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::Buffers 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 | |
13 | =head1 HELPFUL RESOURCES |
46 | =head2 HELPFUL RESOURCES |
14 | |
47 | |
15 | The OpenCL spec used to dveelop this module (1.2 spec was available, but |
48 | The OpenCL spec used to develop this module (1.2 spec was available, but |
16 | no implementation was available to me :). |
49 | no implementation was available to me :). |
17 | |
50 | |
18 | http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf |
51 | http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf |
19 | |
52 | |
20 | OpenCL manpages: |
53 | OpenCL manpages: |
21 | |
54 | |
22 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/ |
55 | http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/ |
23 | |
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 | |
24 | =head1 EXAMPLES |
98 | =head1 EXAMPLES |
25 | |
99 | |
26 | 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. |
27 | |
104 | |
28 | for my $platform (OpenCL::platforms) { |
105 | for my $platform (OpenCL::platforms) { |
29 | warn $platform->info (OpenCL::PLATFORM_NAME); |
106 | printf "platform: %s\n", $platform->info (OpenCL::PLATFORM_NAME); |
30 | warn $platform->info (OpenCL::PLATFORM_EXTENSIONS); |
107 | printf "extensions: %s\n", $platform->info (OpenCL::PLATFORM_EXTENSIONS); |
31 | for my $device ($platform->devices) { |
108 | for my $device ($platform->devices) { |
32 | warn $device->info (OpenCL::DEVICE_NAME); |
109 | printf "+ device: %s\n", $device->info (OpenCL::DEVICE_NAME); |
33 | my $ctx = $device->context_simple; |
110 | my $ctx = $device->context; |
34 | # do stuff |
111 | # do stuff |
35 | } |
112 | } |
36 | } |
113 | } |
37 | |
114 | |
38 | Get a useful context and a command queue: |
115 | =head2 Get a useful context and a command queue. |
39 | |
116 | |
40 | my $dev = ((OpenCL::platforms)[0]->devices)[0]; |
117 | This is a useful boilerplate for any OpenCL program that only wants to use |
41 | my $ctx = $dev->context_simple; |
118 | one device, |
42 | my $queue = $ctx->command_queue_simple ($dev); |
|
|
43 | |
119 | |
44 | Create a buffer with some predefined data, read it back synchronously, |
120 | my ($platform) = OpenCL::platforms; # find first platform |
45 | then asynchronously: |
121 | my ($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 |
46 | |
124 | |
47 | my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); |
|
|
48 | |
|
|
49 | $queue->enqueue_read_buffer ($buf, 1, 1, 3, my $data); |
|
|
50 | warn $data; |
|
|
51 | |
|
|
52 | my $ev = $queue->enqueue_read_buffer ($buf, 0, 1, 3, my $data); |
|
|
53 | $ev->wait; |
|
|
54 | warn $data; |
|
|
55 | |
|
|
56 | Print all supported image formats: |
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. |
57 | |
129 | |
58 | for my $type (OpenCL::MEM_OBJECT_IMAGE2D, OpenCL::MEM_OBJECT_IMAGE3D) { |
130 | for my $type (OpenCL::MEM_OBJECT_IMAGE2D, OpenCL::MEM_OBJECT_IMAGE3D) { |
59 | say "supported image formats for ", OpenCL::enum2str $type; |
131 | print "supported image formats for ", OpenCL::enum2str $type, "\n"; |
60 | |
132 | |
61 | for my $f ($ctx->supported_image_formats (0, $type)) { |
133 | for my $f ($ctx->supported_image_formats (0, $type)) { |
62 | printf " %-10s %-20s\n", OpenCL::enum2str $f->[0], OpenCL::enum2str $f->[1]; |
134 | printf " %-10s %-20s\n", OpenCL::enum2str $f->[0], OpenCL::enum2str $f->[1]; |
63 | } |
135 | } |
64 | } |
136 | } |
65 | |
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 | |
66 | Create and build a program, then create a kernel out of one of its |
150 | =head2 Create and build a program, then create a kernel out of one of its |
67 | functions: |
151 | functions. |
68 | |
152 | |
69 | my $src = ' |
153 | my $src = ' |
70 | __kernel void |
154 | __kernel void |
71 | squareit (__global float *input, __global float *output) |
