March 2017 Archives by author

• Messages sorted by: [ thread ] [ subject ] [ date ]
• More info on this list...

Starting: Wed Mar 1 15:53:59 UTC 2017
Ending: Fri Mar 31 19:41:21 UTC 2017
Messages: 355

• RFR: Turn PrintShenandoahMatrix back on.   Christine Flood
• RFR: Turn PrintShenandoahMatrix back on.   Christine Flood
• Java Thread migration   Zhengyu Gu
• RFR(M): Extend work gang dispatcher for low latency task handoff   Zhengyu Gu
• RFR (XS): Use actual byte value instead of (int)true in C1 matrix barrier   Zhengyu Gu
• RFR: Heap/matrix verification for all reachable objects   Zhengyu Gu
• RFR: Add humongous regions support to partial GC   Zhengyu Gu
• RFR: Partial GC: Implement work-stealing and rehash queue work   Zhengyu Gu
• RFR: Partial GC: Implement work-stealing and rehash queue work   Zhengyu Gu
• RFR(XS) [aarch64] Fixed syntax error   Zhengyu Gu
• RFR(XS) [aarch64] Fixed syntax error   Zhengyu Gu
• RFR: Empty task queues when cancelled partial GC   Zhengyu Gu
• RFR: Empty task queues when cancelled partial GC   Zhengyu Gu
• RFR(XS): Fix bad constant definition   Zhengyu Gu
• RFR: 9+8u: Collection policy cleanups   Zhengyu Gu
• RFR: Use size_t consistently for region sizes, counts   Zhengyu Gu
• RFR: Clear outgoing matrix for root regions during preparation phase   Zhengyu Gu
• RFR: Clear outgoing matrix for root regions during preparation phase   Zhengyu Gu
• RFR: Print out garbage and cset data with -Xlog:gc+ergo   Zhengyu Gu
• RFR: Optimize ShMatrix::clear_(in|out)bound   Zhengyu Gu
• RFR: Make update-refs cancellable   Zhengyu Gu
• RFR: Disable over-strong assert   Zhengyu Gu
• RFR: Correctly iterate references in humongous regions   Zhengyu Gu
• [aarch64-port-dev ] RFR: GensrcMisc.gmk linker issue on windows   Andrew Haley
• RFR (S): Cherry pick fix for "8175887: C1 value numbering handling of Unsafe.get*Volatile is incorrect"   Andrew Haley
• RFR (S): Add the option to disable Shenandoah SATB barriers   Andrew Haley
• RFR: 9+8u: Windows expects "long long" constant in macroAssembler   Andrew Haley
• RFR: C1 fixes to matrix barriers   Andrew Haley
• RFR: C1 fixes to matrix barriers   Andrew Haley
• RFR: C1 fixes to matrix barriers   Andrew Haley
• [aarch64-port-dev ] RFR: GensrcMisc.gmk linker issue on windows   Andrew Hughes
• [aarch64-port-dev ] RFR: GensrcMisc.gmk linker issue on windows   Alex Kashchenko
• RFR: Implement barriers to maintain connection matrix   Roman Kennke
• RFR (S): [9+8u] Min region size should be 256K to allow small heaps   Roman Kennke
• RFR (XS): Heap alignment should agree with ShenandoahMaxRegionSize   Roman Kennke
• RFR (S): [9+8u] Stack overflow in choose_collection_set on high region count   Roman Kennke
• RFR (XS) [9+8u] Explicit ShenandoahHeapRegionSize should be checked against min/max   Roman Kennke
• Fix issue with OOM-during-evac   Roman Kennke
• RFR (XS): Fix DerivedPointerTable handling when scanning roots twice in init-evac phase   Roman Kennke
• RFR (XS): Relax assert to not fire at safepoint   Roman Kennke
• RFR (XS): Fix DerivedPointerTable handling when scanning roots twice in init-evac phase   Roman Kennke
• RFR: Implement barriers to maintain connection matrix   Roman Kennke
• RFR (S): +UseCountedLoopSafepoints sets LoopStripMiningIters=1   Roman Kennke
• RFR (XS): Matrix is always enabled with C2   Roman Kennke
• RFR (XS): Use unsigned comparison, fixes warnings in build   Roman Kennke
• RFR (XS) (JDK8u-only): Use 2-arg form of assert in non-LP64 branch   Roman Kennke
• RFR (XS): Fix Shenandoah argument checking on 32bit builds   Roman Kennke
• RFR (S): Shenandoah matrix update barriers should be conditional   Roman Kennke
• RFR (S): Connection matrix should be char*, not bool*   Roman Kennke
• RFR (S): C2: Matrix update barrier math improvements   Roman Kennke
• RFR (XS): Temporarily disable ArrayCopyLoadStoreMaxElem with UseShenandoahMatrix   Roman Kennke
• RFR (S): Connection matrix printout, enable in product, reformat   Roman Kennke
• RFR (S): Cherry pick fix for "8175887: C1 value numbering handling of Unsafe.get*Volatile is incorrect"   Roman Kennke
• RFR: Partial GC   Roman Kennke
• RFR: Partial GC   Roman Kennke
• RFR: Partial GC   Roman Kennke
• RFR (XS): Use actual byte value instead of (int)true in C1 matrix barrier   Roman Kennke
