Scales, D.J. and M.S. Lam, An Efficient Shared Memory Layer for Distributed Memory Machines,. 1994, Computer Systems Laboratory, Stanford University: CA 94305. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Mechanisms for Efficient Shared-Memory, Lock-Based Synchronization - Kagi (1999) (2 citations) (Correct)
.... Work related to CLEAN, the distributed shared memory system that implements the efficient synchronization primitive called VAQUM, falls into three categories: 1) systems that support dynamic variable cache line sizes in hardware [DL92, JMH97, KW98] 2) software distributed shared memory systems [BZS93, Nik94, 47 JKW95, SL94a, SL94b, SGZ93]; and (3) software annotations to improve performance [LCW94] Dubnicki and LeBlanc propose a coherent cache architecture that attempts to select dynamically a line size that suits best a particular region of memory, at a particular instant of a program s execution [DL92] Their technique uses ....
Daniel J. Scales and Monica S. Lam. An efficient shared memory layer for distributed memory machines. Technical Report CSL-TR-94-627, Computer Systems Laboratory, Stanford University, Stanford, CA, July 1994.
Compilation Issues For Distributed Shared Memory On Clusters Of.. - Roy (1998) (Correct)
....is available on SunOS 4.1, Irix and HP UX, as well as on the DEC Alpha. As part of the experiments of this theses, Quarks was also ported to Solaris 2.x and AIX 3.2.5. 40 The distribution contains sample programs including matrix multiplication and successive over relaxation. 4.1. 6 SAM SAM [49] provides a shared name space and dynamic caching of remotely accessed data by tying synchronization to data accesses. Two types of data are provided, values and accumulators. A process writes to a value and thus shares a producer consumer relationship with all readers of that value. An ....
....that are essentially provided for the shared memory 98 programmer. This could eventually lead to a more efficient implementation and improve performance. SAM already implements such a scheme by encouraging the use of the JADE language and compiler for its use, rather than direct library calls [49]. The SUIF compiler does not use condition variables, which can hence be removed from the target DSM. A possible performance improvement used by CVM is to add specific support for commonly used reduction operations, which can also be detected by the compiler. 7.2 suif2strings Pass The problem in ....
D. J. Scales and M. S. Lam, "An Efficient Shared Memory Layer for Distributed Memory Machines," Tech. Rep. CSL-TR-94-627, Computer Systems Laboratory, Stanford University, 1994.
NIP: A Parallel Object-Oriented Computational Model - Watson, Parastatidis (1998) (2 citations) (Correct)
No context found.
Scales, D.J. and M.S. Lam, An Efficient Shared Memory Layer for Distributed Memory Machines,. 1994, Computer Systems Laboratory, Stanford University: CA 94305.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC