Learn More
We introduce a new dataset, Human3.6M, of 3.6 Million accurate 3D Human poses, acquired by recording the performance of 5 female and 6 male subjects, under 4 different viewpoints, for training realistic human sensing systems and for evaluating the next generation of human pose estimation models and algorithms. Besides increasing the size of the datasets in(More)
This paper presents the integration of two collective I/O techniques into the Clusterfile parallel file system: disk-directed I/O and two-phase I/O. We show that global cooperative cache management improves the collective I/O performance. The solution focuses on integrating disk parallelism with other types of parallelism: memory (by buffering and caching(More)
This paper presents Cluster-Aware Remote Disks (CARDs), a Single System I/O architecture for cluster computing. CARDs virtualize accesses to remote cluster disks over a System Area Network. Their operation is driven by cooperative caching policies that implement a joint management of the cluster caches. All the CARDs of a given disk employ a common policy,(More)
This paper presents the design and performance of remote disk drivers for clusters of Commodity-Off-The-Shelf PCs that fetch disk blocks over System Area Networks. The driver offers a flexible interface, being capable to logically act either as computer-or network-attached storage. It allows for fine-grain remote cache control through exclusive caching. An(More)
The TCP connection endpoint migration allows arbitrary server-side connection endpoint assignments to server nodes in cluster-based servers. The mechanism is client-transparent and supports back-end level request dispatching. It has been implemented in the Linux kernel and can be used as part of a policy-based software architecture for request distribution.(More)
This paper presents speculative TCP connection admission, a mechanism for improving sub-optimal request distribution decisions in cluster-based servers. Overloaded server nodes in the cluster speculatively accept incoming requests only to offload them to less-loaded nodes. Speculative admission uses connection endpoint migration, a technique that allows(More)
This paper presents a framework that supports the implementation of parallel solutions for the widespread para-metric maximum flow computational routines used in image segmentation algorithms. The framework is based on su-pergraphs, a special construction combining several image graphs into a larger one, and works on various architec-tures (multi-core or(More)