[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH 1/9] TCG "sync" op
From: |
Ulrich Hecht |
Subject: |
Re: [Qemu-devel] [PATCH 1/9] TCG "sync" op |
Date: |
Mon, 19 Oct 2009 19:17:33 +0200 |
User-agent: |
KMail/1.9.10 |
On Friday 16 October 2009, Aurelien Jarno wrote:
> This example is a bit biased, as registers are only saved, and never
> reused. Let's comment on it though.
Yeah, well, I searched from the top for the first case where it makes a
difference. If it's of any help, I can upload a complete dump of both
versions somewhere.
> and I don't understand what is the gain compared to
> the use of tcg_gen_ld/st.
There are two sets of TCG values, tcgregs (which would arguably better
called tcgregs64) and tcgregs32. When doing a 32-bit access, tcgregs(64)
is synced, which is a nop if tcgregs(64) hasn't been touched. When doing
a 64-bit access, tcgregs32 is synced, which is a nop if tcgregs32 hasn't
been touched. In practice, 32-bit accesses followed by 64-bit accesses
and vice versa are very rare, so in most cases, sync is a nop.
tcg_gen_ld/st is never a nop. That's the benefit.
CU
Uli
--
SUSE LINUX Products GmbH, GF: Markus Rex, HRB 16746 (AG Nürnberg)
- [Qemu-devel] [PATCH 7/9] linux-user: dup3, fallocate syscalls, (continued)
- Re: [Qemu-devel] [PATCH 3/9] S/390 host/target build system support, Aurelien Jarno, 2009/10/17
- Re: [Qemu-devel] [PATCH 2/9] S/390 CPU emulation, Aurelien Jarno, 2009/10/17
- Re: [Qemu-devel] [PATCH 2/9] S/390 CPU emulation, Ulrich Hecht, 2009/10/19
- Re: [Qemu-devel] [PATCH 2/9] S/390 CPU emulation, Aurelien Jarno, 2009/10/22
Re: [Qemu-devel] [PATCH 1/9] TCG "sync" op, Aurelien Jarno, 2009/10/16
Re: [Qemu-devel] [PATCH 1/9] TCG "sync" op, Edgar E. Iglesias, 2009/10/17
Re: [Qemu-devel] [PATCH 1/9] TCG "sync" op, Ulrich Hecht, 2009/10/19