155 | squareit (__global float *input, __global float *output) |
72 | { |
156 | { |
73 | size_t id = get_global_id (0); |
157 | $id = get_global_id (0); |
74 | output [id] = input [id] * input [id]; |
158 | output [id] = input [id] * input [id]; |
75 | } |
159 | } |
76 | '; |
160 | '; |
77 | |
161 | |
78 | my $prog = $ctx->program_with_source ($src); |
162 | my $prog = $ctx->program_with_source ($src); |
79 | |
163 | |
|
|
164 | # build croaks on compile errors, so catch it and print the compile errors |
80 | eval { $prog->build ($dev); 1 } |
165 | eval { $prog->build ($dev); 1 } |
81 | or die $prog->build_info ($dev, OpenCL::PROGRAM_BUILD_LOG); |
166 | or die $prog->build_info ($dev, OpenCL::PROGRAM_BUILD_LOG); |
82 | |
167 | |
83 | my $kernel = $prog->kernel ("squareit"); |
168 | my $kernel = $prog->kernel ("squareit"); |
84 | |
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: |
|
|
224 | |
85 | =over 4 |
225 | =over 4 |
|
|
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 (C<clGetPlatformInfo>), |
|
|
232 | while this module uses underscores as word separator and often leaves out |
|
|
233 | prefixes (C<< $platform->info >>). |
|
|
234 | |
|
|
235 | =item * OpenCL often specifies fixed vector function arguments as short |
|
|
236 | arrays (C<$origin[3]>), while this module explicitly expects the |
|
|
237 | components as separate arguments- |
|
|
238 | |
|
|
239 | =item * Structures are often specified with their components, and returned |
|
|
240 | as arrayrefs. |
|
|
241 | |
|
|
242 | =item * Where possible, one of the pitch values is calculated from the |
|
|
243 | perl scalar length and need not be specified. |
|
|
244 | |
|
|
245 | =item * When enqueuing commands, the wait list is specified by adding |
|
|
246 | extra arguments to the function - anywhere a C<$wait_events...> argument |
|
|
247 | is documented this can be any number of event objects. |
|
|
248 | |
|
|
249 | =item * When enqueuing commands, if the enqueue method is called in void |
|
|
250 | context, no event is created. In all other contexts an event is returned |
|
|
251 | by the method. |
|
|
252 | |
|
|
253 | =item * This module expects all functions to return C<CL_SUCCESS>. If any |
|
|
254 | other status is returned the function will throw an exception, so you |
|
|
255 | don't normally have to to any error checking. |
|
|
256 | |
|
|
257 | =back |
|
|
258 | |
|
|
259 | =head2 PERL AND OPENCL TYPES |
|
|
260 | |
|
|
261 | This handy(?) table lists OpenCL types and their perl, PDL and pack/unpack |
|
|
262 | format equivalents: |
|
|
263 | |
|
|
264 | OpenCL perl PDL pack/unpack |
|
|
265 | char IV - c |
|
|
266 | uchar IV byte C |
|
|
267 | short IV short s |
|
|
268 | ushort IV ushort S |
|
|
269 | int IV long? l |
|
|
270 | uint IV - L |
|
|
271 | long IV longlong q |
|
|
272 | ulong IV - Q |
|
|
273 | float NV float f |
|
|
274 | half IV ushort S |
|
|
275 | double NV double d |
|
|
276 | |
|
|
277 | =head2 THE OpenCL PACKAGE |
|
|
278 | |
|
|
279 | =over 4 |
|
|
280 | |
|
|
281 | =item $int = OpenCL::errno |
|
|
282 | |
|
|
283 | The last error returned by a function - it's only valid after an error occured |
|
|
284 | and before calling another OpenCL function. |
|
|
285 | |
|
|
286 | =item $str = OpenCL::err2str $errval |
|
|
287 | |
|
|
288 | Comverts an error value into a human readable string. |
|
|
289 | |
|
|
290 | =item $str = OpenCL::enum2str $enum |
|
|
291 | |
|
|
292 | Converts most enum values (inof parameter names, image format constants, |
|
|
293 | object types, addressing and filter modes, command types etc.) into a |
|
|
294 | human readbale string. When confronted with some random integer it can be |
|
|
295 | very helpful to pass it through this function to maybe get some readable |
|
|
296 | string out of it. |
|
|
297 | |
|
|
298 | =item @platforms = OpenCL::platforms |
|
|
299 | |
|
|
