4 Hits in 4.5 sec

PL2: Towards Predictable Low Latency in Rack-Scale Networks [article]

Yanfang Le, Radhika Niranjan Mysore, Lalith Suresh, Gerd Zellweger, Sujata Banerjee, Aditya Akella, Michael Swift
2021 arXiv   pre-print
In this paper, we design a Predictable Low Latency(PL2) network architecture for rack-scale systems with Ethernet as interconnecting fabric.  ...  need low and predictable latency.  ...  In this paper, we present Predictable Low Latency or PL2, a rack-scale lossless network architecture that achieves low latency and high throughput in a transport-agnostic and workload-oblivious manner.  ... 
arXiv:2101.06537v2 fatcat:azogpq3psneldov66rpvrkzm6q

Application-level power and performance characterization and optimization on IBM Blue Gene/Q systems

R. Bertran, Y. Sugawara, H. M. Jacobson, A. Buyuktosunoglu, P. Bose
2013 IBM Journal of Research and Development  
In . Energy accounting for shared virtualized environments under dvfs using pmc-based power models.  ...  In addition, we gratefully acknowledge Robert Walkup and John Gunnels for their help with the benchmarks.  ...  We thankfully acknowledge the support of the European Commission through the HiPEAC-2 Network of Excellence (FP7/ICT 217068), the support of the Spanish Ministry of Education (TIN2007-60625, andCSD2007  ... 
doi:10.1147/jrd.2012.2227580 fatcat:e2yb6krghzdvfkaavxy7ha3li4

Detecting Language Activations with Functional Magnetic Resonance Imaging [chapter]

2004 Human Brain Function  
Global scaling Scaling o f global activity across sessions/subjects is enforced in SPM99 software.  ...  In this case, a multi-subject network can be treated as a multi-group network.  ...  Here I refer to c^X^ZX^^c as design variance in contradistinction to a^c^X^ZX^^c which is contrast or estimator variance (note that when o^=l, the design and contrast variances are equivalent).  ... 
doi:10.1016/b978-012264841-0/50032-9 fatcat:qrj3cfoomzd6zan5iu3gjazd34

Multi-objective query optimization for massively parallel processing in Cloud Computing [article]

Michail Georgoulakis Misegiannis, National Technological University Of Athens
Acknowledgements Experiments presented in this diploma thesis were carried out using the Grid'5000 experimental testbed, being developed under the INRIA ALADDIN development action with support from CNRS  ...  Data replication across nodes provides fault tolerance and low latency across the cluster. Data is modeled in column families consisting of columns and organised by row keys.  ...  The system is built on top of Anna [40] , a low latency autoscaling key-value store implemented by the same research team (UC Berkeley).  ... 
doi:10.26240/heal.ntua.22813 fatcat:43osoibikjd4rcdqr24mwd6qii