1 | =head1 NAME |
1 | =head1 NAME |
2 | |
2 | |
3 | OpenCL - bindings to, well, OpenCL |
3 | OpenCL - Open Computing Language Bindings |
4 | |
4 | |
5 | =head1 SYNOPSIS |
5 | =head1 SYNOPSIS |
6 | |
6 | |
7 | use OpenCL; |
7 | use OpenCL; |
8 | |
8 | |
9 | =head1 DESCRIPTION |
9 | =head1 DESCRIPTION |
10 | |
10 | |
11 | This is an early release which is not useful yet. |
11 | This is an early release which might be useful, but hasn't seen much testing. |
12 | |
12 | |
|
|
13 | =head2 OpenCL FROM 10000 FEET HEIGHT |
|
|
14 | |
|
|
15 | Here is a high level overview of OpenCL: |
|
|
16 | |
|
|
17 | First you need to find one or more OpenCL::Platforms (kind of like |
|
|
18 | vendors) - usually there is only one. |
|
|
19 | |
|
|
20 | Each platform gives you access to a number of OpenCL::Device objects, e.g. |
|
|
21 | your graphics card. |
|
|
22 | |
|
|
23 | From a platform and some device(s), you create an OpenCL::Context, which is |
|
|
24 | a very central object in OpenCL: Once you have a context you can create |
|
|
25 | most other objects: |
|
|
26 | |
|
|
27 | OpenCL::Program objects, which store source code and, after building for a |
|
|
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 |
|
|
30 | which represents basically a function call with argument values. |
|
|
31 | |
|
|
32 | OpenCL::Memory objects of various flavours: OpenCL::Buffer objects (flat |
|
|
33 | memory areas, think arrays or structs) and OpenCL::Image objects (think 2d |
|
|
34 | or 3d array) for bulk data and input and output for kernels. |
|
|
35 | |
|
|
36 | OpenCL::Sampler objects, which are kind of like texture filter modes in |
|
|
37 | OpenGL. |
|
|
38 | |
|
|
39 | OpenCL::Queue objects - command queues, which allow you to submit memory |
|
|
40 | reads, writes and copies, as well as kernel calls to your devices. They |
|
|
41 | also offer a variety of methods to synchronise request execution, for |
|
|
42 | example with barriers or OpenCL::Event objects. |
|
|
43 | |
|
|
44 | OpenCL::Event objects are used to signal when something is complete. |
|
|
45 | |
|
|
46 | =head2 HELPFUL RESOURCES |
|
|
47 | |
|
|
48 | The OpenCL spec used to develop this module (1.2 spec was available, but |
|
|
49 | no implementation was available to me :). |
|
|
50 | |
|
|
51 | http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf |
|
|
52 | |
|
|
53 | OpenCL manpages: |
|
|
54 | |
|
|
55 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/ |
|
|
56 | |
|
|
57 | If you are into UML class diagrams, the following diagram might help - if |
|
|
58 | not, it will be mildly cobfusing: |
|
|
59 | |
|
|
60 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/classDiagram.html |
|
|
61 | |
|
|
62 | Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it |
|
|
63 | is, but at least it's free of charge: |
|
|
64 | |
|
|
65 | http://developer.amd.com/zones/OpenCLZone/courses/Documents/Introduction_to_OpenCL_Programming%20Training_Guide%20%28201005%29.pdf |
|
|
66 | |
|
|
67 | And here's NVIDIA's OpenCL Best Practises Guide: |
|
|
68 | |
|
|
69 | http://developer.download.nvidia.com/compute/cuda/3_2/toolkit/docs/OpenCL_Best_Practices_Guide.pdf |
|
|
70 | |
|
|
71 | =head1 BASIC WORKFLOW |
|
|
72 | |
|
|
73 | To get something done, you basically have to do this once (refer to the |
|
|
74 | examples below for actual code, this is just a high-level description): |
|
|
75 | |
|
|
76 | Find some platform (e.g. the first one) and some device(s) (e.g. the first |
|
|
77 | device of the platform), and create a context from those. |
|
|
78 | |
|
|
79 | Create program objects from your OpenCL source code, then build (compile) |
|
|
80 | the programs for each device you want to run them on. |
|
|
81 | |
|
|
82 | Create kernel objects for all kernels you want to use (surprisingly, these |
|
|
83 | are not device-specific). |
|
|
84 | |
|
|
85 | Then, to execute stuff, you repeat these steps, possibly resuing or |
|
|
86 | sharing some buffers: |
|
|
87 | |
|
|
88 | Create some input and output buffers from your context. Set these as |
|
|
89 | arguments to your kernel. |
|
|
90 | |
|
|
91 | Enqueue buffer writes to initialise your input buffers (when not |
|
|
92 | initialised at creation time). |
|
|
93 | |
|
|
94 | Enqueue the kernel execution. |
|
|
95 | |
|
|
96 | Enqueue buffer reads for your output buffer to read results. |
|
|
97 | |
|
|
98 | =head1 EXAMPLES |
|
|
99 | |
13 | Enumerate all devices and get contexts for them; |
100 | =head2 Enumerate all devices and get contexts for them. |
|
|
101 | |
|
|
102 | Best run this once to get a feel for the platforms and devices in your |
|
|
103 | system. |
14 | |
104 | |
15 | for my $platform (OpenCL::platforms) { |
105 | for my $platform (OpenCL::platforms) { |
16 | warn $platform->info (OpenCL::PLATFORM_NAME); |
106 | printf "platform: %s\n", $platform->info (OpenCL::PLATFORM_NAME); |
17 | warn $platform->info (OpenCL::PLATFORM_EXTENSIONS); |
107 | printf "extensions: %s\n", $platform->info (OpenCL::PLATFORM_EXTENSIONS); |
18 | for my $device ($platform->devices) { |
108 | for my $device ($platform->devices) { |
19 | warn $device->info (OpenCL::DEVICE_NAME); |
109 | printf "+ device: %s\n", $device->info (OpenCL::DEVICE_NAME); |
20 | my $ctx = $device->context_simple; |
110 | my $ctx = $device->context; |
21 | # do stuff |
111 | # do stuff |
22 | } |
112 | } |
23 | } |
113 | } |
24 | |
114 | |
25 | Get a useful context and a command queue: |
115 | =head2 Get a useful context and a command queue. |
26 | |
116 | |
27 | my $dev = ((OpenCL::platforms)[0]->devices)[0]; |
117 | This is a useful boilerplate for any OpenCL program that only wants to use |
28 | my $ctx = $dev->context_simple; |
118 | one device, |
29 | my $queue = $ctx->command_queue_simple ($dev); |
119 | |
|
|
120 | my ($platform) = OpenCL::platforms; # find first platform |
|
|
121 | my ($dev) = $platform->devices; # find first device of platform |
|
|
122 | my $ctx = $platform->context (undef, [$dev]); # create context out of those |
|
|
123 | my $queue = $ctx->queue ($dev); # create a command queue for the device |
|
|
124 | |
|
|
125 | =head2 Print all supported image formats of a context. |
|
|
126 | |
|
|
127 | Best run this once for your context, to see whats available and how to |
|
|
128 | gather information. |
|
|
129 | |
|
|
130 | for my $type (OpenCL::MEM_OBJECT_IMAGE2D, OpenCL::MEM_OBJECT_IMAGE3D) { |
|
|
131 | print "supported image formats for ", OpenCL::enum2str $type, "\n"; |
|
|
132 | |
|
|
133 | for my $f ($ctx->supported_image_formats (0, $type)) { |
|
|
134 | printf " %-10s %-20s\n", OpenCL::enum2str $f->[0], OpenCL::enum2str $f->[1]; |
|
|
135 | } |
|
|
136 | } |
|
|
137 | |
|
|
138 | =head2 Create a buffer with some predefined data, read it back synchronously, |
|
|
139 | then asynchronously. |
