sdk/2.1/docs/man/out_of_order_exec_Inc.xml

    <!-- From section 5.13 -->
    <!-- This is currently only used in clCreateCommandQueueWithProperties -->

    <bridgehead>Out-of-order Execution of Kernels and Memory Object Commands</bridgehead>

    <para>
      The OpenCL functions that are submitted to a command-queue are enqueued in the order
      the calls are made but can be configured to execute in-order or out-of-order. The
      <varname>properties</varname> argument in <function>clCreateCommandQueueWithProperties</function>
      can be used to specify the execution order.
    </para>

    <para>
      If the <constant>CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE</constant>
      property of a command-queue is not set, the commands enqueued to a
      command-queue execute in order. For example, if an application calls
      <citerefentry><refentrytitle>clEnqueueNDRangeKernel</refentrytitle></citerefentry>
      to execute kernel A followed by a
      <citerefentry><refentrytitle>clEnqueueNDRangeKernel</refentrytitle></citerefentry>
      to execute kernel B, the application can assume that kernel A finishes first and then
      kernel B is executed. If the memory objects output by kernel A are inputs to kernel
      B then kernel B will see the correct data in memory objects produced by execution of
      kernel A. If the <constant>CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE</constant> property
      of a command-queue is set, then there is no guarantee that kernel A will finish before
      kernel B starts execution.
    </para>

    <para>
      Applications can configure the commands enqueued to a command-queue to execute
      out-of-order by setting the <constant>CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE</constant>
      property of the command-queue. This can be specified when the command-queue is
      created. In out-of-order execution mode there is no guarantee that the enqueued
      commands will finish execution in the order they were queued. As there is no
      guarantee that kernels will be executed in order, i.e. based on when the
      <citerefentry><refentrytitle>clEnqueueNDRangeKernel</refentrytitle></citerefentry>
      calls are made within a command-queue, it is therefore possible that an earlier
      <citerefentry><refentrytitle>clEnqueueNDRangeKernel</refentrytitle></citerefentry>
      call to execute kernel A identified by event A may execute and/or finish later than a
      <citerefentry><refentrytitle>clEnqueueNDRangeKernel</refentrytitle></citerefentry>
      call to execute kernel B which was called by the application at a later
      point in time. To guarantee a specific order of execution of kernels, a
      wait on a particular event (in this case event A) can be used. The wait for
      event A can be specified in the <varname>event_wait_list</varname> argument to
      <citerefentry><refentrytitle>clEnqueueNDRangeKernel</refentrytitle></citerefentry>
      for kernel B.
    </para>

    <para>
      In addition, a wait for events
      (<citerefentry><refentrytitle>clEnqueueMarkerWithWaitList</refentrytitle></citerefentry>)
      or a barrier
      (<citerefentry><refentrytitle>clEnqueueBarrierWithWaitList</refentrytitle></citerefentry>)
      command can be enqueued to the command-queue. The wait for events command ensures
      that previously enqueued commands identified by the list of events to wait for have
      finished before the next batch of commands is executed. The barrier command ensures
      that all previously enqueued commands in a command-queue have finished execution
      before the next batch of commands is executed.
    </para>

    <para>
      Similarly, commands to read, write, copy or map memory objects that are enqueued after
      <citerefentry><refentrytitle>clEnqueueNDRangeKernel</refentrytitle></citerefentry> or
      <citerefentry><refentrytitle>clEnqueueNativeKernel</refentrytitle></citerefentry>
      commands are not guaranteed to wait for kernels scheduled for execution to have
      completed (if the <constant>CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE</constant>
      property is set). To ensure correct ordering of commands, the event object returned by
      <citerefentry><refentrytitle>clEnqueueNDRangeKernel</refentrytitle></citerefentry> or
      <citerefentry><refentrytitle>clEnqueueNativeKernel</refentrytitle></citerefentry>
      can be used to enqueue a wait for event or a barrier command can be enqueued that
      must complete before reads or writes to the memory object(s) occur.
    </para>

<!-- 25-Dec-2013, rev. 19 -->