linux-mips
[Top] [All Lists]

Re: [SPAM?] Re: [PATCH] mm/pg-r4k.c: Dump the generated code

To: "Maciej W. Rozycki" <macro@linux-mips.org>
Subject: Re: [SPAM?] Re: [PATCH] mm/pg-r4k.c: Dump the generated code
From: Nigel Stephens <nigel@mips.com>
Date: Wed, 10 Oct 2007 13:08:46 +0100
Cc: Franck Bui-Huu <vagabon.xyz@gmail.com>, Ralf Baechle <ralf@linux-mips.org>, Thiemo Seufer <ths@networkno.de>, linux-mips@linux-mips.org
In-reply-to: <Pine.LNX.4.64N.0710101231290.9821@blysk.ds.pg.gda.pl>
Organization: MIPS Technologies
Original-recipient: rfc822;linux-mips@linux-mips.org
References: <Pine.LNX.4.64N.0710021447470.32726@blysk.ds.pg.gda.pl> <20071002141125.GC16772@networkno.de> <20071002154918.GA11312@linux-mips.org> <47038874.9050704@gmail.com> <20071003131158.GL16772@networkno.de> <4703F155.4000301@gmail.com> <20071003201800.GP16772@networkno.de> <47049734.6050802@gmail.com> <20071004121557.GA28928@linux-mips.org> <4705004C.5000705@gmail.com> <Pine.LNX.4.64N.0710041616570.10573@blysk.ds.pg.gda.pl> <4705EFE5.7090704@gmail.com> <Pine.LNX.4.64N.0710051312490.17849@blysk.ds.pg.gda.pl> <470A4349.9090301@gmail.com> <Pine.LNX.4.64N.0710081611460.8873@blysk.ds.pg.gda.pl> <470BE1F4.3070800@gmail.com> <Pine.LNX.4.64N.0710101231290.9821@blysk.ds.pg.gda.pl>
Sender: linux-mips-bounce@linux-mips.org
User-agent: IceDove 1.5.0.12 (X11/20070606)


Maciej W. Rozycki wrote:
On Tue, 9 Oct 2007, Franck Bui-Huu wrote:

What would be the gain for the kernel from using "-march=4ksd" rather than "-march=mips32r2"?

It actually results in a kernel image ~30kbytes smaller for the former
case. It has been discussed sometimes ago on this list. I'm sorry but
I don't know why...

Perhaps the pipeline description for the 4KSd CPU is different from the default for the MIPS32r2 ISA. Barring a study of GCC sources, if that really troubles you, you could build the same version of the kernel with these options:

1. "-march=mips32r2"

2. "-march=4ksd"

3. "-march=mips32r2 -mtune=4ksd"

and compare the results.



I expect the results of #2 and #3 to be the same and it would just back up my suggestion about keeping CPU-specific optimisations separate from the CPU selection.

Actually the -march=4ksd option will allow gcc to use of the SmartMIPS lwxs (indexed load) instruction, which could save a few instructions here and there.


Please also note that our optimisation model is for speed (-O2) rather than size (-Os), so if "-mtune=4ksd" yields smaller code than "-mtune=mips32r2", it just means it is safe for this CPU to shrink code where appropriate without losing performance. One obvious place for such a choice is the use of the hardware multiplier vs shifts and additions where one multiplicand is a constant.


Yes, that's also worth testing.

Nigel

<Prev in Thread] Current Thread [Next in Thread>