NDLI: Performance estimation in a massively parallel system

Please wait, while we are loading the content...

LAPACK: a portable linear algebra library for high-performance computers

Hierarchical blocking and data flow analysis for numerical linear algebra

Multilinear algebra and parallel programming

The impact of memory organization on the performance of matrix multiplication

A linear array of processors with partially shared memory for parallel solution of PDE

On randomly interleaved memories

Tracing application program execution on the Cray X-MP and Cray 2

Parallel program debugging with on-the-fly anomaly detection

Improving instruction cache behavior by reducing cache pollution

A parallel Monte Carlo search algorithm for the conformational analysis of proteins

Folding RNA on the Cray-2

A parallel computational approach using a cluster of IBM ES/3090 600Js for physical mapping of chromosomes

Experience with a performance analyzer for multithreaded applications

Performance evaluation of the IBM RISC System/6000: comparison of an optimized scalar processor with two vector processors

The characterization of two scientific workloads using the CRAY X-MP performance monitor

Supercomputer network selection: a case study

Very high performance networking for supercomputing

Cost-performance analysis of heterogeneity in supercomputer architectures

Fast barrier synchronization hardware

Switch-stacks: a scheme for microtasking nested parallel loops

Parallelization of loops with exits on pipelined architectures

Computation of large-scale constrained matrix problems: the splitting equilibration algorithm

High performance preconditioning on supercomputers for the 3D device simulator MINIMOS

Techniques for improving the performance of sparse matrix factorization on multiprocessor workstations

Fault-tolerant routing in MIN-based supercomputers

Uni-directional hypercubes

Design and analysis of buffered crossbars and banyans with cut-through switching

A parallel object-oriented total architecture: A–NET

A parallel computer model supporting procedure-based communication

A high-performance, memory-based interconnection system for multicomputer environments

Performance estimation in a massively parallel system

Parametrized algorithm decomposition and performance analysis

Another view on parallel speedup

A taxonomy of concepts for evaluating chess strength

Group graphs and computational symmetry on massively parallel architecture

Chess and supercomputers: details about optimizing Cray Blitz

Experiences in building the Clemson computational sciences program

A real introduction to supercomputing: a user training course

Loop displacement: an approach for transforming and scheduling loops for parallel execution

A compiler-assisted approach to SPMD execution

Loop distribution with arbitrary control flow

Large-scale computing on clustered vector multiprocessors

Application of sequential staging of tasks to petroleum reservoir modeling

A vectorized 3-D finite element model for transient simulation of two-phase heat transport with phase transformation and a moving interface

Parallelization of a radiation transport simulation code on the BBN TC2000 parallel computer

Perfect Benchmarks decomposition and performance on VAX multiprocessors

Embedding meshes on the star graph

Logarithmic time cost optimal parallel sorting is not yet fast in practice!

A simple and correct shared-queue algorithm using compare-and-swap

Fine-grain parallelism in the ALPS programming language

Delirium: an embedding coordination language

UC: a language for the connection machine

Parallel algorithm research at CERFACS

A write update cache coherence protocol for MIN-based multiprocessors with accessibility-based split caches

Cache coherence in systems with parallel communication channels & many processors

Data cache performance of supercomputer applications

Resource binding—a universal approach to parallel programming

A flexible communication abstraction for nonshared memory parallel computing

Implementation machine paradigm for parallel programming

Efficient parallel logic simulation techniques for the connection machine

Design of a scalable parallel switch-level simulator for VLSI

SISAL versus FORTRAN: a comparison using the Livermore loops

Experimental analysis of communication/data-conditional aspects of a mixed-mode parallel architecture via synthetic computations

Performance evaluation of mesh-connected wormhole-routed networks for interprocessor communication in multicomputers

Theorem proving in propositional logic on vector computers using a generalized Davis-Putnam procedure

Scan primitives for vector computers

A vectorized long-period shift-register random number generator

Massively parallel computational methods in light scattering by small particles

On the adequacy of message-passing parallel supercomputers for solving neutron transport problems

MONT3E: a Monte Carlo electron heat transfer code

A fiber optic hypermesh for SIMD/MIMD machines

A message passing coprocessor for distributed memory multicomputers

Architectural support for register allocation in the presence of aliasing

Information optimization for Monte Carlo data and application to high-temperature quantum chromodynamics

An optional hypercube direct N-body solver on the connection machine

Monte Carlo simulation of the Ising model and random number generation on the vector processor

P3D: a Lisp-based format for representing general 3D models

Scientific data visualization: a formal introduction to the rendering and geometric modeling aspects

Run-time monitoring of concurrent programs on the Cedar multiprocessor

Future general purpose supercomputer architectures

Building black holes, gravitational waves, and relativistic fluid flows: supercomputer cinema

Quantum molecular modeling with simulated annealing—a distributed processing and visualization application

Computer simulation of high-speed impact response of composites

Time dilation visualization in relativity

Partitioning declarative programs into communicating processes

Parallel processing of near fine grain tasks using static scheduling OSCAR (optimally scheduled advanced multiprocessor)

Generating explicit communication from shared-memory program references

A network-topology independent task allocation strategy for parallel computers

Heuristic methods for dynamic load balancing in a message-passing supercomputer

A semi distributed task allocation strategy for large hypercube supercomputers

Architecture and implementation of a VLIW supercomputer

The design of a RISC based multiprocessor chip

Soviet high-speed computers: the new generation

Performing data flow analysis in parallel

Experience with interprocedural analysis of array side effects

Subdomain dependence test for massive parallelism

Performance estimation in a massively parallel system

Content Provider	ACM Digital Library
Author	Chakradhar, Srimat T. Agrawal, Vishwani D.
Abstract	As more processors are added to a parallel processing system, the speedup gain diminishes. This behavior has been observed for several synchronized iterative algorithms. In this paper, we present a new statistical model of parallel processing for evaluating the performance of such algorithms on multiprocessor systems. A task is characterized by two parameters: the number of atoms and activity. An atom is the smallest part of computation that cannot be distributed to multiple processors and all atoms of a task are assumed to be equal in computational effort. Furthermore, atoms of the task become active with a fixed probability a called the activity. The task is equally divided among processors and the computation is synchronized at periodic instances when the results can be shared. The amount of computational activity of a processor within the period between synchronizations is assumed to be a binomial random variable. The performance of the multiprocessor system is derived from the maximum order-statistic of these random variables. The theoretical performance predicted by our analysis agrees well with the reported experimental performance of logic simulation of production VLSI chips. Even when the inter-processor communication overhead is neglected, the analysis explains many observed phenomena. The speedup continues to increase with the number of processors and assumes values around a x p, where p is the number of processors. As p is increased, the speedup rapidly changes from p to a x p. When the atoms can be equally divided among the p processors, the lower bound on speedup is found to be a x p. For unequal division of atoms to processors, however, the lower bound on speedup is less than a x p. Interestingly, for very low activity, speedups significantly higher than the lower bounds are possible.
Starting Page	306
Ending Page	313
Page Count	8
File Format	PDF
ISBN	0897914120
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	1990-11-12
Access Restriction	Subscribed
Content Type	Text
Resource Type	Article

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in