kvm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Bandan Das <bsd@redhat.com>
To: kvm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, Paolo Bonzini <pbonzini@redhat.com>
Subject: [RFC PATCH 0/2] Emulator speedups - avoid initializations where possible
Date: Thu,  3 Apr 2014 18:27:48 -0400	[thread overview]
Message-ID: <1396564070-5586-1-git-send-email-bsd@redhat.com> (raw)

While initializing emulation context structure, kvm memsets to 0 a 
number of fields some of which are redundant since they get set eventually.
This patch attempts at avoiding some of them.

Here are some before/after numbers on a Haswell host
Note : The before numbers already include Paolo's RFC posted here :
http://comments.gmane.org/gmane.linux.kernel/1676101

Before:
667 cycles/emulated jump instruction
839 cycles/emulated move instruction
892 cycles/emulated arithmetic instruction
995 cycles/emulated memory load instruction
1026 cycles/emulated memory store instruction
1022 cycles/emulated memory RMW instruction

After:
639 cycles/emulated jump instruction
786 cycles/emulated move instruction
802 cycles/emulated arithmetic instruction
936 cycles/emulated memory load instruction
970 cycles/emulated memory store instruction
1000 cycles/emulated memory RMW instruction

Bandan Das (2):
  KVM: emulate: move init_decode_cache to emulate.c
  KVM: emulate: clean up initializations in init_decode_cache

 arch/x86/include/asm/kvm_emulate.h | 17 +++++++------
 arch/x86/kvm/emulate.c             | 49 ++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/x86.c                 | 13 ----------
 3 files changed, 59 insertions(+), 20 deletions(-)

-- 
1.8.3.1

             reply	other threads:[~2014-04-03 22:27 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-04-03 22:27 Bandan Das [this message]
2014-04-03 22:27 ` [RFC PATCH 1/2] KVM: emulate: move init_decode_cache to emulate.c Bandan Das
2014-04-03 22:27 ` [RFC PATCH 2/2] KVM: emulate: clean up initializations in init_decode_cache Bandan Das
2014-04-04  9:47   ` Paolo Bonzini

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=1396564070-5586-1-git-send-email-bsd@redhat.com \
    --to=bsd@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pbonzini@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).