[RFC] Fix full memory barrier on SPARC-V8
David Miller
davem@davemloft.net
Tue Jun 28 05:54:00 GMT 2011
From: Geert Bosch <bosch@adacore.com>
Date: Mon, 27 Jun 2011 22:21:47 -0400
> On Jun 27, 2011, at 19:53, David Miller wrote:
>
>> Adding a ldstub here is going to be really expensive, on UltraSparc
>> that can be 36+ cycles even on a cache hit.
>
> Yes, synchronization in multi-CPU systems is expensive.
> If it's really cheap, you're probably doing something wrong.
First, I fundamentally disagree with this assertion. The reason
proper memory barriers exist is so that you don't need nonsense like
these proposed atomics to get proper memory operation ordering.
A proper membar on your v9 test system is orders of magnitude cheaper
than this stbar+ldstub business.
You then go on to speak about LEON, does LEON implement PSO?
More information about the Gcc-patches
mailing list