)]}' { "log": [ { "commit": "8cf9cb386cd9286d67e879f1ee501ec00d72a4e1", "tree": "88e86e214b425e444760fe4e0ffeee677e1558a2", "parents": [ "914b7b6a6c9f399b26b41e9160e9871ef749e0db" ], "author": { "name": "Andreas Gampe", "email": "agampe@google.com", "time": "Wed Jul 19 09:28:38 2017 -0700" }, "committer": { "name": "Andreas Gampe", "email": "agampe@google.com", "time": "Mon Jul 24 16:07:10 2017 -0700" }, "message": "ART: Include cleanup\n\nLet clang-format reorder the header includes.\n\nDerived with:\n\n* .clang-format:\n BasedOnStyle: Google\n IncludeIsMainRegex: \u0027(_test|-inl)?$\u0027\n\n* Steps:\n find . -name \u0027*.cc\u0027 -o -name \u0027*.h\u0027 | xargs sed -i.bak -e \u0027s/^#include/ #include/\u0027 ; git commit -a -m \u0027ART: Include cleanup\u0027\n git-clang-format -style\u003dfile HEAD^\n manual inspection\n git commit -a --amend\n\nTest: mmma art\nChange-Id: Ia963a8ce3ce5f96b5e78acd587e26908c7a70d02\n" }, { "commit": "28a24b308f665de64c785e2590f9b23ec6ec25aa", "tree": "3e9f0779038cefbbae5581b5844ce742ea782f9b", "parents": [ "6bc7774426cc0b6bbab5566fa62b3c509455e583" ], "author": { "name": "Mathieu Chartier", "email": "mathieuc@google.com", "time": "Wed Apr 19 23:54:33 2017 -0700" }, "committer": { "name": "Mathieu Chartier", "email": "mathieuc@google.com", "time": "Wed Apr 19 23:55:36 2017 -0700" }, "message": "Fix some gtests\n\nForgot to retest.\n\nTest: test-art-host-gtest\n\nChange-Id: I72b07c3872079452a3a01db4fbd2c4ee0060f294\n" }, { "commit": "efd20cb2f63cf647c7d947d00e8987affefeb177", "tree": "666ea53832f1085378bcc75620f314ba1f46a330", "parents": [ "caa348cee1312150a957bd308ce77ad406f3eb64" ], "author": { "name": "Josh Gao", "email": "jmgao@google.com", "time": "Tue Feb 28 16:53:59 2017 -0800" }, "committer": { "name": "Josh Gao", "email": "jmgao@google.com", "time": "Wed Mar 08 15:07:49 2017 -0800" }, "message": "Catch signals that happen inside a fault handler.\n\nUnblock some signals (SIGABRT, SIGBUS, SIGSEGV) that could happen\ninside of the ART internal fault handlers, to report crashes inside of\nthe signal handler. Because we can\u0027t use sigaction to change the\nhandler when this happens, because it modifies global state, add a new\nmember variable in Thread to track whether a call to the fault handler\nis reentrant or not.\n\nRemove the old nested signal implementation that attempted to do this.\n\nBug: http://b/35853436\nTest: changed the #if 0 to #if 1, ran a dummy process that\n threw a NullPointerException, inspected logcat\nChange-Id: I04bb4a09433c6817933d64ec681ec433b528f2a5\n" }, { "commit": "b048cb74b742b03eb6dd5f1d6dd49e559f730b36", "tree": "b1f663cbb343488a548cce4db352dbc4af720a89", "parents": [ "f34077c96af3389e8eae65252d4c5d51cf630039" ], "author": { "name": "Nicolas Geoffray", "email": "ngeoffray@google.com", "time": "Mon Jan 23 22:50:24 2017 +0000" }, "committer": { "name": "Nicolas Geoffray", "email": "ngeoffray@google.com", "time": "Thu Jan 26 09:56:36 2017 +0000" }, "message": "Add per array size allocation entrypoints.\n\n- Update architectures that have fast paths for\n array allocation to use it.\n- Will add more fast paths in follow-up CLs.\n\nTest: test-art-target test-art-host.\nChange-Id: I138cccd16464a85de22a8ed31c915f876e78fb04\n" }, { "commit": "8d91ac31ccb92557e434d89ffade3372466e1af5", "tree": "37fd364ba6c9a6cf5e6a60a00c2542c5ffb12528", "parents": [ "2f670ccba022fe557c637571ac781519f0e84463" ], "author": { "name": "Nicolas Geoffray", "email": "ngeoffray@google.com", "time": "Wed Jan 18 18:07:15 2017 +0000" }, "committer": { "name": "Nicolas Geoffray", "email": "ngeoffray@google.com", "time": "Thu Jan 19 11:56:43 2017 +0000" }, "message": "Remove unused array entrypoints.\n\nTest: test-art-host test-art-target\nChange-Id: I910d1c912c7c9056ecea0e1e7da7afb2a7220dfa\n" }, { "commit": "39cee66a8ddf0254626c9591662cf87e4a1cedc4", "tree": "be25df71e51ce03a8847c23934322b8f282a291b", "parents": [ "a3974581751cd73a896f7c4fcab71beb17c4f9dc" ], "author": { "name": "Nicolas Geoffray", "email": "ngeoffray@google.com", "time": "Fri Jan 13 16:04:53 2017 +0000" }, "committer": { "name": "Nicolas Geoffray", "email": "ngeoffray@google.com", "time": "Wed Jan 18 11:12:33 2017 +0000" }, "message": "Entrypoints cleanup.\n\nRemove unused ones to facilitate the transition to compressed\ndex caches.\n\ntest: test-art-host, test-art-target\nChange-Id: I1d1cb0daffa86dd9dda2eaa3c1ea3650a5c8d9d0\n" }, { "commit": "e71b35446985835363a4508646cf7b1121bd95a3", "tree": "bd40763b04ba2028f3383736b2a14808e407120c", "parents": [ "8bd59a0fd46db83616785168231e09fb95ed2ead" ], "author": { "name": "Roland Levillain", "email": "rpl@google.com", "time": "Mon Jan 16 14:58:23 2017 +0000" }, "committer": { "name": "Roland Levillain", "email": "rpl@google.com", "time": "Tue Jan 17 11:55:07 2017 +0000" }, "message": "Move some fields in art::Thread to reduce maintenance burden.\n\nMove fields `thread_local_start`, `thread_local_pos`,\n`thread_local_end` and `thread_local_objects` before fields\n`jni_entrypoints` and `quick_entrypoints` within\nart::Thread, to avoid repetitive art::Thread field moves in\nfuture CLs caused by the addition or deletion of entry\npoints.\n\nTest: m test-art-host\ntest: m test-art-target (on ARM)\nChange-Id: Ib67842e44a7f21a871ca4d1bb95dc6f7cfedc829\n" }, { "commit": "ac141397dc29189ad2b2df41f8d4312246beec60", "tree": "a2f481463a14695bf9327fd2f549878ecf30c77b", "parents": [ "5c9f90c5ecf2ff6f93ada0f7b18b46d866c59ea1" ], "author": { "name": "Orion Hodson", "email": "oth@google.com", "time": "Fri Jan 13 11:53:47 2017 +0000" }, "committer": { "name": "Orion Hodson", "email": "oth@google.com", "time": "Sun Jan 15 15:18:07 2017 +0000" }, "message": "Revert \"Revert \"ART: Compiler support for invoke-polymorphic.\"\"\n\nThis reverts commit 0fb5af1c8287b1ec85c55c306a1c43820c38a337.\n\nThis takes us back to the original change and attempts to fix the\nissues encountered:\n\n- Adds transition record push/pop around artInvokePolymorphic.\n- Changes X86/X64 relocations for MacSDK.\n- Implements MIPS entrypoint for art_quick_invoke_polymorphic.\n- Corrects size of returned reference in art_quick_invoke_polymorphic\n on ARM.