--- OpenCL/OpenCL.pm 2011/11/15 09:24:40 1.2 +++ OpenCL/OpenCL.pm 2012/04/19 13:06:55 1.34 @@ -1,6 +1,6 @@ =head1 NAME -OpenCL - bindings to, well, OpenCL +OpenCL - Open Computing Language Bindings =head1 SYNOPSIS @@ -8,28 +8,1342 @@ =head1 DESCRIPTION -This is an early release which is not useful yet. +This is an early release which might be useful, but hasn't seen much testing. -Enumerate all devices and get contexts for them; +=head2 OpenCL FROM 10000 FEET HEIGHT + +Here is a high level overview of OpenCL: + +First you need to find one or more OpenCL::Platforms (kind of like +vendors) - usually there is only one. + +Each platform gives you access to a number of OpenCL::Device objects, e.g. +your graphics card. + +From a platform and some device(s), you create an OpenCL::Context, which is +a very central object in OpenCL: Once you have a context you can create +most other objects: + +OpenCL::Program objects, which store source code and, after building for a +specific device ("compiling and linking"), also binary programs. For each +kernel function in a program you can then create an OpenCL::Kernel object +which represents basically a function call with argument values. + +OpenCL::Memory objects of various flavours: OpenCL::Buffer objects (flat +memory areas, think arrays or structs) and OpenCL::Image objects (think 2d +or 3d array) for bulk data and input and output for kernels. + +OpenCL::Sampler objects, which are kind of like texture filter modes in +OpenGL. + +OpenCL::Queue objects - command queues, which allow you to submit memory +reads, writes and copies, as well as kernel calls to your devices. They +also offer a variety of methods to synchronise request execution, for +example with barriers or OpenCL::Event objects. + +OpenCL::Event objects are used to signal when something is complete. + +=head2 HELPFUL RESOURCES + +The OpenCL spec used to develop this module (1.2 spec was available, but +no implementation was available to me :). + + http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf + +OpenCL manpages: + + http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/ + +If you are into UML class diagrams, the following diagram might help - if +not, it will be mildly cobfusing: + + http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/classDiagram.html + +Here's a tutorial from AMD (very AMD-centric, too), not sure how useful it +is, but at least it's free of charge: + + http://developer.amd.com/zones/OpenCLZone/courses/Documents/Introduction_to_OpenCL_Programming%20Training_Guide%20%28201005%29.pdf + +And here's NVIDIA's OpenCL Best Practises Guide: + + http://developer.download.nvidia.com/compute/cuda/3_2/toolkit/docs/OpenCL_Best_Practices_Guide.pdf + +=head1 BASIC WORKFLOW + +To get something done, you basically have to do this once (refer to the +examples below for actual code, this is just a high-level description): + +Find some platform (e.g. the first one) and some device(s) (e.g. the first +device of the platform), and create a context from those. + +Create program objects from your OpenCL source code, then build (compile) +the programs for each device you want to run them on. + +Create kernel objects for all kernels you want to use (surprisingly, these +are not device-specific). + +Then, to execute stuff, you repeat these steps, possibly resuing or +sharing some buffers: + +Create some input and output buffers from your context. Set these as +arguments to your kernel. + +Enqueue buffer writes to initialise your input buffers (when not +initialised at creation time). + +Enqueue the kernel execution. + +Enqueue buffer reads for your output buffer to read results. + +=head1 EXAMPLES + +=head2 Enumerate all devices and get contexts for them. + +Best run this once to get a feel for the platforms and devices in your +system. for my $platform (OpenCL::platforms) { - warn $platform->info (OpenCL::PLATFORM_NAME); - warn $platform->info (OpenCL::PLATFORM_EXTENSIONS); + printf "platform: %s\n", $platform->name; + printf "extensions: %s\n", $platform->extensions; for my $device ($platform->devices) { - warn $device->info (OpenCL::DEVICE_NAME); - my $ctx = $device->context_simple; + printf "+ device: %s\n", $device->name; + my $ctx = $platform->context (undef, [$device]); # do stuff } } -Get a useful context and a command queue: +=head2 Get a useful context and a command queue. + +This is a useful boilerplate for any OpenCL program that only wants to use +one device, + + my ($platform) = OpenCL::platforms; # find first platform + my ($dev) = $platform->devices; # find first device of platform + my $ctx = $platform->context (undef, [$dev]); # create context out of those + my $queue = $ctx->queue ($dev); # create a command queue for the device + +=head2 Print all supported image formats of a context. + +Best run this once for your context, to see whats available and how to +gather information. + + for my $type (OpenCL::MEM_OBJECT_IMAGE2D, OpenCL::MEM_OBJECT_IMAGE3D) { + print "supported image formats for ", OpenCL::enum2str $type, "\n"; + + for my $f ($ctx->supported_image_formats (0, $type)) { + printf " %-10s %-20s\n", OpenCL::enum2str $f->[0], OpenCL::enum2str $f->[1]; + } + } + +=head2 Create a buffer with some predefined data, read it back synchronously, +then asynchronously. + + my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); + + $queue->enqueue_read_buffer ($buf, 1, 1, 3, my $data); + print "$data\n"; + + my $ev = $queue->enqueue_read_buffer ($buf, 0, 1, 3, my $data); + $ev->wait; + print "$data\n"; # prints "elm" + +=head2 Create and build a program, then create a kernel out of one of its +functions. + + my $src = ' + kernel void + squareit (global float *input, global float *output) + { + $id = get_global_id (0); + output [id] = input [id] * input [id]; + } + '; + + my $prog = $ctx->program_with_source ($src); + + # build croaks on compile errors, so catch it and print the compile errors + eval { $prog->build ($dev); 1 } + or die $prog->build_log; + + my $kernel = $prog->kernel ("squareit"); + +=head2 Create some input and output float buffers, then call the +'squareit' kernel on them. + + my $input = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, pack "f*", 1, 2, 3, 4.5); + my $output = $ctx->buffer (0, OpenCL::SIZEOF_FLOAT * 5); + + # set buffer + $kernel->set_buffer (0, $input); + $kernel->set_buffer (1, $output); + + # execute it for all 4 numbers + $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); + + # enqueue a synchronous read + $queue->enqueue_read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); + + # print the results: + printf "%s\n", join ", ", unpack "f*", $data; + +=head2 The same enqueue operations as before, but assuming an out-of-order queue, +showing off barriers. + + # execute it for all 4 numbers + $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); + + # enqueue a barrier to ensure in-order execution + $queue->enqueue_barrier; + + # enqueue an async read + $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); + + # wait for all requests to finish + $queue->finish; + +=head2 The same enqueue operations as before, but assuming an out-of-order queue, +showing off event objects and wait lists. + + # execute it for all 4 numbers + my $ev = $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); + + # enqueue an async read + $ev = $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev); + + # wait for the last event to complete + $ev->wait; + +=head1 DOCUMENTATION + +=head2 BASIC CONVENTIONS + +This is not a one-to-one C-style translation of OpenCL to Perl - instead +I attempted to make the interface as type-safe as possible by introducing +object syntax where it makes sense. There are a number of important +differences between the OpenCL C API and this module: + +=over 4 + +=item * Object lifetime managament is automatic - there is no need +to free objects explicitly (C), the release function +is called automatically once all Perl references to it go away. + +=item * OpenCL uses CamelCase for function names +(e.g. C, C), while this module +uses underscores as word separator and often leaves out prefixes +(C, C<< $platform->info >>). + +=item * OpenCL often specifies fixed vector function arguments as short +arrays (C), while this module explicitly expects the +components as separate arguments (C<$orig_x, $orig_y, $orig_z>) in +function calls. + +=item * Structures are often specified by flattening out their components +as with short vectors, and returned as arrayrefs. + +=item * When enqueuing commands, the wait list is specified by adding +extra arguments to the function - anywhere a C<$wait_events...