From: leathm AT solwarra DOT gbrmpa DOT gov DOT au (Leath Muller)
Message-Id: <199612261157.VAA25999@solwarra.gbrmpa.gov.au>
Subject: Re: Is DJGPP that efficient?
To: junk AT defeating DOT email DOT address
Date: Thu, 26 Dec 1996 21:57:01 +1000 (EST)
Cc: djgpp AT delorie DOT com
In-Reply-To: <aJQDsHAZs4uyEwDL@chocolat.foobar.co.uk> from "Paul Shirley" at Dec 21, 96 07:00:41 am
Content-Type: text

> The P5 has a 3 clk latency (the time it takes from issue to retiring an
> op), a throughput (the time before another op can be issued) of 1 clk
> *unless* you issue consecutive multiplies when is has a 2 clk
> throughput.

I thought that was then Pentium Pro which could only perform a fmul
every other cycle and the pentium could keep going every cycle. I will
check this... :)
 
> AFAIK you can achieve a maximum multiply throughput of 2clks/mul.
> However in real code you have to actually load the next operand or sum
> the result which eats up that otherwise wasted cycle. The gcc fpu code
> is actually pretty good.

If you use fxch, you should be able to get a much better throughput than
gcc can provide...

Leathal.