Task graphs are used for scheduling tasks on shared memory parallel processors when the tasks have dependencies. If the program's task graph is known ahead of time, then the tasks can be statically and optimally allocated to the processors. If the tasks and task dependencies are not known ahead of time (the case in some sparse matrix algorithms), then task scheduling must be performed dynamically. We present a simple algorithm for a concurrent dynamic-task graph. A processor that needs to execute a new task can query the task graph for a new task, and new tasks can be added to the task graph dynamically.
