2 Mar
2021
2 Mar
'21
10:37 a.m.
On Mar 2, 2021, at 4:06 AM, Peter Corlett via cctalk
<cctalk at classiccmp.org> wrote:
On Mon, Mar 01, 2021 at 10:40:41PM -0800, Boris Gimbarzevsky via cctalk wrote:
[...]
If I remember correctly the Apple PowerMac G4 was touted as the first Consumer system
capable of GFLOPS. The G4/450 when released, was an amazing system, but it was very
quickly left in the dust.
Floating Point Systems was a few miles away from where I live. A couple weeks ago, we
drove by there, and I noticed that at least the main office building is still there. I
used to work with a couple of people that had worked there. Years ago I found one of the
Array Processors at Wacky Willies, I didn?t get it, but I did get the PDP-11/44 manual
that was with it. I think I might have a VAX tape around here for one of their Array
Processors.
Zane
Out of curiousity, decided to benchmark one of my
old, really cheap PC
laptops that got in 2010 and it managed 30 Mflops using double precision
arithmetic. 10 Mflop performance no longer as impressive as it used to be.
I'll say. Modern kit gets 1 FLOPS per MHz per core, give or take an order of
magnitude depending on the specific architecture. That machine must have
been appallingly bad to only manage 30 MFLOPS. Although perhaps you meant
GFLOPS, in which case it sounds about right.
The Haswell CPU in my 2014-vintage laptop manages "up to" 147 GFLOPS. Which
is an order of magnitude slower than its GPU. Useful FLOPS for scientific
computing rather than contrived numbers for benchmarking may well lose an
order of magnitude or two in overhead, but it's still not hanging about.