> argument +is documented this can be any number of event objects. + +=item * When enqueuing commands, if the enqueue method is called in void +context, no event is created. In all other contexts an event is returned +by the method. + +=item * This module expects all functions to return C. If any +other status is returned the function will throw an exception, so you +don't normally have to to any error checking. + +=back + +=head2 PERL AND OPENCL TYPES + +This handy(?) table lists OpenCL types and their perl, PDL and pack/unpack +format equivalents: + + OpenCL perl PDL pack/unpack + char IV - c + uchar IV byte C + short IV short s + ushort IV ushort S + int IV long? l + uint IV - L + long IV longlong q + ulong IV - Q + float NV float f + half IV ushort S + double NV double d + +=head2 THE OpenCL PACKAGE + +=over 4 + +=item $int = OpenCL::errno + +The last error returned by a function - it's only valid after an error occured +and before calling another OpenCL function. + +=item $str = OpenCL::err2str $errval + +Comverts an error value into a human readable string. + +=item $str = OpenCL::enum2str $enum + +Converts most enum values (of parameter names, image format constants, +object types, addressing and filter modes, command types etc.) into a +human readable string. When confronted with some random integer it can be +very helpful to pass it through this function to maybe get some readable +string out of it. + +=item @platforms = OpenCL::platforms + +Returns all available OpenCL::Platform objects. + +L + +=item $ctx = OpenCL::context_from_type $properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef + +Tries to create a context from a default device and platform - never worked for me. + +L + +=item OpenCL::wait_for_events $wait_events... + +Waits for all events to complete. + +L + +=back + +=head2 THE OpenCL::Platform CLASS + +=over 4 + +=item @devices = $platform->devices ($type = OpenCL::DEVICE_TYPE_ALL) + +Returns a list of matching OpenCL::Device objects. + +=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef) + +Tries to create a context. Never worked for me, and you need devices explicitly anyway. + +L + +=item $ctx = $platform->context ($properties = undef, @$devices, $notify = undef) + +Create a new OpenCL::Context object using the given device object(s)- a +CL_CONTEXT_PLATFORM property is supplied automatically. + +L + +=item $packed_value = $platform->info ($name) + +Calls C and returns the packed, raw value - for +strings, this will be the string (possibly including terminating \0), for +other values you probably need to use the correct C. + +It's best to avoid this method and use one of the following convenience +wrappers. + +L + +=for gengetinfo begin platform + +=item $string = $platform->profile + +Calls C with C and returns the result. + +=item $string = $platform->version + +Calls C with C and returns the result. + +=item $string = $platform->name + +Calls C with C and returns the result. + +=item $string = $platform->vendor + +Calls C with C and returns the result. + +=item $string = $platform->extensions + +Calls C with C and returns the result. + +=for gengetinfo end platform + +=back + +=head2 THE OpenCL::Device CLASS + +=over 4 + +=item $packed_value = $device->info ($name) + +See C<< $platform->info >> for details. + +L + +=for gengetinfo begin device + +=item $device_type = $device->type + +Calls C with C and returns the result. + +=item $uint = $device->vendor_id + +Calls C with C and returns the result. + +=item $uint = $device->max_compute_units + +Calls C with C and returns the result. + +=item $uint = $device->max_work_item_dimensions + +Calls C with C and returns the result. + +=item $int = $device->max_work_group_size + +Calls C with C and returns the result. + +=item @ints = $device->max_work_item_sizes + +Calls C with C and returns the result. + +=item $uint = $device->preferred_vector_width_char + +Calls C with C and returns the result. + +=item $uint = $device->preferred_vector_width_short + +Calls C with C and returns the