300 | Returns all available OpenCL::Platform objects. |
|
|
301 | |
|
|
302 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformIDs.html> |
|
|
303 | |
|
|
304 | =item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef |
|
|
305 | |
|
|
306 | Tries to create a context from a default device and platform - never worked for me. |
|
|
307 | |
|
|
308 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
|
|
309 | |
|
|
310 | =item OpenCL::wait_for_events $wait_events... |
|
|
311 | |
|
|
312 | Waits for all events to complete. |
|
|
313 | |
|
|
314 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
|
|
315 | |
|
|
316 | =back |
|
|
317 | |
|
|
318 | =head2 THE OpenCL::Platform CLASS |
|
|
319 | |
|
|
320 | =over 4 |
|
|
321 | |
|
|
322 | =item $packed_value = $platform->info ($name) |
|
|
323 | |
|
|
324 | Calls C<clGetPlatformInfo> and returns the packed, raw value - for |
|
|
325 | strings, this will be the string, for other values you probably need to |
|
|
326 | use the correct C<unpack>. This might get improved in the future. Hopefully. |
|
|
327 | |
|
|
328 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetPlatformInfo.html> |
|
|
329 | |
|
|
330 | =item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL) |
|
|
331 | |
|
|
332 | Returns a list of matching OpenCL::Device objects. |
|
|
333 | |
|
|
334 | =item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef) |
|
|
335 | |
|
|
336 | Tries to create a context. Never worked for me, and you need devices explitly anyway. |
|
|
337 | |
|
|
338 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContextFromType.html> |
|
|
339 | |
|
|
340 | =item $ctx = $device->context ($properties = undef, @$devices, $notify = undef) |
|
|
341 | |
|
|
342 | Create a new OpenCL::Context object using the given device object(s)- a |
|
|
343 | CL_CONTEXT_PLATFORM property is supplied automatically. |
|
|
344 | |
|
|
345 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateContext.html> |
|
|
346 | |
|
|
347 | =back |
|
|
348 | |
|
|
349 | =head2 THE OpenCL::Device CLASS |
|
|
350 | |
|
|
351 | =over 4 |
|
|
352 | |
|
|
353 | =item $packed_value = $device->info ($name) |
|
|
354 | |
|
|
355 | See C<< $platform->info >> for details. |
|
|
356 | |
|
|
357 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetDeviceInfo.html> |
|
|
358 | |
|
|
359 | =back |
|
|
360 | |
|
|
361 | =head2 THE OpenCL::Context CLASS |
|
|
362 | |
|
|
363 | =over 4 |
|
|
364 | |
|
|
365 | =item $packed_value = $ctx->info ($name) |
|
|
366 | |
|
|
367 | See C<< $platform->info >> for details. |
|
|
368 | |
|
|
369 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetContextInfo.html> |
|
|
370 | |
|
|
371 | =item $queue = $ctx->queue ($device, $properties) |
|
|
372 | |
|
|
373 | Create a new OpenCL::Queue object from the context and the given device. |
|
|
374 | |
|
|
375 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateCommandQueue.html> |
|
|
376 | |
|
|
377 | =item $ev = $ctx->user_event |
|
|
378 | |
|
|
379 | Creates a new OpenCL::UserEvent object. |
|
|
380 | |
|
|
381 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateUserEvent.html> |
|
|
382 | |
|
|
383 | =item $buf = $ctx->buffer ($flags, $len) |
|
|
384 | |
|
|
385 | Creates a new OpenCL::Buffer object with the given flags and octet-size. |
|
|
386 | |
|
|
387 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateBuffer.html> |
|
|
388 | |
|
|
389 | =item $buf = $ctx->buffer_sv ($flags, $data) |
|
|
390 | |
|
|
391 | Creates a new OpenCL::Buffer object and initialise it with the given data values. |
|
|
392 | |
|
|
393 | =item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $row_pitch = 0, $data = undef) |
|
|
394 | |
|
|
395 | Creates a new OpenCL::Image2D object and optionally initialises it with the given data values. |
|
|
396 | |
|
|
397 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage2D.html> |