• RFR (XS): C2: Missing matrix update for getAndSet intrinsic   Roman Kennke
• RFR (XS): C2: Missing matrix update for getAndSet intrinsic   Roman Kennke
• RFR: Various fixes and improvements for partial GC   Roman Kennke
• RFR: Heap/matrix verification for all reachable objects   Roman Kennke
• RFR (XS): Bad shift coalescing in C2 matrix update barrier   Roman Kennke
• RFR: Add stats for partial GC   Roman Kennke
• RFR (S): Verification code, memory management assert fixes   Roman Kennke
• RFR: Add humongous regions support to partial GC   Roman Kennke
• RFR: Add humongous regions support to partial GC   Roman Kennke
• RFR: Add humongous regions support to partial GC   Roman Kennke
• RFR: Partial GC: Only evacuating threads push oop to work queue   Roman Kennke
• RFR (S): Matrix verification leaks reserved memory   Roman Kennke
• RFR: Fast matrix math & inlining   Roman Kennke
• RFR: Fix full-gc matrix updates   Roman Kennke
• RFR: Fix full-gc matrix updates   Roman Kennke
• RFR: Fix full-gc matrix updates   Roman Kennke
• RFR (S): Add the option to disable Shenandoah SATB barriers   Roman Kennke
• RFR (XS): Set matrix update probability to low in conditional   Roman Kennke
• RFR (XS): -ShenandoahSATBBarrier disables matrix updates   Roman Kennke
• RFR: Empty task queues when cancelled partial GC   Roman Kennke
• RFR: 9+8u: Fix build error in MacroAssembler::needs_explicit_null_check   Roman Kennke
• RFR: Empty task queues when cancelled partial GC   Roman Kennke
• RFR: Offer termination before leaving on cancelled GC   Roman Kennke
• RFR: Use imulptr/addptr in MacroAssembler matrix update   Roman Kennke
• RFR: 9+8u: MacroAssembler and ShenandoahBarrierSet reference x86_64 registers   Roman Kennke
• RFR: 9+8u: Use size_t constants instead of unsigned longs for MAX2   Roman Kennke
• RFR: 9+8u: Fix linkage error on i586, incrementq and addq are not implemented   Roman Kennke
• RFR: Loop strip mining options should be uintx   Roman Kennke
• RFR: Revert part of StubGenerator to ease porting   Roman Kennke
• RFR: Exit gracefully when Shenandoah is not supported   Roman Kennke
• RFR: ObjChunkedArrayTask enum constants overflow   Roman Kennke
• RFR: 9+8u: ShenandoahHeap::_cancelled_gc should be consistently treated as jbyte   Roman Kennke
• RFR: 9+8u: Add missing precompiled.hpp to Shenandoah files   Roman Kennke
• RFR: 9+8u: Remove stray include mman.h   Roman Kennke
• RFR: 9+8u: BrooksPointer::(word|byte)_size should be uint   Roman Kennke
• RFR: Clean up more uint -> size_t, int -> uint uses   Roman Kennke
• RFR: Turn ShenandoahHeapRegion::{Size, Shift} into the type-checked getters   Roman Kennke
• RFR: No variable-length arrays in standard C++   Roman Kennke
• RFR: 9+8u: Windows expects "long long" constant in macroAssembler   Roman Kennke
• RFR: 9+8u: Windows expects "long long" constant in macroAssembler   Roman Kennke
• RFR: Clear outgoing matrix for root regions during preparation phase   Roman Kennke
• RFR: Use constant template arg to build matrix/no-matrix version of partial GC process_oop()   Roman Kennke
• RFR: Clear outgoing matrix for root regions during preparation phase   Roman Kennke
• RFR: C1 fixes to matrix barriers   Roman Kennke
• RFR: C1 fixes to matrix barriers   Roman Kennke
• RFR: C1 fixes to matrix barriers   Roman Kennke
• RFR: Disable matrix for good when -UseShenandoahMatrix   Roman Kennke
• RFR: Disable matrix for good when -UseShenandoahMatrix   Roman Kennke
• RFR: Report correct total garbage data   Roman Kennke
• RFR: 9+8u: Use uintptr_t in assembler.cpp   Roman Kennke
• RFR: Early update references phase   Roman Kennke
• RFR: Early update references phase   Roman Kennke
• RFR: Early update references phase   Roman Kennke
• RFR: Optimize ShMatrix::clear_(in|out)bound   Roman Kennke
• RFR: Add missing null check in assert   Roman Kennke
• RFR: Make update-refs cancellable   Roman Kennke
• RFR: Improve inlining of the update-refs closure. Implement update-refs verification.   Roman Kennke
• RFR: Improve inlining of the update-refs closure. Implement update-refs verification.   Roman Kennke
• RFR: Interleave partial GCs with concurrent GCs   Roman Kennke
• RFR: Interleave partial GCs with concurrent GCs   Roman Kennke
• RFR: Interleave partial GCs with concurrent GCs   Roman Kennke