|
|
140 | |
|
|
141 | my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); |
|
|
142 | |
|
|
143 | $queue->enqueue_read_buffer ($buf, 1, 1, 3, my $data); |
|
|
144 | print "$data\n"; |
|
|
145 | |
|
|
146 | my $ev = $queue->enqueue_read_buffer ($buf, 0, 1, 3, my $data); |
|
|
147 | $ev->wait; |
|
|
148 | print "$data\n"; # prints "elm" |
|
|
149 | |
|
|
150 | =head2 Create and build a program, then create a kernel out of one of its |
|
|
151 | functions. |
|
|
152 | |
|
|
153 | my $src = ' |
|
|
154 | __kernel void |
|
|
155 | squareit (__global float *input, __global float *output) |
|
|
156 | { |
|
|
157 | $id = get_global_id (0); |
|
|
158 | output [id] = input [id] * input [id]; |
|
|
159 | } |
|
|
160 | '; |
|
|
161 | |
|
|
162 | my $prog = $ctx->program_with_source ($src); |
|
|
163 | |
|
|
164 | # build croaks on compile errors, so catch it and print the compile errors |
|
|
165 | eval { $prog->build ($dev); 1 } |
|
|
166 | or die $prog->build_info ($dev, OpenCL::PROGRAM_BUILD_LOG); |
|
|
167 | |
|
|
168 | my $kernel = $prog->kernel ("squareit"); |
|
|
169 | |
|
|
170 | =head2 Create some input and output float buffers, then call the |
|
|
171 | 'squareit' kernel on them. |
|
|
172 | |
|
|
173 | my $input = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, pack "f*", 1, 2, 3, 4.5); |
|
|
174 | my $output = $ctx->buffer (0, OpenCL::SIZEOF_FLOAT * 5); |
|
|
175 | |
|
|
176 | # set buffer |
|
|
177 | $kernel->set_buffer (0, $input); |
|
|
178 | $kernel->set_buffer (1, $output); |
|
|
179 | |
|
|
180 | # execute it for all 4 numbers |
|
|
181 | $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
|
|
182 | |
|
|
183 | # enqueue a synchronous read |
|
|
184 | $queue->enqueue_read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
|
|
185 | |
|
|
186 | # print the results: |
|
|
187 | printf "%s\n", join ", ", unpack "f*", $data; |
|
|
188 | |
|
|
189 | =head2 The same enqueue operations as before, but assuming an out-of-order queue, |
|
|
190 | showing off barriers. |
|
|
191 | |
|
|
192 | # execute it for all 4 numbers |
|
|
193 | $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
|
|
194 | |
|
|
195 | # enqueue a barrier to ensure in-order execution |
|
|
196 | $queue->enqueue_barrier; |
|
|
197 | |
|
|
198 | # enqueue an async read |
|
|
199 | $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); |
|
|
200 | |
|
|
201 | # wait for all requests to finish |
|
|
202 | $queue->finish; |
|
|
203 | |
|
|
204 | =head2 The same enqueue operations as before, but assuming an out-of-order queue, |
|
|
205 | showing off event objects and wait lists. |
|
|
206 | |
|
|
207 | # execute it for all 4 numbers |
|
|
208 | my $ev = $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); |
|
|
209 | |
|
|
210 | # enqueue an async read |
|
|
211 | $ev = $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev); |
|
|
212 | |
|
|
213 | # wait for the last event to complete |
|
|
214 | $ev->wait; |
|
|
215 | |
|
|
216 | =head1 DOCUMENTATION |
|
|
217 | |
|
|
218 | =head2 BASIC CONVENTIONS |
|
|
219 | |
|
|
220 | This is not a one-to-one C-style translation of OpenCL to Perl - instead |
|
|
221 | I attempted to make the interface as type-safe as possible by introducing |
|
|
222 | object syntax where it makes sense. There are a number of important |
|
|
223 | differences between the OpenCL C API and this module: |
30 | |
224 | |
31 | =over 4 |
225 | =over 4 |
32 | |
226 | |
|
|
227 | =item * Object lifetime managament is automatic - there is no need |
|
|
228 | to free objects explicitly (C<clReleaseXXX>), the release function |
|
|
229 | is called automatically once all Perl references to it go away. |
|
|
230 | |
|
|
231 | =item * OpenCL uses CamelCase for function names |
|
|
232 | (e.g. C<clGetPlatformIDs>, C<clGetPlatformInfo>), while this module |
|
|
233 | uses underscores as word separator and often leaves out prefixes |
|
|
234 | (C<OpenCL::platforms>, C<< $platform->info >>). |
|
|
235 | |
|
|
236 | =item * OpenCL often specifies fixed vector function arguments as short |
|
|
237 | arrays (C<size_t origin[3]>), while this module explicitly expects the |
|
|
238 | components as separate arguments (C<$orig_x, $orig_y, $orig_z>) in |
|
|
239 | function calls. |
|
|
240 | |
|
|
241 | =item * Structures are often specified by flattening out their components |
|
|
242 | as with short vectors, and returned as arrayrefs. |
|
|
243 | |
|
|
244 | =item * When enqueuing commands, the wait list is specified by adding |
|
|
245 | extra arguments to the function - anywhere a C<$wait_events...> argument |
|
|
246 | is documented this can be any number of event objects. |
|
|
247 | |
|
|
248 | =item * When enqueuing commands, if the enqueue method is called in void |
|
|
249 | context, no event is created. In all other contexts an event is returned |
|
|
250 | by the method. |
|
|
251 | |
|
|
252 | =item * This module expects all functions to return C<CL_SUCCESS>. If any |
|
|
253 | other status is returned the function will throw an exception, so you |
|
|
254 | don't normally have to to any error checking. |
|
|
255 | |
|
|
256 | =back |
|
|
257 | |
|
|
258 | =head2 PERL AND OPENCL TYPES |
|
|
259 | |
|
|
260 | This handy(?) table lists OpenCL types and their perl, PDL and pack/unpack |
|
|
261 | format equivalents: |
|
|
262 | |
|
|
263 | OpenCL perl PDL pack/unpack |
|
|
264 | char IV - c |
|
|
265 | uchar IV byte C |
|
|
266 | short IV short s |
|
|
267 | ushort IV ushort S |
|
|
268 | int IV long? l |
|
|
269 | uint IV - L |
|
|
270 | long IV longlong q |
|
|
271 | ulong IV - Q |
|
|
272 | float NV float f |
|
|
273 | half IV ushort S |
|
|
274 | double NV double d |
|
|
275 | |
|
|
276 | =head2 THE OpenCL PACKAGE |
|
|
277 | |
|
|
278 | =over 4 |
|
|
279 | |
|
|
280 | =item $int = OpenCL::errno |
|
|
281 | |
|
|
282 | The last error returned by a function - it's only valid after an error occured |
|
|
283 | and before calling another OpenCL function. |
|
|
284 | |
|
|
285 | =item $str = OpenCL::err2str $errval |
|
|
286 | |
|
|
287 | Comverts an error value into a human readable string. |
|
|
288 | |
|
|
289 | =item $str = OpenCL::enum2str $enum |
|
|
290 | |
|
|
291 | Converts most enum values (inof parameter names, image format constants, |
|
|
292 | object types, addressing and filter modes, command types etc.) into a |
|
|
293 | human readbale string. When confronted with some random integer it can be |
|
|
294 | very helpful to pass it through this function to maybe get some readable |
|
|
295 | string out of it. |
|
|
296 | |
|
|
297 | =item @platforms = OpenCL::platforms |
|
|
298 | |
|
|
299 | Returns all available OpenCL::Platform objects. |
|
|
300 | |
|
|
301 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html> |
|
|
302 | |
|
|