\n\nBug: 30550796,33191393\nTest: art/test/run-test 953\nTest: m test-art-run-test\n\nChange-Id: Ib6b93e00b37b9d4ab743a3470ab3d77fe857cda8\n" }, { "commit": "0d3998b5ff619364acf47bec0b541e7a49bd6fe7", "tree": "a4763c0660372f6311b612c09267cbbc2fe71e89", "parents": [ "aa89a4c6fca095904521842c018399f1e3501a45" ], "author": { "name": "Nicolas Geoffray", "email": "ngeoffray@google.com", "time": "Thu Jan 12 15:35:12 2017 +0000" }, "committer": { "name": "Nicolas Geoffray", "email": "ngeoffray@google.com", "time": "Thu Jan 12 16:51:12 2017 +0000" }, "message": "Revert \"Revert \"Make object allocation entrypoints only take a class.\"\"\n\nThis reverts commit f7aaacd97881c6924b8212c7f8fe4a4c8721ef53.\n\nChange-Id: I6756cd1e6110bb45231f62f5e388f16c044cb145\n" }, { "commit": "f7aaacd97881c6924b8212c7f8fe4a4c8721ef53", "tree": "780209ac8e992fa63307062977f672aa5bb55d9e", "parents": [ "2b615ba29c4dfcf54aaf44955f2eac60f5080b2e" ], "author": { "name": "Hiroshi Yamauchi", "email": "yamauchi@google.com", "time": "Thu Jan 12 02:58:38 2017 +0000" }, "committer": { "name": "Hiroshi Yamauchi", "email": "yamauchi@google.com", "time": "Thu Jan 12 02:58:38 2017 +0000" }, "message": "Revert \"Make object allocation entrypoints only take a class.\"\n\n960-default-smali64 is failing.\n\nThis reverts commit 2b615ba29c4dfcf54aaf44955f2eac60f5080b2e.\n\nChange-Id: Iebb8ee5a917fa84c5f01660ce432798524d078ef\n" }, { "commit": "2b615ba29c4dfcf54aaf44955f2eac60f5080b2e", "tree": "0a2fe5f9243645a054d4aa094bff5a69cc1abb88", "parents": [ "c9a060f2688599d4a402ee6234db46c2e9b7463f" ], "author": { "name": "Nicolas Geoffray", "email": "ngeoffray@google.com", "time": "Fri Jan 06 14:40:07 2017 +0000" }, "committer": { "name": "Nicolas Geoffray", "email": "ngeoffray@google.com", "time": "Wed Jan 11 10:34:10 2017 +0000" }, "message": "Make object allocation entrypoints only take a class.\n\nChange motivated by:\n- Dex cache compression: having the allocation fast path do a\n dex cache lookup will be too expensive. So instead, rely on the\n compiler having direct access to the class (either through BSS for\n AOT, or JIT tables for JIT).\n- Inlining: the entrypoints relied on the caller of the allocation to\n have the same dex cache as the outer method (stored at the bottom of\n the stack). This meant we could not inline methods from a different\n dex file that do allocations. By avoiding the dex cache lookup in\n the entrypoint, we can now remove this restriction.\n\nCode expansion on average for Docs/Gms/FB/Framework (go/lem numbers):\n- Around 0.8% on arm64\n- Around 1% for x64, arm\n- Around 1.5% on x86\n\nTest: test-art-host, test-art-target, ART_USE_READ_BARRIER\u003dtrue/false\nTest: test-art-host, test-art-target, ART_DEFAULT_GC_TYPE\u003dSS ART_USE_TLAB\u003dtrue\n\nChange-Id: I41f3748bb4d251996aaf6a90fae4c50176f9295f\n" }, { "commit": "340dafabc8e88378e395cda9027cf17726910e91", "tree": "f742cfc9b9eb3fdf0245a66491d39fb841da7c01", "parents": [ "71d15102b52af67e8fe1193192aa2b4cd1956ae0" ], "author": { "name": "Nicolas Geoffray", "email": "ngeoffray@google.com", "time": "Fri Nov 18 16:03:10 2016 +0000" }, "committer": { "name": "Nicolas Geoffray", "email": "ngeoffray@google.com", "time": "Tue Nov 22 13:08:29 2016 +0000" }, "message": "Use a per-thread VerifierDeps.\n\nAvoid lock contention on a singleton VerifierDeps by allocating\ntemporary per-thread VerifierDeps that get merged after verification.\n\nThis saves around ~35% compile-times on interpret-only.\n\nOnly the creation of extra strings is guarded by a lock, for simplicity.\n\nTest: test-art-host, test-art-target\nbug: 32641252\nbug: 30937355\n\nChange-Id: I11a2367da882b58e39afa7b42cba2e74a209b75d\n" }, { "commit": "b99f4d6463e7cb5654af3893ed7b3113665df658", "tree": "1bacc6a2bd01426c921e2f83f39bb63f9d9d8048", "parents": [ "67381d6298edf18760b0c9b3d16572dc3894e551" ], "author": { "name": "Mathieu Chartier", "email": "mathieuc@google.com", "time": "Mon Nov 07 16:17:26 2016 -0800" }, "committer": { "name": "Mathieu Chartier", "email": "mathieuc@google.com", "time": "Tue Nov 08 12:46:59 2016 -0800" }, "message": "Change check cast entrypoint to check instance of\n\nReduces code size since we do not need to reload class before\ncalling slow path.\n\nTODO: Delete read barriers in the check cast code since the slow\npath will retry with the proper read barriers if the check fails.\n\nBug: 12687968\nBug: 29516974\n\nTest: test-art-host + test-art-target with CC\n\nChange-Id: Ia4eb9bbe3fe2d2016e44523cf0451210828d7b88\n" }, { "commit": "af1e2990cd1406a0fb7cba1d2e208208e950e413", "tree": "07e80e4dcc31931003a87be7884134ea42ceec07", "parents": [ "3f699ae23266b2c4adc98958dcbd80c71c2c3284" ], "author": { "name": "Igor Murashkin", "email": "iam@google.com", "time": "Wed Oct 12 17:44:50 2016 -0700" }, "committer": { "name": "Igor Murashkin", "email": "iam@google.com", "time": "Wed Oct 19 11:38:54 2016 -0700" }, "message": "jni: Support @FastNative methods that return objects\n\nBug: 32088975\nChange-Id: I16f8b7ec6b251812af60ab25f2153d9b72f37044\n" }, { "commit": "05846475c8d48ce191dcd333c76d5ccc17aea9dd", "tree": "bfbcbba324eda45fae27b31ce0ce589c5f472474", "parents": [ "e305eaf2c08a203e3e046c3a8608b90b9dc5a080" ], "author": { "name": "Vladimir Marko", "email": "vmarko@google.com", "time": "Wed Sep 14 12:49:57 2016 +0100" }, "committer": { "name": "Vladimir Marko", "email": "vmarko@google.com", "time": "Wed Sep 14 12:55:09 2016 +0100" }, "message": "Remove ThrowNoSuchMethod entrypoint.\n\nRun ART test suite on host and Nexus 6.\nBug: 31464666\nChange-Id: I5aa737726031adae0b132f759cf802a93d581a7f\n" }, { "commit": "1a0de6acd03b43a03678b58f47b2f21b5215cc22", "tree": "7d03f89b9d64ebc40ea382011de524d18a004f73", "parents": [ "cc55a7ce2aa0f10c2da9efaa89855cf075e56e20" ], "author": { "name": "Chih-Hung Hsieh", "email": "chh@google.com", "time": "Fri Aug 26 15:06:11 2016 -0700" }, "committer": { "name": "Chih-Hung Hsieh", "email": "chh@google.com", "time": "Fri Aug 26 17:52:41 2016 -0700" }, "message": "Fix clang-tidy warnings in art.\n\n* Add parentheses around macro parameters, or\n use NOLINT to suppress warning.\nBug: 28705665\n\nTest: build with WITH_TIDY\u003d1\nChange-Id: Ifc922c2e66215772042bac372754ea70074f0053\n" }, { "commit": "9d4b6da934934c322536ee3309b63ce402740f49", "tree": "9e7ee5023d6036b98e0560411bb0527efdedca01", "parents": [ "2af1aa066e3d20edd8fea5d5b6dbbbad73102d52" ], "author": { "name": "Igor Murashkin", "email": "iam@google.com", "time": "Fri Jul 29 09:51:58 2016 -0700" }, "committer": { "name": "Igor Murashkin", "email": "iam@google.com", "time": "Tue Aug 16 20:19:36 2016 +0000" }, "message": "jni: Fast path for @FastNative annotated java methods\n\nAdds a faster path for java methods annotated with\ndalvik.annotation.optimization.FastNative .