dc.contributor.author | Evripidou, Paraskevas | en |
dc.contributor.author | Gaudiot, J. -L | en |
dc.creator | Evripidou, Paraskevas | en |
dc.creator | Gaudiot, J. -L | en |
dc.date.accessioned | 2019-11-13T10:40:00Z | |
dc.date.available | 2019-11-13T10:40:00Z | |
dc.date.issued | 1995 | |
dc.identifier.uri | http://gnosis.library.ucy.ac.cy/handle/7/53907 | |
dc.description.abstract | Driven by the 'side-effect' environment of sequential von Neumann computing, Input/Output operations have evolved as state operations on shared files. In parallel programs, if multiple instances of an I/O-performing process execute concurrently, either the user or the system must synchronize any accesses to shared files. Data-flow principles of execution provide an elegant way to ensure at runtime that instructions can be executed asynchronously in a parallel environment. However, while the conventional von Neumann model of interpretation inherited a rigid ordering of instructions, it is the very asynchronous character of the data-flow model of execution which introduces conflicts when 'state' tasks (such as I/O operations) must share common data objects. The scheme presented in this paper, Logical Serialization with Distributed File Pointers (LS-DFP), introduces the two basic I/O operations read and write into the dynamic data-flow graph. However, sequencing I/O operations on the same file based on the availability of data as in 'conventional' data-flow is not possible because the name of the file becomes available simultaneously to all operations at program initiation. To impose an order, we sequentialize, (logically serialize-LS), the operations according to their lexicographical ordering. Furthermore, several optimizations are introduced that allow the distributed execution of these I/O operations with the use of Distributed File Pointers (DFP). Thus, the LS-DFP scheme can utilize the full level of parallelism of the dynamic data-flow principles of execution. © 1995. | en |
dc.source | Parallel Computing | en |
dc.source.uri | https://www.scopus.com/inward/record.uri?eid=2-s2.0-0029360287&doi=10.1016%2f0167-8191%2895%2900021-F&partnerID=40&md5=9b44b97cc335e8fb7aebaab6de92d7b1 | |
dc.subject | Sequential von Neumann computing | de |
dc.subject | Optimization | en |
dc.subject | Computational methods | en |
dc.subject | Distributed computer systems | en |
dc.subject | Synchronization | en |
dc.subject | Graph theory | en |
dc.subject | Data processing | en |
dc.subject | Parallel processing systems | en |
dc.subject | Data structures | en |
dc.subject | Data description | en |
dc.subject | Data flow graph | en |
dc.subject | Data-flow graphs | en |
dc.subject | Distributed file pointers | en |
dc.subject | I/O synchronization problem | en |
dc.subject | Input Access Graph (IAG) | en |
dc.subject | Input output programs | en |
dc.subject | Logical serialization | en |
dc.subject | Parallel I/O operations | en |
dc.title | Incorporating input/output operations into dynamic data-flow graphs | en |
dc.type | info:eu-repo/semantics/article | |
dc.identifier.doi | 10.1016/0167-8191(95)00021-F | |
dc.description.volume | 21 | |
dc.description.issue | 8 | |
dc.description.startingpage | 1285 | |
dc.description.endingpage | 1311 | |
dc.author.faculty | 002 Σχολή Θετικών και Εφαρμοσμένων Επιστημών / Faculty of Pure and Applied Sciences | |
dc.author.department | Τμήμα Πληροφορικής / Department of Computer Science | |
dc.type.uhtype | Article | en |
dc.source.abbreviation | Parallel Comput | en |
dc.contributor.orcid | Evripidou, Paraskevas [0000-0002-2335-9505] | |
dc.gnosis.orcid | 0000-0002-2335-9505 | |