558 | |
284 | =item @platforms = OpenCL::platforms |
559 | =item @platforms = OpenCL::platforms |
285 | |
560 | |
286 | Returns all available OpenCL::Platform objects. |
561 | Returns all available OpenCL::Platform objects. |
287 | |
562 | |
288 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html> |
563 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html> |
289 | |
564 | |
290 | =item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef |
565 | =item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr |
291 | |
566 | |
292 | Tries to create a context from a default device and platform - never worked for me. |
567 | Tries to create a context from a default device and platform type - never worked for me. |
293 | |
568 | |
294 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
569 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
295 | |
570 | |
|
|
571 | =item $ctx = OpenCL::context $properties, \@devices, $callback->($err, $pvt) = $print_stderr) |
|
|
572 | |
|
|
573 | Create a new OpenCL::Context object using the given device object(s). This |
|
|
574 | function isn't implemented yet, use C<< $platform->context >> instead. |
|
|
575 | |
|
|
576 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> |
|
|
577 | |
296 | =item OpenCL::wait_for_events $wait_events... |
578 | =item OpenCL::wait_for_events $wait_events... |
297 | |
579 | |
298 | Waits for all events to complete. |
580 | Waits for all events to complete. |
299 | |
581 | |
300 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
582 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
301 | |
583 | |
|
|
584 | =item OpenCL::poll |
|
|
585 | |
|
|
586 | Checks if there are any outstanding events (see L<EVENT SYSTEM>) and |
|
|
587 | invokes their callbacks. |
|
|
588 | |
|
|
589 | =item $OpenCL::INTERRUPT |
|
|
590 | |
|
|
591 | The L<Async::Interrupt> object used to signal asynchronous events (see |
|
|
592 | L<EVENT SYSTEM>). |
|
|
593 | |
|
|
594 | =cut |
|
|
595 | |
|
|
596 | our $INTERRUPT = new Async::Interrupt c_cb => [$POLL_FUNC, 0]; |
|
|
597 | |
|
|
598 | &_eq_initialise ($INTERRUPT->signal_func); |
|
|
599 | |
|
|
600 | =item $OpenCL::WATCHER |
|
|
601 | |
|
|
602 | The L<AnyEvent> watcher object used to watch for asynchronous events (see |
|
|
603 | L<EVENT SYSTEM>). This variable is C<undef> until L<AnyEvent> has been |
|
|
604 | loaded I<and> initialised (e.g. by calling C<AnyEvent::detect>). |
|
|
605 | |
|
|
606 | =cut |
|
|
607 | |
|
|
608 | our $WATCHER; |
|
|
609 | |
|
|
610 | sub _init_anyevent { |
|
|
611 | $INTERRUPT->block; |
|
|
612 | $WATCHER = AE::io ($INTERRUPT->pipe_fileno, 0, sub { $INTERRUPT->handle }); |
|
|
613 | } |
|
|
614 | |
|
|
615 | if (defined $AnyEvent::MODEL) { |
|
|
616 | _init_anyevent; |
|
|
617 | } else { |
|
|
618 | push @AnyEvent::post_detect, \&_init_anyevent; |
|
|
619 | } |
|
|
620 | |
302 | =back |
621 | =back |
303 | |
622 | |
|
|
623 | =head2 THE OpenCL::Object CLASS |
|
|
624 | |
|
|
625 | This is the base class for all objects in the OpenCL module. The only |
|
|
626 | method it implements is the C<id> method, which is only useful if you want |
|
|
627 | to interface to OpenCL on the C level. |
|
|
628 | |
|
|
629 | =over 4 |
|
|
630 | |
|
|
631 | =item $iv = $obj->id |
|
|
632 | |
|
|
633 | OpenCL objects are represented by pointers or integers on the C level. If |
|
|
634 | you want to interface to an OpenCL object directly on the C level, then |
|
|
635 | you need this value, which is returned by this method. You should use an |
|
|
636 | C<IV> type in your code and cast that to the correct type. |
|
|
637 | |
|
|
638 | =cut |
|
|
639 | |
|
|
640 | sub OpenCL::Object::id { |
|
|
641 | ref $_[0] eq "SCALAR" |
|
|
642 | ? ${ $_[0] } |
|
|
643 | : $_[0][0] |
|
|
644 | } |
|
|
645 | |
|
|
646 | =back |
|
|
647 | |
304 | =head2 THE OpenCL::Platform CLASS |
648 | =head2 THE OpenCL::Platform CLASS |
305 | |
649 | |
306 | =over 4 |
650 | =over 4 |
307 | |
651 | |
308 | =item $packed_value = $platform->info ($name) |
|
|
309 | |
|
|
310 | Calls C<clGetPlatformInfo> and returns the packed, raw value - for |
|
|
311 | strings, this will be the string, for other values you probably need to |
|
|
312 | use the correct C<unpack>. This might get improved in the future. Hopefully. |
|
|
313 | |
|
|
314 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html> |
|
|
315 | |
|
|
316 | =item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL) |
652 | =item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL) |
317 | |
653 | |
318 | Returns a list of matching OpenCL::Device objects. |
654 | Returns a list of matching OpenCL::Device objects. |
319 | |
655 | |
320 | =item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef) |
656 | =item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $callback->($err, $pvt) = $print_stderr) |
321 | |
657 | |
322 | Tries to create a context. Never worked for me, and you need devices explitly anyway. |
658 | Tries to create a context. Never worked for me, and you need devices explicitly anyway. |
323 | |
659 | |
324 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
660 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
325 | |
661 | |
326 | =item $ctx = $device->context ($properties = undef, @$devices, $notify = undef) |
662 | =item $ctx = $platform->context ($properties, \@devices, $callback->($err, $pvt) = $print_stderr) |
327 | |
663 | |
328 | Create a new OpenCL::Context object using the given device object(s)- a |
664 | Create a new OpenCL::Context object using the given device object(s)- a |
329 | CL_CONTEXT_PLATFORM property is supplied automatically. |
665 | CL_CONTEXT_PLATFORM property is supplied automatically. |
330 | |
666 | |
331 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> |
667 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> |
332 | |
668 | |
|
|
669 | =item $packed_value = $platform->info ($name) |
|
|
670 | |
|
|
671 | Calls C<clGetPlatformInfo> and returns the packed, raw value - for |
|
|
672 | strings, this will be the string (possibly including terminating \0), for |
|
|
673 | other values you probably need to use the correct C<unpack>. |
|
|
674 | |
|
|
675 | It's best to avoid this method and use one of the following convenience |
|
|
676 | wrappers. |
|
|
677 | |
|
|
678 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html> |
|
|
679 | |
|
|
680 | =item $platform->unload_compiler |
|
|
681 | |
|
|
682 | Attempts to unload the compiler for this platform, for endless |
|
|
683 | profit. Does nothing on OpenCL 1.1. |
|
|
684 | |
|
|
685 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clUnloadPlatformCompiler.html> |
|
|
686 | |
|
|
687 | =for gengetinfo begin platform |
|
|
688 | |
|
|
689 | =item $string = $platform->profile |
|
|
690 | |
|
|
691 | Calls C<clGetPlatformInfo> with C<CL_PLATFORM_PROFILE> and returns the result. |
|
|
692 | |
|
|
693 | =item $string = $platform->version |
|
|
694 | |
|
|
695 | Calls C<clGetPlatformInfo> with C<CL_PLATFORM_VERSION> and returns the result. |
|
|
696 | |
|
|
697 | =item $string = $platform->name |
|
|
698 | |
|
|
699 | Calls C<clGetPlatformInfo> with C<CL_PLATFORM_NAME> and returns the result. |
|
|
700 | |
|
|
701 | =item $string = $platform->vendor |
|
|
702 | |
|
|
703 | Calls C<clGetPlatformInfo> with C<CL_PLATFORM_VENDOR> and returns the result. |
|
|
704 | |
|
|
705 | =item $string = $platform->extensions |
|
|
706 | |
|
|
707 | Calls C<clGetPlatformInfo> with C<CL_PLATFORM_EXTENSIONS> and returns the result. |
|
|
708 | |
|
|
709 | =for gengetinfo end platform |
|
|
710 | |
333 | =back |
711 | =back |
334 | |
712 | |
335 | =head2 THE OpenCL::Device CLASS |
713 | =head2 THE OpenCL::Device CLASS |
336 | |
714 | |
337 | =over 4 |
715 | =over 4 |
… | |
… | |
340 | |
718 | |
341 | See C<< $platform->info >> for details. |
719 | See C<< $platform->info >> for details. |
342 | |
720 | |
343 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetDeviceInfo.html> |
721 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetDeviceInfo.html> |
344 | |
722 | |
|
|
723 | =for gengetinfo begin device |
|
|
724 | |
|
|
725 | =item $device_type = $device->type |
|
|
726 | |
|
|
727 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_TYPE> and returns the result. |
|
|
728 | |
|
|
729 | =item $uint = $device->vendor_id |
|
|
730 | |
|
|
