[图书][B] Parallel computer architecture: a hardware/software approach
The most exciting development in parallel computer architecture is the convergence of
traditionally disparate approaches on a common machine structure. This book explains the …
traditionally disparate approaches on a common machine structure. This book explains the …
[PS][PS] Scalability in the XFS File System.
A Sweeney, D Doucette, W Hu, C Anderson… - USENIX Annual …, 1996 - usenix.org
In this paper we describe the architecture and design of a new file system, XFS, for Silicon
Graphics' IRIX operating system. It is a general purpose file system for use on both …
Graphics' IRIX operating system. It is a general purpose file system for use on both …
Serverless network file systems
TE Anderson, MD Dahlin, JM Neefe… - Proceedings of the …, 1995 - dl.acm.org
In this paper, we propose a new paradigm for network file system design, serverless
network, file systems. While traditional netwc~ rk file systems rely on a central server …
network, file systems. While traditional netwc~ rk file systems rely on a central server …
Serverless network file systems
TE Anderson, MD Dahlin, JM Neefe… - ACM Transactions on …, 1996 - dl.acm.org
We propose a new paradigm for network file system design: serverless network file systems.
While traditional network file systems rely on a central server machine, a serverless system …
While traditional network file systems rely on a central server machine, a serverless system …
Effects of communication latency, overhead, and bandwidth in a cluster architecture
This work provides a systematic study of the impact of communication performance on
parallel applications in a high performance network of workstations. We develop an …
parallel applications in a high performance network of workstations. We develop an …
Fast Messages: Efficient, portable communication for workstation clusters and MPPs
Illinois Fast Messages is a low level software messaging layer designed to meet the
demands of high-performance network hardware. Implementations on a Cray T3D and a …
demands of high-performance network hardware. Implementations on a Cray T3D and a …
Effective distributed scheduling of parallel workloads
We present a distributed algorithm for time-sharing parallel workloads that is competitive
with coscheduling. Implicit scheduling allows each local scheduler in the system to make …
with coscheduling. Implicit scheduling allows each local scheduler in the system to make …
Memory channel network for PCI
RB Gillett - iEEE Micro, 2002 - ieeexplore.ieee.org
A memory-based networking approach provides clusters of computers up to 1,000 times the
communication performance of conventional networks, with no compromise in cost or …
communication performance of conventional networks, with no compromise in cost or …
[PS][PS] An implementation of the Hamlyn sender-managed interface architecture
G Buzzard, D Jacobson, M Mackey… - ACM SIGOPS …, 1996 - usenix.org
Processors are rapidly getting faster, and message-passing multicomputer interconnections
are doing the same, thanks to recent developments in Gb/s links and lowlatency packet …
are doing the same, thanks to recent developments in Gb/s links and lowlatency packet …
High-performance local area communication with fast sockets
Modern switched networks such as ATM and Myrinet enable low-latency, high-bandwidth
communication. This performance has not been realized by current applications, because of …
communication. This performance has not been realized by current applications, because of …