Filters








54,295 Hits in 4.1 sec

Relation-oriented resource allocation for multi-accelerator systems

Teng Yu, Bo Feng, Mark Stillwell, Jose Gabriel F Coutinho, Wenlai Zhao, Shuang Liang, Wayne Luk, Alexander L. Wolf, Yuchun Ma
2016 2016 IEEE 27th International Conference on Application-specific Systems, Architectures and Processors (ASAP)  
Second, an effective technique for resource allocation based on this model, targeting systems with multiple accelerators.  ...  This paper presents a novel approach for allocating resources in systems with multiple accelerators. It has three main contributions.  ...  As shown here, customised resource allocators for specified multi-accelerator systems and certain types of resources have been developed in the literature.  ... 
doi:10.1109/asap.2016.7760809 dblp:conf/asap/YuFSCZLLWM16 fatcat:qlgveuhpq5ektf3lpowq6h2mzu

The Impact of the Reform of Factor Market-oriented Allocation on Grid Companies and Related Suggestions

Zhu Wei, Wang Xinling, Li Haolan, L. Duan, A.Z. Abdullah
2021 E3S Web of Conferences  
On April 9, 2020, the CPC Central Committee and the State Council issued "Opinions on Building a More Complete System and Mechanism for Market-oriented Allocation of Factors" (hereinafter referred to as  ...  As the key link of power allocation, Grid Companies are directly related to the economic and social development of the whole country.  ...  The "Opinions on Building a More Complete System and Mechanism for Market-oriented Allocation of Factors" (hereinafter referred to as the Opinions) has carried out a top-level design of the market-oriented  ... 
doi:10.1051/e3sconf/202124501013 fatcat:krlxxcaphrdjjbdxcicrmioyoq

MultiAmdahl: Optimal Resource Allocation in Heterogeneous Architectures [article]

Leonid Yavits, Amir Morad, Uri Weiser, Ran Ginosar
2017 arXiv   pre-print
We extend MultiAmdahl, an analytical optimization technique for resource allocation in heterogeneous architectures, for energy optimality under a variety of constant system power scenarios.  ...  We conclude that reduction in constant system power should be met by reallocating resources from general-purpose computing to heterogeneous accelerator-dominated computing, to keep the overall energy consumption  ...  ACKNOWLEDGMENT We thank Ronny Ronen for his valuable input.  ... 
arXiv:1705.06923v1 fatcat:kiu5tg5grrahzhdbuetpgh6vka

Research on the Marketization of Urban and Rural Factors and the Coordinated Development of Urban and Rural Industries and Regions

Bin Huang, Xiaoxi Liao
2021 Converter  
and core issue of new urbanization; the market plays a decisive role in the allocation of factor resources.  ...  The development of new urbanization and urban and rural industries depends on the independent flow, efficient and fair allocation of factor markets; market-oriented allocation of factors is the development  ...  Conclusion A sound market system is the prerequisite for a better market-oriented allocation.  ... 
doi:10.17762/converter.201 fatcat:pt56dz45uzezzp7ir5px6jnlky

Profit-Aware Distributed Online Scheduling for Data-Oriented Tasks in Cloud Datacenters

Wei Lu, Ping Lu, Quanying Sun, Shui Yu, Zuqing Zhu
2018 IEEE Access  
As there is an increasing trend to deploy geographically distributed (geo-distributed) cloud datacenters (DCs), the scheduling of data-oriented tasks in such cloud DC systems becomes an appealing research  ...  In this paper, by considering the store-and-forward and anycast schemes, we formulate an optimization problem to maximize the timeaverage profit from serving data-oriented tasks in a cloud DC system and  ...  , while c k i (t) is the allocated IT resources for task processing.  ... 
doi:10.1109/access.2018.2808481 fatcat:p4hkpxc4pnefpb2h24cofvplk4

An open baseband processing architecture for future mobile terminal design

W.W. Lu
2008 IEEE wireless communications  
The paper describes multi-layer open system architecture to maximize the system flexibility and minimize the terminal power consumption, so as to provide an integrated and converged next generation wireless  ...  and mobile communication terminal system.  ...  and dynamic channels allocation The PHY/MAC control module works with the SIMD cores and accelerators through the multi-layer system bus.  ... 
doi:10.1109/mwc.2008.4492984 fatcat:twf33bj73jgvdh62k2l7y4c7mi

A lightweight execution framework for massive independent tasks

Li Hui, Huashan Yu, Li Xiaoming
2008 2008 Workshop on Many-Task Computing on Grids and Supercomputers  
The overhead for extra operations like resource allocating and accessing is significant for MTC, and may counteract the effect of parallel computing in some cases.  ...  Another is to share the effort in resource discovery and allocation among requests by separating resource allocations from request submissions.  ...  This experiment was to make a comparison between the request-oriented resource allocating strategy and our user-oriented resource allocating strategy. 10 tasks were executed on one SMP, and the task grouping  ... 
doi:10.1109/mtags.2008.4777911 dblp:conf/sc/LiYL08 fatcat:hahth43w7ng63anetz74rbnrx4

LiveCloud: A lucid orchestrator for cloud datacenters

Xiang Wang, Zhi Liu, Yaxuan Qi, Jun Li
2012 4th IEEE International Conference on Cloud Computing Technology and Science Proceedings  
LiveCloud is architected as a data-centric and event-driven system with open management interfaces and service-oriented APIs to simplify system integration and service provision.  ...  This paper presents LiveCloud, a management framework for resources in cloud datacenters.  ...  Tenant view For elastic provision and self-service arrangement, management system in multi-tenancy cloud datacenter should support on-demand resource allocation and isolate allocated resources among different  ... 
doi:10.1109/cloudcom.2012.6427544 dblp:conf/cloudcom/WangLQL12 fatcat:p7muz2rflvcvlbndzsktt3wew4

