--- OpenCL/OpenCL.pm	2011/11/15 20:38:07	1.3
+++ OpenCL/OpenCL.pm	2011/11/15 21:16:19	1.4
@@ -82,6 +82,28 @@
 
    my $kernel = $prog->kernel ("squareit");
 
+Create some input and output float buffers, then call squareit 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 barrier ot ensure in-order execution (not really needed in this case)
+   $queue->enqueue_barrier;
+
+   # enqueue an async read (could easily be blocking here though), then wait for it:
+   my $ev = $queue->enqueue_read_buffer ($output, 0, 0, OpenCL::SIZEOF_FLOAT * 4, my $data);
+   $ev->wait;
+
+   # print the results:
+   say join ", ", unpack "f*", $data;
+
 =over 4
 
 =cut
@@ -91,7 +113,7 @@
 use common::sense;
 
 BEGIN {
-   our $VERSION = '0.01';
+   our $VERSION = '0.02';
 
    require XSLoader;
    XSLoader::load (__PACKAGE__, $VERSION);