|
|
398 | |
|
|
399 | =item $img = $ctx->image3d ($flags, $channel_order, $channel_type, $width, $height, $depth, $row_pitch = 0, $slice_pitch = 0, $data = undef) |
|
|
400 | |
|
|
401 | Creates a new OpenCL::Image3D object and optionally initialises it with the given data values. |
|
|
402 | |
|
|
403 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateImage3D.html> |
|
|
404 | |
|
|
405 | =item @formats = $ctx->supported_image_formats ($flags, $image_type) |
|
|
406 | |
|
|
407 | Returns a list of matching image formats - each format is an arrayref with |
|
|
408 | two values, $channel_order and $channel_type, in it. |
|
|
409 | |
|
|
410 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetSupportedImageFormats.html> |
|
|
411 | |
|
|
412 | =item $sampler = $ctx->sampler ($normalized_coords, $addressing_mode, $filter_mode) |
|
|
413 | |
|
|
414 | Creates a new OpenCL::Sampler object. |
|
|
415 | |
|
|
416 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateSampler.html> |
|
|
417 | |
|
|
418 | =item $program = $ctx->program_with_source ($string) |
|
|
419 | |
|
|
420 | Creates a new OpenCL::Program object from the given source code. |
|
|
421 | |
|
|
422 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateProgramWithSource.html> |
|
|
423 | |
|
|
424 | =back |
|
|
425 | |
|
|
426 | =head2 THE OpenCL::Queue CLASS |
|
|
427 | |
|
|
428 | An OpenCL::Queue represents an execution queue for OpenCL. You execute |
|
|
429 | requests by calling their respective C<enqueue_xxx> method and waitinf for |
|
|
430 | it to complete in some way. |
|
|
431 | |
|
|
432 | All the enqueue methods return an event object that can be used to wait |
|
|
433 | for completion, unless the method is called in void context, in which case |
|
|
434 | no event object is created. |
|
|
435 | |
|
|
436 | They also allow you to specify any number of other event objects that this |
|
|
437 | request has to wait for before it starts executing, by simply passing the |
|
|
438 | event objects as extra parameters to the enqueue methods. |
|
|
439 | |
|
|
440 | Queues execute in-order by default, without any parallelism, so in most |
|
|
441 | cases (i.e. you use only one queue) it's not necessary to wait for or |
|
|
442 | create event objects. |
|
|
443 | |
|
|
444 | =over 4 |
|
|
445 | |
|
|
446 | =item $packed_value = $ctx->info ($name) |
|
|
447 | |
|
|
448 | See C<< $platform->info >> for details. |
|
|
449 | |
|
|
450 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetCommandQueueInfo.html> |
|
|
451 | |
|
|
452 | =item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) |
|
|
453 | |
|
|
454 | Reads data from buffer into the given string. |
|
|
455 | |
|
|
456 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBuffer.html> |
|
|
457 | |
|
|
458 | =item $ev = $queue->enqueue_write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) |
|
|
459 | |
|
|
460 | Writes data to buffer from the given string. |
|
|
461 | |
|
|
462 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBuffer.html> |
|
|
463 | |
|
|
464 | =item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) |
|
|
465 | |
|
|
466 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBuffer.html> |
|
|
467 | |
|
|
468 | =item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
|
|
469 | |
|
|
470 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadImage.html> |
|
|
471 | |
|
|
472 | =item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) |
|
|
473 | |
|
|
474 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteImage.html> |
|
|
475 | |
|
|
476 | =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...) |
|
|
477 | |
|
|
478 | Yeah. |
|
|
479 | |
|
|
480 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferRect.html> |
|
|
481 | |
|
|
482 | =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...) |
|
|
483 | |
|
|