\n\nIntended to replace usage of fast JNI (registering with \"!(FOO)BAR\" descriptors).\n\nPerformance Microbenchmark Results (Angler):\n* Regular JNI cost in nanoseconds: 115\n* Fast JNI cost in nanoseconds: 60\n* @FastNative cost in nanoseconds: 36\n\nSummary: Up to 67% faster (vs fast jni) JNI transition cost\n\nChange-Id: Ic23823ae0f232270c068ec999fd89aa993894b0e\n" }, { "commit": "d549c28cfbddba945cb88857bcca3dce1414fb29", "tree": "584d765beea2cd6ceb4d56789ccc5c8f64db967e", "parents": [ "9e27d02040ff87eb8e2d56d21347a77cb800eddf" ], "author": { "name": "Roland Levillain", "email": "rpl@google.com", "time": "Mon Jul 25 12:49:15 2016 +0100" }, "committer": { "name": "Roland Levillain", "email": "rpl@google.com", "time": "Mon Jul 25 12:49:15 2016 +0100" }, "message": "Remove two ReadBarrierMarkRegX entrypoints.\n\nAs entry points ReadBarrierMarkReg30 and\nReadBarrierMarkReg31 are undefined on all architectures\nsupporting the read barrier configuration (ARM, ARM64, x86\nand x86-64), remove them from the entry point list.\n\nTest: ART host and target (ARM, ARM64) tests.\nBug: 29506760\nBug: 12687968\nChange-Id: I500626e54f00aebfc095b4ef5f81b49fa43f7768\n" }, { "commit": "02b75806a80f8b75c3d6ba2ff97c995117630f36", "tree": "ecdb1852c3e33f120110091cc2d07a9737fbd3b5", "parents": [ "5f485719b166ceb8e591329d40e76c5e50988022" ], "author": { "name": "Roland Levillain", "email": "rpl@google.com", "time": "Wed Jul 13 11:54:35 2016 +0100" }, "committer": { "name": "Roland Levillain", "email": "rpl@google.com", "time": "Wed Jul 13 11:54:35 2016 +0100" }, "message": "Introduce more compact ReadBarrierMark slow-paths.\n\nReplace entry point ReadBarrierMark with 32\nReadBarrierMarkRegX entry points, using register\nnumber X as input and output (instead of the standard\nruntime calling convention) to save two moves in Baker\u0027s\nread barrier mark slow-path code.\n\nTest: ART host and target (ARM, ARM64) tests.\nBug: 29506760\nBug: 12687968\nChange-Id: I73cfb82831cf040b8b018e984163c865cc44ed87\n" }, { "commit": "87f3fcbd0db352157fc59148e94647ef21b73bce", "tree": "5bdeabb246f5de86704333b3fcbccc6e9146d246", "parents": [ "b94b5706f0b8e2e1c7e1db22274f9f4bae0c4b5a" ], "author": { "name": "Vladimir Marko", "email": "vmarko@google.com", "time": "Thu Apr 28 15:52:11 2016 +0100" }, "committer": { "name": "Vladimir Marko", "email": "vmarko@google.com", "time": "Tue Jun 21 15:17:38 2016 +0100" }, "message": "Replace String.charAt() with HIR.\n\nReplace String.charAt() with HArrayLength, HBoundsCheck and\nHArrayGet. This allows GVN on the HArrayLength and BCE on\nthe HBoundsCheck as well as using the infrastructure for\nHArrayGet, i.e. better handling of constant indexes than\nthe old intrinsic and using the HArm64IntermediateAddress.\n\nBug: 28330359\nChange-Id: I32bf1da7eeafe82537a60416abf6ac412baa80dc\n" }, { "commit": "952e1e3710158982941fc70326e9fddc3021235d", "tree": "79ba4922cbe7a28d32078516d1667f90354bee6b", "parents": [ "ece5386eeb30aa6be663af2416b68a7ebf9bd42e" ], "author": { "name": "Mathieu Chartier", "email": "mathieuc@google.com", "time": "Mon Jun 13 14:04:02 2016 -0700" }, "committer": { "name": "Mathieu Chartier", "email": "mathieuc@google.com", "time": "Mon Jun 13 18:10:02 2016 -0700" }, "message": "Support unlimited pending checkpoints\n\nPrevents the spinning that used to happen if RunCheckpoint was called\nwith 3 pending checkpoints. This spinning was done when holding\nthread_list_lock_ and thread_suspend_count_lock_ and could deadlock\nif any of the pending checkpoints required any of these locks.\n\nThe fix is to use an overflow list instead of having a fixed limit of\n3.\n\nChanged suspend stress test to have more threads and only compare last\nline since there may be libbacktrace spam like:\n\"+E/libbacktrace(69891): void SignalHandler(int, siginfo_t *, void *):\nTimed out waiting for unwind thread to indicate it completed.\"\n\nBug: 28988206\n\nChange-Id: I2ae611506147d5199d59a08eee0395f7fa35d448\n" }, { "commit": "7e1ce285c3c2cbd8d97c744699c2f2347fa7487b", "tree": "40d525eeda56a05576cb396a72479c366d2d463f", "parents": [ "4e4e64511e530db37b33f450016afe49db3c4b20" ], "author": { "name": "Hiroshi Yamauchi", "email": "yamauchi@google.com", "time": "Fri Dec 11 15:46:19 2015 -0800" }, "committer": { "name": "Hiroshi Yamauchi", "email": "yamauchi@google.com", "time": "Thu Feb 25 14:00:48 2016 -0800" }, "message": "Assembly TLAB allocation fast path for arm.\n\nSpeedup (GSS GC with TLAB on N5):\n BinaryTrees: 1872 -\u003e 796 ms (-57%)\n MemAllocTest: 2522 -\u003e 2219 ms (-12%)\n\nBug: 9986565\nChange-Id: Icb9d1259461f3abe83a4a82c8aff911937eaf57d\n" }, { "commit": "7ed9c561048d79083b6d0576c71a986a3123bca6", "tree": "8e352f05dc5e82126dd61e0e8e6ddb2a1003e16a", "parents": [ "c3cf1d2e35a45bd2e2c60fbc9c2a1a6a56dfc529" ], "author": { "name": "Hiroshi Yamauchi", "email": "yamauchi@google.com", "time": "Tue Feb 02 15:22:09 2016 -0800" }, "committer": { "name": "Hiroshi Yamauchi", "email": "yamauchi@google.com", "time": "Fri Feb 05 12:12:44 2016 -0800" }, "message": "Use 8-byte increment bracket sizes for rosalloc thread local runs.\n\nVery small space savings (\u003c 1%) after device boot and up to 10%\nallocation speedup.\n\nSome minor cleanup.\n\nBug: 9986565\n\nChange-Id: I51d791c4674d6944fe9a7ee78537ac3490c1a02c\n" }, { "commit": "1452bee8f06b9f76a333ddf4760e4beaa82f8099", "tree": "8ffb80498cd8fdff66a4ab272723cf4d4e69e57b", "parents": [ "7f9ea1451bb74055ee5d51ae04fc869faa06cbdd" ], "author": { "name": "buzbee", "email": "buzbee@google.com", "time": "Fri Mar 06 14:43:04 2015 -0800" }, "committer": { "name": "buzbee", "email": "buzbee@google.com", "time": "Mon Jan 11 13:04:49 2016 -0800" }, "message": "Fast Art interpreter\n\nAdd a Dalvik-style fast interpreter to Art.\nThree primary deficiencies in the existing Art interpreter\nwill be addressed:\n\n1. Structural inefficiencies (primarily the bloated\n fetch/decode/execute overhead of the C++ interpreter\n implementation).\n2. Stack memory wastage. Each managed-language invoke\n adds a full copy of the interpreter\u0027s compiler-generated\n locals on the shared stack. We\u0027re at the mercy of\n the compiler now in how much memory is wasted here. An\n assembly based interpreter can manage memory usage more\n effectively.