• RFR: Improve inlining of the root scanning closure in partial GC   Roman Kennke
• RFR: Improve inlining of the root scanning closure in partial GC   Roman Kennke
• RFR: Correctly iterate references in humongous regions   Roman Kennke
• RFR: Correctly iterate references in humongous regions   Roman Kennke
• RFR: Disable over-strong assert   Roman Kennke
• Loop strip mining to decreases safepoint poll frequency   Aleksey Shipilev
• RFR: Implement barriers to maintain connection matrix   Aleksey Shipilev
• RFR (S): [9+8u] Min region size should be 256K to allow small heaps   Aleksey Shipilev
• RFR (S): [9+8u] Min region size should be 256K to allow small heaps   Aleksey Shipilev
• Make a copy of strip mined loops with small number of iterations from profiling   Aleksey Shipilev
• Make a copy of strip mined loops with small number of iterations from profiling   Aleksey Shipilev
• RFR (XS): Heap alignment should agree with ShenandoahMaxRegionSize   Aleksey Shipilev
• RFR (S): [9+8u] Stack overflow in choose_collection_set on high region count   Aleksey Shipilev
• RFR (S): [9+8u] Stack overflow in choose_collection_set on high region count   Aleksey Shipilev
• RFR (XS) [9+8u] Explicit ShenandoahHeapRegionSize should be checked against min/max   Aleksey Shipilev
• Fix issue with OOM-during-evac   Aleksey Shipilev
• RFR (XS): Fix DerivedPointerTable handling when scanning roots twice in init-evac phase   Aleksey Shipilev
• RFR (XS): Relax assert to not fire at safepoint   Aleksey Shipilev
• RFR (XS): Fix DerivedPointerTable handling when scanning roots twice in init-evac phase   Aleksey Shipilev
• RFR: Implement barriers to maintain connection matrix   Aleksey Shipilev
• RFR (S): +UseCountedLoopSafepoints sets LoopStripMiningIters=1   Aleksey Shipilev
• RFR (XS): Matrix is always enabled with C2   Aleksey Shipilev
• RFR (XS): Use unsigned comparison, fixes warnings in build   Aleksey Shipilev
• RFR (XS) (JDK8u-only): Use 2-arg form of assert in non-LP64 branch   Aleksey Shipilev
• RFR (XS): Fix Shenandoah argument checking on 32bit builds   Aleksey Shipilev
• RFR (S): Shenandoah matrix update barriers should be conditional   Aleksey Shipilev
• RFR (S): Shenandoah matrix update barriers should be conditional   Aleksey Shipilev
• RFR (S): Connection matrix should be char*, not bool*   Aleksey Shipilev
• RFR (S): C2: Matrix update barrier math improvements   Aleksey Shipilev
• RFR (XS): Temporarily disable ArrayCopyLoadStoreMaxElem with UseShenandoahMatrix   Aleksey Shipilev
• Heads up: C2 SEGV with Compiler.sunflow with -XX:+UseShenandoahMatrix   Aleksey Shipilev
• RFR (S): Connection matrix printout, enable in product, reformat   Aleksey Shipilev
• Heads up: C2 SEGV with Compiler.sunflow with -XX:+UseShenandoahMatrix   Aleksey Shipilev
• RFR (S): Cherry pick fix for "8175887: C1 value numbering handling of Unsafe.get*Volatile is incorrect"   Aleksey Shipilev
• RFR (S): Cherry pick fix for "8175887: C1 value numbering handling of Unsafe.get*Volatile is incorrect"   Aleksey Shipilev
• RFR: Partial GC   Aleksey Shipilev
• RFR: Partial GC   Aleksey Shipilev
• RFR (XS): Use actual byte value instead of (int)true in C1 matrix barrier   Aleksey Shipilev
• RFR (XS): Use actual byte value instead of (int)true in C1 matrix barrier   Aleksey Shipilev
• RFR: Partial GC   Aleksey Shipilev
• RFR (XS): C2: Missing matrix update for getAndSet intrinsic   Aleksey Shipilev
• RFR (XS): C2: Missing matrix update for getAndSet intrinsic   Aleksey Shipilev
• C2, pre-barrier, getAndSet   Aleksey Shipilev
• RFR: Various fixes and improvements for partial GC   Aleksey Shipilev
• RFR: Heap/matrix verification for all reachable objects   Aleksey Shipilev
• RFR: Heap/matrix verification for all reachable objects   Aleksey Shipilev
• RFR (XS): Bad shift coalescing in C2 matrix update barrier   Aleksey Shipilev
• RFR: Add stats for partial GC   Aleksey Shipilev
• RFR (S): Verification code, memory management assert fixes   Aleksey Shipilev
• RFR: Add humongous regions support to partial GC   Aleksey Shipilev
• RFR: Add humongous regions support to partial GC   Aleksey Shipilev
• RFR: Partial GC: Only evacuating threads push oop to work queue   Aleksey Shipilev
• RFR: Partial GC: Implement work-stealing and rehash queue work   Aleksey Shipilev
