Filters








1,926 Hits in 3.7 sec

An overview on MEMS-based storage, its research issues and open problems

Yifeng Zhu
2004 Proceedings of the international workshop on Storage network architecture and parallel I/Os - SNAPI '04  
A disruptive new storage technology based on Microelectromechanical Systems (MEMS) is emerging as an exciting complement to the memory hierarchy.  ...  design inside storage devices, (4) power consumption modeling, (5) reevaluation of existing disk-type I/O optimization algorithms.  ...  Acknowledgement This project was partially supported by a National Science Foundation grant (EPS-0091900), a Nebraska University Foundation grant, and a UNL Academic Priority Grant, for which we are grateful  ... 
doi:10.1145/1162628.1162635 fatcat:33mxh5yrxbebbmkxos22fkhujq

An autonomic resource provisioning framework for mobile computing grids

Hariharasudhan Viswanathan, Eun Kyung Lee, Ivan Rodero, Dario Pompili
2012 Proceedings of the 9th international conference on Autonomic computing - ICAC '12  
A novel resource provisioning framework is proposed for organizing the heterogeneous sensing, computing, and communication capabilities of static and mobile devices in the vicinity in order to form an  ...  elastic resource pool (a heterogeneous mobile computing grid) that can be harnessed to collectively process massive amounts of locally generated data in parallel.  ...  The arbitrator extracts the following information based on the service advertisements: the devices' (service providers') capability, Γ x = {γ x n }1×N , where x = cpu, mem, net; the associated costs, C  ... 
doi:10.1145/2371536.2371550 dblp:conf/icac/ViswanathanLRP12 fatcat:aqmoyokzffesxohgmg2hx3sk5a

CrossFS: A Cross-layered Direct-Access File System

Yujie Ren, Changwoo Min, Sudarsun Kannan
2020 USENIX Symposium on Operating Systems Design and Implementation  
Finally, CrossFS designs a firmware-level I/O scheduler for efficient dispatch of file descriptor requests.  ...  Evaluation of emulated CrossFS on storage-class memory shows up to 4.87X concurrent access gains for benchmarks and 2.32X gains for real-world applications over the state-of-the-art kernel, userlevel,  ...  Acknowledgements We thank the anonymous reviewers and Emmett Witchel (our shepherd) for their insightful comments and feedback.  ... 
dblp:conf/osdi/RenMK20 fatcat:7tz6cv45wjhk3g5re2kzy42n4a

Matching Database Access Patterns to Storage Characteristics

Jiri Schindler
2003 Very Large Data Bases Conference  
As another example, accesses to relational tables can take advantage of MEMS-based storage parallelism to achieve order of magnitude improvements in selective scans.  ...  By automatically matching access patterns to device strengths, a database storage manager can achieve robust performance even with workloads competing for the same storage resource.  ...  Another example is a MEMS-based storage device (under development at IBM, HP, and Carnegie Mellon University), called MEMStore, which can access data in parallel by a subset of the thousands of available  ... 
dblp:conf/vldb/Schindler03 fatcat:jpff5i4rpbdupmv5gel4bicray

BIBIM: A Prototype Multi-Partition Aware Heterogeneous New Memory

Gyuyoung Park, Miryeong Kwon, Pratyush Mahapatra, Michael M. Swift, Myoungsoo Jung
2018 USENIX Workshop on Hot Topics in Storage and File Systems  
We describe a prototype multi-partition aware new memory controller and subsystem, BIBIM, which precisely integrates DRAM with 3x nm phase change RAM (PRAM) modules.  ...  BIBIM implements hybrid cache logic into a 2x nm FPGA device, which can hide the long latency imposed by the underlying PRAM modules as well as can support persistent operations.  ...  For a better communication between cache ctrl and mem ctrl, mem ctrl exposes a switch register that indicates which memory module will be used and a set of registers that contains the request information  ... 
dblp:conf/hotstorage/ParkKMSJ18 fatcat:vzo5vziygrbqzlzzb5wppcgg7a

