Digest of Papers. COMPCON Spring 89. Thirty-Fourth IEEE Computer Society International Conference: Intellectual Leverage
DOI: 10.1109/cmpcon.1989.301989
|View full text |Cite
|
Sign up to set email alerts
|

Scalable coherent interface

Abstract: The Scalable Coherent Interface (IEEE P1596) is establishing an interface standard for very high performance multiprocessors, supporting a cache-coherent-memory model scalable to systems with op to 64K nodes. This Scalable Coherent Interface (SCI) will supply a peak bandwidth per node of 1 GigaByte/second. The SCI standard should facilitate assembly of processor, memory, I/O and bus bridge cards from multiple vendors into massively parallel systems with throughput far above what is possible today.The SCI stand… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
2
0
1

Publication Types

Select...
3
3

Relationship

1
5

Authors

Journals

citations
Cited by 6 publications
(3 citation statements)
references
References 2 publications
(2 reference statements)
0
2
0
1
Order By: Relevance
“…NUMA allows the clustering of several memory controllers into a single server node, creating several memory domains. Although NUMA systems were deployed as early as 1980s in specialized systems [185], since 2008 all Intel and AMD processors incorporate one memory controller. Thus, most contemporary multi-processor systems are NUMA; therefore, NUMA-awareness is becoming a mainstream challenge.…”
Section: Non-uniform Memory Accessmentioning
confidence: 99%
“…NUMA allows the clustering of several memory controllers into a single server node, creating several memory domains. Although NUMA systems were deployed as early as 1980s in specialized systems [185], since 2008 all Intel and AMD processors incorporate one memory controller. Thus, most contemporary multi-processor systems are NUMA; therefore, NUMA-awareness is becoming a mainstream challenge.…”
Section: Non-uniform Memory Accessmentioning
confidence: 99%
“…Hewlett Packard is preparing parallel/serial converter chips to interface the Dolphin chips (.parallel) to the 1000 Mbit/s encoding used on optical fiber or coaxial cable, and these should be available by year's end. 3 Related Standards Projects…”
Section: Current Sci Statusmentioning
confidence: 99%
“…Σε μερικά συστήματα μάλιστα, [Kranz et al 1993][Cordsen andSchroder-Preikschat 1997] επιτρέπεται -ή και συνιστάται-η ταυτόχρονη και η συνδυασμένη χρήση των προγραμματιστικών μοντέλων (του μοντέλου ανταλλαγής μηνυμάτων και του μοντέλου κοινών μεταβλητών), με αποτέλεσμα τη μεγαλύτερη ευελιξία στη χρήση. [Goodman 1989] [Gustavson 1989][IEEE 1993]. Ο χρόνος που απαιτείται για την προσπέλαση δεδομένων από έναν επεξεργαστή είναι ιδιαίτερα μικρός, αν το ζητούμενο αντικείμενο βρεθεί μέσα στον υπολογιστικό κόμβο, ενώ αυξάνεται σημαντικά (εξ'ού και ο όρος "μη ομοιόμορφη προσπέλαση"), αν αυτό βρεθεί σε απομακρυσμένο κόμβο.…”
Section: ο μεταγλωττιστής and το σύστημα εκτέλεσηςunclassified