result. + +=item $uint = $device->preferred_vector_width_int + +Calls C with C and returns the result. + +=item $uint = $device->preferred_vector_width_long + +Calls C with C and returns the result. + +=item $uint = $device->preferred_vector_width_float + +Calls C with C and returns the result. + +=item $uint = $device->preferred_vector_width_double + +Calls C with C and returns the result. + +=item $uint = $device->max_clock_frequency + +Calls C with C and returns the result. + +=item $bitfield = $device->address_bits + +Calls C with C and returns the result. + +=item $uint = $device->max_read_image_args + +Calls C with C and returns the result. + +=item $uint = $device->max_write_image_args + +Calls C with C and returns the result. + +=item $ulong = $device->max_mem_alloc_size + +Calls C with C and returns the result. + +=item $int = $device->image2d_max_width + +Calls C with C and returns the result. + +=item $int = $device->image2d_max_height + +Calls C with C and returns the result. + +=item $int = $device->image3d_max_width + +Calls C with C and returns the result. + +=item $int = $device->image3d_max_height + +Calls C with C and returns the result. + +=item $int = $device->image3d_max_depth + +Calls C with C and returns the result. + +=item $uint = $device->image_support + +Calls C with C and returns the result. + +=item $int = $device->max_parameter_size + +Calls C with C and returns the result. + +=item $uint = $device->max_samplers + +Calls C with C and returns the result. + +=item $uint = $device->mem_base_addr_align + +Calls C with C and returns the result. + +=item $uint = $device->min_data_type_align_size + +Calls C with C and returns the result. + +=item $device_fp_config = $device->single_fp_config + +Calls C with C and returns the result. + +=item $device_mem_cache_type = $device->global_mem_cache_type + +Calls C with C and returns the result. + +=item $uint = $device->global_mem_cacheline_size + +Calls C with C and returns the result. + +=item $ulong = $device->global_mem_cache_size + +Calls C with C and returns the result. + +=item $ulong = $device->global_mem_size + +Calls C with C and returns the result. + +=item $ulong = $device->max_constant_buffer_size + +Calls C with C and returns the result. + +=item $uint = $device->max_constant_args + +Calls C with C and returns the result. + +=item $device_local_mem_type = $device->local_mem_type + +Calls C with C and returns the result. + +=item $ulong = $device->local_mem_size + +Calls C with C and returns the result. + +=item $boolean = $device->error_correction_support + +Calls C with C and returns the result. + +=item $int = $device->profiling_timer_resolution + +Calls C with C and returns the result. + +=item $boolean = $device->endian_little + +Calls C with C and returns the result. + +=item $boolean = $device->available + +Calls C with C and returns the result. + +=item $boolean = $device->compiler_available + +Calls C with C and returns the result. + +=item $device_exec_capabilities = $device->execution_capabilities + +Calls C with C and returns the result. + +=item $command_queue_properties = $device->properties + +Calls C with C and returns the result. + +=item $ = $device->platform + +Calls C with C and returns the result. + +=item $string = $device->name + +Calls C with C and returns the result. + +=item $string = $device->vendor + +Calls C with C and returns the result. + +=item $string = $device->driver_version + +Calls C with C and returns the result. + +=item $string = $device->profile + +Calls C with C and returns the result. + +=item $string = $device->version + +Calls C with C and returns the result. + +=item $string = $device->extensions + +Calls C with C and returns the result. + +=item $uint = $device->preferred_vector_width_half + +Calls C with C and returns the result. + +=item $uint = $device->native_vector_width_char + +Calls C with C and returns the result. + +=item $uint = $device->native_vector_width_short + +Calls C with C and returns the result. + +=item $uint = $device->native_vector_width_int + +Calls C with C and returns the result. + +=item $uint = $device->native_vector_width_long + +Calls C with C and returns the result. + +=item $uint = $device->native_vector_width_float + +Calls C with C and returns the result. + +=item $uint = $device->native_vector_width_double + +Calls C with C and returns the result. + +=item $uint = $device->native_vector_width_half + +Calls C with C and returns the result. + +=item $device_fp_config = $device->double_fp_config + +Calls C with C and returns the result. + +=item $device_fp_config = $device->half_fp_config + +Calls C with C and returns the result. + +=item $boolean = $device->host_unified_memory + +Calls C with C and returns the result. + +=item $device = $device->parent_device_ext + +Calls C with C and returns the result. + +=item @device_partition_property_exts = $device->partition_types_ext + +Calls C with C and returns the result. + +=item @device_partition_property_exts = $device->affinity_domains_ext + +Calls C with C and returns the result. + +=item $uint = $device->reference_count_ext + +Calls C with C and returns the result. + +=item @device_partition_property_exts = $device->partition_style_ext + +Calls C with C and returns the result. + +=for gengetinfo end device + +=back + +=head2 THE OpenCL::Context CLASS + +=over 4 + +=item $queue = $ctx->queue ($device, $properties) + +Create a new OpenCL::Queue object from the context and the given device. + +L + +=item $ev = $ctx->user_event + +Creates a new OpenCL::UserEvent object. + +L + +=item $buf = $ctx->buffer ($flags, $len) + +Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object with the +given flags and octet-size. + +L + +=item $buf = $ctx->buffer_sv ($flags, $data) + +Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object and +initialise it with the given data values. + +=item $img = $ctx->image2d ($flags, $channel_order, $channel_type, $width, $height, $row_pitch = 0, $data = undef) + +Creates a new OpenCL::Image2D object and optionally initialises it with +the given data values. + +L + +=item $img = $ctx->image3d ($flags, $channel_order, $channel_type, $width, $height, $depth, $row_pitch = 0, $slice_pitch = 0, $data = undef) + +Creates a new OpenCL::Image3D object and optionally initialises it with +the given data values. + +L + +=item $buffer = $ctx->gl_buffer ($flags, $bufobj) + +Creates a new OpenCL::Buffer (actually OpenCL::BufferObj) object that refers to the given +OpenGL buffer object. + +http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLBuffer.html + +=item $ctx->gl_texture2d ($flags, $target, $miplevel, $texture) + +Creates a new OpenCL::Image2D object that refers to the given OpenGL +2D texture object. + +http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture2D.html + +=item $ctx->gl_texture3d ($flags, $target, $miplevel, $texture) + +Creates a new OpenCL::Image3D object that refers to the given OpenGL +3D texture object. + +http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLTexture3D.html + +=item $ctx->gl_renderbuffer ($flags, $renderbuffer) + +Creates a new OpenCL::Image2D object that refers to the given OpenGL +render buffer. + +http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clCreateFromGLRenderbuffer.html + +=item @formats = $ctx->supported_image_formats ($flags, $image_type) + +Returns a list of matching image formats - each format is an arrayref with +two values, $channel_order and $channel_type, in it. + +L + +=item $sampler = $ctx->sampler ($normalized_coords, $addressing_mode, $filter_mode) + +Creates a new OpenCL::Sampler object. - my $dev = ((OpenCL::platforms)[0]->devices)[0]; - my $ctx = $dev->context_simple; - my $queue = $ctx->command_queue_simple ($dev); +L + +=item $program = $ctx->program_with_source ($string) + +Creates a new OpenCL::Program object from the given source code. + +L + +=item $packed_value = $ctx->info ($name) + +See C<< $platform->info >> for details. + +L + +=for gengetinfo begin context + +=item $uint = $context->reference_count + +Calls C with C and returns the result. + +=item @devices = $context->devices + +Calls C with C and returns the result. + +=item @property_ints = $context->properties + +Calls C with C and returns the result. + +=item $uint = $context->num_devices + +Calls C with C and returns the result. + +=for gengetinfo end context + +=back + +=head2 THE OpenCL::Queue CLASS + +An OpenCL::Queue represents