Multiple-bus shared-memory system: Aquarius project

Carlton, Michael J.; Despain, Alvin M.

doi:10.1109/2.55505

Cited by 15 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Multiple-bus architectures have been proposed to connect processors to memory modules in shared-memory multiprocessors using fully-connected topologies 36], partially-connected single-hop topologies 18], and multiple-hop topologies 16]. An example of a bus-based topology for distributed-memory parallel systems is the spanning bus hypercube 34]; though memory is physically distributed, some prototype systems support a shared memory paradigm 8,14]. Other systems support such a paradigm in a hierarchical bus-based topology 11,21].…”

Section: Multichannel Networkmentioning

confidence: 99%

See 1 more Smart Citation

Multicast Communication in Staircase Multichannel Networks

McKinley

1994

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

Section: Multichannel Networkmentioning

confidence: 99%

“…s] m j i = m?h?min(m?h; low) : : :; t?1? hg (8) As an example, in Figure 6(b), let the source be in class 0, let high = 3, and let low = 11.…”

Section: Excess-receiver Staircasementioning

confidence: 99%

Multicast Communication in Staircase Multichannel Networks

McKinley

1994

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

“…Since they rely on broadcasting, snoopy protocols scale poorly. Researchers are exploring ways to improve the scalability of snoopy protocols by using multiple buses arranged hierarchically [CGB89, HLH92,Wil87] or in a grid [CaD90,GoW88]. This approach is promising for programs with access patterns that allow most broadcasts to be restricted to a local cluster of PE's.…”

Section: Related Workmentioning

confidence: 99%

“…ited directory protocols proposed by Agarwal, et al,[Aga88] and several protocols for multiple bus or hybrid bus/MIN architectures, such as the protocol proposed by Algudady, et al,[ADT90] and the DASH[Len90], VMP-MC[CGB89], Aquarius[CaD90], and Galactica Net[WiL92] protocols.Directory protocols are so named because they maintain a directory for each block listing the location of all copies of the block. The first directory protocol, due to Tang[Tan76], specified a single centralized directory.…”

mentioning

confidence: 99%

Concurrency Control in Asynchronous Computations

Williams

View full text Add to dashboard Cite

When independently executing processes share data, some form of concurrency control is needed to enforce the atomicity and sequencing constraints imposed by the program. We believe that concurrency control is hard largely because existing architectural support is inadequate. We define a new class of interconnection networks called isotach networks and explore isotach-based concurrency control by describing techniques that use the isotach network to achieve causal message delivery, atomicity, sequential consistency, and cache coherence.We show processes can pipeline their accesses to shared data in an isotach system without sacrificing sequential consistency. We define the isochron, a multicast with strong ordering properties implemented on an isotach network, and describe techniques by which processes can use isochrons to execute atomic actions without obtaining locks or other exclusive access rights. We describe compatible techniques for enforcing data dependences and show that the isotach network is capable of combining concurrently issued operations on the same shared variable while maintaining atomicity and sequential consistency. We describe a family of new cache coherence protocols called delta-cache protocols that extend isotach-based concurrency control techniques to systems that replicate and migrate shared variables, yielding protocols that are both scalable and more highly concurrent than existing protocols. We report results of a simulation study comparing the performance of isotach and conventional systems. The study shows that isotach systems outperform conventional systems under workloads with atomicity and sequencing constraints.

show abstract

“…To Aquarius project [30] μοιάζει με το Wisconsin multicube και αποτελείται από κόμβους που συνδέονται μεταξύ τους μέσω διαύλων πολλών διαστάσεων. Η κοινή μνήμη είναι κατανεμημένη στους κόμβους.…”

Section: Aquariusunclassified

Ποιοτική και ποσοτική μελέτη απόδοσης της παράλληλης αρχιτεκτονικής κατανεμημένης μνήμης PiSMA

Πίπης¹

View full text Add to dashboard Cite

Γνωστές VSM αρχιτεκτονικές βασισμένες σε υλικό 1.2 Η αρχιτεκτονική PiSMA 1.3 Περίληψη κεφαλαίου 2 Η Αρχιτεκτονική PiSMA 2.1 Εισαγωγή 2.2 Φυσική υλοποίηση της αρχιτεκτονικής PiSMA 2.2.1 Η μνήμη του συστήματος 2.2.1.1 Διατήρηση ορθότητας της μνήμης 29 2.2.1.1.1 Snoopy πρωτόκολλο διατήρησης ορθότητας της κρυφής μνήμης 2.2.1.1.2 «Παγωμένο» πρωτόκολλο διατήρησης συνέπειας 2.2.2 Μηχανισμός διαχείρισης ιδεατής μνήμης της αρχιτεκτονικής PiSMA 31 2.3 Ανοχή Σφαλμάτων στην αρχιτεκτονική PiSMA 31 2.4 Το Λειτουργικό Σύστημα της PiSMA 32 2.4.1 Το επίπεδο του πυρήνα ενός POS 2.4.1.1 Ο Δρομολογητής Διεργασιών 33 2.4.1.2 Ο Διαχειριστής Μηνυμάτων 34 2.4.1.2.1 Διαχείριση μηνυμάτων 34 2.4.1.3 Ο Δυναμικός Κατανεμητής Φόρτου 3 5 2.4.1.3.1 Αλγόριθμος Δυναμικής Κατανομής Φόρτου εργασίας 36 2.4.1.4 Ο Διαχειριστής Μνήμης 37 2.4.2 Το επίπεδο Υποστήριξης Εφαρμογών 38 2.4.2.1 Το προγραμματιστικό μοντέλο 39 2.5 Εναλλακτικοί σχεδιασμοί της αρχιτεκτονικής PiSMA 41 2.5.1 Η αρχιτεκτονική PiSMA με χρήση δικτύου 42 2.6 Περίληψη κεφαλαίου 43

show abstract

Multiple-bus shared-memory system: Aquarius project

Cited by 15 publications

References 4 publications

Multicast Communication in Staircase Multichannel Networks

Multicast Communication in Staircase Multichannel Networks

Concurrency Control in Asynchronous Computations

Ποιοτική και ποσοτική μελέτη απόδοσης της παράλληλης αρχιτεκτονικής κατανεμημένης μνήμης PiSMA

Contact Info

Product

Resources

About