731 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_VENDOR_ID> and returns the result. |
|
|
732 | |
|
|
733 | =item $uint = $device->max_compute_units |
|
|
734 | |
|
|
735 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_COMPUTE_UNITS> and returns the result. |
|
|
736 | |
|
|
737 | =item $uint = $device->max_work_item_dimensions |
|
|
738 | |
|
|
739 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS> and returns the result. |
|
|
740 | |
|
|
741 | =item $int = $device->max_work_group_size |
|
|
742 | |
|
|
743 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_WORK_GROUP_SIZE> and returns the result. |
|
|
744 | |
|
|
745 | =item @ints = $device->max_work_item_sizes |
|
|
746 | |
|
|
747 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_WORK_ITEM_SIZES> and returns the result. |
|
|
748 | |
|
|
749 | =item $uint = $device->preferred_vector_width_char |
|
|
750 | |
|
|
751 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_CHAR> and returns the result. |
|
|
752 | |
|
|
753 | =item $uint = $device->preferred_vector_width_short |
|
|
754 | |
|
|
755 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_SHORT> and returns the result. |
|
|
756 | |
|
|
757 | =item $uint = $device->preferred_vector_width_int |
|
|
758 | |
|
|
759 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_INT> and returns the result. |
|
|
760 | |
|
|
761 | =item $uint = $device->preferred_vector_width_long |
|
|
762 | |
|
|
763 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_LONG> and returns the result. |
|
|
764 | |
|
|
765 | =item $uint = $device->preferred_vector_width_float |
|
|
766 | |
|
|
767 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_FLOAT> and returns the result. |
|
|
768 | |
|
|
769 | =item $uint = $device->preferred_vector_width_double |
|
|
770 | |
|
|
771 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_DOUBLE> and returns the result. |
|
|
772 | |
|
|
773 | =item $uint = $device->max_clock_frequency |
|
|
774 | |
|
|
775 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_CLOCK_FREQUENCY> and returns the result. |
|
|
776 | |
|
|
777 | =item $bitfield = $device->address_bits |
|
|
778 | |
|
|
779 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_ADDRESS_BITS> and returns the result. |
|
|
780 | |
|
|
781 | =item $uint = $device->max_read_image_args |
|
|
782 | |
|
|
783 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_READ_IMAGE_ARGS> and returns the result. |
|
|
784 | |
|
|
785 | =item $uint = $device->max_write_image_args |
|
|
786 | |
|
|
787 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_WRITE_IMAGE_ARGS> and returns the result. |
|
|
788 | |
|
|
789 | =item $ulong = $device->max_mem_alloc_size |
|
|
790 | |
|
|
791 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_MEM_ALLOC_SIZE> and returns the result. |
|
|
792 | |
|
|
793 | =item $int = $device->image2d_max_width |
|
|
794 | |
|
|
795 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE2D_MAX_WIDTH> and returns the result. |
|
|
796 | |
|
|
797 | =item $int = $device->image2d_max_height |
|
|
798 | |
|
|
799 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE2D_MAX_HEIGHT> and returns the result. |
|
|
800 | |
|
|
801 | =item $int = $device->image3d_max_width |
|
|
802 | |
|
|
803 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE3D_MAX_WIDTH> and returns the result. |
|
|
804 | |
|
|
805 | =item $int = $device->image3d_max_height |
|
|
806 | |
|
|
807 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE3D_MAX_HEIGHT> and returns the result. |
|
|
808 | |
|
|
809 | =item $int = $device->image3d_max_depth |
|
|
810 | |
|
|
811 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE3D_MAX_DEPTH> and returns the result. |
|
|
812 | |
|
|
813 | =item $uint = $device->image_support |
|
|
814 | |
|
|
815 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE_SUPPORT> and returns the result. |
|
|
816 | |
|
|
817 | =item $int = $device->max_parameter_size |
|
|
818 | |
|
|
819 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_PARAMETER_SIZE> and returns the result. |
|
|
820 | |
|
|
821 | =item $uint = $device->max_samplers |
|
|
822 | |
|
|
823 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_SAMPLERS> and returns the result. |
|
|
824 | |
|
|
825 | =item $uint = $device->mem_base_addr_align |
|
|
826 | |
|
|
827 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MEM_BASE_ADDR_ALIGN> and returns the result. |
|
|
828 | |
|
|
829 | =item $uint = $device->min_data_type_align_size |
|
|
830 | |
|
|
831 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MIN_DATA_TYPE_ALIGN_SIZE> and returns the result. |
|
|
832 | |
|
|
833 | =item $device_fp_config = $device->single_fp_config |
|
|
834 | |
|
|
835 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_SINGLE_FP_CONFIG> and returns the result. |
|
|
836 | |
|
|
837 | =item $device_mem_cache_type = $device->global_mem_cache_type |
|
|
838 | |
|
|
839 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_GLOBAL_MEM_CACHE_TYPE> and returns the result. |
|
|
840 | |
|
|
841 | =item $uint = $device->global_mem_cacheline_size |
|
|
842 | |
|
|
843 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_GLOBAL_MEM_CACHELINE_SIZE> and returns the result. |
|
|
844 | |
|
|
845 | =item $ulong = $device->global_mem_cache_size |
|
|
846 | |
|
|
847 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_GLOBAL_MEM_CACHE_SIZE> and returns the result. |
|
|
848 | |
|
|
849 | =item $ulong = $device->global_mem_size |
|
|
850 | |
|
|
851 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_GLOBAL_MEM_SIZE> and returns the result. |
|
|
852 | |
|
|
853 | =item $ulong = $device->max_constant_buffer_size |
|
|
854 | |
|
|
855 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_CONSTANT_BUFFER_SIZE> and returns the result. |
|
|
856 | |
|
|
857 | =item $uint = $device->max_constant_args |
|
|
858 | |
|
|
859 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_CONSTANT_ARGS> and returns the result. |
|
|
860 | |
|
|
861 | =item $device_local_mem_type = $device->local_mem_type |
|
|
862 | |
|
|
863 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_LOCAL_MEM_TYPE> and returns the result. |
|
|
864 | |
|
|
865 | =item $ulong = $device->local_mem_size |
|
|
866 | |
|
|
867 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_LOCAL_MEM_SIZE> and returns the result. |
|
|
868 | |
|
|
869 | =item $boolean = $device->error_correction_support |
|
|
870 | |
|
|
871 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_ERROR_CORRECTION_SUPPORT> and returns the result. |
|
|
872 | |
|
|
873 | =item $int = $device->profiling_timer_resolution |
|
|
874 | |
|
|
875 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PROFILING_TIMER_RESOLUTION> and returns the result. |
|
|
876 | |
|
|
877 | =item $boolean = $device->endian_little |
|
|
878 | |
|
|
879 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_ENDIAN_LITTLE> and returns the result. |
|
|
880 | |
|
|
881 | =item $boolean = $device->available |
|
|
882 | |
|
|
883 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_AVAILABLE> and returns the result. |
|
|
884 | |
|
|
885 | =item $boolean = $device->compiler_available |
|
|
886 | |
|
|
887 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_COMPILER_AVAILABLE> and returns the result. |
|
|
888 | |
|
|
889 | =item $device_exec_capabilities = $device->execution_capabilities |
|
|
890 | |
|
|
891 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_EXECUTION_CAPABILITIES> and returns the result. |
|
|
892 | |
|
|
893 | =item $command_queue_properties = $device->properties |
|
|
894 | |
|
|
895 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_QUEUE_PROPERTIES> and returns the result. |
|
|
896 | |
|
|
897 | =item $ = $device->platform |
|
|
898 | |
|
|
899 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PLATFORM> and returns the result. |
|
|
900 | |
|
|
901 | =item $string = $device->name |
|
|
902 | |
|
|
903 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_NAME> and returns the result. |
|
|
904 | |
|
|
905 | =item $string = $device->vendor |
|
|
906 | |
|
|
907 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_VENDOR> and returns the result. |
|
|
908 | |
|
|
909 | =item $string = $device->driver_version |
|
|
910 | |
|
|
911 | Calls C<clGetDeviceInfo> with C<CL_DRIVER_VERSION> and returns the result. |
|
|
912 | |
|
|
913 | =item $string = $device->profile |
