lkml.org 
[lkml]   [1998]   [May]   [29]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: Why all glibc2 programs are FPU programs
From
Date
Ulrich Drepper <drepper@cygnus.com> writes:

|> "Adam J. Richter" <adam@yggdrasil.com> writes:
|>
|> > On x86 On one other linux port?
|> > Is the default floating point mode
|> > different from IEEE? ? ?
|>
|>
|> For Intel the kernel use s0x37f, libc uses now 0x137f which is indeed
|> IEEE. But there are some other value used, as mentioned several times
|> now, for using 53bit mantissa. This would be 0x127f.
|>
|> For other platforms it'll become also important. Alpha has different
|> modes the FPU can run in and the PPC processors as well.

On the m68k both the kernel and libc use zero to get IEEE defaults.
Although the m68k port does not use lazy fpu switches it is still a win
not to touch the fpu unless necessary, because it makes context switches
cheaper.

--
Andreas Schwab "And now for something
schwab@issan.informatik.uni-dortmund.de completely different"
schwab@gnu.org

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu

\
 
 \ /
  Last update: 2005-03-22 13:42    [W:0.037 / U:0.192 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site