--- OpenCL/OpenCL.pm 2011/11/16 06:22:20 1.8 +++ OpenCL/OpenCL.pm 2011/11/17 03:56:07 1.17 @@ -10,7 +10,40 @@ This is an early release which might be useful, but hasn't seen much testing. -=head1 HELPFUL RESOURCES +=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::Buffers 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 :). @@ -21,30 +54,77 @@ http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/ +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 + +If you are into UML class diagrams, the following diagram might help - if +not, it will be mildly cofusing: + + http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/classDiagram.html + +=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->info (OpenCL::PLATFORM_NAME); + printf "extensions: %s\n", $platform->info (OpenCL::PLATFORM_EXTENSIONS); for my $device ($platform->devices) { - warn $device->info (OpenCL::DEVICE_NAME); - my $ctx = $device->context_simple; + printf "+ device: %s\n", $device->info (OpenCL::DEVICE_NAME); + my $ctx = $device->context; # do stuff } } =head2 Get a useful context and a command queue. - my $dev = ((OpenCL::platforms)[0]->devices)[0]; - my $ctx = $dev->context_simple; - my $queue = $ctx->command_queue_simple ($dev); +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) { - say "supported image formats for ", OpenCL::enum2str $type; + 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]; @@ -57,11 +137,11 @@ my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); $queue->enqueue_read_buffer ($buf, 1, 1, 3, my $data); - warn $data; + print "$data\n"; my $ev = $queue->enqueue_read_buffer ($buf, 0, 1, 3, my $data); $ev->wait; - warn $data; + print "$data\n"; # prints "elm" =head2 Create and build a program, then create a kernel out of one of its functions. @@ -70,19 +150,21 @@ __kernel void squareit (__global float *input, __global float *output) { - size_t id = get_global_id (0); + $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 $prog->build_info ($dev, OpenCL::PROGRAM_BUILD_LOG); my $kernel = $prog->kernel ("squareit"); -=head2 Create some input and output float buffers, then call squareit on them. +=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); @@ -98,7 +180,7 @@ $queue->enqueue_read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); # print the results: - say join ", ", unpack "f*", $data; + printf "%s\n", join ", ", unpack "f*", $data; =head2 The same enqueue operations as before, but assuming an out-of-order queue, showing off barriers. @@ -131,8 +213,8 @@ =head2 BASIC CONVENTIONS -This is not a 1:1 C-style translation of OpenCL to Perl - instead I -attempted to make the interface as type-safe as possible and introducing +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: @@ -147,14 +229,17 @@ prefixes (C<< $platform->info >>). =item * OpenCL often specifies fixed vector function arguments as short -arrays (C), while this module explicitly expects the +arrays (C<$origin[3]>), while this module explicitly expects the components as separate arguments- -=item * Where possible, the row_pitch value is calculated from the perl -scalar length and need not be specified. +=item * Structures are often specified with their components, and returned +as arrayrefs. + +=item * Where possible, one of the pitch values is calculated from the +perl scalar length and need not be specified. =item * When enqueuing commands, the wait list is specified by adding -extra arguments to the function - everywhere a C<$wait_events...> argument +extra arguments to the function - anywhere a C<$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 @@ -191,13 +276,14 @@ =item $int = OpenCL::errno -The last error returned by a function - it's only changed on errors. +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::err2str $enum +=item $str = OpenCL::enum2str $enum Converts most enum values (inof parameter names, image format constants, object types, addressing and filter modes, command types etc.) into a @@ -211,7 +297,7 @@ L -=item $ctx = OpenCL::context_from_type_simple $type = OpenCL::DEVICE_TYPE_DEFAULT +=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. @@ -241,12 +327,19 @@ Returns a list of matching OpenCL::Device objects. -=item $ctx = $platform->context_from_type_simple ($type = OpenCL::DEVICE_TYPE_DEFAULT) +=item $ctx = $platform->context_from_type ($properties, $type = OpenCL::DEVICE_TYPE_DEFAULT, $notify = undef) -Tries to create a context. Never worked for me. +Tries to create a context. Never worked for me, and you need devices explitly anyway. L +=item $ctx = $device->context ($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 + =back =head2 THE OpenCL::Device CLASS @@ -259,12 +352,6 @@ L -=item $ctx = $device->context_simple - -Convenience function to create a new OpenCL::Context object. - -L - =back =head2 THE OpenCL::Context CLASS @@ -277,9 +364,9 @@ L -=item $queue = $ctx->command_queue_simple ($device) +=item $queue = $ctx->queue ($device, $properties) -Convenience function to create a new OpenCL::Queue object from the context and the given device. +Create a new OpenCL::Queue object from the context and the given device. L @@ -378,25 +465,25 @@ L -=item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $data, $wait_events...) +=item $ev = $queue->enqueue_write_image ($src, $blocking, $x, $y, $z, $width, $height, $depth, $row_pitch, $slice_pitch, $data, $wait_events...) L -=item $ev = $queue->enqueue_copy_buffer_rect ($src, $dst, $src_x, $src_y, $src_z, $dst_x, $dst_y, $dst_z, $width, $height, $depth, $src_row_pitch, $src_slice_pitch, 4dst_row_pitch, $dst_slice_pitch, $ait_event...) +=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_copy_buffer_to_image (OpenCL::Buffer src, OpenCL::Image dst, size_t src_offset, size_t dst_x, size_t dst_y, size_t dst_z, size_t width, size_t height, size_t depth, ...) +=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_copy_image (OpenCL::Image src, OpenCL::Buffer dst, size_t src_x, size_t src_y, size_t src_z, size_t dst_x, size_t dst_y, size_t dst_z, size_t width, size_t height, size_t depth, ...) +=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 (OpenCL::Image src, OpenCL::Buffer dst, size_t src_x, size_t src_y, size_t src_z, size_t width, size_t height, size_t depth, size_t dst_offset, ...) +=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 @@ -571,7 +658,7 @@ use common::sense; BEGIN { - our $VERSION = '0.03'; + our $VERSION = '0.14'; require XSLoader; XSLoader::load (__PACKAGE__, $VERSION);