303 | =item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef |
|
|
304 | |
|
|
305 | Tries to create a context from a default device and platform - never worked for me. |
|
|
306 | |
|
|
307 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
|
|
308 | |
|
|
309 | =item OpenCL::wait_for_events $wait_events... |
|
|
310 | |
|
|
311 | Waits for all events to complete. |
|
|
312 | |
|
|
313 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
|
|
314 | |
|
|
315 | =back |
|
|
316 | |
|
|
317 | =head2 THE OpenCL::Platform CLASS |
|
|
318 | |
|
|
319 | =over 4 |
|
|
320 | |
|
|
321 | =item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL) |
|
|
322 | |
|
|
323 | Returns a list of matching OpenCL::Device objects. |
|
|
324 | |
|
|
325 | =item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef) |
|
|
326 | |
|
|
327 | Tries to create a context. Never worked for me, and you need devices explicitly anyway. |
|
|
328 | |
|
|
329 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
|
|
330 | |
|
|
331 | =item $ctx = $device->context ($properties = undef, @$devices, $notify = undef) |
|
|
332 | |
|
|
333 | Create a new OpenCL::Context object using the given device object(s)- a |
|
|
334 | CL_CONTEXT_PLATFORM property is supplied automatically. |
|
|
335 | |
|
|
336 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> |
|
|
337 | |
|
|
338 | =item $packed_value = $platform->info ($name) |
|
|
339 | |
|
|
340 | Calls C<clGetPlatformInfo> and returns the packed, raw value - for |
|
|
341 | strings, this will be the string (possibly including terminating \0), for |
|
|
342 | other values you probably need to use the correct C<unpack>. |
|
|
343 | |
|
|
344 | It's best to avoid this method and use one of the following convenience |
|
|
345 | wrappers. |
|
|
346 | |
|
|
347 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html> |
|
|
348 | |
|
|
349 | =for gengetinfo begin platform |
|
|
350 | |
|
|
351 | =item $string = $platform->profile |
|
|
352 | |
|
|
353 | Calls C<clGetPlatformInfo> with C<CL_PLATFORM_PROFILE> and returns the result(s). |
|
|
354 | |
|
|
355 | =item $string = $platform->version |
|
|
356 | |
|
|
357 | Calls C<clGetPlatformInfo> with C<CL_PLATFORM_VERSION> and returns the result(s). |
|
|
358 | |
|
|
359 | =item $string = $platform->name |
|
|
360 | |
|
|
361 | Calls C<clGetPlatformInfo> with C<CL_PLATFORM_NAME> and returns the result(s). |
|
|
362 | |
|
|
363 | =item $string = $platform->vendor |
|
|
364 | |
|
|
365 | Calls C<clGetPlatformInfo> with C<CL_PLATFORM_VENDOR> and returns the result(s). |
|
|
366 | |
|
|
367 | =item $string = $platform->extensions |
|
|
368 | |
|
|
369 | Calls C<clGetPlatformInfo> with C<CL_PLATFORM_EXTENSIONS> and returns the result(s). |
|
|
370 | |
|
|
371 | =for gengetinfo end platform |
|
|
372 | |
|
|
373 | =back |
|
|
374 | |
|
|
375 | =head2 THE OpenCL::Device CLASS |
|
|
376 | |
|
|
377 | =over 4 |
|
|
378 | |
|
|
379 | =item $packed_value = $device->info ($name) |
|
|
380 | |
|
|
381 | See C<< $platform->info >> for details. |
|
|
382 | |
|
|
383 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetDeviceInfo.html> |
|
|
384 | |
|
|
385 | =for gengetinfo begin device |
|
|
386 | |
|
|
387 | =item $device_type = $device->type |
|
|
388 | |
|
|
389 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_TYPE> and returns the result(s). |
|
|
390 | |
|
|
391 | =item $uint = $device->vendor_id |
|
|
392 | |
|
|
393 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_VENDOR_ID> and returns the result(s). |
|
|
394 | |
|
|
395 | =item $uint = $device->max_compute_units |
|
|
396 | |
|
|
397 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_COMPUTE_UNITS> and returns the result(s). |
|
|
398 | |
|
|
399 | =item $uint = $device->max_work_item_dimensions |
|
|
400 | |
|
|
401 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS> and returns the result(s). |
|
|
402 | |
|
|
403 | =item $int = $device->max_work_group_size |
|
|
404 | |
|
|
405 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_WORK_GROUP_SIZE> and returns the result(s). |
|
|
406 | |
|
|
407 | =item @ints = $device->max_work_item_sizes |
|
|
408 | |
|
|
409 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_WORK_ITEM_SIZES> and returns the result(s). |
|
|
410 | |
|
|
411 | =item $uint = $device->preferred_vector_width_char |
|
|
412 | |
|
|
413 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_CHAR> and returns the result(s). |
|
|
414 | |
|
|
415 | =item $uint = $device->preferred_vector_width_short |
|
|
416 | |
|
|
417 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_SHORT> and returns the result(s). |
|
|
418 | |
|
|
419 | =item $uint = $device->preferred_vector_width_int |
|
|
420 | |
|
|
421 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_INT> and returns the result(s). |
|
|
422 | |
|
|
423 | =item $uint = $device->preferred_vector_width_long |
|
|
424 | |
|
|
425 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_LONG> and returns the result(s). |
|
|
426 | |
|
|
427 | =item $uint = $device->preferred_vector_width_float |
|
|
428 | |
|
|
429 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_FLOAT> and returns the result(s). |
|
|
430 | |
|
|
431 | =item $uint = $device->preferred_vector_width_double |
|
|
432 | |
|
|
433 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_DOUBLE> and returns the result(s). |
|
|
434 | |
|
|
435 | =item $uint = $device->max_clock_frequency |
|
|
436 | |
|
|
437 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_CLOCK_FREQUENCY> and returns the result(s). |
|
|
438 | |
|
|
439 | =item $bitfield = $device->address_bits |
|
|
440 | |
|
|
441 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_ADDRESS_BITS> and returns the result(s). |
|
|
442 | |
|
|
443 | =item $uint = $device->max_read_image_args |
|
|
444 | |
|
|
445 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_READ_IMAGE_ARGS> and returns the result(s). |
|
|
446 | |
|
|
447 | =item $uint = $device->max_write_image_args |
|
|
448 | |
|
|
449 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_WRITE_IMAGE_ARGS> and returns the result(s). |
|
|
450 | |
|
|
451 | =item $ulong = $device->max_mem_alloc_size |
|
|
452 | |
|
|
453 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_MEM_ALLOC_SIZE> and returns the result(s). |
|
|
454 | |
|
|
455 | =item $int = $device->image2d_max_width |
|
|
456 | |
|
|
457 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE2D_MAX_WIDTH> and returns the result(s). |
|
|
458 | |
|
|
459 | =item $int = $device->image2d_max_height |
|
|
460 | |
|
|
461 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE2D_MAX_HEIGHT> and returns the result(s). |
|
|
462 | |
|
|
463 | =item $int = $device->image3d_max_width |
|
|
464 | |
|
|
465 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE3D_MAX_WIDTH> and returns the result(s). |
