qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Paolo Bonzini <pbonzini@redhat.com>
To: Eduardo Habkost <ehabkost@redhat.com>
Cc: kvm@vger.kernel.org, "Michael S. Tsirkin" <mst@redhat.com>,
	"Marcelo Tosatti" <mtosatti@redhat.com>,
	qemu-devel@nongnu.org, "Vadim Rozenfeld" <vrozenfe@redhat.com>,
	"Chao Peng" <chao.p.peng@linux.intel.com>,
	"Laszlo Ersek" <lersek@redhat.com>,
	"Andreas Färber" <afaerber@suse.de>
Subject: Re: [Qemu-devel] [PATCH] target-i386: add Intel AVX-512 support
Date: Mon, 27 Oct 2014 16:53:01 +0100	[thread overview]
Message-ID: <544E6A5D.5060406@redhat.com> (raw)
In-Reply-To: <20141027154854.GA10848@thinpad.lan.raisama.net>



On 10/27/2014 04:48 PM, Eduardo Habkost wrote:
> On Fri, Oct 24, 2014 at 07:55:10AM +0200, Paolo Bonzini wrote:
> [...]
>> I think we can keep the macros.  The actual cleanup would be to have a
>> single member for the 32 512-bit ZMM registers, instead of splitting
>> xmm/ymmh/zmmh/zmm_hi16.  This will get rid of the YMM_* and ZMM_*
>> registers.  However, we could not use simple memcpy()s to marshal in and
>> out of the XSAVE data.  We can do it in 2.2.
> 
> Now, about the actual 2.3 plans: I believe the xmm/ymmh/zmmh/zmm_hi16
> separation actually makes the code simpler, because the only code
> touching those registers inside QEMU is xsave/vmstate state
> loading/saving, where the bits of the ZMM registers are split into
> different sections/fields exactly in the same way.
> 
> We can still eliminate the YMM_* and ZMM_* macros while keeping
> xmm/ymmh/zmmh/zmm_hi16 as separate fields, and having a single zmm_regs
> member would just add unnecessary complexity to the
> XSAVE<->CPUX86State<->VMState translation code.
> 
> (But if one day TCG starts implementing AVX or AVX512, then it may be
> worthwhile to move the ZMM registers into a single field.)

Yes, exactly---or even sooner, if we start dumping the 256 or 512 byte
registers.  I think the current separation of xmm/ymmh/zmmh/zmm_hi16 is
a KVM-ism.

Let's see what the patches look like, once they are ready.

Paolo

  reply	other threads:[~2014-10-27 15:53 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-10-23  3:02 [Qemu-devel] [PATCH] target-i386: add Intel AVX-512 support Chao Peng
2014-10-23 14:34 ` Paolo Bonzini
2014-10-24 16:38   ` Eduardo Habkost
2014-10-23 19:49 ` Eduardo Habkost
2014-10-24  1:27   ` Chao Peng
2014-10-24  5:55     ` Paolo Bonzini
2014-10-24 11:12       ` Eduardo Habkost
2014-10-24 11:38         ` Paolo Bonzini
2014-10-27 15:48       ` Eduardo Habkost
2014-10-27 15:53         ` Paolo Bonzini [this message]
2014-10-24 16:01 ` Eduardo Habkost
2014-10-27  2:07   ` Chao Peng
2014-11-02 10:19 ` Michael S. Tsirkin
2014-11-03  1:53   ` Chao Peng
2014-11-03 11:31   ` Paolo Bonzini
2014-11-03 12:34     ` Michael S. Tsirkin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=544E6A5D.5060406@redhat.com \
    --to=pbonzini@redhat.com \
    --cc=afaerber@suse.de \
    --cc=chao.p.peng@linux.intel.com \
    --cc=ehabkost@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=lersek@redhat.com \
    --cc=mst@redhat.com \
    --cc=mtosatti@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=vrozenfe@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).