Abstract
In distributed shared-memory (DSM) multiprocessors, a write operation requires multiple messages to invalidate the nodes which share and cache the memory block to being written. The consequent write stall time impedes the performance of such systems. An effective means of achieving efficient invalidation is to employ multicast messages to reach the sharing nodes. This study evaluates two multicast-based invalidation schemes, dual-path and pruning, by performing application-driven simulation. The experimental settings used herein find that multicasts improve invalidation traffic for four of the six evaluated real applications. The remaining two applications are computationally intensive, and multicast-based invalidation is less effective. However, since multicasts encourage bursty communication, our results indicate that they help relieve network congestion during these periods. Dual-path performs slightly better than pruning, because it is less sensitive to routing delay in the routers. Our results further demonstrate that cache size is an important design parameter for multicast-based invalidation, and is highly effective for DSM multiprocessors with larger caches.
| Original language | English |
|---|---|
| Pages (from-to) | 279-304 |
| Number of pages | 26 |
| Journal | Journal of Supercomputing |
| Volume | 18 |
| Issue number | 3 |
| DOIs | |
| Publication status | Published - 2001 Mar 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
- Theoretical Computer Science
- Information Systems
- Hardware and Architecture
Cite this
}
An application-driven study of multicast communication for write invalidation. / Hsiao, Hung-Chang; King, Chung Ta.
In: Journal of Supercomputing, Vol. 18, No. 3, 01.03.2001, p. 279-304.Research output: Contribution to journal › Article
TY - JOUR
T1 - An application-driven study of multicast communication for write invalidation
AU - Hsiao, Hung-Chang
AU - King, Chung Ta
PY - 2001/3/1
Y1 - 2001/3/1
N2 - In distributed shared-memory (DSM) multiprocessors, a write operation requires multiple messages to invalidate the nodes which share and cache the memory block to being written. The consequent write stall time impedes the performance of such systems. An effective means of achieving efficient invalidation is to employ multicast messages to reach the sharing nodes. This study evaluates two multicast-based invalidation schemes, dual-path and pruning, by performing application-driven simulation. The experimental settings used herein find that multicasts improve invalidation traffic for four of the six evaluated real applications. The remaining two applications are computationally intensive, and multicast-based invalidation is less effective. However, since multicasts encourage bursty communication, our results indicate that they help relieve network congestion during these periods. Dual-path performs slightly better than pruning, because it is less sensitive to routing delay in the routers. Our results further demonstrate that cache size is an important design parameter for multicast-based invalidation, and is highly effective for DSM multiprocessors with larger caches.
AB - In distributed shared-memory (DSM) multiprocessors, a write operation requires multiple messages to invalidate the nodes which share and cache the memory block to being written. The consequent write stall time impedes the performance of such systems. An effective means of achieving efficient invalidation is to employ multicast messages to reach the sharing nodes. This study evaluates two multicast-based invalidation schemes, dual-path and pruning, by performing application-driven simulation. The experimental settings used herein find that multicasts improve invalidation traffic for four of the six evaluated real applications. The remaining two applications are computationally intensive, and multicast-based invalidation is less effective. However, since multicasts encourage bursty communication, our results indicate that they help relieve network congestion during these periods. Dual-path performs slightly better than pruning, because it is less sensitive to routing delay in the routers. Our results further demonstrate that cache size is an important design parameter for multicast-based invalidation, and is highly effective for DSM multiprocessors with larger caches.
UR - http://www.scopus.com/inward/record.url?scp=0035277682&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0035277682&partnerID=8YFLogxK
U2 - 10.1023/A:1008161716113
DO - 10.1023/A:1008161716113
M3 - Article
VL - 18
SP - 279
EP - 304
JO - Journal of Supercomputing
JF - Journal of Supercomputing
SN - 0920-8542
IS - 3
ER -