Messages in this thread | | | Date | Sat, 13 Nov 1999 00:30:24 +0100 | From | Andreas Bombe <> | Subject | [OT] Computers from Mars (was: Re: le32_to_cpu() help...) |
| |
On Thu, Nov 11, 1999 at 02:35:47PM +0100, Tor Arntsen wrote: > In article <fa.h6it7ov.a3gc3l@ifi.uio.no>, > hpa@transmeta.com (H. Peter Anvin) writes: > >Both macros do the same thing on all *currently supported* > >architectures. One never know when a funny thing from Mars shows up; > >perhaps a 48-bit architecture, who knows... > > Norsk Data ND-10 and ND-100 minicomputers could be ordered in a special > version where single-precision floating point registers were 48 bits > instead of 32 bits (double-precision were always 64 bits). > Worked rather nicely actually :-) > > Ah, and integer word size was 16 bits.
Bah, floating point register sizes don't count. They usually are bigger than CPU word size and have strange sizes. Motorola 68k floating point regs are 80 bits long while the CPU itself is a 32 bit architecture.
-- Andreas E. Bombe <andreas.bombe@munich.netsurf.de> http://home.pages.de/~andreas.bombe/ RSA 0x886663c9 30 EC 09 73 84 7B 55 83 C4 7A 91 D9 9D C5 4B B0 DSA 0x04880A44 72E5 7031 4414 2EB6 F6B4 4CBD 1181 7032 0488 0A44
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |