Multiple In-Order Command Queues

The following figure shows an example with two in-order command queues, CQ0 and CQ1. The scheduler dispatches commands from each queue in order, but commands from CQ0 and CQ1 can be pulled out by the scheduler in any order. You must manage synchronization between CQ0 and CQ1 if required.

Figure: Example with Two In-Order Command Queues

Below is the code snippet from the Concurrent Kernel Execution Example in host category from Xilinx On-boarding Example GitHub that sets up multiple in-order command queues and enqueues commands into each queue:

cl_command_queue ordered_queue1 = clCreateCommandQueue(
      world.context, world.device_id, CL_QUEUE_PROFILING_ENABLE, &err)

cl_command_queue ordered_queue2 = clCreateCommandQueue(
world.context, world.device_id, CL_QUEUE_PROFILING_ENABLE, &err);

clEnqueueNDRangeKernel(ordered_queue1, kernel_mscale, 1, offset,
                       global, local, 0, nullptr,
                       &kernel_events[0]));

clEnqueueNDRangeKernel(ordered_queue1, kernel_madd, 1, offset,
                       global, local, 0, nullptr,
                       &kernel_events[1]);

clEnqueueNDRangeKernel(ordered_queue2, kernel_mmult, 1, offset,
                       global, local, 0, nullptr,
                       &kernel_events[2]);