| 5863f85483c8cc0f21adbd44698fa1018c72f9f7 |
|
23-Mar-2017 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: java.lang.System.arraycopy() for copying char[] to char[].
Test: run-test --64 --no-prebuild --optimizing 011-array-copy
Test: run-test --64 --no-prebuild 011-array-copy
Test: run-test --64 --optimizing 011-array-copy
Test: run-test --64 011-array-copy
Test: ART_TEST_OPTIMIZING=true test-art-target-run-test
Test: booted MIPS64R6 emulator.
Change-Id: I418571c639b2776869b3c8f3f67c09aadbb30133
|
| 716d0738c0ed8f924a44e5c645fa89c1a6079c95 |
|
07-Apr-2017 |
Goran Jakovljevic <Goran.Jakovljevic@imgtec.com> |
MIPS64: Fix Math.ceil/floor intrinsics
The latest MIPS64R6 emulator supports NAN2008 standard. When
FCSR.NAN2008=1 (required from R6) ceil.l.d and floor.l.d instructions
will return -2^63 when the input value is smaller than -2^63. This
wasn't the case when FCSR.NAN2008=0. In that case, result from the
instructions was 2^63-1 when the input value was smaller than -2^63.
This fixes test 082-inline-execute.
Test: ./testrunner.py --target --optimizing --64 -j1 (in QEMU)
Change-Id: I3d2cdd1d55b3694549f88f4f5b903a0c4f1c0d09
|
| 74c2058ed83f43aa59f467ac4ecc730edbe42e41 |
|
29-Mar-2017 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Add direct calls to math intrinsics.
- cos - sin - acos - asin
- atan - atan2 - cbrt - cosh
- exp - expm1 - hypot - log
- log10 - nextAfter - sinh - tan
- tanh
Test: run-test --64 --no-prebuild --optimizing 123-inline-execute2
Test: run-test --64 --no-prebuild 123-inline-execute2
Test: run-test --64 --optimizing 123-inline-execute2
Test: run-test --64 123-inline-execute2
Test: Booted MIPS64R6 emulator.
Change-Id: I989a5469e6732dd42f39e8305c3d12c32a75eab4
|
| 1595815c2a914a78df7dfb6f0082f47d4e82bb36 |
|
10-Feb-2017 |
Alexey Frunze <Alexey.Frunze@imgtec.com> |
MIPS: Implement read barriers.
This is the core functionality. Further improvements
will be done separately.
This also adds/moves memory barriers where they belong and
removes the UnsafeGetLongVolatile and UnsafePutLongVolatile
MIPS32 intrinsics as they need to load/store a pair of
registers atomically, which is not supported directly by
the CPU.
Test: booted MIPS32R2 in QEMU
Test: test-art-target-run-test
Test: booted MIPS64 (with 2nd arch MIPS32R6) in QEMU
Test: "testrunner.py --target --optimizing -j1"
Test: same MIPS64 boot/test with ART_READ_BARRIER_TYPE=TABLELOOKUP
Test: "testrunner.py --target --optimizing --32 -j2" on CI20
Test: same CI20 test with ART_READ_BARRIER_TYPE=TABLELOOKUP
Change-Id: I0ff91525fefba3ec1cc019f50316478a888acced
|
| 366d43387f8e31fb64b31419126c88d36b6ca491 |
|
23-Mar-2017 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Remove memcpy() from java.lang.String.getChars intrinsic.
Test: run-test --64 --optimizing 020-string
Test: run-test --64 020-string
Test: run-test --64 --no-prebuild --optimizing 020-string
Test: run-test --64 --no-prebuild 020-string
Test: mma -j2 ART_TEST_OPTIMIZING=true test-art-target-run-test
Test: mma test-art-target-gtest -j2
Test: booted MIPS64R6 emulator.
Note: All tests run against MIPS64 QEMU.
Change-Id: I8ad3e39c66a489779476f7e9f9f88cd0c6270c20
|
| 331605a7ba842573b3876e14c933175382b923c8 |
|
01-Mar-2017 |
Nicolas Geoffray <ngeoffray@google.com> |
Revert "Revert "Intrinsify Integer.valueOf.""
Fix heap poisoning.
LOG INFO instead of ERROR to avoid run-test failures with --no-image.
bug:30933338
Test: ART_HEAP_POISONING=true test-art-host test-art-target
This reverts commit db7b44ac3ea80a722aaed12e913ebc1661a57998.
Change-Id: I0b7d4f1eb11c62c9a3df8e0de0b1a5d8af760181
|
| db7b44ac3ea80a722aaed12e913ebc1661a57998 |
|
28-Feb-2017 |
Nicolas Geoffray <ngeoffray@google.com> |
Revert "Intrinsify Integer.valueOf."
