🚀 go-pugleaf

University of Colorado at Boulder
Department of Computer Science
ECOT 717 Engineering Center
Campus Box 430
Boulder, Colorado 803090430
(303) 492-7514, FAX: (303) 492-2844

CS COLLOQUIUM
Trace-File Compression Using Valve Predictors
Martin Burtscher
Cornell University
Wednesday, October 16, 2002
3:30 - 4:30 PM
Engineering Center Classroom 1B06

Trace files record the execution behavior of programs.  Unfortunately, 
nontrivial program traces tend to be very large and have to be compressed. 
While good compression schemes exist for traces that capture only the PCs 
of the executed instructions, these schemes are quite ineffective on traces 
that include additional information such as register values or effective 
addresses. Our novel value-predictor-based approach compresses this type of 
trace up to six times better.  Moreover, our approach includes several 
other desirable features such as a fixed memory requirement and a 
single-pass algorithm. This talk follows the design steps of our 
compression utility and illustrates how value predictors can be used to 
effectively compress program traces.

Host:  Amer Diwan
------------------------------
http://www.cs.colorado.edu/department/events/colloquia/colloquia.html

Sign Language Interpreters Available Upon Request.  Please contact 
Stephanie Morris, Department of Computer Science, Engineering  ECOT 722, 
303-492-6101, at least five days prior to the colloquium.

_______________________________________________
cscolloq mailing list
cscolloq@cs.colorado.edu
http://www.cs.colorado.edu/mailman/listinfo/cscolloq