484 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyBufferToImage.html>. |
|
|
485 | |
|
|
486 | =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...) |
|
|
487 | |
|
|
488 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImage.html> |
|
|
489 | |
|
|
490 | =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...) |
|
|
491 | |
|
|
492 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueCopyImageToBuffer.html> |
|
|
493 | |
|
|
494 | =item $ev = $queue->enqueue_task ($kernel, $wait_events...) |
|
|
495 | |
|
|
496 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueTask.html> |
|
|
497 | |
|
|
498 | =item $ev = $queue->enqueue_nd_range_kernel ($kernel, @$global_work_offset, @$global_work_size, @$local_work_size, $wait_events...) |
|
|
499 | |
|
|
500 | Enqueues a kernel execution. |
|
|
501 | |
|
|
502 | @$global_work_size must be specified as a reference to an array of |
|
|
503 | integers specifying the work sizes (element counts). |
|
|
504 | |
|
|
505 | @$global_work_offset must be either C<undef> (in which case all offsets |
|
|
506 | are C<0>), or a reference to an array of work offsets, with the same number |
|
|
507 | of elements as @$global_work_size. |
|
|
508 | |
|
|
509 | @$local_work_size must be either C<undef> (in which case the |
|
|
510 | implementation is supposed to choose good local work sizes), or a |
|
|
511 | reference to an array of local work sizes, with the same number of |
|
|
512 | elements as @$global_work_size. |
|
|
513 | |
|
|
514 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueNDRangeKernel.html> |
|
|
515 | |
|
|
516 | =item $ev = $queue->enqueue_marker |
|
|
517 | |
|
|
518 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueMarker.html> |
|
|
519 | |
|
|
520 | =item $ev = $queue->enqueue_wait_for_events ($wait_events...) |
|
|
521 | |
|
|
522 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWaitForEvents.html> |
|
|
523 | |
|
|
524 | =item $queue->enqueue_barrier |
|
|
525 | |
|
|
526 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueBarrier.html> |
|
|
527 | |
|
|
528 | =item $queue->flush |
|
|
529 | |
|
|
530 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFlush.html> |
|
|
531 | |
|
|
532 | =item $queue->finish |
|
|
533 | |
|
|
534 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clFinish.html> |
|
|
535 | |
|
|
536 | =back |
|
|
537 | |
|
|
538 | =head2 THE OpenCL::Memory CLASS |
|
|
539 | |
|
|
540 | This the superclass of all memory objects - OpenCL::Buffer, OpenCL::Image, |
|
|
541 | OpenCL::Image2D and OpenCL::Image3D. The subclasses of this class |
|
|
542 | currently only exist to allow type-checking. |
|
|
543 | |
|
|
544 | =over 4 |
|
|
545 | |
|
|
546 | =item $packed_value = $memory->info ($name) |
|
|
547 | |
|
|
548 | See C<< $platform->info >> for details. |
|
|
549 | |
|
|
550 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetMemObjectInfo.html> |
|
|
551 | |
|
|
552 | =back |
|
|
553 | |
|
|
554 | =head2 THE OpenCL::Sampler CLASS |
|
|
555 | |
|
|
556 | =over 4 |
|
|
557 | |
|
|
558 | =item $packed_value = $sampler->info ($name) |
|
|
559 | |
|
|
560 | See C<< $platform->info >> for details. |
|
|
561 | |
|
|
562 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetSamplerInfo.html> |
|
|
563 | |
|
|
564 | =back |
|
|
565 | |
|
|
566 | =head2 THE OpenCL::Program CLASS |
|
|
567 | |
|
|
568 | =over 4 |
|
|
569 | |
|
|
570 | =item $packed_value = $program->info ($name) |
|
|
571 | |
|
|
572 | See C<< $platform->info >> for details. |
|
|
573 | |
|
|
574 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetProgramInfo.html> |
|
|
575 | |
|
|
576 | =item $program->build ($device, $options = "") |
|
|
577 | |
|
|
578 | Tries to build the program with the givne options. |
|
|
579 | |
|
|
580 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clBuildProgram.html> |
|
|
581 | |
|
|
582 | =item $packed_value = $program->build_info ($device, $name) |
