Mon, 01 Feb 2010 23:18:47 +0100 6921799: JSR 292 call sites should not be fixed-up
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
Mon, 01 Feb 2010 19:29:46 +0100 6921352: JSR 292 needs its own deopt handler
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
Fri, 29 Jan 2010 22:51:41 -0800 6916644: C2 compiler crash on x86
never [Fri, 29 Jan 2010 22:51:41 -0800] rev 4751
6916644: C2 compiler crash on x86 Reviewed-by: kvn, twisti
Fri, 29 Jan 2010 09:27:22 -0800 4360113: Evict nmethods when code cache gets full
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
Fri, 29 Jan 2010 08:33:24 -0800 6921339: backout 6917766
twisti [Fri, 29 Jan 2010 08:33:24 -0800] rev 4749
6921339: backout 6917766 Reviewed-by: mr
Fri, 29 Jan 2010 12:13:05 +0100 6917766: JSR 292 needs its own deopt handler
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
Thu, 28 Jan 2010 20:41:37 -0800 6792161: assert("No dead instructions after post-alloc")
never [Thu, 28 Jan 2010 20:41:37 -0800] rev 4747
6792161: assert("No dead instructions after post-alloc") Reviewed-by: kvn
Thu, 28 Jan 2010 16:28:28 -0800 6920346: G1: "must avoid base_memory and AliasIdxTop"
never [Thu, 28 Jan 2010 16:28:28 -0800] rev 4746
6920346: G1: "must avoid base_memory and AliasIdxTop" Reviewed-by: kvn
Thu, 28 Jan 2010 08:36:34 -0800 6920970: Zero build fixes after 6849984 and 6911204
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>
Wed, 27 Jan 2010 22:38:37 -0800 Merge
ysr [Wed, 27 Jan 2010 22:38:37 -0800] rev 4744
Merge
Tue, 26 Jan 2010 23:36:11 -0800 Merge
ysr [Tue, 26 Jan 2010 23:36:11 -0800] rev 4743
Merge
Tue, 26 Jan 2010 16:52:29 -0800 6920090: G1: Disable ReduceInitialCardMarks at least until 6920109 is fixed
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
Mon, 25 Jan 2010 18:03:29 -0500 6919980: G1: remove +UseG1GC from under experimental options (second attempt)
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
Thu, 21 Jan 2010 18:51:10 -0800 6918006: G1: spill space must be reserved on the stack for barrier calls on Windows x64
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
(0) -3000 -1000 -300 -100 -14 +14 +100 +300 +1000 +3000 +10000 +30000 tip