\n3. Shadow frame model, which not only spends twice the memory\n to store the Dalvik virtual registers, but causes vreg stores\n to happen twice.\n\nThis CL mostly deals with #1 (but does provide some stack memory\nsavings). Subsequent CLs will address the other issues.\n\nCurrent status:\n Passes all run-tests.\n Phone boots interpret-only.\n 2.5x faster than Clang-compiled Art goto interpreter on fetch/decode/execute\n microbenchmark, 5x faster than gcc-compiled goto interpreter.\n 1.6x faster than Clang goto on Caffeinemark overall\n 2.0x faster than Clang switch on Caffeinemark overall\n 68% of Dalvik interpreter performance on Caffeinemark (still much slower,\n primarily because of poor invoke performance and lack of execute-inline)\n Still nearly an order of magnitude slower than Dalvik on invokes\n (but slightly better than Art Clang goto interpreter.\n Importantly, saves ~200 bytes of stack memory per invoke (but still\n wastes ~400 relative to Dalvik).\n\nWhat\u0027s needed:\n Remove the (large quantity of) bring-up hackery in place.\n Integrate into the build mechanism. I\u0027m still using the old Dalvik manual\n build step to generate assembly code from the stub files.\n Remove the suspend check hack. For bring-up purposes, I\u0027m using an explicit\n suspend check (like the other Art interpreters). However, we should be\n doing a Dalvik style suspend check via the table base switch mechanism.\n This should be done during the alternative interpreter activation.\n General cleanup.\n Add CFI info.\n Update the new target bring-up README documentation.\n Add other targets.\n\nIn later CLs:\n Consolidate mterp handlers for expensive operations (such as new-instance) with\n the code used by the switch interpreter. No need to duplicate the code for\n heavyweight operations (but will need some refactoring to align).\n Tuning - some fast paths needs to be moved down to the assembly handlers,\n rather than being dealt with in the out-of-line code.\n JIT profiling. Currently, the fast interpreter is used only in the fast\n case - no instrumentation, no transactions and no access checks. We\n will want to implement fast + JIT-profiling as the alternate fast\n interpreter. All other cases can still fall back to the reference\n interpreter.\n Improve invoke performance. We\u0027re nearly an order of magnitude slower than\n Dalvik here. Some of that is unavoidable, but I suspect we can do\n better.\n Add support for our other targets.\n\nChange-Id: I43e25dc3d786fb87245705ac74a87274ad34fedc\n" }, { "commit": "7c1559a06041c9c299d5ab514d54b2102f204a84", "tree": "c50b54bf82f457f44dbf0741947d836749d4a96a", "parents": [ "7cd230c8f74a227ea04f1dd93c8d855aa81fc1fe" ], "author": { "name": "Roland Levillain", "email": "rpl@google.com", "time": "Tue Dec 15 10:55:36 2015 +0000" }, "committer": { "name": "Roland Levillain", "email": "rpl@google.com", "time": "Tue Dec 15 11:45:56 2015 +0000" }, "message": "x86 Baker\u0027s read barrier fast path implementation.\n\nIntroduce an x86 fast path implementation in Optimizing for\nBaker\u0027s read barriers (for both heap reference loads and GC\nroot loads). The marking phase of the read barrier is\nperformed by a slow path, invoking a new runtime entry point\n(artReadBarrierMark).\n\nOther read barrier algorithms continue to use the original\nslow path based implementation, which has been renamed as\nGenerateReadBarrierSlow/GenerateReadBarrierForRootSlow.\n\nBug: 12687968\nChange-Id: Ie610c4befc19ff22378a8cba38b422dcacb54320\n" }, { "commit": "a4f1220c1518074db18ca1044e9201492975750b", "tree": "796f0dcd733ad5ffd7d8310af871f3e2c22ee0be", "parents": [ "763fd2d3d131898cad6295a19ae9a30e22ce5f2a" ], "author": { "name": "Mark Mendell", "email": "mark.p.mendell@intel.com", "time": "Thu Aug 06 15:23:34 2015 -0400" }, "committer": { "name": "Mark Mendell", "email": "mark.p.mendell@intel.com", "time": "Thu Dec 10 13:23:49 2015 -0500" }, "message": "Optimizing: Add direct calls to math intrinsics\n\nSupport the double forms of:\n cos, sin, acos, asin, atan, atan2, cbrt, cosh, exp, expm1,\n hypot, log, log10, nextAfter, sinh, tan, tanh\n\nAdd these entries to the vector addressed off the thread pointer. Call\nthe libc routines directly, which means that we have to implement the\nnative ABI, not the ART one. For x86_64, that includes saving XMM12-15\nas the native ABI considers them caller-save, while the ART ABI\nconsiders them callee-save. We save them by marking them as used by the\ncall to the math function. For x86, this is not an issue, as all the XMM\nregisters are caller-save.\n\nOther architectures will call Java as before until they are ready to\nimplement the new intrinsics.\n\nBump the OAT version since we are incompatible with old boot.oat files.\n\nChange-Id: Ic6332c3555c09393a17d1ad4daf62932488722fb\nSigned-off-by: Mark Mendell \u003cmark.p.mendell@intel.com\u003e\n" }, { "commit": "0d5a281c671444bfa75d63caf1427a8c0e6e1177", "tree": "fd9bbe0f1c581bcc7c05bbfb2643ffe0b1fb014e", "parents": [ "dd4cbcc924c8ba2a578914a4a366996693bdcd74" ], "author": { "name": "Roland Levillain", "email": "rpl@google.com", "time": "Fri Nov 13 10:07:31 2015 +0000" }, "committer": { "name": "Roland Levillain", "email": "rpl@google.com", "time": "Sun Nov 15 12:16:41 2015 +0000" }, "message": "x86/x86-64 read barrier support for concurrent GC in Optimizing.\n\nThis first implementation uses slow paths to instrument heap\nreference loads and GC root loads for the concurrent copying\ncollector, respectively calling the artReadBarrierSlow and\nartReadBarrierForRootSlow (new) runtime entry points.\n\nNotes:\n- This implementation does not instrument HInvokeVirtual\n nor HInvokeInterface instructions (for class reference\n loads), as the corresponding read barriers are not stricly\n required with the current concurrent copying collector.\n- Intrinsics which may eventually call (on slow path) are\n disabled when read barriers are enabled, as the current\n slow path infrastructure does not support this case.\n- When read barriers are enabled, the code generated for a\n HArraySet instruction always go into the array set slow\n path for object arrays (delegating the operation to the\n runtime), as we are lacking a mechanism to keep a\n temporary register live accross a runtime call (needed for\n the instrumentation of type checking code, which requires\n two successive read barriers).