--- OpenCL/OpenCL.pm 2012/04/24 14:24:42 1.52 +++ OpenCL/OpenCL.pm 2012/04/28 13:33:04 1.62 @@ -45,19 +45,22 @@ =head2 HELPFUL RESOURCES -The OpenCL spec used to develop this module (1.2 spec was available, but -no implementation was available to me :). +The OpenCL specs used to develop this module: http://www.khronos.org/registry/cl/specs/opencl-1.1.pdf + http://www.khronos.org/registry/cl/specs/opencl-1.2.pdf + http://www.khronos.org/registry/cl/specs/opencl-1.2-extensions.pdf OpenCL manpages: http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/ + http://www.khronos.org/registry/cl/sdk/1.2/docs/man/xhtml/ If you are into UML class diagrams, the following diagram might help - if -not, it will be mildly cobfusing: +not, it will be mildly confusing (also, the class hierarchy of this module +is much more fine-grained): - http://www.khronos.org/registry/cl/sdk/1.1/docs/man/xhtml/classDiagram.html + http://www.khronos.org/registry/cl/sdk/1.2/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: @@ -140,10 +143,10 @@ my $buf = $ctx->buffer_sv (OpenCL::MEM_COPY_HOST_PTR, "helmut"); - $queue->enqueue_read_buffer ($buf, 1, 1, 3, my $data); + $queue->read_buffer ($buf, 1, 1, 3, my $data); print "$data\n"; - my $ev = $queue->enqueue_read_buffer ($buf, 0, 1, 3, my $data); + my $ev = $queue->read_buffer ($buf, 0, 1, 3, my $data); $ev->wait; print "$data\n"; # prints "elm" @@ -173,10 +176,10 @@ $kernel->set_buffer (1, $output); # execute it for all 4 numbers - $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); + $queue->nd_range_kernel ($kernel, undef, [4], undef); # enqueue a synchronous read - $queue->enqueue_read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); + $queue->read_buffer ($output, 1, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); # print the results: printf "%s\n", join ", ", unpack "f*", $data; @@ -185,13 +188,13 @@ showing off barriers. # execute it for all 4 numbers - $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); + $queue->nd_range_kernel ($kernel, undef, [4], undef); # enqueue a barrier to ensure in-order execution - $queue->enqueue_barrier; + $queue->barrier; # enqueue an async read - $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); + $queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data); # wait for all requests to finish $queue->finish; @@ -200,10 +203,10 @@ showing off event objects and wait lists. # execute it for all 4 numbers - my $ev = $queue->enqueue_nd_range_kernel ($kernel, undef, [4], undef); + my $ev = $queue->nd_range_kernel ($kernel, undef, [4], undef); # enqueue an async read - $ev = $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev); + $ev = $queue->read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data, $ev); # wait for the last event to complete $ev->wait; @@ -272,15 +275,15 @@ for (my $time; ; ++$time) { # acquire objects from opengl - $queue->enqueue_acquire_gl_objects ([$tex]); + $queue->acquire_gl_objects ([$tex]); # configure and run our kernel $kernel->set_image2d (0, $tex); $kernel->set_float (1, $time); - $queue->enqueue_nd_range_kernel ($kernel, undef, [256, 256], undef); + $queue->nd_range_kernel ($kernel, undef, [256, 256], undef); # release objects to opengl again - $queue->enqueue_release_gl_objects ([$tex]); + $queue->release_gl_objects ([$tex]); # wait $queue->finish; @@ -378,14 +381,127 @@ have been created and be made current, and C must be available and capable of finding the function via C. +=head2 EVENT SYSTEM + +OpenCL can generate a number of (potentially) asynchronous events, for +example, after compiling a program, to signal a context-related error or, +perhaps most important, to signal completion of queued jobs (by setting +callbacks on OpenCL::Event objects). + +To facilitate this, this module maintains an event queue - each +time an asynchronous event happens, it is queued, and perl will be +interrupted. This is implemented via the L module. In +addition, this module has L support, so it can seamlessly +integrate itself into many event loops. + +Since this module is a bit hard to understand, here are some case examples: + +=head3 Don't use callbacks. + +When your program never uses any callbacks, then there will never be any +notifications you need to take care of, and therefore no need to worry +about all this. + +You can achieve a great deal by explicitly waiting for events, or using +barriers and flush calls. In many programs, there is no need at all to +tinker with asynchronous events. + +=head3 Use AnyEvent + +This module automatically registers a watcher that invokes all outstanding +event callbacks when AnyEvent is initialised (and block asynchronous +interruptions). Using this mode of operations is the safest and most +recommended one. + +To use this, simply use AnyEvent and this module normally, make sure you +have an event loop running: + + use Gtk2 -init; + use AnyEvent; + + # initialise AnyEvent, by creating a watcher, or: + AnyEvent::detect; + + my $e = $queue->marker; + $e->cb (sub { + warn "opencl is finished\n"; + }) + + main Gtk2; + +Note that this module will not initialise AnyEvent for you. Before +AnyEvent is initialised, the module will asynchronously interrupt perl +instead. To avoid any surprises, it's best to explicitly initialise +AnyEvent. + +You can temporarily enable asynchronous interruptions (see next paragraph) +by calling C<$OpenCL::INTERRUPT->unblock> and disable them again by +calling C<$OpenCL::INTERRUPT->block>. + +=head3 Let yourself be interrupted at any time + +This mode is the default unless AnyEvent is loaded and initialised. In +this mode, OpenCL asynchronously interrupts a running perl program. The +emphasis is on both I and I here. + +Asynchronously means that perl might execute your callbacks at any +time. For example, in the following code (I), +the C loop following the marker call will be interrupted by the +callback: + + my $e = $queue->marker; + my $flag; + $e->cb (sub { $flag = 1 }); + 1 until $flag; + # $flag is now 1 + +The reason why you shouldn't blindly copy the above code is that +busy waiting is a really really bad thing, and really really bad for +performance. + +While at first this asynchronous business might look exciting, it can be +really hard, because you need to be prepared for the callback code to be +executed at any time, which limits the amount of things the callback code +can do safely. + +This can be mitigated somewhat by using C<< +$OpenCL::INTERRUPT->scope_block >> (see the L +documentation for details). + +The other problem is that your program must be actively I to be +interrupted. When you calculate stuff, your program is running. When you +hang in some C functions or other block execution (by calling C, +C