kvn [Mon, 01 Feb 2010 16:49:49 -0800] rev 4754
6614597: Performance variability in jvm2008 xml.validation
Summary: Fix incorrect marking of methods as not compilable.
Reviewed-by: never
twisti [Mon, 01 Feb 2010 23:18:47 +0100] rev 4753
6921799: JSR 292 call sites should not be fixed-up
Summary: MethodHandle invoke call sites should not be fixed-up by SharedRuntime::fixup_callers_callsite as c2i/i2c adapters are used to implement MethodHandle actions.
Reviewed-by: kvn, never
twisti [Mon, 01 Feb 2010 19:29:46 +0100] rev 4752
6921352: JSR 292 needs its own deopt handler
Summary: We need to introduce a new MH deopt handler so we can easily determine if the deopt happened at a MH call site or not.
Reviewed-by: never, jrose
never [Fri, 29 Jan 2010 22:51:41 -0800] rev 4751
6916644: C2 compiler crash on x86
Reviewed-by: kvn, twisti
kvn [Fri, 29 Jan 2010 09:27:22 -0800] rev 4750
4360113: Evict nmethods when code cache gets full
Summary: Speculatively unload the oldest nmethods when code cache gets full.
Reviewed-by: never, kvn
Contributed-by: eric.caspole@amd.com
twisti [Fri, 29 Jan 2010 08:33:24 -0800] rev 4749
6921339: backout 6917766
Reviewed-by: mr
twisti [Fri, 29 Jan 2010 12:13:05 +0100] rev 4748
6917766: JSR 292 needs its own deopt handler
Summary: We need to introduce a new MH deopt handler so we can easily determine if the deopt happened at a MH call site or not.
Reviewed-by: never, jrose
never [Thu, 28 Jan 2010 20:41:37 -0800] rev 4747
6792161: assert("No dead instructions after post-alloc")
Reviewed-by: kvn
never [Thu, 28 Jan 2010 16:28:28 -0800] rev 4746
6920346: G1: "must avoid base_memory and AliasIdxTop"
Reviewed-by: kvn
twisti [Thu, 28 Jan 2010 08:36:34 -0800] rev 4745
6920970: Zero build fixes after 6849984 and 6911204
Summary: Two recent commits broke the build on Zero.
Reviewed-by: twisti
Contributed-by: Gary Benson <gbenson@redhat.com>
ysr [Wed, 27 Jan 2010 22:38:37 -0800] rev 4744
Merge
ysr [Tue, 26 Jan 2010 23:36:11 -0800] rev 4743
Merge
ysr [Tue, 26 Jan 2010 16:52:29 -0800] rev 4742
6920090: G1: Disable ReduceInitialCardMarks at least until 6920109 is fixed
Summary: G1 now answers "no" to the query can_elide_initializing_store_barrier() in the product build. A debug flag allows alternate behaviour in debug builds.
Reviewed-by: iveresov, tonyp
tonyp [Mon, 25 Jan 2010 18:03:29 -0500] rev 4741
6919980: G1: remove +UseG1GC from under experimental options (second attempt)
Summary: Trying this again, as the original change was lost.
Reviewed-by: ysr, jmasa
apetrusenko [Thu, 21 Jan 2010 18:51:10 -0800] rev 4740
6918006: G1: spill space must be reserved on the stack for barrier calls on Windows x64
Summary: Stub code generated to call G1 barriers does not allocate spill space on the stack as required by Windows x64 ABI. The fix is to use more ABI-friendly call_VM_leaf().
Reviewed-by: iveresov, never, kvn