\n\nBug: 12687968\nChange-Id: I14cd6107233c326389120336f93955b28ffbb329\n" }, { "commit": "3cfa4d05afa76e19ca99ec964b535a15c73683f0", "tree": "28c4950dff3700f69e3d32fc496890a722cfc379", "parents": [ "f4156986d1ba5b6dd7dfe89754c8562557cd1bc5" ], "author": { "name": "Andreas Gampe", "email": "agampe@google.com", "time": "Tue Oct 06 17:04:01 2015 -0700" }, "committer": { "name": "Andreas Gampe", "email": "agampe@google.com", "time": "Wed Oct 07 09:50:25 2015 -0700" }, "message": "ART: Remove interpreter entrypoints\n\nThese are no longer used as entrypoints. Make them proper runtime\nfunctions local to the interpreter.\n\nBump oat version.\n\nChange-Id: Icdd92e20eafc5668b68eeebf55cf624560f462b3\n" }, { "commit": "99170c636dfae4908b102347cfe9f92bad1881cc", "tree": "1ecff5dd69ea20b09e622cb88e7835a55dfa4be8", "parents": [ "5836f8465ddd0a7f5cbeec9c30d739bd0619867f" ], "author": { "name": "Mingyao Yang", "email": "mingyao@google.com", "time": "Mon Jul 06 11:10:37 2015 -0700" }, "committer": { "name": "Sebastien Hertz", "email": "shertz@google.com", "time": "Thu Sep 17 17:07:22 2015 +0200" }, "message": "Deoptimization support in optimizing compiler for setting local values\n\nDue to compiler optimizations, we may not always be able to update\nthe value of a local variable in a compiled frame (like a variable\nseen as constant by the compiler). To avoid that situation, we simply\ndeoptimize compiled frames updated by the debugger so they are\nexecuted by the interpreter with the updated value.\n\nWhen the debugger attempts to set a local variable (actually a DEX\nregister or a pair of registers) in a compiled frame, we allocate a\nShadowFrame associated to that frame (using its frame id) and set the\nnew value in that ShadowFrame. When we know we are about to continue\nthe execution of the compiled frame, we deoptimize the stack using\nthe preallocated ShadowFrame (instead of creating a new one). We\ninitialize it with the current value of all DEX registers except\nthe ones that have been set by the debugger. Therefore, the\nShadowFrame represent the runtime context modified by the debugger.\n\nBumps oat version to force recompilation.\n\nBug: 19944235\nChange-Id: I0ebe6241264f7a3be0f14ee4516c1f7436e04da6\n" }, { "commit": "0747466fca310eedea5fc49e37d54f240a0b3c0f", "tree": "6d27922fa35330dd8d863ea56c82c5f04b711822", "parents": [ "9ee5d6cdc14ac94b64ea1961bf221bad48746929" ], "author": { "name": "Sebastien Hertz", "email": "shertz@google.com", "time": "Tue Aug 25 15:12:33 2015 +0000" }, "committer": { "name": "Sebastien Hertz", "email": "shertz@google.com", "time": "Wed Aug 26 16:54:32 2015 +0200" }, "message": "Revert \"Revert \"Fix deoptimization with pending exception\"\"\n\nThis reverts commit 6e2d5747d00697a25251d25dd33b953e54709507.\n\nFixes the deoptimization path from compiled code (generated by the\nOptimizing compiler) by adding wrapper artDeoptimizeFromCompiledCode.\nThis wrapper, called through the matching assembler stub\nart_quick_deoptimize_from_compiled_code, pushes the deoptimization\ncontext just before deoptimizing the stack.\n\nBug: 23371176\nBug: 19944235\nChange-Id: Ia7082656998aebdd0157438f7e6504c120e10d3e\n" }, { "commit": "6e2d5747d00697a25251d25dd33b953e54709507", "tree": "b68a418e93780ed55abd79dc8e76f3459e884254", "parents": [ "54b62480636ae846d705fc180c7bd6cd08ec1e42" ], "author": { "name": "Sebastien Hertz", "email": "shertz@google.com", "time": "Tue Aug 25 15:05:17 2015 +0000" }, "committer": { "name": "Sebastien Hertz", "email": "shertz@google.com", "time": "Tue Aug 25 15:05:17 2015 +0000" }, "message": "Revert \"Fix deoptimization with pending exception\"\n\nThis reverts commit 54b62480636ae846d705fc180c7bd6cd08ec1e42.\n\nThis is causing test failures with Optimizing compiler.\n\nBug: 23371176\nBug: 19944235\nChange-Id: Ie3ffbcf2b6d2ca8bc93cb008a4e29a7567d04a7c\n" }, { "commit": "54b62480636ae846d705fc180c7bd6cd08ec1e42", "tree": "d46a6c7bebb45ddbbd5b0a6818b3bb2ce49f48ed", "parents": [ "f0170ded84fbcd3d9152cdbcf9ffbf74c71b03ba" ], "author": { "name": "Sebastien Hertz", "email": "shertz@google.com", "time": "Thu Aug 20 12:07:57 2015 +0200" }, "committer": { "name": "Sebastien Hertz", "email": "shertz@google.com", "time": "Tue Aug 25 15:13:49 2015 +0200" }, "message": "Fix deoptimization with pending exception\n\nWhen deoptimizing the stack, we set a fake exception in the current\nThread* (see method Thread::GetDeoptimizationException). On the next\nexception check, the QuickExceptionHandler will deoptimize the stack.\n\nThe issue is when we deoptimize while an exception is already pending\nin the current Thread*: setting the fake exception will clobber the\npending exception which is not correct. This happens in the\nartQuickToInterpreterBridge when returning from the interpreter and\nwe want to deoptimize the stack for debugging (like single-stepping).\n\nThis CL saves the pending exception before asking for deoptimization.\nThen the exception is restored just before executing the deoptimized\nframes with the interpreter.\n\nAlso cleans up the way we save deoptimization context (return value\nand pending exception).\n\nBug: 23371176\nBug: 19944235\nChange-Id: I7f4c8347b328817c452beda3399e210eba3a88a4\n" }, { "commit": "1aee900d5a0b3a8d78725a7551356bda0d8554e1", "tree": "325cb4ce99cf7824eb56dda1d85f23ad9c74f10a", "parents": [ "a09d5df5128c5c51226028d4a82ed461cf993024" ], "author": { "name": "Man Cao", "email": "manc@google.com", "time": "Tue Jul 14 22:31:42 2015 -0700" }, "committer": { "name": "Man Cao", "email": "manc@google.com", "time": "Tue Jul 28 10:45:02 2015 -0700" }, "message": "Add read barrier support to the entrypoints.\n\nAlso remove \"THIS_LOAD_REQUIRES_READ_BARRIER\" since reading\nan ArtMethod* no longer needs read barrier.\n\nstub_test should also work with read barriers now.