|
|
466 | |
|
|
467 | =item $int = $device->image3d_max_height |
|
|
468 | |
|
|
469 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE3D_MAX_HEIGHT> and returns the result(s). |
|
|
470 | |
|
|
471 | =item $int = $device->image3d_max_depth |
|
|
472 | |
|
|
473 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE3D_MAX_DEPTH> and returns the result(s). |
|
|
474 | |
|
|
475 | =item $uint = $device->image_support |
|
|
476 | |
|
|
477 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_IMAGE_SUPPORT> and returns the result(s). |
|
|
478 | |
|
|
479 | =item $int = $device->max_parameter_size |
|
|
480 | |
|
|
481 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_PARAMETER_SIZE> and returns the result(s). |
|
|
482 | |
|
|
483 | =item $uint = $device->max_samplers |
|
|
484 | |
|
|
485 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_SAMPLERS> and returns the result(s). |
|
|
486 | |
|
|
487 | =item $uint = $device->mem_base_addr_align |
|
|
488 | |
|
|
489 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MEM_BASE_ADDR_ALIGN> and returns the result(s). |
|
|
490 | |
|
|
491 | =item $uint = $device->min_data_type_align_size |
|
|
492 | |
|
|
493 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MIN_DATA_TYPE_ALIGN_SIZE> and returns the result(s). |
|
|
494 | |
|
|
495 | =item $device_fp_config = $device->single_fp_config |
|
|
496 | |
|
|
497 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_SINGLE_FP_CONFIG> and returns the result(s). |
|
|
498 | |
|
|
499 | =item $device_mem_cache_type = $device->global_mem_cache_type |
|
|
500 | |
|
|
501 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_GLOBAL_MEM_CACHE_TYPE> and returns the result(s). |
|
|
502 | |
|
|
503 | =item $uint = $device->global_mem_cacheline_size |
|
|
504 | |
|
|
505 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_GLOBAL_MEM_CACHELINE_SIZE> and returns the result(s). |
|
|
506 | |
|
|
507 | =item $ulong = $device->global_mem_cache_size |
|
|
508 | |
|
|
509 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_GLOBAL_MEM_CACHE_SIZE> and returns the result(s). |
|
|
510 | |
|
|
511 | =item $ulong = $device->global_mem_size |
|
|
512 | |
|
|
513 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_GLOBAL_MEM_SIZE> and returns the result(s). |
|
|
514 | |
|
|
515 | =item $ulong = $device->max_constant_buffer_size |
|
|
516 | |
|
|
517 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_CONSTANT_BUFFER_SIZE> and returns the result(s). |
|
|
518 | |
|
|
519 | =item $uint = $device->max_constant_args |
|
|
520 | |
|
|
521 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_MAX_CONSTANT_ARGS> and returns the result(s). |
|
|
522 | |
|
|
523 | =item $device_local_mem_type = $device->local_mem_type |
|
|
524 | |
|
|
525 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_LOCAL_MEM_TYPE> and returns the result(s). |
|
|
526 | |
|
|
527 | =item $ulong = $device->local_mem_size |
|
|
528 | |
|
|
529 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_LOCAL_MEM_SIZE> and returns the result(s). |
|
|
530 | |
|
|
531 | =item $boolean = $device->error_correction_support |
|
|
532 | |
|
|
533 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_ERROR_CORRECTION_SUPPORT> and returns the result(s). |
|
|
534 | |
|
|
535 | =item $int = $device->profiling_timer_resolution |
|
|
536 | |
|
|
537 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PROFILING_TIMER_RESOLUTION> and returns the result(s). |
|
|
538 | |
|
|
539 | =item $boolean = $device->endian_little |
|
|
540 | |
|
|
541 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_ENDIAN_LITTLE> and returns the result(s). |
|
|
542 | |
|
|
543 | =item $boolean = $device->available |
|
|
544 | |
|
|
545 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_AVAILABLE> and returns the result(s). |
|
|
546 | |
|
|
547 | =item $boolean = $device->compiler_available |
|
|
548 | |
|
|
549 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_COMPILER_AVAILABLE> and returns the result(s). |
|
|
550 | |
|
|
551 | =item $device_exec_capabilities = $device->execution_capabilities |
|
|
552 | |
|
|
553 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_EXECUTION_CAPABILITIES> and returns the result(s). |
|
|
554 | |
|
|
555 | =item $command_queue_properties = $device->properties |
|
|
556 | |
|
|
557 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_QUEUE_PROPERTIES> and returns the result(s). |
|
|
558 | |
|
|
559 | =item $ = $device->platform |
|
|
560 | |
|
|
561 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PLATFORM> and returns the result(s). |
|
|
562 | |
|
|
563 | =item $string = $device->name |
|
|
564 | |
|
|
565 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_NAME> and returns the result(s). |
|
|
566 | |
|
|
567 | =item $string = $device->vendor |
|
|
568 | |
|
|
569 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_VENDOR> and returns the result(s). |
|
|
570 | |
|
|
571 | =item $string = $device->driver_version |
|
|
572 | |
|
|
573 | Calls C<clGetDeviceInfo> with C<CL_DRIVER_VERSION> and returns the result(s). |
|
|
574 | |
|
|
575 | =item $string = $device->profile |
|
|
576 | |
|
|
577 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PROFILE> and returns the result(s). |
|
|
578 | |
|
|
579 | =item $string = $device->version |
|
|
580 | |
|
|
581 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_VERSION> and returns the result(s). |
|
|
582 | |
|
|
583 | =item $string = $device->extensions |
|
|
584 | |
|
|
585 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_EXTENSIONS> and returns the result(s). |
|
|
586 | |
|
|
587 | =item $uint = $device->preferred_vector_width_half |
|
|
588 | |
|
|
589 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PREFERRED_VECTOR_WIDTH_HALF> and returns the result(s). |
|
|
590 | |
|
|
591 | =item $uint = $device->native_vector_width_char |
|
|
592 | |
|
|
593 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_CHAR> and returns the result(s). |
|
|
594 | |
|
|
595 | =item $uint = $device->native_vector_width_short |
|
|
596 | |
|
|
597 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_SHORT> and returns the result(s). |
|
|
598 | |
|
|
599 | =item $uint = $device->native_vector_width_int |
|
|
600 | |
|
|
601 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_INT> and returns the result(s). |
|
|
602 | |
|
|
603 | =item $uint = $device->native_vector_width_long |
|
|
604 | |
|
|
605 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_LONG> and returns the result(s). |
|
|
606 | |
|
|
607 | =item $uint = $device->native_vector_width_float |
|
|
608 | |
|
|
609 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_FLOAT> and returns the result(s). |
|
|
610 | |
|
|
611 | =item $uint = $device->native_vector_width_double |