RC3E: Provision and Management of Reconfigurable Hardware Accelerators in a Cloud Environment [article]

Oliver Knodel, Rainer G. Spallek
2015 arXiv   pre-print
Heterogeneous systems consisting of general-purpose processors and different types of hardware accelerators are becoming more and more common in HPC systems.  ...  Adding FPGAs to clouds or data centers allows easy access to such reconfigurable resources.  ...  INTRODUCTION Multi-core and multi-threaded processors were in recent years combined with special dedicated hardware accelerators to improve the performance of applications.  ... 
arXiv:1508.06843v1 fatcat:fzo3f7e3fbbv7dbhewyrnnvdza

Quality of Service Driven Runtime Resource Allocation in Reconfigurable HPC Architectures

Marcello Pogliani, Gianluca C. Durelli, Antonio Miele, Tobias Becker
2016 2016 IEEE Intl Conference on Computational Science and Engineering (CSE) and IEEE Intl Conference on Embedded and Ubiquitous Computing (EUC) and 15th Intl Symposium on Distributed Computing and Applications for Business Engineering (DCABES)  
We propose a novel resource manager able to dynamically vary the number of FPGAs allocated to each of the jobs running in a multi-accelerator system, with the goal of meeting a given Quality of Service  ...  This work tackles the problem of runtime resource management of a system using FPGA-based co-processors to accelerate multiprogrammed HPC workloads.  ...  Given a set of jobs J and a number N of resources, a well-formed allocation θ is a function θ : We allocate resources to meet explicit goals, following a goal-oriented approach.  ... 
doi:10.1109/cse-euc-dcabes.2016.156 dblp:conf/cse/PoglianiDMB16 fatcat:zox4kxyxhfa5dlaizatez3lzhq

System-On-Chip for Biologically Inspired Vision Applications

Sungho Park, Ahmed Al Maashri, Kevin M. Irick, Aarti Chandrashekhar, Matthew Cotter, Nandhini Chandramoorthy, Michael Debole, Vijaykrishnan Narayanan
2012 IPSJ Transactions on System LSI Design Methodology  
This paper discusses these requirements and proposes a framework for mapping neuromorphic vision applications on a System-on-Chip, SoC.  ...  In essence, acceleration of neuromorphic algorithms requires adherence to specific computational and communicational requirements.  ...  Cerebrum includes an IPbased, multi-FPGA mapping algorithm designed to optimally allocate IP components according to resource use, connectivity, and I/O requirements.  ... 
doi:10.2197/ipsjtsldm.5.71 fatcat:j4v6t5cd2rfhnlbqlffnrq65hy

Shared memory heterogeneous computation on PCIe-supported platforms

Sambit K. Shukla, Yang Yang, Laxmi N. Bhuyan, Philip Brisk
2013 2013 23rd International Conference on Field programmable Logic and Applications  
In this paper, we present a shared virtual memory real system design for PCIe-based HAs to enable parallel heterogeneous execution in CPU and HAs without driver overheads.  ...  Domain-disparity between CPU and Hardware Accelerators(HA) leads to CPU under-utilization and inter-domain data copy overheads.  ...  First applications allocate heterogeneous data arrays using our custom acc malloc system call. This allocates the virtual address space for the data by invoking LMM and AMM.  ... 
doi:10.1109/fpl.2013.6645580 dblp:conf/fpl/ShuklaYBB13 fatcat:ypfkiuxaavcnvlsgehaoqh3cdm

Series Editorial: Inauguration Issue of the Series on Machine Learning in Communications and Networks

Geoffrey Y. Li, Walid Saad, Ayfer Ozgur, Peter Kairouz, Zhijin Qin, Jakob Hoydis, Zhu Han, Deniz Gunduz, Jaafar Elmirghani
2021 IEEE Journal on Selected Areas in Communications  
for their support and  ...  ACKNOWLEDGMENT We would like to express our great gratitude to all authors for their submissions and over 400 anonymous reviewers for their insightful reviews and suggestions that have helped maintain  ...  Then, for both the CPU and GPU scenarios, the authors formulate a training acceleration optimization problem to solve for the optimal joint batch size selection and communication resource allocation.  ... 
doi:10.1109/jsac.2020.3036785 fatcat:pdmsdg6zrreqzgqye3qrj5f3na

High-Level Synthesis for Embedded Systems [chapter]

Michael Dossis
2012 Embedded Systems - Theory and Design Methodology  
multi-process designed system performance.  ...  This method is suitable for dataflow-oriented designs with linear control.  ...  High-Level Synthesis for Embedded Systems, Embedded Systems -Theory and Design Methodology, Dr.  ... 
doi:10.5772/38370 fatcat:olgvo4yrcfa4ti37aqefduubfi

HALO 1.0: A Hardware-agnostic Accelerator Orchestration Framework for Enabling Hardware-agnostic Programming with True Performance Portability for Heterogeneous HPC [article]

Michael Riera, Erfan Bank Tavakoli, Masudul Hassan Quraishi, Fengbo Ren
2021 arXiv   pre-print
This paper presents HALO 1.0, an open-ended extensible multi-agent software framework that implements a set of proposed hardware-agnostic accelerator orchestration (HALO) principles.  ...  HALO implements a novel compute-centric message passing interface (C^2MPI) specification for enabling the performance-portable execution of a hardware-agnostic host application across heterogeneous accelerators  ...  Multi-Agent System. HALO 1.0 is a multi-agent system.  ... 
arXiv:2011.10896v4 fatcat:3z3g4gbhozhh5jpaaqgjmg6k44
« Previous Showing results 1 — 15 out of 54,295 results