[prev in list] [next in list] [prev in thread] [next in thread] 

List:       qemu-discuss
Subject:    simulation of aarch64 store-exclusive instructions with backoff in QEMU TCG mode
From:       Robert Henry <rrh.henry () gmail ! com>
Date:       2022-02-16 0:10:28
Message-ID: CAEYr_8kpVcTTvuCUPu1cEvnBZOGXB3hk7pj3pYTPqHTeRsPuJQ () mail ! gmail ! com
[Download RAW message or body]

I'm wondering if there is any prior art in changing the implementation of
the aarch64 store-exclusive instructions so that they fail with some
additional backoff protocol.  For example, if the store-exclusive
instruction were to succeed, then it will actually fail with a probability
of P, and thus forcing the surrounding aarch64 code to (typically) loop
back and redo the load-exclusive/store-exclusive sequence.

[Attachment #3 (text/html)]

<div dir="ltr">I&#39;m wondering if there is any prior art in changing the \
implementation of the aarch64 store-exclusive instructions so that they fail with \
some additional backoff protocol.   For example, if the store-exclusive instruction \
were to succeed, then it will actually fail with a probability of P, and thus forcing \
the surrounding aarch64 code to (typically) loop back and redo the \
load-exclusive/store-exclusive sequence.</div>



[prev in list] [next in list] [prev in thread] [next in thread]