an execution queue for OpenCL. You execute +requests by calling their respective C method and waitinf for +it to complete in some way. + +All the enqueue methods return an event object that can be used to wait +for completion, unless the method is called in void context, in which case +no event object is created. + +They also allow you to specify any number of other event objects that this +request has to wait for before it starts executing, by simply passing the +event objects as extra parameters to the enqueue methods. + +Queues execute in-order by default, without any parallelism, so in most +cases (i.e. you use only one queue) it's not necessary to wait for or +create event objects. + +=over 4 + +=item $ev = $queue->enqueue_read_buffer ($buffer, $blocking, $offset, $len, $data, $wait_events...) + +Reads data from buffer into the given string. + +L + +=item $ev = $queue->enqueue_write_buffer ($buffer, $blocking, $offset, $data, $wait_events...) + +Writes data to buffer from the given string. + +L + +=item $ev = $queue->enqueue_copy_buffer ($src, $dst, $src_offset, $dst_offset, $len, $wait_events...) + +L + +=item $ev = $queue->enqueue_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...) + +http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueReadBufferRect.html + +=item $ev = $queue->enqueue_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...) + +http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/clEnqueueWriteBufferRect.html + +=item $ev = $queue->enqueue_read_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) + +L + +=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...) + +L + +=item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) + +L + +=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...) + +L + +=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...) + +L + +=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...) + +Yeah. + +L. + +=item $ev = $queue->enqueue_task ($kernel, $wait_events...) + +L + +=item $ev = $queue->enqueue_nd_range_kernel ($kernel, @$global_work_offset, @$global_work_size, @$local_work_size, $wait_events...) + +Enqueues a kernel execution. + +@$global_work_size must be specified as a reference to an array of +integers specifying the work sizes (element counts). + +@$global_work_offset must be either C (in which case all offsets +are C<0>), or a reference to an array of work offsets, with the same number +of elements as @$global_work_size. + +@$local_work_size must be either C (in which case the +implementation is supposed to choose good local work sizes), or a +reference to an array of local work sizes, with the same number of +elements as @$global_work_size. + +L + +=item $ev = $queue->enqueue_marker + +L + +=item $ev = $queue->enqueue_wait_for_events ($wait_events...) + +L + +=item $queue->enqueue_barrier + +L + +=item $queue->flush + +L + +=item $queue->finish + +L + +=item $packed_value = $queue->info ($name) + +See C<< $platform->info >> for details. + +L + +=for gengetinfo begin command_queue + +=item $ctx = $command_queue->context + +Calls C with C and returns the result. + +=item $device = $command_queue->device + +Calls C with C and returns the result. + +=item $uint = $command_queue->reference_count + +Calls C with C and returns the result. + +=item $command_queue_properties = $command_queue->properties + +Calls C with C and returns the result. + +=for gengetinfo end command_queue + +=back + +=head2 THE OpenCL::Memory CLASS + +This the superclass of all memory objects - OpenCL::Buffer, OpenCL::Image, +OpenCL::Image2D and OpenCL::Image3D. + +=over 4 + +=item $packed_value = $memory->info ($name) + +See C<< $platform->info >> for details. + +L + +=for gengetinfo begin mem + +=item $mem_object_type = $mem->type + +Calls C with C and returns the result. + +=item $mem_flags = $mem->flags + +Calls C with C and returns the result. + +=item $int = $mem->size + +Calls C with C and returns the result. + +=item $ptr_value = $mem->host_ptr + +Calls C with C and returns the result. + +=item $uint = $mem->map_count + +Calls C with C and returns the result. + +=item $uint = $mem->reference_count + +Calls C with C and returns the result. + +=item $ctx = $mem->context + +Calls C with