[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [RFC PATCH V7 00/19] Multithread TCG.
From: |
Benjamin Herrenschmidt |
Subject: |
Re: [Qemu-devel] [RFC PATCH V7 00/19] Multithread TCG. |
Date: |
Tue, 11 Aug 2015 20:09:16 +1000 |
On Tue, 2015-08-11 at 10:29 +0100, Peter Maydell wrote:
> Is it possible in some of these combinations to use the load-acquire
> and store-release instructions rather than explicit barriers?
> (ARMv8 has those, which I think should be slightly less heavyweight
> than explicit barriers everywhere, if the semantics line up.)
Possibly though I suppose starting with a simple barrier and then adding
more fine-grained ones to TCG might be a workable path. IE, it shouldn't
be too hard.
The problem of course is that not 2 architecture have exactly the same
semantics :-)
Cheers,
Ben.
- [Qemu-devel] [RFC PATCH V7 19/19] target-arm/psci.c: wake up sleeping CPUs (MTTCG), (continued)
Re: [Qemu-devel] [RFC PATCH V7 00/19] Multithread TCG., Paolo Bonzini, 2015/08/11