RFR: In ASM SATB barrier, mov pre_val to c_rarg0 before call early, to protect c_rarg1

Aleksey Shipilev shade at redhat.com
Wed Jun 20 14:09:46 UTC 2018


On 06/20/2018 04:08 PM, Roman Kennke wrote:
> Am 20. Juni 2018 15:38:23 MESZ schrieb Aleksey Shipilev <shade at redhat.com>:
>> On 06/20/2018 02:45 PM, Roman Kennke wrote:
>>> http://cr.openjdk.java.net/~rkennke/c1-satb-regs/webrev.00/
>>
>> I verified with VerifyJCStress in my failing workload -- it passes.
>>
>> Minor nit: "smarged"?
>>  266   assert(thread != c_rarg0, "smarged arg");
> 
> You've never heard of 'smarged' ? It's like 'smashed', but Mordor-speak ;-)

Well, I looked it up in Urban Dictionary, and it was unsettling ;)
  https://www.urbandictionary.com/define.php?term=smarged

-Aleksey



More information about the shenandoah-dev mailing list