\n\nChange-Id: I3fba18042de2f867a18dbdc38519986212bd9769\n" }, { "commit": "c6f3439b67962584cfb764133e192c3317f0e1fc", "tree": "58f31ef9ed7155cd386f139be230383d943a1c72", "parents": [ "e978aba24094cce90453ad3294b8c4536ee8e4b4", "eac4424b3420c280f97ff2f815b5dedd8dac9801" ], "author": { "name": "Mathieu Chartier", "email": "mathieuc@google.com", "time": "Tue Jul 14 01:47:39 2015 +0000" }, "committer": { "name": "Gerrit Code Review", "email": "noreply-gerritcodereview@google.com", "time": "Tue Jul 14 01:47:39 2015 +0000" }, "message": "Merge \"ART: JNI thread state transition optimization\"" }, { "commit": "eac4424b3420c280f97ff2f815b5dedd8dac9801", "tree": "4e7c31b4312aa000bd3d2250df6a05daf61523d7", "parents": [ "ec97825f8553b3a99b6dfbbb90a50fe65301ea94" ], "author": { "name": "Yu Li", "email": "yu.l.li@intel.com", "time": "Mon Jun 29 10:50:03 2015 +0800" }, "committer": { "name": "Man Cao", "email": "manc@google.com", "time": "Mon Jul 13 15:56:19 2015 -0700" }, "message": "ART: JNI thread state transition optimization\n\nThis patch improves the JNI performance by removing the explicit acquiring and\nreleasing the mutator lock when a thread state transits between suspended and\nrunnable states.\n\nThe functions responsible for changing the state were found to be the costliest\npart of the JNI. Originally, a thread needs to acquire a shared mutator lock by\na CAS instruction when entering the runnable state and also needs to release\nthe lock by a CAS when entering the native state from runnable. This patch\nremoves these CAS operations when a thread state transits between suspended and\nrunnable. A thread in the runnable state is considered to have shared ownership\nof the mutator lock and therefore transitions in and out of the runnable state\nhave associated implication on the mutator lock ownership. Meanwhile, a barrier\nis added to control suspending all threads from running.\n\nJNI transition overhead was reduced by 25% on IA platform and by 17% on ARM\nplatform by this patch, while it has little impact on GC pause time (measured\nwith \"suspend all histogram\").\n\nChange-Id: Icee95d8ffff1bbfc95309a41cc48836536fec689\nSigned-off-by: Yu, Li \u003cyu.l.li@intel.com\u003e\nSigned-off-by: Haitao, Feng \u003chaitao.feng@intel.com\u003e\nSigned-off-by: Lei, Li \u003clei.l.li@intel.com\u003e\n" }, { "commit": "0b71357fb52be9bb06d35396a3042b4381b01041", "tree": "44b8d6b0ca4a71f33cda55068fa9e14864c55625", "parents": [ "0e87d1809443d41b431ce3a686b4e074df2d7b8b" ], "author": { "name": "Hiroshi Yamauchi", "email": "yamauchi@google.com", "time": "Tue Jun 16 18:29:23 2015 -0700" }, "committer": { "name": "Hiroshi Yamauchi", "email": "yamauchi@google.com", "time": "Mon Jul 13 15:50:20 2015 -0700" }, "message": "Thread-local mark stacks for the CC collector.\n\nThread-local mark stacks are assigned to mutators where they push\nreferences in read barriers to reduce the (CAS) synchronization cost\nin a global mark stack/queue.\n\nWe step through three mark stack modes (thread-local, shared,\nGC-exclusive) and use per-thread flags to disable/enable system weak\naccesses (only for the CC collector) instead of the existing global\none to safely perform the marking phase. The reasons are 1)\nthread-local mark stacks for mutators need to be revoked using a\ncheckpoint to avoid races (incorrectly leaving a reference on mark\nstacks) when terminating marking, and 2) we can’t use a checkpoint\nwhile system weak accesses are disabled (or a deadlock would\nhappen). More details are described in the code comments.\n\nPerformance improvements in Ritzperf EAAC: a ~2.8% improvement\n(13290-\u003e12918) in run time and a ~23% improvement (51.6s-\u003e39.8s) in\nthe total GC time on N5.\n\nBug: 12687968\nChange-Id: I5d234d7e48bf115cd773d38bdb62ad24ce9116c7\n" }, { "commit": "1f2d3ba6af52cf6f566deb38b7e07735c9a08fb6", "tree": "af6ae612d43c50703292d39a8a0b37dda3f919a6", "parents": [ "ccd6337f31d13706c602f3d9436e9b4025075b63" ], "author": { "name": "Mingyao Yang", "email": "mingyao@google.com", "time": "Mon May 18 12:12:50 2015 -0700" }, "committer": { "name": "Mingyao Yang", "email": "mingyao@google.com", "time": "Mon Jun 08 00:53:55 2015 -0700" }, "message": "Fix nested deoptimization.\n\nHandle nested deoptimization cases. Create a stacked shadow frame\nrecords to keep track of deoptimization shadow frames. Shadow frames\nunder construction can be tracked in the same stack.\n\nBug: 20845490\nChange-Id: I768285792c29e7c3cfcd21e7a2600802506024d8\n" }, { "commit": "449357d3f61bdd134967ecdacc3516e1707cf882", "tree": "650ef203d23926485398200888cadfc9aa7608fc", "parents": [ "2519fc40d4ae89322d28d1ff610fe81bb90fb564" ], "author": { "name": "Andreas Gampe", "email": "agampe@google.com", "time": "Mon Jun 01 22:29:51 2015 -0700" }, "committer": { "name": "Andreas Gampe", "email": "agampe@google.com", "time": "Wed Jun 03 16:10:33 2015 -0700" }, "message": "ART: Refactor Thread::Init\n\nThis refactor allows the parent thread to allocate the JNIEnvExt\nfor the child (with a fallback in place in Init). This allows to\nthrow an OOME in CreateNativeThread instead of aborting in the\nchild.\n\nBug: 21291279\n\n(cherry picked from commit 520abbd0edcf333f07164539620ce65258c72383)\n\nChange-Id: Iccc1a5c202999f5bfacec706d9833e53135ba2fa\n" }, { "commit": "1cc71ebf333ca323ae0e130fefbce4593e385c10", "tree": "e94897ebb36a21f1c276fc69c44f6a3522cbe093", "parents": [ "35b6625c21e9304dd79700f4ff1c26a7e30d2b2d" ], "author": { "name": "Hiroshi Yamauchi", "email": "yamauchi@google.com", "time": "Thu May 07 10:47:27 2015 -0700" }, "committer": { "name": "Hiroshi Yamauchi", "email": "yamauchi@google.com", "time": "Thu May 07 11:28:08 2015 -0700" }, "message": "Insert a read barrier in the JNI bridge.\n\nBug: 20720510\nBug: 12687968\nChange-Id: Ia9edb614853bad45ec25d6e2142361a8bda1eccf\n" }, { "commit": "848f70a3d73833fc1bf3032a9ff6812e429661d9", "tree": "b0349b3a40aab5a915af491b100659a5ca9fbbf6", "parents": [ "d14438f0c5071962be7fab572b54687d32d9d087" ], "author": { "name": "Jeff Hao", "email": "jeffhao@google.com", "time": "Wed Jan 15 13:49:50 2014 -0800" }, "committer": { "name": "Jeff Hao", "email": "jeffhao@google.com", "time": "Mon Apr 27 18:54:52 2015 -0700" }, "message": "Replace String CharArray with internal uint16_t array.\n\nSummary of high level changes:\n - Adds compiler inliner support to identify string init methods\n - Adds compiler support (quick \u0026 optimizing) with new invoke code path\n that calls method off the thread pointer\n - Adds thread entrypoints for all string init methods\n - Adds map to verifier to log when receiver of string init has been\n copied to other registers. used by compiler and interpreter\n\nChange-Id: I797b992a8feb566f9ad73060011ab6f51eb7ce01\n" }, { "commit": "d43b3ac88cd46b8815890188c9c2b9a3f1564648", "tree": "6c599c3f40d57e92786bd7f41c0541d9eaa2643b", "parents": [ "a109632b240f3c9355ca95500f6f48e4478e3c51" ], "author": { "name": "Mingyao Yang", "email": "mingyao@google.com", "time": "Wed Apr 01 14:03:04 2015 -0700" }, "committer": { "name": "Mingyao Yang", "email": "mingyao@google.com", "time": "Wed Apr 01 14:05:13 2015 -0700" }, "message": "Revert \"Revert \"Deoptimization-based bce.