Taming Algorithmic Priority Inversion in Mission-Critical Perception Pipelines

With online task arrivals, the objective of the BASIC problem is to derive a schedule x to maximize the aggregate system utility. The schedule decides three outputs: task stage execution order on the GPU, number of stages to execute for each task, and task batching decisions. For each scheduling period t, we use xt(i, j) {0, 1} to denote whether the j-th stage of task Ti is executed. Besides, we use P to denote a batch of tasks, where ‖P‖ denotes the number of tasks being batched.