Seeing error in one test on ARM: org.openjdk.jcstress.tests.volatiles.ReadTwiceOverVolatileReadTest

[Aleksey Shipilev]

On 02/25/2017 11:40 AM, Andrew Haley wrote:
> On 23/02/17 14:35, Aleksey Shipilev wrote:
>> Yes. And JMM actually allows this result for plain memory ops, hence the test
>> grading fix. But it is suspicious to see this behavior on the actual hardware,
>> because hardware is supposed to exhibit "coherency": a single modification order
>> for a particular memory location. Reading x:1, and then x:0 is the evidence of
>> coherency violation. See JMMSample_03 for more discussion.
> 
> But such coherency violations should be flagged as INTERESTING, even
> if they are allowed, should they not?

Probably, depends on your vantage point :) I'll change in next round.

-Aleksey