Changes between Version 1 and Version 2 of Ticket #1619


Ignore:
Timestamp:
Mar 27, 2012 1:28:18 PM (2 years ago)
Author:
rrnewton
Comment:

Legend:

Unmodified
Added
Removed
Modified
  • Ticket #1619 – Description

    v1 v2  
    33The problem is that aggregate data for an entire execution is rather coarse. It's not correlated temporally with phases of program execution, nor are specific measured phenomena related to anything in the Haskell source. 
    44 
    5 This could be improved. A simple example would be to measure memory-reuse distance (an architecture-independent characterization of locality) but to distinguish garbage collection from normal memory access. It would be quite nice to 
     5This could be improved. A simple example would be to measure memory-reuse distance (an architecture-independent characterization of locality) but to distinguish garbage collection from normal memory access. It would be quite nice to see a histogram of reuse-distances in which GC accesses appear as a separate layer (different color) from normal accesses. 
    66 
    77How to go about this? Fortunately, the existing MICA pintool can build today (v0.4) and measure memory reuse distances.  
     
    3333== Interested Students (Include enough identifying info to find/reach you!) == 
    3434 
    35