• RFR: Partial GC: Implement work-stealing and rehash queue work   Aleksey Shipilev
• RFR (S): Matrix verification leaks reserved memory   Aleksey Shipilev
• RFR: Fast matrix math & inlining   Aleksey Shipilev
• RFR(XS) [aarch64] Fixed syntax error   Aleksey Shipilev
• RFR: Fix full-gc matrix updates   Aleksey Shipilev
• RFR (S): Add the option to disable Shenandoah SATB barriers   Aleksey Shipilev
• RFR (S): Add the option to disable Shenandoah SATB barriers   Aleksey Shipilev
• RFR (XS): Set matrix update probability to low in conditional   Aleksey Shipilev
• RFR (XS): -ShenandoahSATBBarrier disables matrix updates   Aleksey Shipilev
• RFR: Empty task queues when cancelled partial GC   Aleksey Shipilev
• RFR: 9+8u: Fix build error in MacroAssembler::needs_explicit_null_check   Aleksey Shipilev
• RFR: Empty task queues when cancelled partial GC   Aleksey Shipilev
• RFR: Use imulptr/addptr in MacroAssembler matrix update   Aleksey Shipilev
• RFR: Offer termination before leaving on cancelled GC   Aleksey Shipilev
• RFR: 9+8u: MacroAssembler and ShenandoahBarrierSet reference x86_64 registers   Aleksey Shipilev
• RFR: 9+8u: Use size_t constants instead of unsigned longs for MAX2   Aleksey Shipilev
• RFR: 9+8u: Fix linkage error on i586, incrementq and addq are not implemented   Aleksey Shipilev
• RFR: Loop strip mining options should be uintx   Aleksey Shipilev
• RFR: Revert part of StubGenerator to ease porting   Aleksey Shipilev
• RFR: Exit gracefully when Shenandoah is not supported   Aleksey Shipilev
• RFR: ObjChunkedArrayTask enum constants overflow   Aleksey Shipilev
• RFR: 9+8u: ShenandoahHeap::_cancelled_gc should be consistently treated as jbyte   Aleksey Shipilev
• RFR(XS): Fix bad constant definition   Aleksey Shipilev
• RFR: 9+8u: Collection policy cleanups   Aleksey Shipilev
• RFR: 9+8u: Add missing precompiled.hpp to Shenandoah files   Aleksey Shipilev
• RFR: Use size_t consistently for region sizes, counts   Aleksey Shipilev
• RFR: 9+8u: Remove stray include mman.h   Aleksey Shipilev
• RFR: 9+8u: BrooksPointer::(word|byte)_size should be uint   Aleksey Shipilev
• RFR: Clean up more uint -> size_t, int -> uint uses   Aleksey Shipilev
• RFR: Turn ShenandoahHeapRegion::{Size,Shift} into the type-checked getters   Aleksey Shipilev
• RFR: ShenandoahSupport: fix precedence and opcode check   Aleksey Shipilev
• RFR: No variable-length arrays in standard C++   Aleksey Shipilev
• RFR: 9+8u: Windows expects "long long" constant in macroAssembler   Aleksey Shipilev
• RFR: 9+8u: Windows expects "long long" constant in macroAssembler   Aleksey Shipilev
• RFR: Clear outgoing matrix for root regions during preparation phase   Aleksey Shipilev
• RFR: Use constant template arg to build matrix/no-matrix version of partial GC process_oop()   Aleksey Shipilev
• RFR: Turn PrintShenandoahMatrix back on.   Aleksey Shipilev
• RFR: Turn PrintShenandoahMatrix back on.   Aleksey Shipilev
• RFR: C1 fixes to matrix barriers   Aleksey Shipilev
• RFR: Disable matrix for good when -UseShenandoahMatrix   Aleksey Shipilev
• RFR: Disable matrix for good when -UseShenandoahMatrix   Aleksey Shipilev
• RFR: Print out garbage and cset data with -Xlog:gc+ergo   Aleksey Shipilev
• RFR: Report correct total garbage data   Aleksey Shipilev
• RFR: 9+8u: Use uintptr_t in assembler.cpp   Aleksey Shipilev
• RFR: 9+8u: Use uintptr_t in assembler.cpp   Aleksey Shipilev
• RFR: Early update references phase   Aleksey Shipilev
• RFR: Optimize ShMatrix::clear_(in|out)bound   Aleksey Shipilev
• RFR: Add missing null check in assert   Aleksey Shipilev
• RFR: Improve inlining of the update-refs closure. Implement update-refs verification.   Aleksey Shipilev
• RFR: Interleave partial GCs with concurrent GCs   Aleksey Shipilev
• RFR: Interleave partial GCs with concurrent GCs   Aleksey Shipilev
• RFR: Interleave partial GCs with concurrent GCs   Aleksey Shipilev
• RFR: Interleave partial GCs with concurrent GCs   Aleksey Shipilev
• RFR: Improve inlining of the root scanning closure in partial GC   Aleksey Shipilev
• RFR: Improve inlining of the root scanning closure in partial GC   Aleksey Shipilev
• RFR: Correctly iterate references in humongous regions   Aleksey Shipilev
• RFR: GensrcMisc.gmk linker issue on windows   Michal Vala