C and returns the result. + +=item $mem = $mem->associated_memobject + +Calls C with C and returns the result. + +=item $int = $mem->offset + +Calls C with C and returns the result. + +=for gengetinfo end mem + +=item ($type, $name) = $mem->gl_object_info + +Returns the OpenGL object type (e.g. OpenCL::GL_OBJECT_TEXTURE2D) and the +object "name" (e.g. the texture name) used to create this memory object. + +L + +=back + +=head2 THE OpenCL::Buffer CLASS + +This is a subclass of OpenCL::Memory, and the superclass of +OpenCL::BufferObj. Its purpose is simply to distinguish between buffers +and sub-buffers. + +=head2 THE OpenCL::BufferObj CLASS + +This is a subclass of OpenCL::Buffer and thus OpenCL::Memory. It exists +because one cna create sub buffers of OpenLC::BufferObj objects, but not +sub buffers from these sub buffers. + +=over 4 + +=item $subbuf = $buf_obj->sub_buffer_region ($flags, $origin, $size) + +Creates an OpenCL::Buffer objects from this buffer and returns it. The +C is assumed to be C. + +L + +=back + +=head2 THE OpenCL::Image CLASS + +This is the superclass of all image objects - OpenCL::Image2D and OpenCL::Image3D. + +=over 4 + +=item $packed_value = $ev->image_info ($name) + +See C<< $platform->info >> for details. + +The reason this method is not called C is that there already is an +C<< ->info >> method inherited from C. + +L + +=for gengetinfo begin image + +=item $int = $image->element_size + +Calls C with C and returns the result. + +=item $int = $image->row_pitch + +Calls C with C and returns the result. + +=item $int = $image->slice_pitch + +Calls C with C and returns the result. + +=item $int = $image->width + +Calls C with C and returns the result. + +=item $int = $image->height + +Calls C with C and returns the result. + +=item $int = $image->depth + +Calls C with C and returns the result. + +=for gengetinfo end image + +=for gengetinfo begin gl_texture + +=item $GLenum = $gl_texture->target + +Calls C with C and returns the result. + +=item $GLint = $gl_texture->gl_mipmap_level + +Calls C with C and returns the result. + +=for gengetinfo end gl_texture + +=back + +=head2 THE OpenCL::Sampler CLASS + +=over 4 + +=item $packed_value = $sampler->info ($name) + +See C<< $platform->info >> for details. + +L + +=for gengetinfo begin sampler + +=item $uint = $sampler->reference_count + +Calls C with C and returns the result. + +=item $ctx = $sampler->context + +Calls C with C and returns the result. + +=item $addressing_mode = $sampler->normalized_coords + +Calls C with C and returns the result. + +=item $filter_mode = $sampler->addressing_mode + +Calls C with C and returns the result. + +=item $boolean = $sampler->filter_mode + +Calls C with C and returns the result. + +=for gengetinfo end sampler + +=back + +=head2 THE OpenCL::Program CLASS + +=over 4 + +=item $program->build ($device, $options = "") + +Tries to build the program with the givne options. + +L + +=item $packed_value = $program->build_info ($device, $name) + +Similar to C<< $platform->info >>, but returns build info for a previous +build attempt for the given device. + +L + +=item $kernel = $program->kernel ($function_name) + +Creates an OpenCL::Kernel object out of the named C<__kernel> function in +the program. + +L + +=for gengetinfo begin program_build + +=item $build_status = $program->build_status ($device) + +Calls C with C and returns the result. + +=item $string = $program->build_options ($device) + +Calls C with C and returns the result. + +=item $string = $program->build_log ($device) + +Calls C with C and returns the result. + +=for gengetinfo end program_build + +=item $packed_value = $program->info ($name) + +See C<< $platform->info >> for details. + +L + +=for gengetinfo begin program + +=item $uint = $program->reference_count + +Calls C with C and returns the result. + +=item $ctx = $program->context + +Calls C with C and returns the result. + +=item $uint = $program->num_devices + +Calls C with C and returns the result. + +=item @devices = $program->devices + +Calls C with C and returns the result. + +=item $string = $program->source + +Calls C with C and returns the result. + +=item @ints = $program->binary_sizes + +Calls C with C and returns the