From: dewar@cs.nyu.edu (Robert Dewar)
Subject: Re: Fixed-point question
Date: 1995/04/07
Date: 1995-04-07T00:00:00+00:00 [thread overview]
Message-ID: <dewar.797306016@gnat> (raw)
In-Reply-To: EACHUS.95Apr7192319@spectre.mitre.org
On the Pentium, floating-point multiplication is faster than integer
multiplication, and this is a common pattern on modern RISC chips, where
the floating-point multiply is pipelined, but it is not considered worth
pipelining the integer multiply (and also, as I pointed out, you usually
have an extra shift for the fixed-point multiply).
As has been pointed out, there may be considerations of space in using
fixed-point, but there will be a time cost in the typical case.
next prev parent reply other threads:[~1995-04-07 0:00 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
1995-04-01 0:00 Fixed-point question Garlington KE
1995-04-06 0:00 ` Robert Dewar
1995-04-07 0:00 ` Robert I. Eachus
1995-04-07 0:00 ` Robert Dewar [this message]
1995-04-07 0:00 ` Garlington KE
1995-04-07 0:00 ` Robert Dewar
-- strict thread matches above, loose matches on Subject: below --
2015-06-26 13:20 Patrick Noffke
2015-06-26 16:56 ` Jeffrey R. Carter
2015-06-26 18:21 ` Patrick Noffke
2015-06-26 20:21 ` Anh Vo
2015-06-26 20:25 ` Jeffrey R. Carter
2015-06-27 2:55 ` Patrick Noffke
2015-06-26 23:14 ` Qun-Ying
2015-06-27 3:00 ` Patrick Noffke
2015-06-27 4:44 ` Jeffrey R. Carter
2015-06-27 17:59 ` Patrick Noffke
2015-06-27 18:38 ` Jeffrey R. Carter
2015-06-27 19:20 ` Bob Duff
2015-06-27 19:57 ` Jeffrey R. Carter
2015-06-27 20:42 ` Bob Duff
2015-06-28 11:39 ` Brian Drummond
2015-06-29 13:28 ` Patrick Noffke
2015-06-29 14:13 ` Bob Duff
2015-06-27 23:41 ` Anh Vo
replies disabled
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox