Search

Despite increases in qubit count and connectivity in quantum annealers, a quantum speedup has yet to be observed for problems of practical significance. In order to further improve annealer performance, some researchers focus on tuning annealer parameters, such as the annealing schedule. In this work, we focus on pausing, an annealing schedule modification that has been shown to improve the probability of solving an optimization problem by orders of magnitude. However, a challenge associated with pausing is selecting an appropriate pause location, as pausing is only effective in problem-dependent regions and ineffective elsewhere. Moreover, there is little advice on how to determine where pausing is effective. Thus, pausing effectively is difficult and often inaccessible to the majority of users. To address these issues, we propose a data-driven method that leverages machine learning to predict optimal pause locations. First, we construct a dataset consisting of optimization problems and their corresponding optimal pause locations. The optimal pause locations are determined using spin-vector Monte Carlo, a method known to yield results similar to quantum annealing. Next, we train a convolutional neural network on this dataset, demonstrating its ability to distinguish between problem types and accurately predict the optimal pause location. Finally, we evaluate the model on multiple types of optimization problems. Our results show that the pause locations predicted by our method improve solution quality for all selected problem types. Additionally, our model can be pre-trained and easily distributed, making the power of pausing accessible to users unfamiliar with annealing schedule modifications.

Dedicated infrastructures are commonly used for urgent computations. However, using dedicated resources is not always affordable due to budget constraints. As a result, utilizing shared infrastructures becomes an alternative solution for urgent computations. Since the infrastructures are meant to serve many users, the urgent jobs may arrive when regular jobs are using the necessary resources. In such a case, it is necessary to preempt the regular jobs so that urgent jobs can be executed immediately. Most conventional methods for job scheduling have focused on reducing the response times and waiting times of all jobs. However, these methods can delay urgent jobs and hinder them from being completed within a stipulated deadline. Furthermore, in heterogeneous systems with coprocessors, preemption becomes more difficult because coprocessors rely on several system software functionalities provided by the host processor. In this paper, we propose a parallel job scheduling method to effectively use shared heterogeneous systems for urgent computations. Our method employs an in-memory process swapping mechanism to preempt jobs running on the coprocessor devices. The results of our simulations show that our method can achieve a significant reduction in the response time and slowdown of regular jobs without substantial delays of urgent jobs.

The mapping of tasks to processor cores, called task mapping, is crucial to achieving scalable performance on multicore processors. On modern NUMA (non-uniform memory access) systems, the memory congestion problem could degrade the performance more severely than the data locality problem because heavy congestion on shared caches and memory controllers could cause long latencies. Conventional work on task mapping mostly focuses on improving the locality of memory accesses. However, our previous work showed that on modern NUMA systems, maximizing the locality can degrade the performance due to memory congestion. In this work, we propose a task mapping method that addresses the locality and the memory congestion problems to improve the performance of parallel applications. In the proposed method, first, the spatial and temporal communication behaviors of the applications are analyzed from the time-series dataset of communications among the parallel tasks. Then, a data clustering technique is employed to detect groups of tasks that potentially cause the memory congestion. Finally, this information is used to compute the task mapping to improve the locality and reduce the memory congestion. We also provide a set of metrics to describe the communication behaviors and to evaluate if the target application can benefit from our method. The proposed method is evaluated with the NPB and PARSEC applications on a real NUMA system and a multicore simulator. A detailed analysis of the sources of performance gain is also provided. Experimental results show that our method can achieve up to a 61% performance improvement compared with the state-of-the-art locality-based method.