The purpose of resource scheduling is to deal with all kinds of unexpected events that may occur in life, such as fire, traffic jam, earthquake and other emergencies, and the scheduling algorithm is one of the key factors affecting the intelligent scheduling system. In the traditional resource scheduling system, because of the slow decision-making, it is difficult to meet the needs of the actual situation, especially in the face of emergencies, the traditional resource scheduling methods have great disadvantages. In order to solve the above problems, this paper takes emergency resource scheduling, a prominent scheduling problem, as an example. Based on Vague set theory and adaptive grid particle swarm optimization algorithm, a multi-objective emergency resource scheduling model is constructed under different conditions. This model can not only integrate the advantages of Vague set theory in dealing with uncertain problems, but also retain the advantages of adaptive grid particle swarm optimization that can solve multi-objective optimization problems and can quickly converge. The research results show that compared with the traditional resource scheduling optimization algorithm, the emergency resource scheduling model has higher resolution accuracy, more reasonable resource allocation, higher efficiency and faster speed in dealing with emergency events than the traditional resource scheduling model. Compared with the conventional fuzzy theory emergency resource scheduling model, its handling speed has increased by more than 3.82 times.

This paper proposes a novel intelligent framework for oversubscription management in CPU-GPU UVM. We analyze the current rule-based methods of GPU memory oversubscription with unified memory, and the current learning-based methods for other computer architectural components. We then identify the performance gap between the existing rule-based methods and the theoretical upper bound. We also identify the advantages of applying machine intelligence and the limitations of the existing learning-based methods. This paper proposes a novel intelligent framework for oversubscription management in CPU-GPU UVM. It consists of an access pattern classifier followed by a pattern-specific Transformer-based model using a novel loss function aiming for reducing page thrashing. A policy engine is designed to leverage the model's result to perform accurate page prefetching and pre-eviction. We evaluate our intelligent framework on a set of 11 memory-intensive benchmarks from popular benchmark suites. Our solution outperforms the state-of-the-art (SOTA) methods for oversubscription management, reducing the number of pages thrashed by 64.4\% under 125\% memory oversubscription compared to the baseline, while the SOTA method reduces the number of pages thrashed by 17.3\%. Our solution achieves an average IPC improvement of 1.52X under 125\% memory oversubscription, and our solution achieves an average IPC improvement of 3.66X under 150\% memory oversubscription. Our solution outperforms the existing learning-based methods for page address prediction, improving top-1 accuracy by 6.45\% (up to 41.2\%) on average for a single GPGPU workload, improving top-1 accuracy by 10.2\% (up to 30.2\%) on average for multiple concurrent GPGPU workloads.