|
|
914 | |
|
|
915 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PROFILE> and returns the result. |
|
|
916 | |
|
|
917 | =item $string = $device->version |
|
|
918 | |
|
|
919 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_VERSION> and returns the result. |
|
|
920 | |
|
|
921 | =item $string = $device->extensions |
|
|
922 | |
|
|
923 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_EXTENSIONS> and returns the result. |
|
|
924 | |
|
|
925 | =item $uint = $device->preferred_vector_width_half |
|
|
926 | |
|
|
927 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_HALF> and returns the result. |
|
|
928 | |
|
|
929 | =item $uint = $device->native_vector_width_char |
|
|
930 | |
|
|
931 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_CHAR> and returns the result. |
|
|
932 | |
|
|
933 | =item $uint = $device->native_vector_width_short |
|
|
934 | |
|
|
935 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_SHORT> and returns the result. |
|
|
936 | |
|
|
937 | =item $uint = $device->native_vector_width_int |
|
|
938 | |
|
|
939 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_INT> and returns the result. |
|
|
940 | |
|
|
941 | =item $uint = $device->native_vector_width_long |
|
|
942 | |
|
|
943 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_LONG> and returns the result. |
|
|
944 | |
|
|
945 | =item $uint = $device->native_vector_width_float |
|
|
946 | |
|
|
947 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_FLOAT> and returns the result. |
|
|
948 | |
|
|
949 | =item $uint = $device->native_vector_width_double |
|
|
950 | |
|
|
951 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_DOUBLE> and returns the result. |
|
|
952 | |
|
|
953 | =item $uint = $device->native_vector_width_half |
|
|
954 | |
|
|
955 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_HALF> and returns the result. |
|
|
956 | |
|
|
957 | =item $device_fp_config = $device->double_fp_config |
|
|
958 | |
|
|
959 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_DOUBLE_FP_CONFIG> and returns the result. |
|
|
960 | |
|
|
961 | =item $device_fp_config = $device->half_fp_config |
|
|
962 | |
|
|
963 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_HALF_FP_CONFIG> and returns the result. |
|
|
964 | |
|
|
965 | =item $boolean = $device->host_unified_memory |
|
|
966 | |
|
|
967 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_HOST_UNIFIED_MEMORY> and returns the result. |
|
|
968 | |
|
|
969 | =item $device = $device->parent_device_ext |
|
|
970 | |
|
|
971 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARENT_DEVICE_EXT> and returns the result. |
|
|
972 | |
|
|
973 | =item @device_partition_property_exts = $device->partition_types_ext |
|
|
974 | |
|
|
975 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_TYPES_EXT> and returns the result. |
|
|
976 | |
|
|
977 | =item @device_partition_property_exts = $device->affinity_domains_ext |
|
|
978 | |
|
|
979 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_AFFINITY_DOMAINS_EXT> and returns the result. |
|
|
980 | |
|
|
981 | =item $uint = $device->reference_count_ext |
|
|
982 | |
|
|
983 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_REFERENCE_COUNT_EXT> and returns the result. |
|
|
984 | |
|
|
985 | =item @device_partition_property_exts = $device->partition_style_ext |
|
|
986 | |
|
|
987 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_STYLE_EXT> and returns the result. |
|
|
988 | |
|
|
989 | =for gengetinfo end device |
|
|
990 | |
345 | =back |
991 | =back |
346 | |
992 | |
347 | =head2 THE OpenCL::Context CLASS |
993 | =head2 THE OpenCL::Context CLASS |
348 | |
994 | |
349 | =over 4 |
995 | =over 4 |
350 | |
996 | |
351 | =item $packed_value = $ctx->info ($name) |
997 | =item $prog = $ctx->build_program ($program, $options = "") |
352 | |
998 | |
353 | See C<< $platform->info >> for details. |
999 | This convenience function tries to build the program on all devices in |
|
|
1000 | the context. If the build fails, then the function will C<croak> with the |
|
|
1001 | build log. Otherwise ti returns the program object. |
354 | |
1002 | |
355 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetContextInfo.html> |
1003 | The C<$program> can either be a C<OpenCL::Program> object or a string |
|
|
1004 | containing the program. In the latter case, a program objetc will be |
|
|
1005 | created automatically. |
|
|
1006 | |
|
|
1007 | =cut |
|
|
1008 | |
|
|
1009 | sub OpenCL::Context::build_program { |
|
|
1010 | my ($self, $prog, $options) = @_; |
|
|
1011 | |
|
|
1012 | $prog = $self->program_with_source ($prog) |
|
|
1013 | unless ref $prog; |
|
|
1014 | |
|
|
1015 | eval { $prog->build (undef, $options); 1 } |
|
|
1016 | or errno == BUILD_PROGRAM_FAILURE |
|
|
1017 | or errno == INVALID_BINARY # workaround nvidia bug |
|
|
1018 | or Carp::croak "OpenCL::Context->build_program: " . err2str; |
|
|
1019 | |
|
|
1020 | # we check status for all devices |
|
|
1021 | for my $dev ($self->devices) { |
|
|
1022 | $prog->build_status ($dev) == BUILD_SUCCESS |
|
|
1023 | or Carp::croak "Building OpenCL program for device '" . $dev->name . "' failed:\n" |
|
|
1024 | . $prog->build_log ($dev); |
|
|
1025 | } |
|
|
1026 | |
|
|
1027 | $prog |
|
|
1028 | } |
356 | |
1029 | |
357 | =item $queue = $ctx->queue ($device, $properties) |
1030 | =item $queue = $ctx->queue ($device, $properties) |
358 | |
1031 | |
359 | Create a new OpenCL::Queue object from the context and the given device. |
1032 | Create a new OpenCL::Queue object from the context and the given device. |
360 | |
1033 | |
361 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html> |
1034 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html> |
362 | |
1035 | |
|
|
1036 | Example: create an out-of-order queue. |
|
|
1037 | |
|
|
1038 | $queue = $ctx->queue ($device, OpenCL::QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE); |
|
|
1039 | |
363 | =item $ev = $ctx->user_event |
1040 | =item $ev = $ctx->user_event |
364 | |
1041 | |
365 | Creates a new OpenCL::UserEvent object. |
1042 | Creates a new OpenCL::UserEvent object. |
366 | |
1043 | |
367 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateUserEvent.html> |
1044 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateUserEvent.html> |
368 | |
1045 | |
369 | =item $buf = $ctx->buffer ($flags, $len) |
1046 | =item $buf = $ctx->buffer ($flags, $len) |
370 | |
1047 | |
371 | Creates a new OpenCL::Buffer object with the given flags and octet-size. |
1048 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object with the |
|
|
1049 | given flags and octet-size. |
372 | |
1050 | |
373 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateBuffer.html> |
1051 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateBuffer.html> |
374 | |
1052 | |
375 | =item $buf = $ctx->buffer_sv ($flags, $data) |
1053 | =item $buf = $ctx->buffer_sv ($flags, $data) |
376 | |
1054 | |
377 | Creates a new OpenCL::Buffer object and initialise it with the given data values. |
1055 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and |
|
|
1056 | initialise it with the given data values. |
378 | |
1057 | |
|
|
1058 | =item $img = $ctx->image ($self, $flags, $channel_order, $channel_type, $type, $width, $height, $depth = 0, $array_size = 0, $row_pitch = 0, $slice_pitch = 0, $num_mip_level = 0, $num_samples = 0, $*data = &PL_sv_undef) |
|
|
1059 | |
|
|
1060 | Creates a new OpenCL::Image object and optionally initialises it with |
|
|
1061 | the given data values. |
|
|
1062 | |
|
|
1063 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateImage.html> |
|
|
1064 | |
379 | =item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $data) |
1065 | =item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $row_pitch = 0, $data = undef) |
380 | |
1066 | |
381 | Creates a new OpenCL::Image2D object and optionally initialises it with the given data values. |
1067 | Creates a new OpenCL::Image2D object and optionally initialises it with |
|
|
1068 | the given data values. |
382 | |
1069 | |
383 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage2D.html> |
1070 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage2D.html> |
384 | |
1071 | |
385 | =item $img = $ctx->image3d ($flags, $channel_order, $channel_type, $width, $height, $depth, $slice_pitch, $data) |
