RFR: 8351997: AArch64: Interpreter volatile reference stores with G1 are not sequentially consistent
Andrew Haley
aph at openjdk.org
Wed May 28 14:32:53 UTC 2025
On Wed, 28 May 2025 14:15:43 GMT, Erik Österlund <eosterlund at openjdk.org> wrote:
> This extra leading fence on volatile loads when C2 is available masked the lack of trailing fence on the store side. Therefore, the Dekker duality in the test that hung worked out anyway then.
Ha, yes. It's a funny old world. For what it's worth, I wanted to use seq cst loads and stores for all volatile accesses in the interpreter, but I was talked out of it.
-------------
PR Comment: https://git.openjdk.org/jdk/pull/25483#issuecomment-2916569792
More information about the hotspot-runtime-dev
mailing list