• [aarch64-port-dev ] RFR: GensrcMisc.gmk linker issue on windows   Michal Vala
• [aarch64-port-dev ] RFR: GensrcMisc.gmk linker issue on windows   Michal Vala
• [aarch64-port-dev ] RFR: GensrcMisc.gmk linker issue on windows   Michal Vala
• Loop strip mining to decreases safepoint poll frequency   Roland Westrelin
• Loop strip mining to decreases safepoint poll frequency   Roland Westrelin
• Make a copy of strip mined loops with small number of iterations from profiling   Roland Westrelin
• profile based loop predication   Roland Westrelin
• Make a copy of strip mined loops with small number of iterations from profiling   Roland Westrelin
• Heads up: C2 SEGV with Compiler.sunflow with -XX:+UseShenandoahMatrix   Roland Westrelin
• RFR: ShenandoahSupport: fix precedence and opcode check   Roland Westrelin
• hg: shenandoah/jdk9/hotspot: Fix issue with OOM-during-evac.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Added #ifdef ASSERT around debug-only code to fix release build.   roman at kennke.org
• hg: shenandoah/jdk8u/hotspot: Fix issue with OOM-during-evac.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: 2 new changesets   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Implement barriers for maintaining connection matrix.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Use unsigned comparison, fixes warnings in build.   roman at kennke.org
• hg: shenandoah/jdk8u/hotspot: 2 new changesets   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Fix Shenandoah argument checking on 32bit builds.   roman at kennke.org
• hg: shenandoah/jdk8u/hotspot: Fix Shenandoah argument checking on 32bit builds.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Partial GC   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Various fixes and improvements for partial GC.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Add stats for partial GC.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Add humongous regions support to partial GC.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Partial GC: Only evacuating threads push oop to work queue.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Fast matrix math & inlining.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Fix full-gc matrix updates.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Empty task queues when cancelled partial GC.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Offer termination before leaving on cancelled GC.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Revert part of StubGenerator to ease porting.   roman at kennke.org
• hg: shenandoah/jdk8u/hotspot: Revert part of StubGenerator to ease porting.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: 2 new changesets   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: C1 fixes to matrix barriers.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Implement early update references phase.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Add missing null check in assert.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Make update-refs cancellable.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Improve inlining of the update-refs closure. Implement update-refs verification.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Interleave partial GCs with concurrent GCs.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: Improve inlining of the root scanning closure in partial GC.   roman at kennke.org
• hg: shenandoah/jdk9/hotspot: ShenandoahMinRegionSize should be 256K to allow small heaps.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: ShenandoahMinRegionSize should be 256K to allow small heaps.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Heap alignment should agree with ShenandoahMaxRegionSize.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Heap alignment should agree with ShenandoahMaxRegionSize.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Stack overflow in choose_collection_set on high region count.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Stack overflow in choose_collection_set on high region count.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Explicit ShenandoahHeapRegionSize should be checked against min/max.