Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 16 Feb 2004 13:51:25 +0000
From:      Colin Percival <colin.percival@wadham.ox.ac.uk>
To:        Trent Nelson <trent@teleri.net>
Cc:        freebsd-hackers@freebsd.org
Subject:   Re: Branch prediction
Message-ID:  <6.0.1.1.1.20040216134828.0390bfa0@imap.sfu.ca>
In-Reply-To: <20040215164231.GA54709@teleri.net>
References:  <20040215164231.GA54709@teleri.net>

next in thread | previous in thread | raw e-mail | index | archive | help
At 16:42 15/02/2004, Trent Nelson wrote:
>does the old adage of "always predict
>false" still hold true the first time a branch is encountered?

   Most processors predict that forward branches are not taken,
and backward branches are taken (since backward branches occur
most often in loops).
   Of course, some processors now have hints (conditional-jump-
which-is-usually-taken, conditional-jump-which-is-usually-not-
taken, etc.)

Colin Percival




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?6.0.1.1.1.20040216134828.0390bfa0>