KiloCore: A Fine-Grained 1,000-Processor Array for Task-Parallel Applications

Many important applications can be expressed as a group of fine-grained interconnected tasks, in which individual tasks require under 100 instructions and little data memory. KiloCore, an array of 1,000 independent processors and 12 memory modules, has been designed to efficiently support these appl...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE MICRO Jg. 37; H. 2; S. 63 - 69
Hauptverfasser: Bohnenstiehl, Brent, Stillmaker, Aaron, Pimentel, Jon, Andreas, Timothy, Liu, Bin, Tran, Anh, Adeagbo, Emmanuel, Baas, Bevan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Los Alamitos IEEE 01.03.2017
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
CMOS
Computer memory
locally synchronous; scheduling and task partitioning
many-core; multicore; GALS; globally asynchronous
Memory management
Microprocessors
Modules
Multicore processing
Parallel processing
Parity check codes
Processors
Program processors
Scheduling
Throughput
ISSN:0272-1732, 1937-4143
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Many important applications can be expressed as a group of fine-grained interconnected tasks, in which individual tasks require under 100 instructions and little data memory. KiloCore, an array of 1,000 independent processors and 12 memory modules, has been designed to efficiently support these applications, and has been fabricated in 32-nm PD-SOI CMOS. Each programmable processor occupies 0.055 mm 2 and supports energy-efficient computation of small tasks, requiring 17 mW to operate with a clock frequency of 1.24 GHz at 0.9 V. Processors may operate up to 1.78 GHz at 1.1 V, or down to 115 MHz and 0.61 mW at 0.56 V. Coarse-grained tasks are supported with the assistance of the independent memory modules, which can each supply 64 Kbytes of data and instructions to neighboring processors. Processors are connected using complementary circuit and packet-based networks, which offer a total array bisection bandwidth of up to 4.2 Tbps at 1.1 V. Fine-grained tasks are found to have low communication link densities in sampled applications, allowing a large majority of links to be assigned to the energy-efficient, high-performance circuit network.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0272-1732
1937-4143
DOI:10.1109/MM.2017.34