Preserving Row Buffer Locality for PCM Wear-Leveling under Massive Parallelism

Xinning Wang, Bin Wang, Zhuo Liu, Weikuan Yu
2015 2015 IEEE 23rd International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems  
In this paper, we introduce a combination of two techniques, matrix-based partial randomization and rowbuffer locality-aware rotation, to alleviate the locality disruption of address transformation and  ...  preserve the row buffer locality of PCM-based global memory in GPU.  ...  Meanwhile, RBL-aware address mapping also saves 1500 cycles for the memory sub-system to service the six requests.  ... 
doi:10.1109/mascots.2015.39 dblp:conf/mascots/WangWLY15 fatcat:soqwokfeovhodeqqxqbsz4scfu

Uncertainty-Aware Autonomic Resource Provisioning for Mobile Cloud Computing

Hariharasudhan Viswanathan, Eun Kyung Lee, Ivan Rodero, Dario Pompili
2015 IEEE Transactions on Parallel and Distributed Systems  
A novel resource provisioning framework for organizing the heterogeneous sensing, computing, and communication capabilities of static and mobile devices in the vicinity in order to form an elastic resource  ...  In order to address challenges such as the inherent uncertainty in the hybrid grid (in terms of network connectivity and device availability), the proposed role-based resource provisioning framework is  ...  Our major contributions include: A role-based and uncertainty-aware architectural framework for imparting the self-organization capability, i.e., for handling service discovery and service request arrivals  ... 
doi:10.1109/tpds.2014.2345057 fatcat:s7xdof2tgvehhmgzkmigi3h6vy

QoS-Based Service-Time Scheduling in the IoT-Edge Cloud

Briytone Mutichiro, Minh-Ngoc Tran, Young-Han Kim
2021 Sensors  
In this paper, we propose STaSA, a service time aware scheduler for the edge environment.  ...  The effectiveness of our scheduling model is demonstrated through implementation on KubeEdge, a container orchestration platform based on Kubernetes.  ...  We introduce Algorithm 1, a heuristic algorithm called STaSA (Service-Time-Aware Scheduling Algorithm for multi-node KubeEdge cluster) based on an enhanced version of the ACO.  ... 
doi:10.3390/s21175797 pmid:34502688 pmcid:PMC8434349 fatcat:hsbz5kcgsjcbfitxmwmrz3jzwe

Dynamic load balancing for I/O-intensive applications on clusters

Xiao Qin, Hong Jiang, Adam Manzanares, Xiaojun Ruan, Shu Yin
2009 ACM Transactions on Storage  
non-I/O-aware load-balancing schemes, including CPU-and Memory-aware schemes and a PBS-like batch scheduler for parallel and sequential jobs, for a diverse set of workload conditions.  ...  For example, the proposed approaches deliver 23.6-88.0 % performance improvements for I/Ointensive applications such as LU decomposition, Sparse Cholesky, Titan, Parallel text searching, and Data Mining  ...  ., device rotation, arm positioning, and data transfer). Our model is also valid for clusters equipped with networked storage systems. The reason is twofold.  ... 
doi:10.1145/1629075.1629078 fatcat:jlj5fqkof5elldzaqg5nkau7ii

Mobility-Aware IoT Applications Placement in the Cloud Edge Continuum

Dragi Kimovski, Narges Mehran, Christopher Emanuel Kerth, Radu Prodan
2021 IEEE Transactions on Services Computing  
cost as conflicting objectives. mMAPO utilizes a Markov model for predictive analysis of the Edge device mobility and constrains the optimization to devices that do not frequently move through the network  ...  To address this gap, we propose a novel mobility-aware multi-objective IoT application placement (mMAPO) method in the Cloud -Edge Continuum that optimizes completion time, energy consumption, and economic  ...  Every resource is a triple r j = (CPU j , MEM j , STOR j ) that describes its number of instructions per second CPU j , memory size MEM j , and permanent storage size STOR j [28] .  ... 
doi:10.1109/tsc.2021.3094322 fatcat:elrfeep6ovfivbau7vuyemltzy

