|
Authored by: feldegast on Friday, March 29 2013 @ 05:08 PM EDT |
80487DX -> 80486DX
the processors were 8086, 8088, 80286, 80386 (sx and dx) and 80486 (sx and dx)
the math co-processors always ended in 7 but never the CPUs for that vintage and
class
---
IANAL
My posts are ©2004-2013 and released under the Creative Commons License
Attribution-Noncommercial 2.0
P.J. has permission for commercial use.[ Reply to This | Parent | # ]
|
- a minor nit - Authored by: Anonymous on Sunday, March 31 2013 @ 12:33 PM EDT
- a minor nit - Authored by: Anonymous on Tuesday, April 02 2013 @ 03:24 AM EDT
|
Authored by: Anonymous on Saturday, March 30 2013 @ 06:19 PM EDT |
Actually, the Linux kernel includes FPU emulation so that it can run on a 486 SX
unless that was removed recently along with 386 support. Of course, hardly
anybody actually uses software FPU emulation anymore as 486 DX or Pentium 1
systems are pretty much free.[ Reply to This | Parent | # ]
|
|
Authored by: tiger99 on Sunday, March 31 2013 @ 04:36 AM EDT |
Intel turned out their first CPU in about 1972, and that was the 4 bit 4004,
which could be used to perforn decimal arithmetic one digit at a time, which is
why it was designed. However that is hardly relevant. Unix was created in
1969, on a PDP-7 and soon on a PDP-11. Now many PDP-11 models had floating point
hardware, and at some fairly early stage, possibly when the kernel was re-coded
in C, floating point libraries appeared, which would inevitably have included
rounding algorithms. I don't know the exact date. But before that were
mainframes...... This MUST have been done in the 1960s, if not even
earlier. Unlike a certain juror in a recent trial, we know that as far as
patents are concerned, things do read across from one computing environment to
another, and it did not have to be on any kind of Intel architecture to be prior
art. It would have been routinely done before Intel existed. [ Reply to This | Parent | # ]
|
|
|
|
|