Disk caching with an optical ring.

@article{Carrera2000DiskCW,
  title={Disk caching with an optical ring.},
  author={Enrique V. Carrera and Ricardo Bianchini},
  journal={Applied optics},
  year={2000},
  volume={39 35},
  pages={
          6663-80
        }
}
We propose a simple extension to the optical network of a scalable multiprocessor that optimizes page swap outs. More specifically, we propose to extend the network with an optical ring that not only transfers swapped-out pages between the local memories and the disks of the multiprocessor but also acts as a systemwide write cache for these pages. This extended optical network confers several performance benefits: It provides a staging area where swapped-out pages can reside until the disk is… 

Sensitivity-Based Optimization of Disk Architecture

TLDR
This paper presents the sensitivity-based optimization methodology for disk architectures (SODA), which leverages results previously obtained in digital circuit design optimization scenarios and shows how SODA can aid in design and runtime optimization of disk drive architectures.

Comparison of in-network versus Staggered Multicast video distribution models

TLDR
A mathematical model of the VIN system was derived and used to explore the performance of VIN in terms of the maximum number of concurrent video streams which can be supported by the system, and it was found that VIN has a number of advantages over Staggered Multicast.

SODA: Sensitivity Based Optimization of Disk Architecture

TLDR
This work presents a sensitivity-based optimization for disk architectures (SODA) which leverages results from digital circuit design and shows how SODA can aid in design and runtime optimization.

References

SHOWING 1-10 OF 41 REFERENCES

NetCache: A Network/Cache Hybrid for Multiprocessors

TLDR
This paper compares a 16-node multiprocessor with a third-level NetCache against two highly-efficient systems based on the DMON and LambdaNet optical interconnects and demonstrates that the NetCache multiprocessionor outperforms theDMON and lambdaNet systems by as much as 99 and 79%, respectively.

OPTNET: a cost-effective optical network for multiprocessors

TLDR
The OPTNET is proposed, a novel optical network and associated coherence protocol for scalable multiprocessors that strikes an excellent cost/performance ratio under most architectural assumptions.

Designing and Evaluating a Cost-Effective Optical Network for Multiprocessors

TLDR
The main conclusion is that the combination of the OPTNET network and coherence protocol strikes an excellent cost/performance ratio for scalable multiprocessors under most architectural assumptions.

DCD—disk caching disk: a new approach for boosting I/O performance

TLDR
This paper presents a novel disk storage architecture called DCD, Disk Caching Disk, for the purpose of optimizing I/O performance, which can be applied directly to current file systems without the need of changing the operating system.

DCD --- Disk Caching Disk: A New Approach for Boosting I/O Performance

  • Yimin HuQing Yang
  • Computer Science
    23rd Annual International Symposium on Computer Architecture (ISCA'96)
  • 1996
TLDR
This paper presents a novel disk storage architecture called DCD, Disk Caching Disk, for the purpose of optimizing I/O performance, which can be applied directly to current file systems without the need of changing the operating system.

Photonic architectures for distributed shared memory multiprocessors

  • P. DowdJ. Chu
  • Computer Science
    First International Workshop on Massively Parallel Processing Using Optical Interconnections
  • 1994
TLDR
The function of a control channel is extended to include broadcast support of cache-level control information, in addition to its primary role of data channel reservation, thereby enabling a snooping based coherence protocol to be considered.

SPEED DMON: Cache Coherence on an Optical Multichannel Interconnect Architecture

TLDR
The proposed scheme has the potential to reduce network latency by up to 85% as a result of its global independence between read and write operations, full concurrency in channel access, reduced link contention, and efficient broadcast of coherence and synchronization events.

A trace-driven comparison of algorithms for parallel prefetching and caching

TLDR
The effects of several combined prefetching and caching strategies for systems with multiple disks are studied using disk-accurate tracedriven simulation to explore the performance characteristics of each of the algorithms in cases in which applications provide full advance knowledge of accesses using hints.

UNIX Disk Access Patterns

TLDR
A detailed characterization of every lowlevel disk access generated by three quite different systems over a two month period is presented, finding that using a small non-volatile cache at each disk allowed writes to be serviced considerably faster than with a regular disk.

The MIT Alewife machine: architecture and performance

Alewife is a multiprocessor architecture that supports up to 512 processing nodes connected over a scalable and cost-effective mesh network at a constant cost per node. The MIT Alewife machine, a