27 Oct
2018
27 Oct
'18
11:02 a.m.
On 10/26/18 6:10 AM, Gordon Henderson via cctalk wrote:
However it was a royal PITA to code for although a
32-bit CPU, it would
read memory 64 bits at a time (actually 128 IIRC to satisfy the cache),
with half that 64-bit word being an instruction for the integer unit and
half for the floating point unit, so you effectively had to build a
floating point pipeline by hand coded instructions, so 8 (I think)
instructions to load the pipeline, then each subsequent instruction
would feed another value into the pipe, then another 8 at the end to
empty it. Great for big matrix operations, rubbish for a single add of 2
FP numbers.
My impression of the i860 was that it might have been fun for about 2
weeks for which to code assembly, but after that, you'd really start
looking hard for an HLL to do the dirty work for you. While there's a
sense of accomplishment over looking at a page of painfully
hand-optimized code that manages to keep everything busy with no
"bubbles", you begin to wonder if there isn't a better way to spend your
life.
--Chuck