1072 | =item $img = $ctx->image3d ($flags, $channel_order, $channel_type, $width, $height, $depth, $row_pitch = 0, $slice_pitch = 0, $data = undef) |
386 | |
1073 | |
387 | Creates a new OpenCL::Image3D object and optionally initialises it with the given data values. |
1074 | Creates a new OpenCL::Image3D object and optionally initialises it with |
|
|
1075 | the given data values. |
388 | |
1076 | |
389 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage3D.html> |
1077 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage3D.html> |
|
|
1078 | |
|
|
1079 | =item $buffer = $ctx->gl_buffer ($flags, $bufobj) |
|
|
1080 | |
|
|
1081 | Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object that refers to the given |
|
|
1082 | OpenGL buffer object. |
|
|
1083 | |
|
|
1084 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLBuffer.html |
|
|
1085 | |
|
|
1086 | =item $img = $ctx->gl_texture ($flags, $target, $miplevel, $texture) |
|
|
1087 | |
|
|
1088 | Creates a new OpenCL::Image object that refers to the given OpenGL |
|
|
1089 | texture object or buffer. |
|
|
1090 | |
|
|
1091 | http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clCreateFromGLTexture.html |
|
|
1092 | |
|
|
1093 | =item $img = $ctx->gl_texture2d ($flags, $target, $miplevel, $texture) |
|
|
1094 | |
|
|
1095 | Creates a new OpenCL::Image2D object that refers to the given OpenGL |
|
|
1096 | 2D texture object. |
|
|
1097 | |
|
|
1098 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture2D.html |
|
|
1099 | |
|
|
1100 | =item $img = $ctx->gl_texture3d ($flags, $target, $miplevel, $texture) |
|
|
1101 | |
|
|
1102 | Creates a new OpenCL::Image3D object that refers to the given OpenGL |
|
|
1103 | 3D texture object. |
|
|
1104 | |
|
|
1105 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture3D.html |
|
|
1106 | |
|
|
1107 | =item $ctx->gl_renderbuffer ($flags, $renderbuffer) |
|
|
1108 | |
|
|
1109 | Creates a new OpenCL::Image2D object that refers to the given OpenGL |
|
|
1110 | render buffer. |
|
|
1111 | |
|
|
1112 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLRenderbuffer.html |
390 | |
1113 | |
391 | =item @formats = $ctx->supported_image_formats ($flags, $image_type) |
1114 | =item @formats = $ctx->supported_image_formats ($flags, $image_type) |
392 | |
1115 | |
393 | Returns a list of matching image formats - each format is an arrayref with |
1116 | Returns a list of matching image formats - each format is an arrayref with |
394 | two values, $channel_order and $channel_type, in it. |
1117 | two values, $channel_order and $channel_type, in it. |
… | |
… | |
405 | |
1128 | |
406 | Creates a new OpenCL::Program object from the given source code. |
1129 | Creates a new OpenCL::Program object from the given source code. |
407 | |
1130 | |
408 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateProgramWithSource.html> |
1131 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateProgramWithSource.html> |
409 | |
1132 | |
|
|
1133 | =item $packed_value = $ctx->info ($name) |
|
|
1134 | |
|
|
1135 | See C<< $platform->info >> for details. |
|
|
1136 | |
|
|
1137 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetContextInfo.html> |
|
|
1138 | |
|
|
1139 | =for gengetinfo begin context |
|
|
1140 | |
|
|
1141 | =item $uint = $context->reference_count |
|
|
1142 | |
|
|
1143 | Calls C<clGetContextInfo> with C<CL_CONTEXT_REFERENCE_COUNT> and returns the result. |
|
|
1144 | |
|
|
1145 | =item @devices = $context->devices |
|
|
1146 | |
|
|
1147 | Calls C<clGetContextInfo> with C<CL_CONTEXT_DEVICES> and returns the result. |
|
|
1148 | |
|
|
1149 | =item @property_ints = $context->properties |
|
|
1150 | |
|
|
1151 | Calls C<clGetContextInfo> with C<CL_CONTEXT_PROPERTIES> and returns the result. |
|
|
1152 | |
|
|
1153 | =item $uint = $context->num_devices |
|
|
1154 | |
|
|
1155 | Calls C<clGetContextInfo> with C<CL_CONTEXT_NUM_DEVICES> and returns the result. |
|
|
1156 | |
|
|
1157 | =for gengetinfo end context |
|
|
1158 | |
410 | =back |
1159 | =back |
411 | |
1160 | |
412 | =head2 THE OpenCL::Queue CLASS |
1161 | =head2 THE OpenCL::Queue CLASS |
413 | |
1162 | |
414 | An OpenCL::Queue represents an execution queue for OpenCL. You execute |
1163 | An OpenCL::Queue represents an execution queue for OpenCL. You execute |
415 | requests by calling their respective C<enqueue_xxx> method and waitinf for |
1164 | requests by calling their respective method and waiting for it to complete |
416 | it to complete in some way. |
1165 | in some way. |
417 | |
1166 | |
418 | All the enqueue methods return an event object that can be used to wait |
1167 | Most methods that enqueue some request return an event object that can |
419 | for completion, unless the method is called in void context, in which case |
1168 | be used to wait for completion (optionally using a callback), unless |
420 | no event object is created. |
1169 | the method is called in void context, in which case no event object is |
|
|
1170 | created. |
421 | |
1171 | |
422 | They also allow you to specify any number of other event objects that this |
1172 | They also allow you to specify any number of other event objects that this |
423 | request has to wait for before it starts executing, by simply passing the |
1173 | request has to wait for before it starts executing, by simply passing the |
424 | event objects as extra parameters to the enqueue methods. |
1174 | event objects as extra parameters to the enqueue methods. To simplify |
|
|
1175 | program design, this module ignores any C<undef> values in the list of |
|
|
1176 | events. This makes it possible to code operations such as this, without |
|
|
1177 | having to put a valid event object into C<$event> first: |
|
|
1178 | |
|
|
1179 | $event = $queue->xxx (..., $event); |
425 | |
1180 | |
426 | Queues execute in-order by default, without any parallelism, so in most |
1181 | Queues execute in-order by default, without any parallelism, so in most |
427 | cases (i.e. you use only one queue) it's not necessary to wait for or |
1182 | cases (i.e. you use only one queue) it's not necessary to wait for or |
428 | create event objects. |
1183 | create event objects, althoguh an our of order queue is often a bit |
|
|
1184 | faster. |
429 | |
1185 | |
430 | =over 4 |
1186 | =over 4 |
431 | |
1187 | |
432 | =item $packed_value = $ctx->info ($name) |
|
|
433 | |
|
|
434 | See C<< $platform->info >> for details. |
|
|
435 | |
|
|
436 | L<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...) |
1188 | =item $ev = $queue->read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) |
439 | |
1189 | |
440 | Reads data from buffer into the given string. |
1190 | Reads data from buffer into the given string. |
441 | |
1191 | |
442 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html> |
1192 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html> |
443 | |
1193 | |
444 | =item $ev = $queue->enqueue_write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) |
1194 | =item $ev = $queue->write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) |
445 | |
1195 | |
446 | Writes data to buffer from the given string. |
1196 | Writes data to buffer from the given string. |
447 | |
1197 | |
448 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html> |
1198 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html> |
449 | |
1199 | |
450 | =item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) |
1200 | =item $ev = $queue->copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) |
451 | |
1201 | |
452 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> |
1202 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> |
453 | |
1203 | |
|
|
1204 | =item $ev = $queue->read_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) |
|
|
1205 | |
|
|
1206 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html |
|
|
1207 | |
|
|
1208 | =item $ev = $queue->write_buffer_rect (OpenCL::Memory buf, cl_bool blocking, $buf_x, $buf_y, $buf_z, $host_x, $host_y, $host_z, $width, $height, $depth, $buf_row_pitch, $buf_slice_pitch, $host_row_pitch, $host_slice_pitch, $data, $wait_events...) |
|
|
1209 | |
|
|
1210 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html |
|
|
1211 | |
454 | =item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
1212 | =item $ev = $queue->read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
|
|
1213 | |
|
|
1214 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html> |
|
|
1215 | |
|
|
1216 | =item $ev = $queue->copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
455 | |
1217 | |
456 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> |
1218 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> |
457 | |
1219 | |
458 | =item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $data, $wait_events...) |
1220 | =item $ev = $queue->write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
459 | |
1221 | |
460 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> |
1222 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> |
461 | |
1223 | |
|
|
1224 | =item $ev = $queue->copy_image ($src_image, $dst_image, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
|
|
1225 | |
|
|
1226 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> |
|
|
1227 | |
|
|
1228 | =item $ev = $queue->copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...) |
|
|
1229 | |
|
|
1230 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html> |
|
|
1231 | |
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, $wait_event...) |
1232 | =item $ev = $queue->copy_buffer_rect ($src, $dst, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $src_row_pitch, $src_slice_pitch, $dst_row_pitch, $dst_slice_pitch, $wait_event...) |
463 | |
1233 | |
464 | Yeah. |
1234 | Yeah. |
465 | |
1235 | |
466 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html> |
|
|
467 | |
|
|
468 | =item $ev = $queue->enqueue_copy_buffer_to_image ($src_buffer, $dst_image, $src_offset, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
|
|
469 | |
|
|
470 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
1236 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
471 | |
1237 | |
472 | =item $ev = $queue->enqueue_copy_image ($src_image, $dst_image, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $wait_events...) |
1238 | =item $ev = $queue->fill_buffer ($mem, $pattern, $offset, $size, ...) |
473 | |
1239 | |
|
|
1240 | Fills the given buffer object with repeated applications of C<$pattern>, |
|
|
1241 | starting at C<$offset> for C<$size> octets. |
|
|
1242 | |
|
|
1243 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillBuffer.html> |
|
|
1244 | |
|
|
1245 | =item $ev = $queue->fill_image ($img, $r, $g, $b, $a, $x, $y, $z, $width, $height, $depth, ...) |
|
|
1246 | |
|
|
1247 | Fills the given image area with the given rgba colour components. The |
|
|
1248 | components are normally floating point values between C<0> and C<1>, |
|
|
1249 | except when the image channel data type is a signe dor unsigned |
|
|
1250 | unnormalised format, in which case the range is determined by the format. |
|
|
1251 | |
474 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> |
1252 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueFillImage.html> |
475 | |
1253 | |
476 | =item $ev = $queue->enqueue_copy_image_to_buffer ($src_image, $dst_image, $src_x, $src_y, $src_z, $width, $height, $depth, $dst_offset, $wait_events...) |
|
|
477 | |
|
|
478 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html> |
|
|
479 | |
|
|
480 | =item $ev = $queue->enqueue_task ($kernel, $wait_events...) |
1254 | =item $ev = $queue->task ($kernel, $wait_events...) |
481 | |
1255 | |
482 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
1256 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
483 | |
1257 | |
484 | =item $ev = $queue->enqueue_nd_range_kernel ($kernel, @$global_work_offset, @$global_work_size, @$local_work_size, $wait_events...) |
1258 | =item $ev = $queue->nd_range_kernel ($kernel, \@global_work_offset, \@global_work_size, \@local_work_size, $wait_events...) |
485 | |
1259 | |
486 | Enqueues a kernel execution. |
1260 | Enqueues a kernel execution. |
487 | |
1261 | |
488 | @$global_work_size must be specified as a reference to an array of |
1262 | \@global_work_size must be specified as a reference to an array of |
489 | integers specifying the work sizes (element counts). |
1263 | integers specifying the work sizes (element counts). |
490 | |
1264 | |
491 | @$global_work_offset must be either C<undef> (in which case all offsets |
1265 | \@global_work_offset must be either C<undef> (in which case all offsets |
492 | are C<0>), or a reference to an array of work offsets, with the same number |
1266 | are C<0>), or a reference to an array of work offsets, with the same number |
493 | of elements as @$global_work_size. |
1267 | of elements as \@global_work_size. |
494 | |
1268 | |
495 | @$local_work_size must be either C<undef> (in which case the |
1269 | \@local_work_size must be either C<undef> (in which case the |
496 | implementation is supposed to choose good local work sizes), or a |
1270 | implementation is supposed to choose good local work sizes), or a |
497 | reference to an array of local work sizes, with the same number of |
1271 | reference to an array of local work sizes, with the same number of |
498 | elements as @$global_work_size. |
1272 | elements as \@global_work_size. |
499 | |
1273 | |
500 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
1274 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
501 | |
1275 | |
502 | =item $ev = $queue->enqueue_marker |
1276 | =item $ev = $queue->acquire_gl_objects ([object, ...], $wait_events...) |
503 | |
1277 | |
|
|
1278 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be acquired |
|
|
1279 | for subsequent OpenCL usage. |
|
|
1280 | |
504 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueMarker.html> |
1281 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueAcquireGLObjects.html> |
505 | |
1282 | |
|
|
1283 | =item $ev = $queue->release_gl_objects ([object, ...], $wait_events...) |
|
|
1284 | |
|
|
1285 | Enqueues a list (an array-ref of OpenCL::Memory objects) to be released |
|
|
1286 | for subsequent OpenGL usage. |
|
|
1287 | |
|
|
1288 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReleaseGLObjects.html> |
|
|
1289 | |
506 | =item $ev = $queue->enqueue_wait_for_events ($wait_events...) |
1290 | =item $ev = $queue->wait_for_events ($wait_events...) |
507 | |
1291 | |
508 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
1292 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
509 | |
1293 | |
510 | =item $queue->enqueue_barrier |
1294 | =item $ev = $queue->marker ($wait_events...) |
511 | |
1295 | |
|
|
1296 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueMarkerWithWaitList.html> |
|
|
1297 | |
|
|
1298 | =item $ev = $queue->barrier ($wait_events...) |
|
|
1299 | |
512 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueBarrier.html> |
1300 | L<http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/clEnqueueBarrierWithWaitList.html> |
513 | |
1301 | |
514 | =item $queue->flush |
1302 | =item $queue->flush |
515 | |
1303 | |
516 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html> |
1304 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html> |
517 | |
1305 | |
518 | =item $queue->finish |
1306 | =item $queue->finish |
519 | |
1307 | |
520 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFinish.html> |
1308 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFinish.html> |
521 | |
1309 | |
|
|
1310 | =item $packed_value = $queue->info ($name) |
|
|
1311 | |
|
|
1312 | See C<< $platform->info >> for details. |
|
|
1313 | |
|
|
1314 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetCommandQueueInfo.html> |
|
|
1315 | |
|
|
1316 | =for gengetinfo begin command_queue |
|
|
1317 | |
|
|
1318 | =item $ctx = $command_queue->context |
|
|
1319 | |
|
|
1320 | Calls C<clGetCommandQueueInfo> with C<CL_QUEUE_CONTEXT> and returns the result. |
|
|
1321 | |
|
|
1322 | =item $device = $command_queue->device |
|
|
1323 | |
|
|
1324 | Calls C<clGetCommandQueueInfo> with C<CL_QUEUE_DEVICE> and returns the result. |
|
|
1325 | |
|
|
1326 | =item $uint = $command_queue->reference_count |
|
|
1327 | |
|
|
1328 | Calls C<clGetCommandQueueInfo> with C<CL_QUEUE_REFERENCE_COUNT> and returns the result. |
|
|
1329 | |
|
|
1330 | =item $command_queue_properties = $command_queue->properties |
|
|
1331 | |
|
|
1332 | Calls C<clGetCommandQueueInfo> with C<CL_QUEUE_PROPERTIES> and returns the result. |
|
|
1333 | |
|
|
1334 | =for gengetinfo end command_queue |
|
|
1335 | |
522 | =back |
1336 | =back |
523 | |
1337 | |
524 | =head2 THE OpenCL::Memory CLASS |
1338 | =head2 THE OpenCL::Memory CLASS |
