From: linuxkaffee@gmx.net   
      
   Many modern compilers support packed instructions (also called SIMD).   
   However, languages like ANSI-C do not allow to express the data   
   parallelism explicitly. So, some compiler vendors provide intrinsic   
   functions that can be manually added into the source code and force   
   the compiler to generate packed instructions. However, the manual   
   insertion of these intrinsic functions makes the code not more   
   portable.   
      
   Do you know of any compiler source-to-source optimizations that   
   automatically analyse ANSI-C code, find opportunities for the   
   utilization of packed instructions and finally add them to the source   
   code that is passed in the next step to a compiler? If so, how do such   
   approaches work in general?   
      
   Best,   
   Stephan   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)