J.A. Magallon writes:
> On 20011126 n0ano@indstorage.com wrote:
>> Uh, what exactly do you think you have here? The I860 was a
>> completely new architecture that Intel dropped over 5 years
>> ago. I've got one running Unix SVR4 in my basement but you
>> can't buy an I860 motherboard today.
>>
>> (For the record the 860 was a great architecture for the time
>> and I'm still bitter that Intel dropped it but that's a different
>> story.)
>
> You are talking about intel i860 _processor_, and he asks about
> I860 chipset.
>
> BTW, I always desired to put my hands on an i860. It is the only real
> good chip by Intel (it really looked like a Moto...). The only ones
> I used were inside an HP Graphics accelerator on a 9000/385.
You people are insane, but hey, it'd be cool to have i860 Linux.
Maybe you don't realize just how unfit this chip is for normal
UNIX-like use.
It's a RISC chip with the Pentium MMU. To get any speed out of it,
you have to enable some strange features. First of all, you need
the double-instruction mode. In every 64-bit chunk of memory you
place 1 floating-point instruction and 1 integer instruction.
Second of all, you need to enable pipelined FPU operation. This is
an exposed pipeline, so watch out! Look what happens:
a = x + x
b = a + a <-- uses old value of "a", not x+x
nop
nop
nop
c = a + a
Yep, c!=a after this! Actually, "c" won't be set until a few
instructions later because it too is still in the pipeline.
You need a few dummy operations to push it out.
Now lets have a trap of some sort while that floating-point
pipeline is full. The chip leaves itself in a horrible messy
state that may well require thousands of lines of assembly
code to sort out. I'm not kidding.
The chip made a fine DSP. You could put a few dozen together
for radar.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Sat Dec 15 2001 - 21:00:14 EST