|
|
612 | |
|
|
613 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_DOUBLE> and returns the result(s). |
|
|
614 | |
|
|
615 | =item $uint = $device->native_vector_width_half |
|
|
616 | |
|
|
617 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_NATIVE_VECTOR_WIDTH_HALF> and returns the result(s). |
|
|
618 | |
|
|
619 | =item $device_fp_config = $device->double_fp_config |
|
|
620 | |
|
|
621 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_DOUBLE_FP_CONFIG> and returns the result(s). |
|
|
622 | |
|
|
623 | =item $device_fp_config = $device->half_fp_config |
|
|
624 | |
|
|
625 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_HALF_FP_CONFIG> and returns the result(s). |
|
|
626 | |
|
|
627 | =item $boolean = $device->host_unified_memory |
|
|
628 | |
|
|
629 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_HOST_UNIFIED_MEMORY> and returns the result(s). |
|
|
630 | |
|
|
631 | =item $device = $device->parent_device_ext |
|
|
632 | |
|
|
633 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARENT_DEVICE_EXT> and returns the result(s). |
|
|
634 | |
|
|
635 | =item @device_partition_property_exts = $device->partition_types_ext |
|
|
636 | |
|
|
637 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_TYPES_EXT> and returns the result(s). |
|
|
638 | |
|
|
639 | =item @device_partition_property_exts = $device->affinity_domains_ext |
|
|
640 | |
|
|
641 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_AFFINITY_DOMAINS_EXT> and returns the result(s). |
|
|
642 | |
|
|
643 | =item $uint = $device->reference_count_ext |
|
|
644 | |
|
|
645 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_REFERENCE_COUNT_EXT > and returns the result(s). |
|
|
646 | |
|
|
647 | =item @device_partition_property_exts = $device->partition_style_ext |
|
|
648 | |
|
|
649 | Calls C<clGetDeviceInfo> with C<CL_DEVICE_PARTITION_STYLE_EXT> and returns the result(s). |
|
|
650 | |
|
|
651 | =for gengetinfo end device |
|
|
652 | |
|
|
653 | =back |
|
|
654 | |
|
|
655 | =head2 THE OpenCL::Context CLASS |
|
|
656 | |
|
|
657 | =over 4 |
|
|
658 | |
|
|
659 | =item $queue = $ctx->queue ($device, $properties) |
|
|
660 | |
|
|
661 | Create a new OpenCL::Queue object from the context and the given device. |
|
|
662 | |
|
|
663 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html> |
|
|
664 | |
|
|
665 | =item $ev = $ctx->user_event |
|
|
666 | |
|
|
667 | Creates a new OpenCL::UserEvent object. |
|
|
668 | |
|
|
669 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateUserEvent.html> |
|
|
670 | |
|
|
671 | =item $buf = $ctx->buffer ($flags, $len) |
|
|
672 | |
|
|
673 | Creates a new OpenCL::Buffer object with the given flags and octet-size. |
|
|
674 | |
|
|
675 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateBuffer.html> |
|
|
676 | |
|
|
677 | =item $buf = $ctx->buffer_sv ($flags, $data) |
|
|
678 | |
|
|
679 | Creates a new OpenCL::Buffer object and initialise it with the given data values. |
|
|
680 | |
|
|
681 | =item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $row_pitch = 0, $data = undef) |
|
|
682 | |
|
|
683 | Creates a new OpenCL::Image2D object and optionally initialises it with the given data values. |
|
|
684 | |
|
|
685 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage2D.html> |
|
|
686 | |
|
|
687 | =item $img = $ctx->image3d ($flags, $channel_order, $channel_type, $width, $height, $depth, $row_pitch = 0, $slice_pitch = 0, $data = undef) |
|
|
688 | |
|
|
689 | Creates a new OpenCL::Image3D object and optionally initialises it with the given data values. |
|
|
690 | |
|
|
691 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage3D.html> |
|
|
692 | |
|
|
693 | =item @formats = $ctx->supported_image_formats ($flags, $image_type) |
|
|
694 | |
|
|
695 | Returns a list of matching image formats - each format is an arrayref with |
|
|
696 | two values, $channel_order and $channel_type, in it. |
|
|
697 | |
|
|
698 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetSupportedImageFormats.html> |
|
|
699 | |
|
|
700 | =item $sampler = $ctx->sampler ($normalized_coords, $addressing_mode, $filter_mode) |
|
|
701 | |
|
|
702 | Creates a new OpenCL::Sampler object. |
|
|
703 | |
|
|
704 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateSampler.html> |
|
|
705 | |
|
|
706 | =item $program = $ctx->program_with_source ($string) |
|
|
707 | |
|
|
708 | Creates a new OpenCL::Program object from the given source code. |
|
|
709 | |
|
|
710 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateProgramWithSource.html> |
|
|
711 | |
|
|
712 | =item $packed_value = $ctx->info ($name) |
|
|
713 | |
|
|
714 | See C<< $platform->info >> for details. |
|
|
715 | |
|
|
716 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetContextInfo.html> |
|
|
717 | |
|
|
718 | =for gengetinfo begin context |
|
|
719 | |
|
|
720 | =item $uint = $context->reference_count |
|
|
721 | |
|
|
722 | Calls C<clGetContextInfo> with C<CL_CONTEXT_REFERENCE_COUNT> and returns the result(s). |
|
|
723 | |
|
|
724 | =item @devices = $context->devices |
|
|
725 | |
|
|
726 | Calls C<clGetContextInfo> with C<CL_CONTEXT_DEVICES> and returns the result(s). |
|
|
727 | |
|
|
728 | =item @property_ints = $context->properties |
|
|
729 | |
|
|
730 | Calls C<clGetContextInfo> with C<CL_CONTEXT_PROPERTIES> and returns the result(s). |
|
|
731 | |
|
|
732 | =item $uint = $context->num_devices |
|
|
733 | |
|
|
734 | Calls C<clGetContextInfo> with C<CL_CONTEXT_NUM_DEVICES> and returns the result(s). |
|
|
735 | |
|
|
736 | =for gengetinfo end context |
|
|
737 | |
|
|
738 | =back |
|
|
739 | |
|
|
740 | =head2 THE OpenCL::Queue CLASS |
|
|
741 | |
|
|
742 | An OpenCL::Queue represents an execution queue for OpenCL. You execute |
|
|
743 | requests by calling their respective C<enqueue_xxx> method and waitinf for |
|
|
744 | it to complete in some way. |
|
|
745 | |
|
|
746 | All the enqueue methods return an event object that can be used to wait |
|
|
747 | for completion, unless the method is called in void context, in which case |
|
|
748 | no event object is created. |
|
|
749 | |
|
|
750 | They also allow you to specify any number of other event objects that this |
|
|
751 | request has to wait for before it starts executing, by simply passing the |
|
|
752 | event objects as extra parameters to the enqueue methods. |
|
|
753 | |
|
|
754 | Queues execute in-order by default, without any parallelism, so in most |
|
|
755 | cases (i.e. you use only one queue) it's not necessary to wait for or |
|
|
756 | create event objects. |
|
|
757 | |
|
|
758 | =over 4 |
|
|
759 | |
|
|
760 | =item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) |
|
|
761 | |
|
|
762 | Reads data from buffer into the given string. |
|
|
763 | |
|
|
764 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html> |
