Many scientific and numeric computations rely on matrix-matrix multiplication as a fundamental component of their algorithms. It constitutes the building block in many matrix operations used in numeric solvers and gra...
详细信息
ISBN:
(纸本)9783031648809;9783031648816
Many scientific and numeric computations rely on matrix-matrix multiplication as a fundamental component of their algorithms. It constitutes the building block in many matrix operations used in numeric solvers and graph theory problems. Several algorithms have been proposed and implemented for matrix-matrix multiplication, especially, for distributed-memory systems, and these have been greatly studied. In particular, the Cannon's algorithm has been implemented for distributed-memory systems, mostly since the memory needs remain constant and are not influenced by the number of processors employed. The algorithm, however, involves block shifting of both matrices being multiplied. This paper presents a similar block-oriented parallel algorithm for matrix-matrix multiplication on a 2-dimensional processor grid, but with block shifting restricted to only one of the matrices. We refer to this as the Single Matrix Block Shift (SMBS) algorithm. The algorithm, we propose, is a variant of the Cannon's algorithm on distributed architectures and improves upon the performance complexity of the Cannon and SRUMMA algorithms. We present analytic as well as experimental comparative results of our algorithm with the standard Cannon's algorithm on 2-dimensional processor grids, showing over 4X performance improvement.
Accurately accounting for carbon emissions is a fundamental requirement for understanding the trends in carbon emissions in the power system, effectively implementing carbon reduction measures, and promoting the green...
详细信息
In order to effectively improve the consumption level of distributed energy and promote the healthy development of the electricity market, an efficient and reliable energy trading mechanism needs to be proposed urgent...
详细信息
ISBN:
(纸本)9781510655201;9781510655195
In order to effectively improve the consumption level of distributed energy and promote the healthy development of the electricity market, an efficient and reliable energy trading mechanism needs to be proposed urgently. This paper takes the micro-energy grid system as the research object, and comprehensively considers the user's energy demand changes, market energy management, and transaction mechanisms, combined with Electricity spot market, and designs a distributed energy trading model oriented to the spot market. Optimal output, to solve the economic benefits of the unit and the economic benefits of the region. The study of distributed energy trading mechanisms in this article provides a reference for future electricity market transactions in micro-grids and also provides an important basis for the promotion of green certificate transactions.
With the development of the scale of the power system and the maturity of robotics, the use of inspection robots instead of manual inspection can effectively improve the efficiency of inspection and realize the intell...
详细信息
In parallel and distributed communication networks, task scheduling is essential for attaining the best system performance. Innovative ways that may intelligently distribute computing resources while minimizing energy...
详细信息
Renewable energy is the main energy in China. It has great development potential, but it also brings severe challenges to the operation and management of power system. Firstly, this paper combs the distributed robust ...
详细信息
Blockchain is a closed island in the traditional power transaction platform and cannot freely trade with others, which limits the flexibility and autonomy of the distributed power trading market. Aiming at the problem...
详细信息
In order to seize more users and market share, network operators and service providers must continuously improve their service level and quality to meet the increasing demands of customers. Therefore, the quality of u...
详细信息
Multi-parallelgrid-connected inverter system is increasingly applied in distributed power generation systems. Due to the existence of grid impedance, the output current of the grid-connected inverter cannot be fed to...
详细信息
We witnessed great advancement in Artificial Intelligence (AI) powered technologies in recent years, and yet, when applied to certain high-stake contexts, such as medical diagnosis, automatic driving and criminal just...
详细信息
ISBN:
(纸本)9781665473156
We witnessed great advancement in Artificial Intelligence (AI) powered technologies in recent years, and yet, when applied to certain high-stake contexts, such as medical diagnosis, automatic driving and criminal justice, they are not qualified. This matter can be greatly settled by Human-Machine computing (HMC), which is an effective computing paradigm that couples the expertise and demonstration abilities of humans with the high-performance computing power of machines. This work studies an optimal task scheduling problem for HMC systems, where various tasks are decomposed and dispatched to humans and AI-enabled machines to provide significantly better benefits compared to either type of computing resources in isolation. However, designing such optimal task scheduling is challenging because of the stochastic hybrid features of machines, as well as various human professional abilities. Considering the Quality of Service (QoS) and the heterogeneity of human-machine computing resources, we propose CoupHM, a feasible task scheduler using gradient based optimization for HMC systems. In particular, we firstly present the underlying architecture of HMC system and details of the task-driven workload model. On that basis, we then formulate the objective optimization problem to be solved and describe the composition of the CoupHM scheduler. Finally, the performance of our solution is evaluated by the simulation experiments, and the results indicate that the proposed scheduler has preferable performance both in balancing resources and guaranteeing QoS, which can serve as guidelines for future research on HMC systems.
暂无评论