\"\"\n\nThis reverts commit 0ba627337274ccfb8c9cb9bf23fffb1e1b9d1430.\n\nChange-Id: I1ca10d15bbb49897a0cf541ab160431ec180a006\n" }, { "commit": "0ba627337274ccfb8c9cb9bf23fffb1e1b9d1430", "tree": "0e1d0813c1d8d1c7239a900c1653296975713df0", "parents": [ "e295e6ec5beaea31be5d7d3c996cd8cfa2053129" ], "author": { "name": "Andreas Gampe", "email": "agampe@google.com", "time": "Tue Mar 24 02:39:46 2015 +0000" }, "committer": { "name": "Andreas Gampe", "email": "agampe@google.com", "time": "Tue Mar 24 02:39:46 2015 +0000" }, "message": "Revert \"Deoptimization-based bce.\"\n\nThis breaks compiling the core image:\n\n Error after BCE: art::SSAChecker: Instruction 219 in block 1 does not dominate use 221 in block 1.\n\nThis reverts commit e295e6ec5beaea31be5d7d3c996cd8cfa2053129.\n\nChange-Id: Ieeb48797d451836ed506ccb940872f1443942e4e\n" }, { "commit": "e295e6ec5beaea31be5d7d3c996cd8cfa2053129", "tree": "4d8a657d23d511743ce35bee596544d7f652efdb", "parents": [ "d24ba2c44c76a2b2dd13aafe8f7981c15be31a98" ], "author": { "name": "Mingyao Yang", "email": "mingyao@google.com", "time": "Sat Mar 07 06:37:59 2015 -0800" }, "committer": { "name": "Mingyao Yang", "email": "mingyao@google.com", "time": "Mon Mar 23 16:39:37 2015 -0700" }, "message": "Deoptimization-based bce.\n\nA mechanism is introduced that a runtime method can be called\nfrom code compiled with optimizing compiler to deoptimize into\ninterpreter. This can be used to establish invariants in the managed code\nIf the invariant does not hold at runtime, we will deoptimize and continue\nexecution in the interpreter. This allows to optimize the managed code as\nif the invariant was proven during compile time. However, the exception\nwill be thrown according to the semantics demanded by the spec.\n\nThe invariant and optimization included in this patch are based on the\nlength of an array. Given a set of array accesses with constant indices\n{c1, ..., cn}, we can optimize away all bounds checks iff all 0 \u003c\u003d min(ci) and\nmax(ci) \u003c array-length. The first can be proven statically. The second can be\nestablished with a deoptimization-based invariant. This replaces n bounds\nchecks with one invariant check (plus slow-path code).\n\nChange-Id: I8c6e34b56c85d25b91074832d13dba1db0a81569\n" }, { "commit": "12d625f87bcd6c4059a205bb39007a255f57f382", "tree": "b69f6f80f56977c176e0c441869d2f1de06ede70", "parents": [ "b871a15f1f662c8efe10d41199180bd00b6decd1" ], "author": { "name": "Mathieu Chartier", "email": "mathieuc@google.com", "time": "Fri Mar 13 11:33:37 2015 -0700" }, "committer": { "name": "Mathieu Chartier", "email": "mathieuc@google.com", "time": "Fri Mar 13 16:38:25 2015 -0700" }, "message": "Change method verifiers to be thread local roots\n\nBug: 10921004\n\nChange-Id: I3a1425d76cd380587ba67ef6d5ec1227564e55bf\n" }, { "commit": "14691c5e786e8c2c5734f687e4c96217340771be", "tree": "7c2156671b323c70ffdd1d48d5e2f1d1de79c5fc", "parents": [ "3d7d2af4c6502b771b032ee9bf3ab30e78f9c60d" ], "author": { "name": "Nicolas Geoffray", "email": "ngeoffray@google.com", "time": "Thu Mar 05 10:40:17 2015 +0000" }, "committer": { "name": "Nicolas Geoffray", "email": "ngeoffray@google.com", "time": "Mon Mar 09 10:09:33 2015 +0000" }, "message": "Compute the right catch location for the debugger.\n\nAlso remove tls ThrowLocation, it is not needed anymore.\n\nChange-Id: I78fddf09ce968ca475e39c17fa76d699c589c8d9\n" }, { "commit": "7642cfc90fc9c3ebfd8e3b5041915705c93b5cf0", "tree": "807b3c797483310ac23954c5eddb7441b91749c5", "parents": [ "dc47e986941b1a3754447fabea272485f3f0f382" ], "author": { "name": "Nicolas Geoffray", "email": "ngeoffray@google.com", "time": "Thu Feb 26 10:56:09 2015 +0000" }, "committer": { "name": "Nicolas Geoffray", "email": "ngeoffray@google.com", "time": "Tue Mar 03 17:50:49 2015 +0000" }, "message": "Change how we report exceptions to the debugger.\n\nThis is only a refactoring/cleanup. Bug fixes with respect\nto catch location, and more cleanups will follow.\n\nChange-Id: I30d3c6260b0c8f8115a811621397225b88f2063a\n" }, { "commit": "2cd334ae2d4287216523882f0d298cf3901b7ab1", "tree": "b72d3d07e5a04151caca96cae345075b6e4452b0", "parents": [ "604e2828896fbb8663897d1e75112da7305ead4c" ], "author": { "name": "Hiroshi Yamauchi", "email": "yamauchi@google.com", "time": "Fri Jan 09 14:03:35 2015 -0800" }, "committer": { "name": "Hiroshi Yamauchi", "email": "yamauchi@google.com", "time": "Fri Jan 23 14:07:32 2015 -0800" }, "message": "More of the concurrent copying collector.\n\nBug: 12687968\nChange-Id: I62f70274d47df6d6cab714df95c518b750ce3105\n" }, { "commit": "956af0f0cb05422e38c1d22cbef309d16b8a1a12", "tree": "b558c804d206dad8da648b815750f1b3c97610ae", "parents": [ "407d77f344cfbdbbfb50531c5f0766bc0892e2fe" ], "author": { "name": "Elliott Hughes", "email": "enh@google.com", "time": "Thu Dec 11 14:34:28 2014 -0800" }, "committer": { "name": "Elliott Hughes", "email": "enh@google.com", "time": "Fri Dec 12 09:33:34 2014 -0800" }, "message": "Remove portable.\n\nChange-Id: I3bf3250fa866fd2265f1b115d52fa5dedc48a7fc\n" }, { "commit": "13735955f39b3b304c37d2b2840663c131262c18", "tree": "0a731ac42b8230f9929172fa3e3d8051874e2b18", "parents": [ "25b18bbdaa36ff936eb44f228f0518d4223e9d52" ], "author": { "name": "Ian Rogers", "email": "irogers@google.com", "time": "Wed Oct 08 12:43:28 2014 -0700" }, "committer": { "name": "Ian Rogers", "email": "irogers@google.com", "time": "Thu Oct 09 16:05:58 2014 -0700" }, "message": "stdint types all the way!\n\nChange-Id: I4e4ef3a2002fc59ebd9097087f150eaf3f2a7e08\n" }, { "commit": "8ce6b9040747054b444a7fa706503cd257801936", "tree": "04712170addb252d307ef9015abfc9bfc2b73581", "parents": [ "a0a0da29e7d4d5c1bd471c49f1a4b6ec98fb767a" ], "author": { "name": "Dave Allison", "email": "dallison@google.com", "time": "Tue Aug 26 11:07:58 2014 -0700" }, "committer": { "name": "Dave Allison", "email": "dallison@google.com", "time": "Wed Aug 27 12:47:44 2014 -0700" }, "message": "Handle nested signals\n\nThis allows for signals to be raised inside the ART signal handler.