That was an error on my side. The wrong memory model had gotten cached
in a generated make script. Lets drop membar_leon3 also then :)
On 2014-07-11 11:15, Eric Botcazou wrote:
The full barrier pattern membar_leon3 also gets generated so I think
that one should be kept also.
Do you have a testcase? membar is generated by sparc_emit_membar_for_model
and, for the TSO model of LEON3, implied = StoreStore | LoadLoad | LoadStore
so mm can only be StoreLoad, which means that membar_storeload will match so
the full barrier never will.