[prev in list] [next in list] [prev in thread] [next in thread] 

List:       openembedded-core
Subject:    Re: [OE-core] [PATCH] qemumips: Use 34Kf CPU emulation
From:       "Khem Raj" <raj.khem () gmail ! com>
Date:       2020-07-29 17:58:24
Message-ID: CAMKF1spTG7P72GKL9hZF-RkPRKyZ4557KeQidMLVCrnGKFw_sA () mail ! gmail ! com
[Download RAW message or body]

On Wed, Jul 29, 2020 at 3:13 AM Richard Purdie
<richard.purdie@linuxfoundation.org> wrote:
>
> On Wed, 2020-07-29 at 10:56 +0100, Richard Purdie via
> lists.openembedded.org wrote:
> > On Tue, 2020-07-28 at 19:28 -0700, Khem Raj wrote:
> > > Few years ago we switched to using mips32r2 tunings for qemumips
> > > however
> > > the default CPU emulation still remained 24Kf which is not optimal
> > > for
> > > mips32r2 ISA for qemu [1], therefore switch to recommended 32Kf for
> > > CPU
> > > emulation when running qemu in system mode
> > >
> > > Boot time to console is ~1s faster with this setting, hopefully
> > > this
> > > should speed up qemumips in general
> > >
> > > [1]
> > > https://www.qemu.org/docs/master/system/target-mips.html#preferred-cpu-models-for-mips-hosts
> > >
> > > Signed-off-by: Khem Raj <raj.khem@gmail.com>
> > > ---
> > >  meta/conf/machine/qemumips.conf | 2 ++
> > >  1 file changed, 2 insertions(+)
> > >
> > > diff --git a/meta/conf/machine/qemumips.conf
> > > b/meta/conf/machine/qemumips.conf
> > > index 31ad754483..4617c3c7b6 100644
> > > --- a/meta/conf/machine/qemumips.conf
> > > +++ b/meta/conf/machine/qemumips.conf
> > > @@ -12,3 +12,5 @@ KERNEL_ALT_IMAGETYPE = "vmlinux.bin"
> > >  SERIAL_CONSOLES ?= "115200;ttyS0 115200;ttyS1"
> > >
> > >  QB_SYSTEM_NAME = "qemu-system-mips"
> > > +
> > > +QB_CPU = "-cpu 34Kf"
> >
> > Thanks!
> >
> > I did run some tests locally, timing core-image-sato -c testimage
> > before and after this change. It took 999s before, 1018s after but
> > the difference looks like noise rather than any speedup or slowdown.
>
> Another try at "after" got 986s so who knows :)
>

Yeah I saw that first boot was slower but reboots were always 1s
faster, but hopefully it
will help with irregular timeouts on tests which is what we are looking for.

> Cheers,
>
> Richard
>


-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.

View/Reply Online (#141101): https://lists.openembedded.org/g/openembedded-core/message/141101
Mute This Topic: https://lists.openembedded.org/mt/75857901/4454766
Group Owner: openembedded-core+owner@lists.openembedded.org
Unsubscribe: https://lists.openembedded.org/g/openembedded-core/unsub  [openembedded-core@marc.info]
-=-=-=-=-=-=-=-=-=-=-=-


[prev in list] [next in list] [prev in thread] [next in thread]