\nThis can occur when the JavaStackTraceHandler attempts to generate\na stack trace and something goes wrong.\n\nIt also fixes an issue where the fault manager was not being\ncorrectly shut down inside the signal chaining code. In this\ncase the signal handler was not restored to the original.\n\nBug: 17006816\nBug: 17133266\n\n(cherry picked from commit fabe91e0d558936ac26b98d2b4ee1af08f58831d)\n\nChange-Id: I10730ef52d5d8d34610a5293253b3be6caf4829e\n" }, { "commit": "37f05ef45e0393de812d51261dc293240c17294d", "tree": "7c7793862efa52e1deb42babbdcb652c245ab941", "parents": [ "e25826e28ea65d9c1aa23f84788a091c677b20c7" ], "author": { "name": "Fred Shih", "email": "ffred@google.com", "time": "Wed Jul 16 18:38:08 2014 -0700" }, "committer": { "name": "Fred Shih", "email": "ffred@google.com", "time": "Mon Aug 25 11:16:53 2014 -0700" }, "message": "Reduced memory usage of primitive fields smaller than 4-bytes\n\nReduced memory used by byte and boolean fields from 4 bytes down to a\nsingle byte and shorts and chars down to two bytes. Fields are now\narranged as Reference followed by decreasing component sizes, with\nfields shuffled forward as needed.\n\nBug: 8135266\nChange-Id: I65eaf31ed27e5bd5ba0c7d4606454b720b074752\n" }, { "commit": "648d7112609dd19c38131b3e71c37bcbbd19d11e", "tree": "54062831327c660acb309e877e8d8df9ba0c2d5d", "parents": [ "99c251bbd225dd97d0deece29559a430b12a0b66" ], "author": { "name": "Dave Allison", "email": "dallison@google.com", "time": "Fri Jul 25 16:15:27 2014 -0700" }, "committer": { "name": "Dave Allison", "email": "dallison@google.com", "time": "Wed Aug 13 09:01:41 2014 -0700" }, "message": "Reduce stack usage for overflow checks\n\nThis reduces the stack space reserved for overflow checks to 12K, split\ninto an 8K gap and a 4K protected region. GC needs over 8K when running\nin a stack overflow situation.\n\nAlso prevents signal runaway by detecting a signal inside code that\nresulted from a signal handler invokation. And adds a max signal count to\nthe SignalTest to prevent it running forever.\n\nAlso reduces the number of iterations for the InterfaceTest as this was\ntaking (almost) forever with the --trace option on run-test.\n\nBug: 15435566\n\nChange-Id: Id4fd46f22d52d42a9eb431ca07948673e8fda694\n" }, { "commit": "d9cb8ae2ed78f957a773af61759432d7a7bf78af", "tree": "884d76d6e47193f704a7c7cb27c9a6c1ed2b49f3", "parents": [ "ebaca192314e21d26b97646fa962e468ff07b893" ], "author": { "name": "Douglas Leung", "email": "douglas@mips.com", "time": "Wed Jul 09 14:28:35 2014 -0700" }, "committer": { "name": "Douglas Leung", "email": "douglas@mips.com", "time": "Tue Jul 15 18:39:57 2014 -0700" }, "message": "Fix art test failures for Mips.\n\nThis patch fixes the following art test failures for Mips:\n003-omnibus-opcodes\n030-bad-finalizer\n041-narrowing\n059-finalizer-throw\n\nChange-Id: I4e0e9ff75f949c92059dd6b8d579450dc15f4467\nSigned-off-by: Douglas Leung \u003cdouglas@mips.com\u003e\n" }, { "commit": "e63db27db913f1a88e2095a1ee8239b2bb9124e8", "tree": "893dee6783bca6717259321a6e4ba029c9c123e2", "parents": [ "07b8441303ea82fca3cb85d71ecf8752d73cedd7" ], "author": { "name": "Ian Rogers", "email": "irogers@google.com", "time": "Tue Jul 15 15:36:11 2014 -0700" }, "committer": { "name": "Ian Rogers", "email": "irogers@google.com", "time": "Tue Jul 15 17:07:49 2014 -0700" }, "message": "Break apart header files.\n\nCreate libart-gtest for common runtime and compiler gtest routines.\nRename CompilerCallbacksImpl that is quick compiler specific.\nRename trace clock source constants to not use the overloaded profiler term.\n\nChange-Id: I4aac4bdc7e7850c68335f81e59a390133b54e933\n" }, { "commit": "86797a791d692f81def5c1b5f0918992c49ed122", "tree": "09cb46c5aa56e39a6399e3f3620dc2047948b872", "parents": [ "29978887552542e3b7e7792070dad06392377648" ], "author": { "name": "Serban Constantinescu", "email": "serban.constantinescu@arm.com", "time": "Thu Jun 19 16:17:56 2014 +0100" }, "committer": { "name": "Andreas Gampe", "email": "agampe@google.com", "time": "Mon Jun 30 14:00:23 2014 -0700" }, "message": "AArch64: Add memcmp16() for Arm64; ensure xSELF not clobbered\n\nThis patch modifies memcmp() to memcmp16(). Please note that this\nimplementation of memcmp16() is based on the bionic\u0027s memcmp().\n\nHowever, to reflect a recent specification change, the file has been\nmodified to respect the new String.compareTo() behavior.\n\nA test for memcmp16() has been added. The string_compareto test in\nstub_test has been changed to invoke __memcmp16 in assembly stubs.\n\nAdd artIsAssignableFromCode to the list of native downcalls to\nstore and reload x18. Remove CheckSuspendFromCode, as it is unused.\n\nSigned-off-by: Serban Constantinescu \u003cserban.constantinescu@arm.com\u003e\nChange-Id: Ie0b5425ecfb62906d29a5d02e84c7e07ffb34a11\n" }, { "commit": "4d0589c90971e19c25894414ae7da579269e1fe2", "tree": "0bb8a8bea051cfee85e26719eaf4045da9fb2132", "parents": [ "69d57a89595c7c0fba7b7f7b7c6b431a92137215" ], "author": { "name": "Andreas Gampe", "email": "agampe@google.com", "time": "Tue Jun 10 16:10:56 2014 -0700" }, "committer": { "name": "Andreas Gampe", "email": "agampe@google.com", "time": "Tue Jun 10 16:21:33 2014 -0700" }, "message": "ART: Move __memcmp16 from Bionic to ART\n\nHandle __memcmp16 / MemCmp16 in ART. Import assembly implementations\nfor arm and mips from Bionic. Use a generic C version for all other\nplatforms.\n\nRemoves the memcmp16 quick entrypoint, as it is never used. Bump\nthe oat version and update thread.cc and checks to reflect the\nstructural change.\n\nChange-Id: I54a5a1da2a0a43ef271c8aeda0bf2276b8b11ac6\n" }, { "commit": "4352b4556c138eb9f583367d678531930b5b8fb0", "tree": "92c0d56eb32f0dedfbc8ab8b1615e9afb409916d", "parents": [ "d2395646c71d4e781d7362b025d49df482ffec94" ], "author": { "name": "Andreas Gampe", "email": "agampe@google.com", "time": "Wed Jun 04 18:59:01 2014 -0700" }, "committer": { "name": "Andreas Gampe", "email": "agampe@google.com", "time": "Wed Jun 04 19:00:38 2014 -0700" }, "message": "ART: Add a test checking TLS offsets and entrypoints\n\nAdd a test (runtime for now, as compile-time checks seem not\npossible with current infrastructure) that checks the structure\nof the thread tls and entrypoint structs. A failure of the test\nindicates a structural change, which hints at a necessary oat\nversion bump.\n\nChange-Id: I500b5cd940c916ebfc1580e9dd2c287c4d263956\n" } ] }