525 | |
1339 | |
526 | This the superclass of all memory objects - OpenCL::Buffer, OpenCL::Image, |
1340 | This the superclass of all memory objects - OpenCL::Buffer, OpenCL::Image, |
527 | OpenCL::Image2D and OpenCL::Image3D. The subclasses of this class |
1341 | OpenCL::Image2D and OpenCL::Image3D. |
528 | currently only exist to allow type-checking. |
|
|
529 | |
1342 | |
530 | =over 4 |
1343 | =over 4 |
531 | |
1344 | |
532 | =item $packed_value = $memory->info ($name) |
1345 | =item $packed_value = $memory->info ($name) |
533 | |
1346 | |
534 | See C<< $platform->info >> for details. |
1347 | See C<< $platform->info >> for details. |
535 | |
1348 | |
536 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetMemObjectInfo.html> |
1349 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetMemObjectInfo.html> |
537 | |
1350 | |
|
|
1351 | =for gengetinfo begin mem |
|
|
1352 | |
|
|
1353 | =item $mem_object_type = $mem->type |
|
|
1354 | |
|
|
1355 | Calls C<clGetMemObjectInfo> with C<CL_MEM_TYPE> and returns the result. |
|
|
1356 | |
|
|
1357 | =item $mem_flags = $mem->flags |
|
|
1358 | |
|
|
1359 | Calls C<clGetMemObjectInfo> with C<CL_MEM_FLAGS> and returns the result. |
|
|
1360 | |
|
|
1361 | =item $int = $mem->size |
|
|
1362 | |
|
|
1363 | Calls C<clGetMemObjectInfo> with C<CL_MEM_SIZE> and returns the result. |
|
|
1364 | |
|
|
1365 | =item $ptr_value = $mem->host_ptr |
|
|
1366 | |
|
|
1367 | Calls C<clGetMemObjectInfo> with C<CL_MEM_HOST_PTR> and returns the result. |
|
|
1368 | |
|
|
1369 | =item $uint = $mem->map_count |
|
|
1370 | |
|
|
1371 | Calls C<clGetMemObjectInfo> with C<CL_MEM_MAP_COUNT> and returns the result. |
|
|
1372 | |
|
|
1373 | =item $uint = $mem->reference_count |
|
|
1374 | |
|
|
1375 | Calls C<clGetMemObjectInfo> with C<CL_MEM_REFERENCE_COUNT> and returns the result. |
|
|
1376 | |
|
|
1377 | =item $ctx = $mem->context |
|
|
1378 | |
|
|
1379 | Calls C<clGetMemObjectInfo> with C<CL_MEM_CONTEXT> and returns the result. |
|
|
1380 | |
|
|
1381 | =item $mem = $mem->associated_memobject |
|
|
1382 | |
|
|
1383 | Calls C<clGetMemObjectInfo> with C<CL_MEM_ASSOCIATED_MEMOBJECT> and returns the result. |
|
|
1384 | |
|
|
1385 | =item $int = $mem->offset |
|
|
1386 | |
|
|
1387 | Calls C<clGetMemObjectInfo> with C<CL_MEM_OFFSET> and returns the result. |
|
|
1388 | |
|
|
1389 | =for gengetinfo end mem |
|
|
1390 | |
|
|
1391 | =item ($type, $name) = $mem->gl_object_info |
|
|
1392 | |
|
|
1393 | Returns the OpenGL object type (e.g. OpenCL::GL_OBJECT_TEXTURE2D) and the |
|
|
1394 | object "name" (e.g. the texture name) used to create this memory object. |
|
|
1395 | |
|
|
1396 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetGLObjectInfo.html> |
|
|
1397 | |
538 | =back |
1398 | =back |
539 | |
1399 | |
|
|
1400 | =head2 THE OpenCL::Buffer CLASS |
|
|
1401 | |
|
|
1402 | This is a subclass of OpenCL::Memory, and the superclass of |
|
|
1403 | OpenCL::BufferObj. Its purpose is simply to distinguish between buffers |
|
|
1404 | and sub-buffers. |
|
|
1405 | |
|
|
1406 | =head2 THE OpenCL::BufferObj CLASS |
|
|
1407 | |
|
|
1408 | This is a subclass of OpenCL::Buffer and thus OpenCL::Memory. It exists |
|
|
1409 | because one cna create sub buffers of OpenLC::BufferObj objects, but not |
|
|
1410 | sub buffers from these sub buffers. |
|
|
1411 | |
|
|
1412 | =over 4 |
|
|
1413 | |
|
|
1414 | =item $subbuf = $buf_obj->sub_buffer_region ($flags, $origin, $size) |
|
|
1415 | |
|
|
1416 | Creates an OpenCL::Buffer objects from this buffer and returns it. The |
|
|
1417 | C<buffer_create_type> is assumed to be C<CL_BUFFER_CREATE_TYPE_REGION>. |
|
|
1418 | |
|
|
1419 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateSubBuffer.html> |
|
|
1420 | |
|
|
1421 | =back |
|
|
1422 | |
|
|
1423 | =head2 THE OpenCL::Image CLASS |
|
|
1424 | |
|
|
1425 | This is the superclass of all image objects - OpenCL::Image1D, |
|
|
1426 | OpenCL::Image1DArray, OpenCL::Image1DBuffer, OpenCL::Image2D, |
|
|
1427 | OpenCL::Image2DArray and OpenCL::Image3D. |
|
|
1428 | |
|
|
1429 | =over 4 |
|
|
1430 | |
|
|
1431 | =item $packed_value = $image->image_info ($name) |
|
|
1432 | |
|
|
1433 | See C<< $platform->info >> for details. |
|
|
1434 | |
|
|
1435 | The reason this method is not called C<info> is that there already is an |
|
|
1436 | C<< ->info >> method inherited from C<OpenCL::Memory>. |
|
|
1437 | |
|
|
1438 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html> |
|
|
1439 | |
|
|
1440 | =item ($channel_order, $channel_data_type) = $image->format |
|
|
1441 | |
|
|
1442 | Returns the channel order and type used to create the image by calling |
|
|
1443 | C<clGetImageInfo> with C<CL_IMAGE_FORMAT>. |
|
|
1444 | |
|
|
1445 | =for gengetinfo begin image |
|
|
1446 | |
|
|
1447 | =item $int = $image->element_size |
|
|
1448 | |
|
|
1449 | Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result. |
|
|
1450 | |
|
|
1451 | =item $int = $image->row_pitch |
|
|
1452 | |
|
|
1453 | Calls C<clGetImageInfo> with C<CL_IMAGE_ROW_PITCH> and returns the result. |
|
|
1454 | |
|
|
1455 | =item $int = $image->slice_pitch |
|
|
1456 | |
|
|
1457 | Calls C<clGetImageInfo> with C<CL_IMAGE_SLICE_PITCH> and returns the result. |
|
|
1458 | |
|
|
1459 | =item $int = $image->width |
|
|
1460 | |
|
|
1461 | Calls C<clGetImageInfo> with C<CL_IMAGE_WIDTH> and returns the result. |
|
|
1462 | |
|
|
1463 | =item $int = $image->height |
|
|
1464 | |
|
|
1465 | Calls C<clGetImageInfo> with C<CL_IMAGE_HEIGHT> and returns the result. |
|
|
1466 | |
|
|
1467 | =item $int = $image->depth |
|
|
1468 | |
|
|
1469 | Calls C<clGetImageInfo> with C<CL_IMAGE_DEPTH> and returns the result. |
|
|
1470 | |
|
|
1471 | =for gengetinfo end image |
|
|
1472 | |
|
|
1473 | =for gengetinfo begin gl_texture |
|
|
1474 | |
|
|
1475 | =item $GLenum = $gl_texture->target |
|
|
1476 | |
|
|
1477 | Calls C<clGetGLTextureInfo> with C<CL_GL_TEXTURE_TARGET> and returns the result. |
|
|
1478 | |
|
|
1479 | =item $GLint = $gl_texture->gl_mipmap_level |
|
|
1480 | |
|
|
1481 | Calls C<clGetGLTextureInfo> with C<CL_GL_MIPMAP_LEVEL> and returns the result. |
|
|
1482 | |
|
|
1483 | =for gengetinfo end gl_texture |
|
|
1484 | |
|
|
1485 | =back |
|
|
1486 | |
540 | =head2 THE OpenCL::Sampler CLASS |
1487 | =head2 THE OpenCL::Sampler CLASS |
541 | |
1488 | |
542 | =over 4 |
1489 | =over 4 |
543 | |
1490 | |
544 | =item $packed_value = $sampler->info ($name) |
1491 | =item $packed_value = $sampler->info ($name) |
545 | |
1492 | |
546 | See C<< $platform->info >> for details. |
1493 | See C<< $platform->info >> for details. |
547 | |
1494 | |
548 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetSamplerInfo.html> |
1495 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetSamplerInfo.html> |
549 | |
1496 | |
|
|
1497 | =for gengetinfo begin sampler |
|
|
1498 | |
|
|
1499 | =item $uint = $sampler->reference_count |
|
|
1500 | |
|
|
1501 | Calls C<clGetSamplerInfo> with C<CL_SAMPLER_REFERENCE_COUNT> and returns the result. |
|
|
1502 | |
|
|
1503 | =item $ctx = $sampler->context |
|
|
1504 | |
|
|
1505 | Calls C<clGetSamplerInfo> with C<CL_SAMPLER_CONTEXT> and returns the result. |
|
|
1506 | |
|
|
1507 | =item $addressing_mode = $sampler->normalized_coords |
|
|
1508 | |
|
|
1509 | Calls C<clGetSamplerInfo> with C<CL_SAMPLER_NORMALIZED_COORDS> and returns the result. |
|
|
1510 | |
|
|
1511 | =item $filter_mode = $sampler->addressing_mode |
|
|
1512 | |
|
|
1513 | Calls C<clGetSamplerInfo> with C<CL_SAMPLER_ADDRESSING_MODE> and returns the result. |
|
|
1514 | |
|
|
1515 | =item $boolean = $sampler->filter_mode |
|
|
1516 | |
|
|
1517 | Calls C<clGetSamplerInfo> with C<CL_SAMPLER_FILTER_MODE> and returns the result. |
|
|
1518 | |
|
|
1519 | =for gengetinfo end sampler |
|
|
1520 | |
550 | =back |
1521 | =back |
551 | |
1522 | |
552 | =head2 THE OpenCL::Program CLASS |
1523 | =head2 THE OpenCL::Program CLASS |
553 | |
1524 | |
554 | =over 4 |
1525 | =over 4 |
555 | |
1526 | |
556 | =item $packed_value = $program->info ($name) |
1527 | =item $program->build (\@devices = undef, $options = "", $cb->($program) = undef) |
557 | |
1528 | |
558 | See C<< $platform->info >> for details. |
|
|
559 | |
|
|
560 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetProgramInfo.html> |
|
|
561 | |
|
|
562 | =item $program->build ($device, $options = "") |
