Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!tut.cis.ohio-state.edu!ucbvax!pasteur!ames!think!barmar
From: barmar@think.COM (Barry Margolin)
Newsgroups: comp.arch
Subject: Re: Context switch tasks
Message-ID: <36507@think.UUCP>
Date: 19 Feb 89 03:55:22 GMT
References: <788@atanasoff.cs.iastate.edu> <497@pyuxf.UUCP>
Sender: news@think.UUCP
Reply-To: barmar@kulla.think.com.UUCP (Barry Margolin)
Organization: Thinking Machines Corporation, Cambridge, MA
Lines: 26

In article <497@pyuxf.UUCP> asg@pyuxf.UUCP (alan geller) writes:
>My office-mate and I were both curious about these things, so we took
>a walk through the scheduler code.  After recoiling in disgust, we
>rewrote the scheduler (from scratch, mostly in assembler, rather than
>the 90% C it was delivered in), and got an enormous (5x to 20x measured)
>performance improvement.

Why was it necessary to rewrite it in assembler?  From your
description of the improvements you made, they mostly seemed to be at
the algorithm level, not the implementation level.  It's true that you
used some nice instructions in the implementation of the run queues
(which, by the way, seemed alot like the Multics run queues), but you
could have done that by writing a small number of assembly
subroutines.  And it's not clear how important those special
instructions actually are to your code; I'm not really familiar with
the Vax, but I suspect that their primary benefit is in user code
operating on shared memory, because they are indivisible operations.
They're probably not a whole lot faster than the corresponding C code.



Barry Margolin
Thinking Machines Corp.

barmar@think.com
{uunet,harvard}!think!barmar