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Explicit ShenandoahHeapRegionSize should be checked against min/max.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: +UseCountedLoopSafepoints sets LoopStripMiningIters=1.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Matrix is always enabled with C2.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Shenandoah matrix update barriers should be conditional.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Connection matrix should be char*, not bool*.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: ShenandoahConnectionMatrix destructor should use char, not bool.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: C2: Matrix update barrier math improvements.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Temporarily disable ArrayCopyLoadStoreMaxElem with UseShenandoahMatrix.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Connection matrix printout, enable in product, reformat.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Cherry pick fix for "8175887: C1 value numbering handling of Unsafe.get*Volatile is incorrect".   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Matrix barrier bool->char conversion leftovers.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: C2: Missing matrix update for getAndSet intrinsic.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Heap/matrix verification for all reachable objects.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Remove double-counting for NMT, uncommit_memory does it.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Bad shift coalescing in C2 matrix update barrier.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Verification code, memory management assert fixes.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Partial GC: Implement work-stealing and rehash queue work.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Matrix verification leaks reserved memory.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Add the option to disable Shenandoah SATB barriers.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Set matrix update probability to low in conditional.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: -ShenandoahSATBBarrier disables matrix updates.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Fix build error in MacroAssembler::needs_explicit_null_check.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Fix build error in MacroAssembler::needs_explicit_null_check.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Use imulptr/addptr in MacroAssembler matrix update.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: MacroAssembler and ShenandoahBarrierSet reference x86_64 registers.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: MacroAssembler and ShenandoahBarrierSet reference x86_64 registers.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Use size_t constants instead of unsigned longs for MAX2.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Use size_t constants instead of unsigned longs for MAX2.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Fix linkage error on i586, incrementq and addq are not implemented.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Fix linkage error on i586, incrementq and addq are not implemented.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Loop strip mining options should be uintx.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Exit gracefully when Shenandoah is not supported.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: ObjChunkedArrayTask enum constants overflow.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: ShenandoahHeap::_cancelled_gc should be consistently treated as jbyte.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: ShenandoahHeap::_cancelled_gc should be consistently treated as jbyte.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Collection policy cleanups.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Collection policy cleanups.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Add missing precompiled.hpp to Shenandoah files.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Add missing precompiled.hpp to Shenandoah files.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Use size_t consistently for region sizes, counts.