|
|
563 | |
|
|
564 | Tries to build the program with the givne options. |
1529 | Tries to build the program with the given options. See also the |
|
|
1530 | C<$ctx->build> convenience function. |
|
|
1531 | |
|
|
1532 | If a callback is specified, then it will be called when compilation is |
|
|
1533 | finished. Note that many OpenCL implementations block your program while |
|
|
1534 | compiling whether you use a callback or not. See C<build_async> if you |
|
|
1535 | want to make sure the build is done in the background. |
|
|
1536 | |
|
|
1537 | Note that some OpenCL implementations act up badly, and don't call the |
|
|
1538 | callback in some error cases (but call it in others). This implementation |
|
|
1539 | assumes the callback will always be called, and leaks memory if this is |
|
|
1540 | not so. So best make sure you don't pass in invalid values. |
|
|
1541 | |
|
|
1542 | Some implementations fail with C<OpenCL::INVALID_BINARY> when the |
|
|
1543 | compilation state is successful but some later stage fails. |
565 | |
1544 | |
566 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
1545 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
|
|
1546 | |
|
|
1547 | =item $program->build_async (\@devices = undef, $options = "", $cb->($program) = undef) |
|
|
1548 | |
|
|
1549 | Similar to C<< ->build >>, except it starts a thread, and never fails (you |
|
|
1550 | need to check the compilation status form the callback, or by polling). |
567 | |
1551 | |
568 | =item $packed_value = $program->build_info ($device, $name) |
1552 | =item $packed_value = $program->build_info ($device, $name) |
569 | |
1553 | |
570 | Similar to C<< $platform->info >>, but returns build info for a previous |
1554 | Similar to C<< $platform->info >>, but returns build info for a previous |
571 | build attempt for the given device. |
1555 | build attempt for the given device. |
… | |
… | |
577 | Creates an OpenCL::Kernel object out of the named C<__kernel> function in |
1561 | Creates an OpenCL::Kernel object out of the named C<__kernel> function in |
578 | the program. |
1562 | the program. |
579 | |
1563 | |
580 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html> |
1564 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html> |
581 | |
1565 | |
|
|
1566 | =item @kernels = $program->kernels_in_program |
|
|
1567 | |
|
|
1568 | Returns all kernels successfully compiled for all devices in program. |
|
|
1569 | |
|
|
1570 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernelsInProgram.html |
|
|
1571 | |
|
|
1572 | =for gengetinfo begin program_build |
|
|
1573 | |
|
|
1574 | =item $build_status = $program->build_status ($device) |
|
|
1575 | |
|
|
1576 | Calls C<clGetProgramBuildInfo> with C<CL_PROGRAM_BUILD_STATUS> and returns the result. |
|
|
1577 | |
|
|
1578 | =item $string = $program->build_options ($device) |
|
|
1579 | |
|
|
1580 | Calls C<clGetProgramBuildInfo> with C<CL_PROGRAM_BUILD_OPTIONS> and returns the result. |
|
|
1581 | |
|
|
1582 | =item $string = $program->build_log ($device) |
|
|
1583 | |
|
|
1584 | Calls C<clGetProgramBuildInfo> with C<CL_PROGRAM_BUILD_LOG> and returns the result. |
|
|
1585 | |
|
|
1586 | =for gengetinfo end program_build |
|
|
1587 | |
|
|
1588 | =item $packed_value = $program->info ($name) |
|
|
1589 | |
|
|
1590 | See C<< $platform->info >> for details. |
|
|
1591 | |
|
|
1592 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetProgramInfo.html> |
|
|
1593 | |
|
|
1594 | =for gengetinfo begin program |
|
|
1595 | |
|
|
1596 | =item $uint = $program->reference_count |
|
|
1597 | |
|
|
1598 | Calls C<clGetProgramInfo> with C<CL_PROGRAM_REFERENCE_COUNT> and returns the result. |
|
|
1599 | |
|
|
1600 | =item $ctx = $program->context |
|
|
1601 | |
|
|
1602 | Calls C<clGetProgramInfo> with C<CL_PROGRAM_CONTEXT> and returns the result. |
|
|
1603 | |
|
|
1604 | =item $uint = $program->num_devices |
|
|
1605 | |
|
|
1606 | Calls C<clGetProgramInfo> with C<CL_PROGRAM_NUM_DEVICES> and returns the result. |
|
|
1607 | |
|
|
1608 | =item @devices = $program->devices |
|
|
1609 | |
|
|
1610 | Calls C<clGetProgramInfo> with C<CL_PROGRAM_DEVICES> and returns the result. |
|
|
1611 | |
|
|
1612 | =item $string = $program->source |
|
|
1613 | |
|
|
1614 | Calls C<clGetProgramInfo> with C<CL_PROGRAM_SOURCE> and returns the result. |
|
|
1615 | |
|
|
1616 | =item @ints = $program->binary_sizes |
|
|
1617 | |
|
|
1618 | Calls C<clGetProgramInfo> with C<CL_PROGRAM_BINARY_SIZES> and returns the result. |
|
|
1619 | |
|
|
1620 | =for gengetinfo end program |
|
|
1621 | |
|
|
1622 | =item @blobs = $program->binaries |
|
|
1623 | |
|
|
1624 | Returns a string for the compiled binary for every device associated with |
|
|
1625 | the program, empty strings indicate missing programs, and an empty result |
|
|
1626 | means no program binaries are available. |
|
|
1627 | |
|
|
1628 | These "binaries" are often, in fact, informative low-level assembly |
|
|
1629 | sources. |
|
|
1630 | |
|
|
1631 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetProgramInfo.html> |
|
|
1632 | |
582 | =back |
1633 | =back |
583 | |
1634 | |
584 | =head2 THE OpenCL::Kernel CLASS |
1635 | =head2 THE OpenCL::Kernel CLASS |
585 | |
1636 | |
586 | =over 4 |
1637 | =over 4 |
… | |
… | |
589 | |
1640 | |
590 | See C<< $platform->info >> for details. |
1641 | See C<< $platform->info >> for details. |
591 | |
1642 | |
592 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetKernelInfo.html> |
1643 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetKernelInfo.html> |
593 | |
1644 | |
|
|
1645 | =for gengetinfo begin kernel |
|
|
1646 | |
|
|
1647 | =item $string = $kernel->function_name |
|
|
1648 | |
|
|
1649 | Calls C<clGetKernelInfo> with C<CL_KERNEL_FUNCTION_NAME> and returns the result. |
|
|
1650 | |
|
|
1651 | =item $uint = $kernel->num_args |
|
|
1652 | |
|
|
1653 | Calls C<clGetKernelInfo> with C<CL_KERNEL_NUM_ARGS> and returns the result. |
|
|
1654 | |
|
|
1655 | =item $uint = $kernel->reference_count |
|
|
1656 | |
|
|
1657 | Calls C<clGetKernelInfo> with C<CL_KERNEL_REFERENCE_COUNT> and returns the result. |
|
|
1658 | |
|
|
1659 | =item $ctx = $kernel->context |
|
|
1660 | |
|
|
1661 | Calls C<clGetKernelInfo> with C<CL_KERNEL_CONTEXT> and returns the result. |
|
|
1662 | |
|
|
1663 | =item $program = $kernel->program |
|
|
1664 | |
|
|
1665 | Calls C<clGetKernelInfo> with C<CL_KERNEL_PROGRAM> and returns the result. |
|
|
1666 | |
|
|
1667 | =for gengetinfo end kernel |
|
|
1668 | |
|
|
1669 | =item $packed_value = $kernel->work_group_info ($device, $name) |
|
|
1670 | |
|
|
1671 | See C<< $platform->info >> for details. |
|
|
1672 | |
|
|
1673 | The reason this method is not called C<info> is that there already is an |
|
|
1674 | C<< ->info >> method. |
|
|
1675 | |
|
|
1676 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetKernelWorkGroupInfo.html> |
|
|
1677 | |
|
|
1678 | =for gengetinfo begin kernel_work_group |
|
|
1679 | |
|
|
1680 | =item $int = $kernel->work_group_size ($device) |
|
|
1681 | |
|
|
1682 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_WORK_GROUP_SIZE> and returns the result. |
|
|
1683 | |
|
|
1684 | =item @ints = $kernel->compile_work_group_size ($device) |
|
|
1685 | |
|
|
1686 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_COMPILE_WORK_GROUP_SIZE> and returns the result. |
|
|
1687 | |
|
|
1688 | =item $ulong = $kernel->local_mem_size ($device) |
|
|
1689 | |
|
|
1690 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_LOCAL_MEM_SIZE> and returns the result. |
|
|
1691 | |
|
|
1692 | =item $int = $kernel->preferred_work_group_size_multiple ($device) |
|
|
1693 | |
|
|
1694 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PREFERRED_WORK_GROUP_SIZE_MULTIPLE> and returns the result. |
|
|
1695 | |
|
|
1696 | =item $ulong = $kernel->private_mem_size ($device) |
|
|
1697 | |
|
|
1698 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result. |
|
|
1699 | |
|
|
1700 | =for gengetinfo end kernel_work_group |
|
|
1701 | |
|
|
1702 | =item $kernel->setf ($format, ...) |
|
|
1703 | |
|
|
1704 | Sets the arguments of a kernel. Since OpenCL 1.1 doesn't have a generic |
|
|
1705 | way to set arguments (and with OpenCL 1.2 it might be rather slow), you |
|
|
1706 | need to specify a format argument, much as with C<printf>, to tell OpenCL |
|
|
