Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

An Architecture for High-Performance Scalable Shared-Memory Multiprocessors Exploiting

Summary: An Architecture for High-Performance Scalable
Shared-Memory Multiprocessors Exploiting
On-Chip Integration
Manuel E. Acacio, JoseŽ GonzaŽlez, Member, IEEE Computer Society,
JoseŽ M. GarciŽa, Member, IEEE, and JoseŽ Duato, Member, IEEE
Abstract--Recent technology improvements allow multiprocessor designers to put some key components inside the processor chip,
such as the memory controller, the coherence hardware, and the network interface/router. In this paper, we exploit such integration
scale, presenting a novel node architecture aimed at reducing the long L2 miss latencies and the memory overhead of using directories
that characterize cc-NUMA machines and limit their scalability. Our proposal replaces the traditional directory with a novel three-level
directory architecture, as well as it adds a small shared data cache to each of the nodes of a multiprocessor system. Due to their small
size, the first-level directory and the shared data cache are integrated into the processor chip in every node, which enhances
performance by saving accesses to the slower main memory. Scalability is guaranteed by having the second and third-level directories
out of the processor chip and using compressed data structures. A taxonomy of the L2 misses, according to the actions performed by
the directory to satisfy them, is also presented. Using execution-driven simulations, we show that significant latency reductions can be
obtained by using the proposed node architecture, which translates into reductions of more than 30 percent in several cases in the
application execution time.
Index Terms--cc-NUMA multiprocessor, directory memory overhead, L2 miss latency, three-level directory, shared data cache, on-
processor-chip integration.


Source: Acacio, Manuel - Departamento de Ingenieria y Tecnologia de Computadores, Universidad de Murcia


Collections: Computer Technologies and Information Sciences