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Remove stray include mman.h.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Remove stray include mman.h.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: BrooksPointer::(word|byte)_size should be uint.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: BrooksPointer::(word|byte)_size should be uint.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Turn ShenandoahHeapRegion::{Size, Shift} into the type-checked getters.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: ShenandoahSupport: fix precedence and opcode check.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: No variable-length arrays in standard C++.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: No variable-length arrays in standard C++.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Clean up more uint -> size_t, int -> uint, int -> jint uses.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Add missing precompiled.hpp to Shenandoah files, #2.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Wrap log_develop_trace in block to make compiler happy.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Wrap log_develop_trace in block to make compiler happy.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Windows expects "long long" constant in macroAssembler.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Windows expects "long long" constant in macroAssembler.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Fix fastdebug build failures due to missed uint->size_t update.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: ObjChunkedArrayTask enum constants overflow.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Use size_t consistently for region sizes, counts.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Turn ShenandoahHeapRegion::{Size, Shift} into the type-checked getters.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Clean up more uint -> size_t, int -> uint, int -> jint uses.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Disable MSVC 4522, as taskqueue.hpp does.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: 2 new changesets   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Hook up Shenandoah to Windows build list.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Make MSVC 2010 happy by spelling out (un)signess.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Fix non-LP64 version of ObjArrayChunkedTask.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Disable matrix for good when -UseShenandoahMatrix.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Print out garbage and cset data with -Xlog:gc+ergo.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Report correct total garbage data.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Use uintptr_t in assembler.cpp.   ashipile at redhat.com
• hg: shenandoah/jdk8u/hotspot: Use uintptr_t in assembler.cpp.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Optimize ShMatrix::clear_(in|out)bound.   ashipile at redhat.com
• hg: shenandoah/jdk9/hotspot: Fix Print Matrix   chf at redhat.com
• hg: shenandoah/jdk9/hotspot: fix a boo boo   chf at redhat.com
• hg: shenandoah/jdk9/hotspot: loop strip mining   rwestrel at redhat.com
• hg: shenandoah/jdk9/hotspot: Make a copy of strip mined loops with small number of iterations from profiling   rwestrel at redhat.com
• hg: shenandoah/jdk9/hotspot: profile based loop predication   rwestrel at redhat.com
• hg: shenandoah/jdk9/hotspot: fix matrix update elimination   rwestrel at redhat.com
• hg: shenandoah/jdk9/hotspot: missed barrier elimination opportunity in ShenandoahBarrierNode::try_common()   rwestrel at redhat.com
• hg: shenandoah/jdk9/hotspot: matrix update and unsafe load store fix   rwestrel at redhat.com
• hg: shenandoah/jdk9/hotspot: enable small array copy optimization when no oop is copied   rwestrel at redhat.com
• hg: shenandoah/jdk9/hotspot: Fixed a syntax error.   zgu at redhat.com
• hg: shenandoah/jdk9/hotspot: Fix bad constant definition   zgu at redhat.com
• hg: shenandoah/jdk8u/hotspot: Fix bad constant definition   zgu at redhat.com

Last message date: Fri Mar 31 19:41:21 UTC 2017
Archived on: Fri May 5 17:16:33 UTC 2017

• Messages sorted by: [ thread ] [ subject ] [ date ]
• More info on this list...