|
|
765 | |
|
|
766 | =item $ev = $queue->enqueue_write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) |
|
|
767 | |
|
|
768 | Writes data to buffer from the given string. |
|
|
769 | |
|
|
770 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html> |
|
|
771 | |
|
|
772 | =item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) |
|
|
773 | |
|
|
774 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> |
|
|
775 | |
|
|
776 | =item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
|
|
777 | |
|
|
778 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> |
|
|
779 | |
|
|
780 | =item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
|
|
781 | |
|
|
782 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> |
|
|
783 | |
|
|
784 | =item $ev = $queue->enqueue_copy_buffer_rect ($src, $dst, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $src_row_pitch, $src_slice_pitch, $dst_row_pitch, $dst_slice_pitch, $wait_event...) |
|
|
785 | |
|
|
786 | Yeah. |
|
|
787 | |
|
|
788 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html> |
|
|
789 | |
|
|
790 | =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...) |
|
|
791 | |
|
|
792 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
|
|
793 | |
|
|
794 | =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...) |
|
|
795 | |
|
|
796 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> |
|
|
797 | |
|
|
798 | =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...) |
|
|
799 | |
|
|
800 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html> |
|
|
801 | |
|
|
802 | =item $ev = $queue->enqueue_task ($kernel, $wait_events...) |
|
|
803 | |
|
|
804 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
|
|
805 | |
|
|
806 | =item $ev = $queue->enqueue_nd_range_kernel ($kernel, @$global_work_offset, @$global_work_size, @$local_work_size, $wait_events...) |
|
|
807 | |
|
|
808 | Enqueues a kernel execution. |
|
|
809 | |
|
|
810 | @$global_work_size must be specified as a reference to an array of |
|
|
811 | integers specifying the work sizes (element counts). |
|
|
812 | |
|
|
813 | @$global_work_offset must be either C<undef> (in which case all offsets |
|
|
814 | are C<0>), or a reference to an array of work offsets, with the same number |
|
|
815 | of elements as @$global_work_size. |
|
|
816 | |
|
|
817 | @$local_work_size must be either C<undef> (in which case the |
|
|
818 | implementation is supposed to choose good local work sizes), or a |
|
|
819 | reference to an array of local work sizes, with the same number of |
|
|
820 | elements as @$global_work_size. |
|
|
821 | |
|
|
822 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
|
|
823 | |
|
|
824 | =item $ev = $queue->enqueue_marker |
|
|
825 | |
|
|
826 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueMarker.html> |
|
|
827 | |
|
|
828 | =item $ev = $queue->enqueue_wait_for_events ($wait_events...) |
|
|
829 | |
|
|
830 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
|
|
831 | |
|
|
832 | =item $queue->enqueue_barrier |
|
|
833 | |
|
|
834 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueBarrier.html> |
|
|
835 | |
|
|
836 | =item $queue->flush |
|
|
837 | |
|
|
838 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html> |
|
|
839 | |
|
|
840 | =item $queue->finish |
|
|
841 | |
|
|
842 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFinish.html> |
|
|
843 | |
|
|
844 | =item $packed_value = $queue->info ($name) |
|
|
845 | |
|
|
846 | See C<< $platform->info >> for details. |
|
|
847 | |
|
|
848 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetCommandQueueInfo.html> |
|
|
849 | |
|
|
850 | =for gengetinfo begin command_queue |
|
|
851 | |
|
|
852 | =item $ctx = $command_queue->context |
|
|
853 | |
|
|
854 | Calls C<clGetCommandQueueInfo> with C<CL_QUEUE_CONTEXT> and returns the result(s). |
|
|
855 | |
|
|
856 | =item $device = $command_queue->device |
|
|
857 | |
|
|
858 | Calls C<clGetCommandQueueInfo> with C<CL_QUEUE_DEVICE> and returns the result(s). |
|
|
859 | |
|
|
860 | =item $uint = $command_queue->reference_count |
|
|
861 | |
|
|
862 | Calls C<clGetCommandQueueInfo> with C<CL_QUEUE_REFERENCE_COUNT> and returns the result(s). |
|
|
863 | |
|
|
864 | =item $command_queue_properties = $command_queue->properties |
|
|
865 | |
|
|
866 | Calls C<clGetCommandQueueInfo> with C<CL_QUEUE_PROPERTIES> and returns the result(s). |
|
|
867 | |
|
|
868 | =for gengetinfo end command_queue |
|
|
869 | |
|
|
870 | =back |
|
|
871 | |
|
|
872 | =head2 THE OpenCL::Memory CLASS |
|
|
873 | |
|
|
874 | This the superclass of all memory objects - OpenCL::Buffer, OpenCL::Image, |
|
|
875 | OpenCL::Image2D and OpenCL::Image3D. |
|
|
876 | |
|
|
877 | =over 4 |
|
|
878 | |
|
|
879 | =item $packed_value = $memory->info ($name) |
|
|
880 | |
|
|
881 | See C<< $platform->info >> for details. |
|
|
882 | |
|
|
883 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetMemObjectInfo.html> |
|
|
884 | |
|
|
885 | =for gengetinfo begin mem |
|
|
886 | |
|
|
887 | =item $mem_object_type = $mem->type |
|
|
888 | |
|
|
889 | Calls C<clGetMemObjectInfo> with C<CL_MEM_TYPE> and returns the result(s). |
|
|
890 | |
|
|
891 | =item $mem_flags = $mem->flags |
|
|
892 | |
|
|
893 | Calls C<clGetMemObjectInfo> with C<CL_MEM_FLAGS> and returns the result(s). |
|
|
894 | |
|
|
895 | =item $int = $mem->size |
|
|
896 | |
|
|
897 | Calls C<clGetMemObjectInfo> with C<CL_MEM_SIZE> and returns the result(s). |
|
|
898 | |
|
|
899 | =item $ptr_value = $mem->host_ptr |
|
|
900 | |
|
|
901 | Calls C<clGetMemObjectInfo> with C<CL_MEM_HOST_PTR> and returns the result(s). |
|
|
902 | |
|
|
903 | =item $uint = $mem->map_count |
|
|
904 | |
|
|
905 | Calls C<clGetMemObjectInfo> with C<CL_MEM_MAP_COUNT> and returns the result(s). |
|
|
906 | |
|
|
907 | =item $uint = $mem->reference_count |
|
|
908 | |
|
|
909 | Calls C<clGetMemObjectInfo> with C<CL_MEM_REFERENCE_COUNT> and returns the result(s). |
|
|
910 | |
|
|
911 | =item $ctx = $mem->context |
|
|
912 | |
|
|
913 | Calls C<clGetMemObjectInfo> with C<CL_MEM_CONTEXT> and returns the result(s). |
|
|
914 | |
|
|
915 | =item $mem = $mem->associated_memobject |
|
|
916 | |
|
|
917 | Calls C<clGetMemObjectInfo> with C<CL_MEM_ASSOCIATED_MEMOBJECT> and returns the result(s). |
|
|
918 | |
|
|
919 | =item $int = $mem->offset |
|
|
920 | |
|
|
921 | Calls C<clGetMemObjectInfo> with C<CL_MEM_OFFSET> and returns the result(s). |
|
|
922 | |
|
|
923 | =for gengetinfo end mem |
|
|
924 | |
|
|
925 | =back |
|
|
926 | |
|
|
927 | =head2 THE OpenCL::Image CLASS |
|
|
928 | |
|
|
929 | This is the superclass of all image objects - OpenCL::Image2D and OpenCL::Image3D. |
|
|
930 | |
|
|
931 | =over 4 |
|
|
932 | |
|
|
933 | =item $packed_value = $ev->image_info ($name) |
|
|
934 | |
|