result. + +=for gengetinfo end program + +=item @blobs = $program->binaries + +Returns a string for the compiled binary for every device associated with +the program, empty strings indicate missing programs, and an empty result +means no program binaries are available. + +These "binaries" are often, in fact, informative low-level assembly +sources. + +L + +=back + +=head2 THE OpenCL::Kernel CLASS =over 4 +=item $packed_value = $kernel->info ($name) + +See C<< $platform->info >> for details. + +L + +=for gengetinfo begin kernel + +=item $string = $kernel->function_name + +Calls C with C and returns the result. + +=item $uint = $kernel->num_args + +Calls C with C and returns the result. + +=item $uint = $kernel->reference_count + +Calls C with C and returns the result. + +=item $ctx = $kernel->context + +Calls C with C and returns the result. + +=item $program = $kernel->program + +Calls C with C and returns the result. + +=for gengetinfo end kernel + +=item $packed_value = $kernel->work_group_info ($device, $name) + +See C<< $platform->info >> for details. + +The reason this method is not called C is that there already is an +C<< ->info >> method. + +L + +=for gengetinfo begin kernel_work_group + +=item $int = $kernel->work_group_size ($device) + +Calls C with C and returns the result. + +=item @ints = $kernel->compile_work_group_size ($device) + +Calls C with C and returns the result. + +=item $ulong = $kernel->local_mem_size ($device) + +Calls C with C and returns the result. + +=item $int = $kernel->preferred_work_group_size_multiple ($device) + +Calls C with C and returns the result. + +=item $ulong = $kernel->private_mem_size ($device) + +Calls C with C and returns the result. + +=for gengetinfo end kernel_work_group + +=item $kernel->set_TYPE ($index, $value) + +This is a family of methods to set the kernel argument with the number C<$index> to the give C<$value>. + +TYPE is one of C, C, C, C, C, C, +C, C, C, C, C, C, C, +C, C, C or C. + +Chars and integers (including the half type) are specified as integers, +float and double as floating point values, memory/buffer/image2d/image3d +must be an object of that type or C, and sampler and event must be +objects of that type. + +L + +=back + +=head2 THE OpenCL::Event CLASS + +This is the superclass for all event objects (including OpenCL::UserEvent +objects). + +=over 4 + +=item $ev->wait + +Waits for the event to complete. + +L + +=item $packed_value = $ev->info ($name) + +See C<< $platform->info >> for details. + +L + +=for gengetinfo begin event + +=item $queue = $event->command_queue + +Calls C with C and returns the result. + +=item $command_type = $event->command_type + +Calls C with C and returns the result. + +=item $uint = $event->reference_count + +Calls C with C and returns the result. + +=item $uint = $event->command_execution_status + +Calls C with C and returns the result. + +=item $ctx = $event->context + +Calls C with C and returns the result. + +=for gengetinfo end event + +=item $packed_value = $ev->profiling_info ($name) + +See C<< $platform->info >> for details. + +The reason this method is not called C is that there already is an +C<< ->info >> method. + +L + +=for gengetinfo begin profiling + +=item $ulong = $event->profiling_command_queued + +Calls C with C and returns the result. + +=item $ulong = $event->profiling_command_submit + +Calls C with C and returns the result. + +=item $ulong = $event->profiling_command_start + +Calls C with C and returns the result. + +=item $ulong = $event->profiling_command_end + +Calls C with C and returns the result. + +=for gengetinfo end profiling + +=back + +=head2 THE OpenCL::UserEvent CLASS + +This is a subclass of OpenCL::Event. + +=over 4 + +=item $ev->set_status ($execution_status) + +L + +=back + =cut package OpenCL; @@ -37,16 +1351,24 @@ use common::sense; BEGIN { - our $VERSION = '0.01'; + our $VERSION = '0.92'; require XSLoader; XSLoader::load (__PACKAGE__, $VERSION); + + @OpenCL::Buffer::ISA = + @OpenCL::Image::ISA = OpenCL::Memory::; + + @OpenCL::BufferObj::ISA = OpenCL::Buffer::; + + @OpenCL::Image2D::ISA = + @OpenCL::Image3D::ISA = OpenCL::Image::; + + @OpenCL::UserEvent::ISA = OpenCL::Event::; } 1; -=back - =head1 AUTHOR Marc Lehmann