amurillo [Thu, 08 Oct 2015 14:28:55 -0700] rev 33092
Merge
dlong [Thu, 08 Oct 2015 19:16:42 +0000] rev 33091
Merge
adinn [Wed, 07 Oct 2015 06:56:58 -0400] rev 33090
8139042: AARCH64: Correct regression introduced by 8080293
Summary: Reinstate unsafe volatile optimization broken by JDK-8080293
Reviewed-by: aph, kvn
iveresov [Mon, 05 Oct 2015 20:02:40 -0700] rev 33089
8132207: update for x86 exp in the math lib
Summary: Add new java.lang.Math() intrinsics from x86
Reviewed-by: kvn, iveresov
Contributed-by: vivek.r.deshpande@intel.com
enevill [Wed, 30 Sep 2015 04:35:39 -0400] rev 33088
8138583: aarch64: add support for vectorizing fabs/fneg
Reviewed-by: aph, roland
Contributed-by: felix.yang@linaro.org
iveresov [Thu, 08 Oct 2015 09:51:12 -0700] rev 33087
8139094: Tier1 test java/util/zip/TestCRC32C.java fails due to fixes for JDK-8134553
Summary: Match correct intrinsic kind
Reviewed-by: iveresov, kvn
Contributed-by: tomasz.wojtowicz@intel.com
amurillo [Thu, 01 Oct 2015 11:52:44 -0700] rev 33086
Merge
enevill [Wed, 23 Sep 2015 12:39:30 -0400] rev 33085
8135231: aarch64: add support for vectorizing double precision sqrt
Reviewed-by: roland, aph
aph [Mon, 28 Sep 2015 16:18:15 +0000] rev 33084
8136165: AARCH64: Tidy up compiled native calls
Summary: Do some cleaning
Reviewed-by: roland, kvn, enevill
iveresov [Fri, 25 Sep 2015 12:04:35 -0700] rev 33083
Merge
roland [Thu, 17 Sep 2015 16:53:42 +0200] rev 33082
8136820: Generate better code for some Unsafe addressing patterns
Summary: reshape address computation to move invariant part out of loops
Reviewed-by: kvn
ppunegov [Thu, 24 Sep 2015 20:13:04 +0300] rev 33081
8066157: JEP-JDK-8046155: Test task: method matcher
Summary: MethodMatcher test and framework
Reviewed-by: iignatyev, neliasso
kzhaldyb [Thu, 24 Sep 2015 18:24:10 +0300] rev 33080
8137020: [TESTBUG] Utils.runAndCheckException doesn't work well if no exception thrown
Summary: Changed handling a case when expected exception wasn't thrown
Reviewed-by: iignatyev
enevill [Wed, 16 Sep 2015 13:50:57 +0000] rev 33079
8136615: aarch64: elide DecodeN when followed by CmpP 0
Summary: remove DecodeN when comparing a narrow oop with 0
Reviewed-by: kvn, adinn
roland [Tue, 22 Sep 2015 15:25:34 +0200] rev 33078
8136926: phi == NULL assert in PhaseIdealLoop::try_move_store_after_loop
Summary: multiple phis on same slice are possible in a loop
Reviewed-by: kvn, mcberg
roland [Mon, 21 Sep 2015 10:51:33 +0200] rev 33077
8136596: Remove aarch64: MemBarRelease when final field's allocation is NoEscape or ArgEscape
Summary: elide MemBar when AllocateNode _is_non_escaping
Reviewed-by: kvn, roland
Contributed-by: hui.shi@linaro.org
zmajo [Tue, 22 Sep 2015 13:42:09 +0200] rev 33076
8136914: compiler/loopopts/superword/SumRedSqrt_Double.java times out
Summary: Change test to execute only on relevant (x86-based) platforms.
Reviewed-by: kvn, dlong
adinn [Wed, 16 Sep 2015 09:52:58 -0400] rev 33075
8080293: AARCH64: Remove unnecessary dmbs from generated CAS code
Summary: The current encoding for CAS generates unnecessary leading and trailing dmbs for the MemBarAcquire and MemBarRelease which ought to be elided
Reviewed-by: kvn
iignatyev [Sat, 19 Sep 2015 11:19:22 +0200] rev 33074
Merge
dpochepk [Sat, 19 Sep 2015 12:04:38 +0300] rev 33073
8136718: [TESTBUG] introduce FileInstaller functionality
Reviewed-by: iignatyev
tpivovarova [Sat, 19 Sep 2015 12:03:36 +0300] rev 33072
8136693: add package statement 'compiler.testlibrary' to CompilerUtils
Reviewed-by: iignatyev
coleenp [Fri, 18 Sep 2015 16:37:12 -0400] rev 33071
Merge
mdoerr [Thu, 17 Sep 2015 09:03:57 +0200] rev 33070
8136525: Generate interpreter entries only once and avoid unnecessary jump to jump
Reviewed-by: coleenp, twisti, aph
neliasso [Fri, 18 Sep 2015 10:11:11 +0200] rev 33069
8135068: Extract method matchers from CompilerOracle
Summary: Ecapsulate code to enable reuse
Reviewed-by: roland, kvn
iveresov [Thu, 17 Sep 2015 13:42:50 -0700] rev 33068
Merge
thartmann [Thu, 17 Sep 2015 08:08:47 +0200] rev 33067
8134739: compiler/loopopts/superword/TestVectorizationWithInvariant crashes in loop opts
Summary: Bail out of superword optimization if loop was removed (i.e., if zero-trip Opaque1Node was removed).
Reviewed-by: kvn, roland
kvn [Wed, 16 Sep 2015 15:54:32 -0700] rev 33066
8134553: CRC32C implementations for x86/x64 targets
Reviewed-by: kvn
Contributed-by: tomasz.wojtowicz@intel.com
mcberg [Wed, 16 Sep 2015 13:16:17 -0700] rev 33065
8134802: LCM register pressure scheduling
Summary: Calculate register pressure in a block to help instructions scheduling.
Reviewed-by: kvn, dlong