by Ashley Saulsbury, Tim Wilkinson, John Carter, Anders Landin
In Proceedings of the First Annual Symposium on High Performance Computer Architecture
http://www.cs.utah.edu/flux/papers/coma.ps.Z
Add To MetaCart
Abstract:
We present design details and some initial performance results of a novel scalable shared memory multiprocessor architecture. This architecture features the automatic data migration and replication capabilities of cache-only memory architecture (COMA) machines, without the accompanying hardware complexity. A software layer manages cache space allocation at a page-granularity- similarly to distributed virtual shared memory (DVSM) systems, leaving simpler hardware to maintain shared memory coherence at a cache line granularity. By reducing the hardware complexity, the machine cost and development time are reduced. We call the resulting hybrid hardware and software multiprocessor architecture Simple COMA. Preliminary results indicate that the performance of Simple COMA is comparable to that of more complex contemporary allhardware designs. 1
Citations
|
848
|
Memory coherence in shared virtual memory systems
– Li, Hudak
- 1989
|
|
705
|
SPLASH: Stanford Parallel Applications for Shared Memory
– Singh, Weber, et al.
- 1992
|
|
531
|
Implementation and performance of Munin
– Carter, Bennet, et al.
- 1991
|
|
338
|
The Directory-Based Cache Coherence Protocol for the Dash Multiprocessor
– Lenoski
- 1990
|
|
323
|
Tempest and Typhoon: User-Level Shared Memory
– Reinhardt, Larus, et al.
- 1994
|
|
196
|
An Evaluation of Directory Schemes for Cache Coherence
– Agarwal, Simoni, et al.
- 1988
|
|
187
|
The Wisconsin Wind Tunnel: Virtual prototyping of parallel computers
– Reinhardt, Hill, et al.
- 1993
|
|
149
|
DDM - A Cache-Only Memory Architecture
– Hagersten, Landin, et al.
- 1992
|
|
93
|
On the inclusion properties for multi-level cache hierarchies
– BAER, WANG
- 1988
|
|
74
|
Experimental Comparison of Memory Management Policies for NUMA Multiprocessors
– Ellis
- 1991
|
|
45
|
NUMA Policies and Their Relation to Memory Architecture
– Bolosky, Scott, et al.
- 1991
|
|
41
|
III, ‘‘Overview of the KSR1 Computer System
– Burkhardt
- 1992
|
|
41
|
Toward Scalable Cache Only Memory Architectures
– Hagersten
- 1992
|
|
40
|
Evaluating the Memory Overhead Required for COMA Architectures
– JOE, HENNESSY
- 1994
|
|
26
|
Simple COMA Node Implementations
– Hagersten
- 1994
|
|
16
|
Data Diffusion Machine--a scalable shared virtual memory multiprocessor
– Warren, Haridi
- 1988
|
|
14
|
Distributed-Directory Protocol
– Stanford
- 1990
|
|
4
|
Supporting fine-grain shared memory
– Saulsbury
- 1993
|
|
3
|
Handling replacement
– Saulsbury, Wilkinson, et al.
- 1994
|
|
1
|
Latency analysis of cc-numa and cc-coma hierarchical ring multiprocessors
– Zhang, Yan
- 1994
|
