Download:
|
by Mark Oskin, Frederic T. Chong, Timothy Sherwood
In International Conference on Computer Design
http://zambezi.cs.ucdavis.edu/~mark/ap-iccd99.ps
Add To MetaCart
Abstract:
Current trends in DRAM memory chip fabrication have led many researchers to propose "intelligent memory " architectures that integrate microprocessors or logic with memory. Such architectures offer a potential solution to the growing communication bottleneck between conventional microprocessors and memory. Previous studies, however, have focused upon single-chip systems and have largely neglected off-chip communication in larger systems. We introduce ActiveOS, an operating system which demonstrates multi-process execution on Active Pages [OCS98], a page-based intelligent memory architecture. We present results from multiprogrammed workloads running on a prototype operating system implemented on top of the SimpleScalar processor simulator. Our results indicate that paging and inter-chip communication can be scheduled to achieve high performance for applications that use Active Pages with minimal adverse effects to applications that only use conventional pages. Overall, ActiveOS allows Active Pages to accelerate individual applications by up to 1000 percent and to accelerate total workloads from 20 to 60 percent as long as physical memory can contain the working set of each individual application.
Citations
|
1253
|
The Simplescalar toolset, version 2.0
– Burger, Austin
- 1997
|
|
237
|
Users' guide for the Harwell-Boeing sparse matrix collection (release I).Technical Report TR/PA/92/86, Research and Technology Division, Boeing Computer Services
– Duff, Grimes, et al.
- 1992
|
|
212
|
Maximizing Multiprocessor Performance with the SUIF
– Hall, Anderson, et al.
- 1996
|
|
172
|
Hitting the memory wall: Implications of the obvious
– Wulf, McKee
- 1995
|
|
158
|
Memory bandwidth limitations of future microprocessors
– Burger, Goodman, et al.
- 1996
|
|
91
|
Virtual memory
– Denning
- 1970
|
|
75
|
Active Pages: A Computation Model for Intelligent Memory
– Oskin, Chong, et al.
|
|
57
|
Tradeoffs in supporting two page sizes
– Talluri, Kong, et al.
- 1992
|
|
40
|
The structure and performance of interpreters
– Romer, Lee, et al.
- 1996
|
|
38
|
Active disks – remote execution for networkattached storage
– Riedel, Gibson
- 1997
|
|
20
|
The memory wall and the CMOS end-point
– Wilkes
- 1995
|
|
13
|
SLIF: A Specification-Level Intermediate Format for System Design
– Vahid, Gajski
- 1995
|
|
13
|
et al. A Case for Intelligent RAM: IRAM
– Patterson, Anderson
- 1997
|
|
11
|
IRAM and SmartSIMM: Overcoming the I/O bus bottleneck
– Keeton, Arpaci-Dusseau, et al.
- 1997
|
|
10
|
Algorithms on Strings, Trees and Sequences
– eld
- 1997
|
|
4
|
Design of an active memory system for network applications
– Asthana, Cravatts, et al.
- 1994
|
|
4
|
Programmable active memories: Recongurable systems come of age
– Vuillemin, Bertin, et al.
- 1996
|
|
2
|
Spec Benchmark Specifications
– SPEC
- 1995
|
|
2
|
SLIF: A speci cation-level intermediate format for system design
– Vahid, Gajski
- 1995
|
|
1
|
Maximizing multiprocessor performance with the suif compiler
– Strings, Trees, et al.
- 1997
|
|
1
|
Singel and Nandit Soparkar. Logic-enhanced memories for data-intensive processing (extended abstract
– Van
- 1995
|
|
1
|
Surpassing the TLB perfomance of superpages with less operating system support
– Talluri, Hill
- 1994
|
|
1
|
Spec benchmark speci cations
– SPEC
- 1995
|