On the effects of allocation strategies for exascale computing systems with distributed storage and unified interconnects

Jose A. Pascual, Joshua Lant, Caroline Concatto, Andrew Attwood, Javier Navaridas, Mikel Luján, John Goodacre
2018 Concurrency and Computation  
We consider several aspects of data-aware allocation such as the effect of spatial and temporal locality, the affinity of data to storage sources and network-level traffic prioritization for different  ...  These results suggest that scheduling policies exposing data-locality information can be essential for the appropriate utilization of future large-scale systems.  ...  data-aware allocation policies for scheduling in a fully distributed storage architecture such as ours.  ... 
doi:10.1002/cpe.4784 fatcat:tl43kiqe4bhszh6v2qtcih3qcq

Characterizing and optimizing TPC-C workloads on large-scale systems using SSD arrays

Jidong Zhai, Feng Zhang, Qingwen Li, Wenguang Chen, Weimin Zheng
2016 Science China Information Sciences  
In this paper, we designed and implemented a large-scale TPC-C evaluation system based on the latest TPC-C specification using solid-state drive (SSD) storage devices.  ...  Second, we propose using a NOOP-based disk scheduling algorithm to reduce the utilization rate of processors and improve the average input/output service time.  ...  NOOP-based I/O scheduling for SSD devices There are a large number of disk I/O requests during the TPC-C test, and so the efficient scheduling of I/O requests can greatly improve associated performance  ... 
doi:10.1007/s11432-015-5383-x fatcat:xhffo2d2ojaflazxgce5f67yya

KAWS: Coordinate Kernel-Aware Warp Schedulingand Warp Sharing Mechanism for Advanced GPUs

Viet Tan Vo, Cheol Hong Kim
2021 Journal of Information Processing Systems  
Modern graphics processor unit (GPU) architectures offer significant hardware resource enhancements for parallel computing.  ...  Existing warp schedulers cannot be aware of the kernel progress to provide an effective scheduling policy.  ...  Our kernel-aware warp scheduler switches to a progress-based scheduling policy immediately as the kernel releases its final CTA.  ... 
doi:10.3745/jips.01.0084 dblp:journals/jips/VoK21 fatcat:fb2ewugjsbaaxmq5k67tlwwsry

Sprinkler: Maximizing resource utilization in many-chip solid state disks

Myoungsoo Jung, Mahmut T. Kandemir
2014 2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA)  
Specifically, Sprinkler relaxes parallelism dependency by scheduling I/O requests based on internal resource layout rather than the order imposed by the device-level queue.  ...  Further, it improves overall resource utilization by 68.8% under different I/O request patterns and provides, on average, 80.2% more flash-level parallelism by reducing half of the flash memory requests  ...  For all the schedulers tested, we introduce a standard command queue, which allows storage devices to execute I/Os in an out-of-order fashion [34] .  ... 
doi:10.1109/hpca.2014.6835961 dblp:conf/hpca/JungK14 fatcat:l6x4tpyscbaubkeqs3jskx6ote

Deep Learning Based Security Model for Cloud based Task Scheduling

2020 KSII Transactions on Internet and Information Systems  
We have designed a deep learning-based security model for scheduling tasks in cloud computing and it has been implemented using CloudSim 3.0 simulator written in Java and verification of the results from  ...  The demand for resources fluctuates dynamically hence the prearranging of resources is a challenging task. Many task-scheduling approaches have been used in the cloud-computing environment.  ...  The security-aware scheduling is essential to run the takes in cloud-based customer security specification.  ... 
doi:10.3837/tiis.2020.09.005 fatcat:n6rpbagx3fbcfcs35rklahli6u
« Previous Showing results 1 — 15 out of 1,926 results