|
935 | See C<< $platform->info >> for details. |
|
|
936 | |
|
|
937 | The reason this method is not called C<info> is that there already is an |
|
|
938 | C<< ->info >> method inherited from C<OpenCL::Memory>. |
|
|
939 | |
|
|
940 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetImageInfo.html> |
|
|
941 | |
|
|
942 | =for gengetinfo begin image |
|
|
943 | |
|
|
944 | =item $int = $image->element_size |
|
|
945 | |
|
|
946 | Calls C<clGetImageInfo> with C<CL_IMAGE_ELEMENT_SIZE> and returns the result(s). |
|
|
947 | |
|
|
948 | =item $int = $image->row_pitch |
|
|
949 | |
|
|
950 | Calls C<clGetImageInfo> with C<CL_IMAGE_ROW_PITCH> and returns the result(s). |
|
|
951 | |
|
|
952 | =item $int = $image->slice_pitch |
|
|
953 | |
|
|
954 | Calls C<clGetImageInfo> with C<CL_IMAGE_SLICE_PITCH> and returns the result(s). |
|
|
955 | |
|
|
956 | =item $int = $image->width |
|
|
957 | |
|
|
958 | Calls C<clGetImageInfo> with C<CL_IMAGE_WIDTH> and returns the result(s). |
|
|
959 | |
|
|
960 | =item $int = $image->height |
|
|
961 | |
|
|
962 | Calls C<clGetImageInfo> with C<CL_IMAGE_HEIGHT> and returns the result(s). |
|
|
963 | |
|
|
964 | =item $int = $image->depth |
|
|
965 | |
|
|
966 | Calls C<clGetImageInfo> with C<CL_IMAGE_DEPTH> and returns the result(s). |
|
|
967 | |
|
|
968 | =for gengetinfo end image |
|
|
969 | |
|
|
970 | =back |
|
|
971 | |
|
|
972 | =head2 THE OpenCL::Sampler CLASS |
|
|
973 | |
|
|
974 | =over 4 |
|
|
975 | |
|
|
976 | =item $packed_value = $sampler->info ($name) |
|
|
977 | |
|
|
978 | See C<< $platform->info >> for details. |
|
|
979 | |
|
|
980 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetSamplerInfo.html> |
|
|
981 | |
|
|
982 | =for gengetinfo begin sampler |
|
|
983 | |
|
|
984 | =item $uint = $sampler->reference_count |
|
|
985 | |
|
|
986 | Calls C<clGetSamplerInfo> with C<CL_SAMPLER_REFERENCE_COUNT> and returns the result(s). |
|
|
987 | |
|
|
988 | =item $ctx = $sampler->context |
|
|
989 | |
|
|
990 | Calls C<clGetSamplerInfo> with C<CL_SAMPLER_CONTEXT> and returns the result(s). |
|
|
991 | |
|
|
992 | =item $addressing_mode = $sampler->normalized_coords |
|
|
993 | |
|
|
994 | Calls C<clGetSamplerInfo> with C<CL_SAMPLER_NORMALIZED_COORDS> and returns the result(s). |
|
|
995 | |
|
|
996 | =item $filter_mode = $sampler->addressing_mode |
|
|
997 | |
|
|
998 | Calls C<clGetSamplerInfo> with C<CL_SAMPLER_ADDRESSING_MODE> and returns the result(s). |
|
|
999 | |
|
|
1000 | =item $boolean = $sampler->filter_mode |
|
|
1001 | |
|
|
1002 | Calls C<clGetSamplerInfo> with C<CL_SAMPLER_FILTER_MODE> and returns the result(s). |
|
|
1003 | |
|
|
1004 | =for gengetinfo end sampler |
|
|
1005 | |
|
|
1006 | =back |
|
|
1007 | |
|
|
1008 | =head2 THE OpenCL::Program CLASS |
|
|
1009 | |
|
|
1010 | =over 4 |
|
|
1011 | |
|
|
1012 | =item $program->build ($device, $options = "") |
|
|
1013 | |
|
|
1014 | Tries to build the program with the givne options. |
|
|
1015 | |
|
|
1016 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
|
|
1017 | |
|
|
1018 | =item $packed_value = $program->build_info ($device, $name) |
|
|
1019 | |
|
|
1020 | Similar to C<< $platform->info >>, but returns build info for a previous |
|
|
1021 | build attempt for the given device. |
|
|
1022 | |
|
|
1023 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetBuildInfo.html> |
|
|
1024 | |
|
|
1025 | =item $kernel = $program->kernel ($function_name) |
|
|
1026 | |
|
|
1027 | Creates an OpenCL::Kernel object out of the named C<__kernel> function in |
|
|
1028 | the program. |
|
|
1029 | |
|
|
1030 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html> |
|
|
1031 | |
|
|
1032 | =for gengetinfo begin program_build |
|
|
1033 | |
|
|
1034 | =item $build_status = $program->build_status ($device) |
|
|
1035 | |
|
|
1036 | Calls C<clGetProgramBuildInfo> with C<CL_PROGRAM_BUILD_STATUS> and returns the result(s). |
|
|
1037 | |
|
|
1038 | =item $string = $program->build_options ($device) |
|
|
1039 | |
|
|
1040 | Calls C<clGetProgramBuildInfo> with C<CL_PROGRAM_BUILD_OPTIONS> and returns the result(s). |
|
|
1041 | |
|
|
1042 | =item $string = $program->build_log ($device) |
|
|
1043 | |
|
|
1044 | Calls C<clGetProgramBuildInfo> with C<CL_PROGRAM_BUILD_LOG> and returns the result(s). |
|
|
1045 | |
|
|
1046 | =for gengetinfo end program_build |
|
|
1047 | |
|
|
1048 | =item $packed_value = $program->info ($name) |
|
|
1049 | |
|
|
1050 | See C<< $platform->info >> for details. |
|
|
1051 | |
|
|
1052 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetProgramInfo.html> |
|
|
1053 | |
|
|
1054 | =for gengetinfo begin program |
|
|
1055 | |
|
|
1056 | =item $uint = $program->reference_count |
|
|
1057 | |
|
|
1058 | Calls C<clGetProgramInfo> with C<CL_PROGRAM_REFERENCE_COUNT> and returns the result(s). |
|
|
1059 | |
|
|
1060 | =item $ctx = $program->context |
|
|
1061 | |
|
|
1062 | Calls C<clGetProgramInfo> with C<CL_PROGRAM_CONTEXT> and returns the result(s). |
|
|
1063 | |
|
|
1064 | =item $uint = $program->num_devices |
|
|
1065 | |
|
|
1066 | Calls C<clGetProgramInfo> with C<CL_PROGRAM_NUM_DEVICES> and returns the result(s). |
|
|
1067 | |
|
|
1068 | =item @devices = $program->devices |
|
|
1069 | |
|
|
1070 | Calls C<clGetProgramInfo> with C<CL_PROGRAM_DEVICES> and returns the result(s). |
|
|
1071 | |
|
|
1072 | =item $string = $program->source |
|
|
1073 | |
|
|
1074 | Calls C<clGetProgramInfo> with C<CL_PROGRAM_SOURCE> and returns the result(s). |
|
|
1075 | |
|
|
1076 | =item @ints = $program->binary_sizes |
|
|
1077 | |
|
|
1078 | Calls C<clGetProgramInfo> with C<CL_PROGRAM_BINARY_SIZES> and returns the result(s). |
|
|
1079 | |
|
|
1080 | =for gengetinfo end program |
|
|
1081 | |
|
|
1082 | =back |
|
|
1083 | |
|
|
1084 | =head2 THE OpenCL::Kernel CLASS |
|
|
1085 | |
|
|
1086 | =over 4 |
|
|
1087 | |
|
|
1088 | =item $packed_value = $kernel->info ($name) |
|
|
1089 | |
|
|
1090 | See C<< $platform->info >> for details. |
|
|
1091 | |
|
|
1092 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetKernelInfo.html> |
|
|
1093 | |
|
|
1094 | =for gengetinfo begin kernel |
|
|
1095 | |
|
|
1096 | =item $string = $kernel->function_name |
|
|
1097 | |
|
|
1098 | Calls C<clGetKernelInfo> with C<CL_KERNEL_FUNCTION_NAME> and returns the result(s). |
|
|
1099 | |
|
|
1100 | =item $uint = $kernel->num_args |
|
|
1101 | |
|
|
1102 | Calls C<clGetKernelInfo> with C<CL_KERNEL_NUM_ARGS> and returns the result(s). |
|
|
1103 | |
|
|
1104 | =item $uint = $kernel->reference_count |
|
|
1105 | |
|
|
1106 | Calls C<clGetKernelInfo> with C<CL_KERNEL_REFERENCE_COUNT> and returns the result(s). |
|
|
1107 | |
|
|
1108 | =item $ctx = $kernel->context |
|
|
1109 | |
|
|
1110 | Calls C<clGetKernelInfo> with C<CL_KERNEL_CONTEXT> and returns the result(s). |
|
|
1111 | |
|
