Changes between Version 10 and Version 11 of DynamicByDefault


Ignore:
Timestamp:
Nov 24, 2012 4:05:54 PM (2 years ago)
Author:
igloo
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • DynamicByDefault

    v10 v11  
    11 
    2 OS X 64bit 
     2= Dynamic by default = 
    33 
    4 http://lambda.haskell.org/~igloo/dynamic-by-default/nofib-osx-x86_64.html 
     4== Performance == 
    55 
    6 OS X 32bit 
     6Full nofib results showing the effect of switching to dynamic-by-default are available for  
     7[http://lambda.haskell.org/~igloo/dynamic-by-default/nofib-osx-x86_64.html OS X 64bit], 
     8[http://lambda.haskell.org/~igloo/dynamic-by-default/nofib-osx-x86.html OS X 32bit], 
     9[http://lambda.haskell.org/~igloo/dynamic-by-default/nofib-linux-x86_64.html Linux 64bit] and 
     10[http://lambda.haskell.org/~igloo/dynamic-by-default/nofib-linux-x86.html Linux 32bit]. There is also a table of the highlights below. In summary: 
    711 
    8 http://lambda.haskell.org/~igloo/dynamic-by-default/nofib-osx-x86.html 
     12Binary sizes are way down across the board, as we are now dynamically linking to the libraries. 
    913 
    10 Linux 64bit 
     14Things are rosiest on OS X 64bit. On this platform, `-fPIC` is always on, so using dynamic libraries doesn't mean giving up a register for PIC. Overall, performance is a few percent ''better'' with dynamic by default. 
    1115 
    12 http://lambda.haskell.org/~igloo/dynamic-by-default/nofib-linux-x86_64.html 
     16On OS X 32bit, the situation is not so nice. On x86 we are very short on registers, and giving up another for PIC means we end up around 15% down on performance. 
    1317 
    14 Linux 32bit 
     18On Linux 64bit we have more registers, so the effect of giving one up for PIC isn't so pronounced, but we still lose a few percent performance overall. 
    1519 
    16 http://lambda.haskell.org/~igloo/dynamic-by-default/nofib-linux-x86.html 
    17  
    18  
    19  
    20  
     20For unknown reasons, 32bit Linux suffers even worse than 32bit OS X, with around a 30% performance penalty. 
    2121 
    2222{{{