[Webkit-unassigned] [Bug 169984] New: [jsc][mips] study whether using SYNC_MB for memoryFence/storeFence works and improves performances

[bugzilla-daemon at webkit.org]

https://bugs.webkit.org/show_bug.cgi?id=169984

            Bug ID: 169984
           Summary: [jsc][mips] study whether using SYNC_MB for
                    memoryFence/storeFence works and improves performances
           Product: WebKit
           Version: Other
          Hardware: Other
                OS: Linux
            Status: NEW
          Severity: Normal
          Priority: P2
         Component: JavaScriptCore
          Assignee: webkit-unassigned at lists.webkit.org
          Reporter: guijemont at igalia.com

For MacroAssemblerMIPS::memoryFence() and ::storeFence(), we use a sync instruction with SYNC (0) in the stype field. We should check whether the optional SYNC_MB (0x10) stype can work for our needs. It is defined as forcing the order of memory accesses, but unlike SYNC, SYNC_MB does not require all older instructions to be completed when the sync instruction completes, but only that they reach the load/store ordering point before the sync instruction completes, which is a slightly lighter constraint that should still be good enough for us, while potentially having a lower performance hit.

-- 
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.webkit.org/pipermail/webkit-unassigned/attachments/20170323/f164b8a3/attachment.html>