|
|
583 | |
|
|
584 | Similar to C<< $platform->info >>, but returns build info for a previous |
|
|
585 | build attempt for the given device. |
|
|
586 | |
|
|
587 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetBuildInfo.html> |
|
|
588 | |
|
|
589 | =item $kernel = $program->kernel ($function_name) |
|
|
590 | |
|
|
591 | Creates an OpenCL::Kernel object out of the named C<__kernel> function in |
|
|
592 | the program. |
|
|
593 | |
|
|
594 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateKernel.html> |
|
|
595 | |
|
|
596 | =back |
|
|
597 | |
|
|
598 | =head2 THE OpenCL::Kernel CLASS |
|
|
599 | |
|
|
600 | =over 4 |
|
|
601 | |
|
|
602 | =item $packed_value = $kernel->info ($name) |
|
|
603 | |
|
|
604 | See C<< $platform->info >> for details. |
|
|
605 | |
|
|
606 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetKernelInfo.html> |
|
|
607 | |
|
|
608 | =item $kernel->set_TYPE ($index, $value) |
|
|
609 | |
|
|
610 | This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>. |
|
|
611 | |
|
|
612 | TYPE is one of C<char>, C<uchar>, C<short>, C<ushort>, C<int>, C<uint>, |
|
|
613 | C<long>, C<ulong>, C<half>, C<float>, C<double>, C<memory>, C<buffer>, |
|
|
614 | C<image2d>, C<image3d>, C<sampler> or C<event>. |
|
|
615 | |
|
|
616 | Chars and integers (including the half type) are specified as integers, |
|
|
617 | float and double as floating point values, memory/buffer/image2d/image3d |
|
|
618 | must be an object of that type or C<undef>, and sampler and event must be |
|
|
619 | objects of that type. |
|
|
620 | |
|
|
621 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetKernelArg.html> |
|
|
622 | |
|
|
623 | =back |
|
|
624 | |
|
|
625 | =head2 THE OpenCL::Event CLASS |
|
|
626 | |
|
|
627 | This is the superclass for all event objects (including OpenCL::UserEvent |
|
|
628 | objects). |
|
|
629 | |
|
|
630 | =over 4 |
|
|
631 | |
|
|
632 | =item $packed_value = $ev->info ($name) |
|
|
633 | |
|
|
634 | See C<< $platform->info >> for details. |
|
|
635 | |
|
|
636 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clGetEventInfo.html> |
|
|
637 | |
|
|
638 | =item $ev->wait |
|
|
639 | |
|
|
640 | Waits for the event to complete. |
|
|
641 | |
|
|
642 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clWaitForEvents.html> |
|
|
643 | |
|
|
644 | =back |
|
|
645 | |
|
|
646 | =head2 THE OpenCL::UserEvent CLASS |
|
|
647 | |
|
|
648 | This is a subclass of OpenCL::Event. |
|
|
649 | |
|
|
650 | =over 4 |
|
|
651 | |
|
|
652 | =item $ev->set_status ($execution_status) |
|
|
653 | |
|
|
654 | L<http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clSetUserEventStatus.html> |
|
|
655 | |
|
|
656 | =back |
86 | |
657 | |
87 | =cut |
658 | =cut |
88 | |
659 | |
89 | package OpenCL; |
660 | package OpenCL; |
90 | |
661 | |
91 | use common::sense; |
662 | use common::sense; |
92 | |
663 | |
93 | BEGIN { |
664 | BEGIN { |
94 | our $VERSION = '0.01'; |
665 | our $VERSION = '0.15'; |
95 | |
666 | |
96 | require XSLoader; |
667 | require XSLoader; |
97 | XSLoader::load (__PACKAGE__, $VERSION); |
668 | XSLoader::load (__PACKAGE__, $VERSION); |
98 | |
669 | |
99 | @OpenCL::Buffer::ISA = |
670 | @OpenCL::Buffer::ISA = |
100 | @OpenCL::Image::ISA = OpenCL::Memory::; |
671 | @OpenCL::Image::ISA = OpenCL::Memory::; |
101 | |
672 | |
102 | @OpenCL::Image2D::ISA = |
673 | @OpenCL::Image2D::ISA = |
103 | @OpenCL::Image3D::ISA = OpenCL::Image::; |
674 | @OpenCL::Image3D::ISA = OpenCL::Image::; |
|
|
675 | |
|
|
676 | @OpenCL::UserEvent::ISA = OpenCL::Event::; |
104 | } |
677 | } |
105 | |
678 | |
106 | 1; |
679 | 1; |
107 | |
|
|
108 | =back |
|
|
109 | |
680 | |
110 | =head1 AUTHOR |
681 | =head1 AUTHOR |
111 | |
682 | |
112 | Marc Lehmann <schmorp@schmorp.de> |
683 | Marc Lehmann <schmorp@schmorp.de> |
113 | http://home.schmorp.de/ |
684 | http://home.schmorp.de/ |