[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-arm] about armv8's prefetch decode
From: |
Ori Chalak (A) |
Subject: |
Re: [Qemu-arm] about armv8's prefetch decode |
Date: |
Fri, 24 Mar 2017 08:59:29 +0000 |
Hi Peter,
Indeed, prefetch instruction affects only the micro architecture, and hence not
needed for running correctly the generated code.
However, we developed a performance simulator for a detailed ARMv8 CPU model,
and use Qemu to resolve the functionality.
And for this purpose we need to translate all instructions that may affect the
pipeline behavior, caches, etc.
This is not the major usage of Qemu, however there may be others doing this and
it may help them.
http://www.linux-kvm.org/images/4/45/01x09-Christopher_Covington-Using_Upstream_QEMU_for_CASS.pdf
Regards,
Ori Chalak
-----Original Message-----
From: Peter Maydell [mailto:address@hidden
Sent: Thursday, March 23, 2017 7:05 PM
To: Wangjintang
Cc: qemu-arm; Shlomo Pongratz (A); Ori Chalak (A)
Subject: Re: [Qemu-arm] about armv8's prefetch decode
On 20 March 2017 at 06:35, Wangjintang <address@hidden> wrote:
> We see that armv8's prefetch instruction decode have been
> skipped in qemu. For some user, they need prefetch instruction, for
> example, they use qemu to generate the instruction trace.
> We want to merge this patch to community, it's ok or not? Thanks.
It would be helpful if you could be more precise about what is missing and what
goes wrong (eg which instructions we mishandle). In general I believe that we
do correctly handle the various prefetch instructions. They don't need to
generate any intermediate code, of course, because prefetch is just a hint.
It's possible we got the decode wrong for some subset of them.
thanks
-- PMM
Re: [Qemu-arm] about armv8's prefetch decode, Peter Maydell, 2017/03/23