1707 | what type of argument it is. |
|
|
1708 | |
|
|
1709 | The format arguments are single letters: |
|
|
1710 | |
|
|
1711 | c char |
|
|
1712 | C unsigned char |
|
|
1713 | s short |
|
|
1714 | S unsigned short |
|
|
1715 | i int |
|
|
1716 | I unsigned int |
|
|
1717 | l long |
|
|
1718 | L unsigned long |
|
|
1719 | |
|
|
1720 | h half float (0..65535) |
|
|
1721 | f float |
|
|
1722 | d double |
|
|
1723 | |
|
|
1724 | z local (octet size) |
|
|
1725 | |
|
|
1726 | m memory object (buffer or image) |
|
|
1727 | a sampler |
|
|
1728 | e event |
|
|
1729 | |
|
|
1730 | Space characters in the format string are ignored. |
|
|
1731 | |
|
|
1732 | Example: set the arguments for a kernel that expects an int, two floats, a buffer and an image. |
|
|
1733 | |
|
|
1734 | $kernel->setf ("i ff mm", 5, 0.5, 3, $buffer, $image); |
|
|
1735 | |
594 | =item $kernel->set_TYPE ($index, $value) |
1736 | =item $kernel->set_TYPE ($index, $value) |
595 | |
1737 | |
|
|
1738 | =item $kernel->set_char ($index, $value) |
|
|
1739 | |
|
|
1740 | =item $kernel->set_uchar ($index, $value) |
|
|
1741 | |
|
|
1742 | =item $kernel->set_short ($index, $value) |
|
|
1743 | |
|
|
1744 | =item $kernel->set_ushort ($index, $value) |
|
|
1745 | |
|
|
1746 | =item $kernel->set_int ($index, $value) |
|
|
1747 | |
|
|
1748 | =item $kernel->set_uint ($index, $value) |
|
|
1749 | |
|
|
1750 | =item $kernel->set_long ($index, $value) |
|
|
1751 | |
|
|
1752 | =item $kernel->set_ulong ($index, $value) |
|
|
1753 | |
|
|
1754 | =item $kernel->set_half ($index, $value) |
|
|
1755 | |
|
|
1756 | =item $kernel->set_float ($index, $value) |
|
|
1757 | |
|
|
1758 | =item $kernel->set_double ($index, $value) |
|
|
1759 | |
|
|
1760 | =item $kernel->set_memory ($index, $value) |
|
|
1761 | |
|
|
1762 | =item $kernel->set_buffer ($index, $value) |
|
|
1763 | |
|
|
1764 | =item $kernel->set_image ($index, $value) |
|
|
1765 | |
|
|
1766 | =item $kernel->set_sampler ($index, $value) |
|
|
1767 | |
|
|
1768 | =item $kernel->set_local ($index, $value) |
|
|
1769 | |
|
|
1770 | =item $kernel->set_event ($index, $value) |
|
|
1771 | |
596 | This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>. |
1772 | This is a family of methods to set the kernel argument with the number |
597 | |
1773 | C<$index> to the give C<$value>. |
598 | TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>, |
|
|
599 | C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>, |
|
|
600 | C<image2d>, C<image3d>, C<sampler> or C<event>. |
|
|
601 | |
1774 | |
602 | Chars and integers (including the half type) are specified as integers, |
1775 | Chars and integers (including the half type) are specified as integers, |
603 | float and double as floating point values, memory/buffer/image2d/image3d |
1776 | float and double as floating point values, memory/buffer/image must be |
604 | must be an object of that type or C<undef>, and sampler and event must be |
1777 | an object of that type or C<undef>, local-memory arguments are set by |
605 | objects of that type. |
1778 | specifying the size, and sampler and event must be objects of that type. |
|
|
1779 | |
|
|
1780 | Note that C<set_memory> works for all memory objects (all types of buffers |
|
|
1781 | and images) - the main purpose of the more specific C<set_TYPE> functions |
|
|
1782 | is type checking. |
|
|
1783 | |
|
|
1784 | Setting an argument for a kernel does NOT keep a reference to the object - |
|
|
1785 | for example, if you set an argument to some image object, free the image, |
|
|
1786 | and call the kernel, you will run into undefined behaviour. |
606 | |
1787 | |
607 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html> |
1788 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html> |
608 | |
1789 | |
609 | =back |
1790 | =back |
610 | |
1791 | |
… | |
… | |
613 | This is the superclass for all event objects (including OpenCL::UserEvent |
1794 | This is the superclass for all event objects (including OpenCL::UserEvent |
614 | objects). |
1795 | objects). |
615 | |
1796 | |
616 | =over 4 |
1797 | =over 4 |
617 | |
1798 | |
|
|
1799 | =item $ev->wait |
|
|
1800 | |
|
|
1801 | Waits for the event to complete. |
|
|
1802 | |
|
|
1803 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
|
|
1804 | |
|
|
1805 | =item $ev->cb ($exec_callback_type, $callback->($event, $event_command_exec_status)) |
|
|
1806 | |
|
|
1807 | Adds a callback to the callback stack for the given event type. There is |
|
|
1808 | no way to remove a callback again. |
|
|
1809 | |
|
|
1810 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetEventCallback.html> |
|
|
1811 | |
618 | =item $packed_value = $ev->info ($name) |
1812 | =item $packed_value = $ev->info ($name) |
619 | |
1813 | |
620 | See C<< $platform->info >> for details. |
1814 | See C<< $platform->info >> for details. |
621 | |
1815 | |
622 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html> |
1816 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html> |
623 | |
1817 | |
624 | =item $ev->wait |
1818 | =for gengetinfo begin event |
625 | |
1819 | |
626 | Waits for the event to complete. |
1820 | =item $queue = $event->command_queue |
627 | |
1821 | |
|
|
1822 | Calls C<clGetEventInfo> with C<CL_EVENT_COMMAND_QUEUE> and returns the result. |
|
|
1823 | |
|
|
1824 | =item $command_type = $event->command_type |
|
|
1825 | |
|
|
1826 | Calls C<clGetEventInfo> with C<CL_EVENT_COMMAND_TYPE> and returns the result. |
|
|
1827 | |
|
|
1828 | =item $uint = $event->reference_count |
|
|
1829 | |
|
|
1830 | Calls C<clGetEventInfo> with C<CL_EVENT_REFERENCE_COUNT> and returns the result. |
|
|
1831 | |
|
|
1832 | =item $uint = $event->command_execution_status |
|
|
1833 | |
|
|
1834 | Calls C<clGetEventInfo> with C<CL_EVENT_COMMAND_EXECUTION_STATUS> and returns the result. |
|
|
1835 | |
|
|
1836 | =item $ctx = $event->context |
|
|
1837 | |
|
|
1838 | Calls C<clGetEventInfo> with C<CL_EVENT_CONTEXT> and returns the result. |
|
|
1839 | |
|
|
1840 | =for gengetinfo end event |
|
|
1841 | |
|
|
1842 | =item $packed_value = $ev->profiling_info ($name) |
|
|
1843 | |
|
|
1844 | See C<< $platform->info >> for details. |
|
|
1845 | |
|
|
1846 | The reason this method is not called C<info> is that there already is an |
|
|
1847 | C<< ->info >> method. |
|
|
1848 | |
628 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
1849 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetProfilingInfo.html> |
|
|
1850 | |
|
|
1851 | =for gengetinfo begin profiling |
|
|
1852 | |
|
|
1853 | =item $ulong = $event->profiling_command_queued |
|
|
1854 | |
|
|
1855 | Calls C<clGetEventProfilingInfo> with C<CL_PROFILING_COMMAND_QUEUED> and returns the result. |
|
|
1856 | |
|
|
1857 | =item $ulong = $event->profiling_command_submit |
|
|
1858 | |
|
|
1859 | Calls C<clGetEventProfilingInfo> with C<CL_PROFILING_COMMAND_SUBMIT> and returns the result. |
|
|
1860 | |
|
|
1861 | =item $ulong = $event->profiling_command_start |
|
|
1862 | |
|
|
1863 | Calls C<clGetEventProfilingInfo> with C<CL_PROFILING_COMMAND_START> and returns the result. |
|
|
1864 | |
|
|
1865 | =item $ulong = $event->profiling_command_end |
|
|
1866 | |
|
|
1867 | Calls C<clGetEventProfilingInfo> with C<CL_PROFILING_COMMAND_END> and returns the result. |
|
|
1868 | |
|
|
1869 | =for gengetinfo end profiling |
629 | |
1870 | |
630 | =back |
1871 | =back |
631 | |
1872 | |
632 | =head2 THE OpenCL::UserEvent CLASS |
1873 | =head2 THE OpenCL::UserEvent CLASS |
633 | |
1874 | |
… | |
… | |
635 | |
1876 | |
636 | =over 4 |
1877 | =over 4 |
637 | |
1878 | |
638 | =item $ev->set_status ($execution_status) |
1879 | =item $ev->set_status ($execution_status) |
639 | |
1880 | |
|
|
1881 | Sets the execution status of the user event. Can only be called once, |
|
|
1882 | either with OpenCL::COMPLETE or a negative number as status. |
|
|
1883 | |
640 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html> |
1884 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html> |
641 | |
1885 | |
642 | =back |
1886 | =back |
643 | |
1887 | |
644 | =cut |
1888 | =cut |
645 | |
|
|
646 | package OpenCL; |
|
|
647 | |
|
|
648 | use common::sense; |
|
|
649 | |
|
|
650 | BEGIN { |
|
|
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 | } |
|
|
664 | |
1889 | |
665 | 1; |
1890 | 1; |
666 | |
1891 | |
667 | =head1 AUTHOR |
1892 | =head1 AUTHOR |
668 | |
1893 | |