|
1112 | =item $program = $kernel->program |
|
|
1113 | |
|
|
1114 | Calls C<clGetKernelInfo> with C<CL_KERNEL_PROGRAM> and returns the result(s). |
|
|
1115 | |
|
|
1116 | =for gengetinfo end kernel |
|
|
1117 | |
|
|
1118 | =item $packed_value = $kernel->work_group_info ($device, $name) |
|
|
1119 | |
|
|
1120 | See C<< $platform->info >> for details. |
|
|
1121 | |
|
|
1122 | The reason this method is not called C<info> is that there already is an |
|
|
1123 | C<< ->info >> method. |
|
|
1124 | |
|
|
1125 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetKernelWorkGroupInfo.html> |
|
|
1126 | |
|
|
1127 | =for gengetinfo begin kernel_work_group |
|
|
1128 | |
|
|
1129 | =item $int = $kernel->work_group_size ($device) |
|
|
1130 | |
|
|
1131 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_WORK_GROUP_SIZE> and returns the result(s). |
|
|
1132 | |
|
|
1133 | =item @ints = $kernel->compile_work_group_size ($device) |
|
|
1134 | |
|
|
1135 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_COMPILE_WORK_GROUP_SIZE> and returns the result(s). |
|
|
1136 | |
|
|
1137 | =item $ulong = $kernel->local_mem_size ($device) |
|
|
1138 | |
|
|
1139 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_LOCAL_MEM_SIZE> and returns the result(s). |
|
|
1140 | |
|
|
1141 | =item $int = $kernel->preferred_work_group_size_multiple ($device) |
|
|
1142 | |
|
|
1143 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PREFERRED_WORK_GROUP_SIZE_MULTIPLE> and returns the result(s). |
|
|
1144 | |
|
|
1145 | =item $ulong = $kernel->private_mem_size ($device) |
|
|
1146 | |
|
|
1147 | Calls C<clGetKernelWorkGroupInfo> with C<CL_KERNEL_PRIVATE_MEM_SIZE> and returns the result(s). |
|
|
1148 | |
|
|
1149 | =for gengetinfo end kernel_work_group |
|
|
1150 | |
|
|
1151 | =item $kernel->set_TYPE ($index, $value) |
|
|
1152 | |
|
|
1153 | This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>. |
|
|
1154 | |
|
|
1155 | TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>, |
|
|
1156 | C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>, |
|
|
1157 | C<image2d>, C<image3d>, C<sampler> or C<event>. |
|
|
1158 | |
|
|
1159 | Chars and integers (including the half type) are specified as integers, |
|
|
1160 | float and double as floating point values, memory/buffer/image2d/image3d |
|
|
1161 | must be an object of that type or C<undef>, and sampler and event must be |
|
|
1162 | objects of that type. |
|
|
1163 | |
|
|
1164 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html> |
|
|
1165 | |
|
|
1166 | =back |
|
|
1167 | |
|
|
1168 | =head2 THE OpenCL::Event CLASS |
|
|
1169 | |
|
|
1170 | This is the superclass for all event objects (including OpenCL::UserEvent |
|
|
1171 | objects). |
|
|
1172 | |
|
|
1173 | =over 4 |
|
|
1174 | |
|
|
1175 | =item $ev->wait |
|
|
1176 | |
|
|
1177 | Waits for the event to complete. |
|
|
1178 | |
|
|
1179 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
|
|
1180 | |
|
|
1181 | =item $packed_value = $ev->info ($name) |
|
|
1182 | |
|
|
1183 | See C<< $platform->info >> for details. |
|
|
1184 | |
|
|
1185 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html> |
|
|
1186 | |
|
|
1187 | =for gengetinfo begin event |
|
|
1188 | |
|
|
1189 | =item $queue = $event->command_queue |
|
|
1190 | |
|
|
1191 | Calls C<clGetEventInfo> with C<CL_EVENT_COMMAND_QUEUE> and returns the result(s). |
|
|
1192 | |
|
|
1193 | =item $command_type = $event->command_type |
|
|
1194 | |
|
|
1195 | Calls C<clGetEventInfo> with C<CL_EVENT_COMMAND_TYPE> and returns the result(s). |
|
|
1196 | |
|
|
1197 | =item $uint = $event->reference_count |
|
|
1198 | |
|
|
1199 | Calls C<clGetEventInfo> with C<CL_EVENT_REFERENCE_COUNT> and returns the result(s). |
|
|
1200 | |
|
|
1201 | =item $uint = $event->command_execution_status |
|
|
1202 | |
|
|
1203 | Calls C<clGetEventInfo> with C<CL_EVENT_COMMAND_EXECUTION_STATUS> and returns the result(s). |
|
|
1204 | |
|
|
1205 | =item $ctx = $event->context |
|
|
1206 | |
|
|
1207 | Calls C<clGetEventInfo> with C<CL_EVENT_CONTEXT> and returns the result(s). |
|
|
1208 | |
|
|
1209 | =for gengetinfo end event |
|
|
1210 | |
|
|
1211 | =item $packed_value = $ev->profiling_info ($name) |
|
|
1212 | |
|
|
1213 | See C<< $platform->info >> for details. |
|
|
1214 | |
|
|
1215 | The reason this method is not called C<info> is that there already is an |
|
|
1216 | C<< ->info >> method. |
|
|
1217 | |
|
|
1218 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetProfilingInfo.html> |
|
|
1219 | |
|
|
1220 | =for gengetinfo begin profiling |
|
|
1221 | |
|
|
1222 | =item $ulong = $event->profiling_command_queued |
|
|
1223 | |
|
|
1224 | Calls C<clGetEventProfilingInfo> with C<CL_PROFILING_COMMAND_QUEUED> and returns the result(s). |
|
|
1225 | |
|
|
1226 | =item $ulong = $event->profiling_command_submit |
|
|
1227 | |
|
|
1228 | Calls C<clGetEventProfilingInfo> with C<CL_PROFILING_COMMAND_SUBMIT> and returns the result(s). |
|
|
1229 | |
|
|
1230 | =item $ulong = $event->profiling_command_start |
|
|
1231 | |
|
|
1232 | Calls C<clGetEventProfilingInfo> with C<CL_PROFILING_COMMAND_START> and returns the result(s). |
|
|
1233 | |
|
|
1234 | =item $ulong = $event->profiling_command_end |
|
|
1235 | |
|
|
1236 | Calls C<clGetEventProfilingInfo> with C<CL_PROFILING_COMMAND_END> and returns the result(s). |
|
|
1237 | |
|
|
1238 | =for gengetinfo end profiling |
|
|
1239 | |
|
|
1240 | =back |
|
|
1241 | |
|
|
1242 | =head2 THE OpenCL::UserEvent CLASS |
|
|
1243 | |
|
|
1244 | This is a subclass of OpenCL::Event. |
|
|
1245 | |
|
|
1246 | =over 4 |
|
|
1247 | |
|
|
1248 | =item $ev->set_status ($execution_status) |
|
|
1249 | |
|
|
1250 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html> |
|
|
1251 | |
|
|
1252 | =back |
|
|
1253 | |
33 | =cut |
1254 | =cut |
34 | |
1255 | |
35 | package OpenCL; |
1256 | package OpenCL; |
36 | |
1257 | |
37 | use common::sense; |
1258 | use common::sense; |
38 | |
1259 | |
39 | BEGIN { |
1260 | BEGIN { |
40 | our $VERSION = '0.01'; |
1261 | our $VERSION = '0.55'; |
41 | |
1262 | |
42 | require XSLoader; |
1263 | require XSLoader; |
43 | XSLoader::load (__PACKAGE__, $VERSION); |
1264 | XSLoader::load (__PACKAGE__, $VERSION); |
|
|
1265 | |
|
|
1266 | @OpenCL::Buffer::ISA = |
|
|
1267 | @OpenCL::Image::ISA = OpenCL::Memory::; |
|
|
1268 | |
|
|
1269 | @OpenCL::Image2D::ISA = |
|
|
1270 | @OpenCL::Image3D::ISA = OpenCL::Image::; |
|
|
1271 | |
|
|
1272 | @OpenCL::UserEvent::ISA = OpenCL::Event::; |
44 | } |
1273 | } |
45 | |
1274 | |
46 | 1; |
1275 | 1; |
47 | |
|
|
48 | =back |
|
|
49 | |
1276 | |
50 | =head1 AUTHOR |
1277 | =head1 AUTHOR |
51 | |
1278 | |
52 | Marc Lehmann <schmorp@schmorp.de> |
1279 | Marc Lehmann <schmorp@schmorp.de> |
53 | http://home.schmorp.de/ |
1280 | http://home.schmorp.de/ |