Modeling parallel computers as memory hierarchies

A parameterized generic model that captures the features of diverse computer architectures would facilitate the development of portable programs. Specific models appropriate to particular computers are obtained by specifying parameters of the generic model. A generic model should be simple, and for each machine that it is intended to represent, it should have a reasonably accurate specific model. The Parallel Memory Hierarchy (PMH) model of computation uses a single mechanism to model the costs of both interprocessor communication and memory hierarchy traffic. A computer is modeled as a tree of memory modules with processors at the leaves. All data movement takes the form of block transfers between children and their parents. The paper assesses the strengths and weaknesses of the PMH model as a generic model.<<ETX>>

[1]  Robert W. Floyd,et al.  Permuting Information in Idealized Two-Level Storage , 1972, Complexity of Computer Computations.

[2]  Alfred V. Aho,et al.  The Design and Analysis of Computer Algorithms , 1974 .

[3]  Steven Fortune,et al.  Parallelism in random access machines , 1978, STOC.

[4]  H. T. Kung,et al.  I/O complexity: The red-blue pebble game , 1981, STOC '81.

[5]  Charles E. Leiserson,et al.  Fat-trees: Universal networks for hardware-efficient supercomputing , 1985, IEEE Transactions on Computers.

[6]  Lawrence Snyder,et al.  Type architectures, shared memory, and the corollary of modest potential , 1986 .

[7]  Alok Aggarwal,et al.  Hierarchical memory with block transfer , 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[8]  Bowen Alpern,et al.  A model for hierarchical memory , 1987, STOC.

[9]  Phillip B. Gibbons.  A more practical PRAM model , 1989, SPAA '89.

[10]  Alok Aggarwal,et al.  On communication latency in PRAM computations , 1989, SPAA '89.

[11]  Tak Wah Lam,et al.  Tradeoffs between communication and space , 1989, STOC '89.

[12]  Jeffrey Scott Vitter,et al.  Optimal disk I/O with parallel block transfer , 1990, STOC '90.

[13]  Lawrence Snyder,et al.  A Comparison of Programming Models for Shared Memory Multiprocessors , 1990, ICPP.

[14]  Michael L. Scott,et al.  Multi-model parallel programming in psyche , 1990, PPOPP '90.

[15]  Bowen Alpern,et al.  Uniform memory hierarchies , 1990, Proceedings [1990] 31st Annual Symposium on Foundations of Computer Science.

[16]  Leslie G. Valiant,et al.  A bridging model for parallel computation , 1990, CACM.

[17]  Bowen Alpern,et al.  Visualizing computer memory architectures , 1990, Proceedings of the First IEEE Conference on Visualization: Visualization `90.

[18]  Roger W. Hockney.  A framework for benchmark performance analysis , 1991 .

[19]  Sanjay Ranka,et al.  A practical hierarchical model of parallel computation , 1991, Proceedings of the Third IEEE Symposium on Parallel and Distributed Processing.

[20]  E T. Leighton,et al.  Introduction to parallel algorithms and architectures , 1991 .

[21]  Richard J. Anderson,et al.  A comparison of shared and nonshared memory models of parallel computation , 1991 .

[22]  Lawrence Snyder,et al.  On the influence of programming models on shared memory computer performance , 1992, Proceedings Scalable High Performance Computing Conference SHPCC-92..

[23]  D. Culler,et al.  Active Messages: A Mechanism for Integrated Communication and Computation , 1992, [1992] Proceedings the 19th Annual International Symposium on Computer Architecture.

[24]  Bowen Alpern,et al.  Rectilinear Steiner Tree Minimization on a Workstation , 1992, Computational Support for Discrete Mathematics.

[25]  Sanjay Ranka,et al.  A Practical Hierarchical Model of Parallel Computation. I. The Model , 1992, J. Parallel Distributed Comput..

[26]  Seth Copen Goldstein,et al.  Active Messages: A Mechanism for Integrated Communication and Computation , 1992, [1992] Proceedings the 19th Annual International Symposium on Computer Architecture.

[27]  L. Carter,et al.  Towards a Model for Portable Parallel Performance: Exposing the Memory Hierarchy , 1993 .

[28]  Ramesh Subramonian,et al.  LogP: towards a realistic model of parallel computation , 1993, PPOPP '93.