A technique is described to automatically compile performance models in the course of program translation. The performance models are fully symbolic in order to preserve as much diagnostic information as possible. Although compiled statically, the models account for the effects of resource contention, due to the introduction of a novel algorithm within the symbolic compilation scheme. It is shown that the compilation approach fundamentally outperforms traditional static estimation procedures in terms of precision at a negligible increase in cost. This claim is illustrated by a case study of an LU factorization algorithm on a multiprocessor.
|
374
|
Can Programming be Liberated from the von Neumann Style? 1979 Turing Award Lecture
– Backus
|
|
295
|
Bounds on Multiprocessing Timing Anomalies
– Graham
- 1969
|
|
233
|
Partitioning and scheduling parallel programs for multi-processors
– Sarkar
- 1989
|
|
182
|
Open, closed and mixed networks of queues with different classes of customers
– Baskett, Chandy, et al.
- 1975
|
|
175
|
A static performance estimator to guide data partitioning decisions
– Balasundaram, Fox, et al.
- 1991
|
|
161
|
Concepts and notations for concurrent programming
– Andrews, Schneider
- 1983
|
|
161
|
I962J. A Programming Language
– Iverson
- 1962
|
|
152
|
Mean Value Analysis of Closed Multichain Queueing Networks
– Reiser, Lavenberg
- 1980
|
|
111
|
Computer Performance Modelling Handbook
– Lavenberg
- 1983
|
|
105
|
G.: Performance Models of Multiprocessor Systems
– Marsan, Balbo, et al.
- 1986
|
|
81
|
Predicting the Performance of Parallel Computations
– Mak, Lundstrom
- 1990
|
|
60
|
Mechanical program analysis
– Wegbreit
- 1975
|
|
56
|
System Simulation Programming Styles and Languages
– Kreutzer
- 1986
|
|
42
|
Approximate analysis of multiclass closed networks of queues, in
– Schweitzer
- 1979
|
|
41
|
Performance prediction of parallel processing systems: The Pamela methodology
– Gemund
- 1993
|
|
33
|
PAPS - The Parallel Program Performance Prediction Toolset
– Wabnig, Haring
- 1994
|
|
29
|
Automating program analysis
– Hickey, Cohen
- 1988
|
|
25
|
Some extensions to multiclass queueing network analysis
– Bard
- 1979
|
|
22
|
A static parameter-based performance prediction tool for parallel programs
– Fahringer, Zima
- 1993
|
|
20
|
A system for Computing The Speedup of Parallel Programs
– Lester
- 1986
|
|
19
|
Speedup Bounds and Processor Allocation for Parallel Programs on Multiprocessors
– Polychronopoulos, Banerjee
- 1986
|
|
19
|
Intelligent program optimization and parallelization for parallel computers
– WANG
- 1991
|
|
15
|
A speedup analyzer for parallel programs
– So, Bolmarcich, et al.
- 1987
|
|
14
|
A complexity calculus for recursive tree algorithms
– Flajolet, Steyaert
- 1987
|
|
13
|
Queueing models of parallel applications: The Glamis methodology," to appear
– Jonkers
- 1994
|
|
12
|
Performance prediction of loop constructs on multiprocessor hierarchical memory systems
– Gallivan, Jalby, et al.
- 1989
|
|
11
|
Building analytical models into an interactive prediction tool
– Atapattu, Gannon
- 1989
|
|
11
|
Deterministic Timing Schema for Parallel Programs
– Shaw
- 1991
|
|
10
|
et al., Quantitative System Performance: Computer System Analysis Using Queueing Network Models
– Lazowska
- 1984
|
|
9
|
Access Conflicts in Multiprocessor Memories Queuing Models and Simulation Studies
– Bucher, Calahan
- 1990
|
|
8
|
The PAMELA Run-Time Library Version 1.0
– Gemund
- 1994
|
|
7
|
Introduction to probabilistic performance modelling of parallel applications
– Jonkers
- 1993
|
|
7
|
LAPAS: A performance evaluation tool for large parallel systems
– Mierendorff, Schwarzwald
- 1990
|
|
5
|
On the analysis of Pamela models
– Gemund
- 1993
|
|
3
|
The Pamela approach to performance simulation of parallel and distributed systems
– Gemund
- 1993
|
|
1
|
Supercomputing: Big bang or steady state
– Gurd
- 1993
|
|
