In Search of a Standards Based Approach to Hybrid Performance Monitoring                                                                        

Jim Harden, Donna Reese, Marlene Evans, Sudi Kadambi, Greg Henley, and Chuck Hudnall                               
NSF Engineering Research Center for Computational Field Simulation                                   
Mississippi State University                                                
Cedell Alexander                                                      
IBM Networking Har dwar e Division                                                
Research Triangle Park, NC


Abstract
A new multicomputer performance monitoring system is described in this     
paper.  Where possible, the system employs portable performance monitoring instrumentation                            
technology and leverages previous work.  Trace event acquisition is hardware assisted and                            
based on the MultiKron, a single chip measurement solution developed at the National             
Institute for Standards and Technology .  The user interface is based on the Pablo Performance                       
Analysis Environment, a visualization and sonification toolkit developed at the University of                         
Illinois.  The SPIscope is introduced as a component that bridges the gap between these            
emerging standard interfaces.  The SPIscope provides a high bandwidth path to a large                                 
secondary storage for recording performance data.  Connectivity to the user's performance     
analysis workstation is via a TCP/IP LAN.  Facilities are provided to support                                         
applicationspecific trace events, breakpoint style debugging, on line transmission of selected                       
data, and dynamic acquisitionrate control.  By using existing technology and interfaces, we                          
hope to contribute a performance monitoring component with greater utility throughout the                             
parallel processing community .                                                                                       


REFERENCES                                                
[1]  M. van Riek, B. Tourancheau, X. Vigour oux, Monitoring of Distributed Memory                         
     Multicomputer Programs, T ech. Report CS93204, Univ. of Tennessee, Knoxville, TN,  1993.           
     url=ftp://cs.utk.edu/pub/T         echReports/                                                        
[2]  D. Haban and D. Wybranietz, A Hybrid Monitor for Behavior and Performance Analysis of                
     Distributed Systems, IEEE Trans. Software Engr., vol. 16, no. 2, pp. 197211, February 1990.         
[3]  M. Siegle and R. Hofmann, Monitoring Pr ogram Behaviour on SUPRENUM, in                            Proc. 19th
     Int. Symp. Comput. Arch., May 1992, pp. 332341.                                                      
[4]  J. Harden, D. Reese, F. To, D. Linder, C. Borchert, G. Jones, A Performance Monitor for the          
     MSP ARC Multicomputer , IEEE Southeastcon '92, April 1215, 1992.                                    
[5]  R. Hofmann, R. Klar , B. Mohr, A. Quick, M. Siegle, Distributed Performance Monitoring:              
     Methods, Tools, and Applications, IEEE Trans. Parallel Distribributed Syst., vol. 5, no. 6, pp.      
     585597, June 1994.                                                                                   
[6]  A. Mink, R. J. Carpenter , G. Nacht, and J. Roberts, Multipr ocessor Performance                     
     Measur ement Instrumentation, IEEE Computer, pp. 6375, Sept. 1990.                                  
[7]  D. A. Reed et al., The Pablo Performance Analysis Envir onment, T ech. Rep., Dept. of               
     Comput. Sci., Univ. of Illinois, Nov. 1992.                                                           
[8]  A. Mink and R. J. Carpenter , Operating Principles of MultiKr on Performance                         
     Instr umentation for MIMD Computers, T ech. Rep. NISTIR 4737, National Institute of                  
     Standar ds and Technology, Mar. 1992.                                                                 
[9]  D. Reese and E. Luke, Object Oriented Fortran for Development of Portable Parallel                   
     Programs, in Proc. 3rd IEEE Symp. Parallel Distrbuted Processing, December 1991, pp. 608615.        
[10] D. A. Reed, Distributed Memory W orking Gr oup Summary , in Instrumentation for Future              
     Parallel Computing Systems, ed. M. Simmons, R. Koskela, and Ingrid Bucher, New York:  ACM             
     Press, 1989, pp. 239250.                                                                             
[11] B. P. Miller et al., IPS2:  The Second Generation of a Parallel Program Measur ement System,       
     IEEE Trans. Parallel Distrib. Syst., vol. 1, no. 2, pp. 206217, Apr. 1990.                           
[12] C. Alexander, D. Reese, and J. Harden, NearCritical Path Analysis of Pr ogram Activity              
     Graphs, Proc. IEEE MASCOTS`94, Jan. 31  Feb. 2, 1994.                                               
[13] D. L. Whitfield and M. J. Janus, Three Dimensional Unsteady Euler Equations Solution Using           
     Flux Vector Splitting, AIAA Paper 841552, June 1984.                                                
[14] MPI: A MessagePassing Interface Standar d, Tech. Report CS94230, Univ. of Tennessee,             
     Knoxville, TN, May 5, 1994. (To appear in the International Journal of Super computing                
     Applications, Vol. 8, No. 3/4, 1994, url=ftp://netlib2.cs.utk.edu/mpi/mpi_report.ps)