Heap poisoning missing
jit-gcstress not optimizing it.
bug:30933338
This reverts commit cd0b27287843cfd904dd163056322579ab4bbf27.
Change-Id: I5ece1818afbca5214babb6803f62614a649aedeb
|
| 64fa84fba1d46afd5a2dc7dc3cc1de77461888bc |
|
27-Feb-2017 |
Goran Jakovljevic <Goran.Jakovljevic@imgtec.com> |
Apply String.equals() optimizations on MIPS32 and MIPS64
Also extended test 536-checker-intrinsic-optimization.
Test: mma test-art-target-run-test in QEMU (MIPS64R6 and MIPS32R6)
Test: mma test-art-target-run-test on CI20 (MIPS32R2)
Change-Id: I6bff42f81dcb05094ac698181df16c56193bb4a8
|
| cd0b27287843cfd904dd163056322579ab4bbf27 |
|
23-Feb-2017 |
Nicolas Geoffray <ngeoffray@google.com> |
Intrinsify Integer.valueOf.
Improves performance of ArrayListStress and Ritz by ~10% and ~3%.
Test: test-art-host test-art-target
bug: 30933338
Change-Id: I639046e3a18dae50069d3a7ecb538a900bb590a1
|
| c061de1236e98fdd34d0214a9bbcc0e2149ff226 |
|
14-Feb-2017 |
Alexey Frunze <Alexey.Frunze@imgtec.com> |
MIPS: Implement heap poisoning in ART's Optimizing compiler.
This is in preparation for read barrier support.
Bug: 12687968
Test: test-art-host-gtest
Test: booted MIPS32R2 in QEMU
Test: test-art-target
Test: booted MIPS64 (with 2nd arch MIPS32R6) in QEMU
Test: test-art-target (both MIPS64R6 and MIPS32R6)
Note: built with ART_HEAP_POISONING=true.
Change-Id: I0e6e04ff8de2fc8ca6126388409fa218e6920734
|
| f94fa81e20d00929ef52707cd577353b95d40284 |
|
10-Feb-2017 |
Goran Jakovljevic <Goran.Jakovljevic@imgtec.com> |
String Compression for MIPS32 and MIPS64
Changes on intrinsics and Code Generation on MIPS32 and MIPS64 for
string compression feature.
Testing is done with STRING_COMPRESSION_ENABLED = true (in libcore),
mirror::kUseStringCompression = true and STRING_COMPRESSION_FEATURE set
to 1.
Test: booted MIPS32 and MIPS64 in QEMU
Test: mma test-art-target-run-test on CI20 (MIPS32R2)
Test: mma test-art-target-run-test in QEMU (MIPS64R6)
Change-Id: If50a6b6c0792bfa34d4fdff6bf2c7542211d2689
|
| 5e8d5f01b0fe87a6c649bd3a9f1534228b93423d |
|
18-Oct-2016 |
Roland Levillain <rpl@google.com> |
Fix some typos in ART.
Test: m build-art-host
Test: m cpplint-art
Change-Id: Ifc6ce3d0d645c4a8dca72dd483fc03fc05077130
|
| e36605910cb13da1440fb9d7a8293842a9209c97 |
|
09-Nov-2016 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: java.lang.String.getChars
Test: run-test --64 --optimizing 020-string
Test: run-test --64 020-string
Test: run-test --64 --no-prebuild --optimizing 020-string
Test: run-test --64 --no-prebuild 020-string
Test: run-test --64 --optimizing 082-inline-execute
Test: run-test --64 082-inline-execute
Test: run-test --64 --no-prebuild --optimizing 082-inline-execute
Test: run-test --64 --no-prebuild 082-inline-execute
Test: mma -j2 ART_TEST_OPTIMIZING=true test-art-target-run-test
Test: mma test-art-target-gtest -j2
Test: booted MIPS64R6 emulator.
Note: All tests run against MIPS64 QEMU.
Change-Id: I48b9a87465f2516044a2e4f598cc5dce56b0d1c9
|
| 71bf7b43380eb445973f32a7f789d9670f8cc97d |
|
16-Nov-2016 |
Aart Bik <ajcbik@google.com> |
Optimizations around escape analysis. With tests.
Details:
(1) added new intrinsics
(2) implemented optimizations
more !can be null information
more null check removals
replace return-this uses with incoming parameter
remove dead StringBuffer/Builder calls (with escape analysis)
(3) Fixed exposed bug in CanBeMoved()
Performance gain:
This improves CafeineString by about 360%
(removes null check from first loop, eliminates second loop completely)
Test: test-art-host
Change-Id: Iaf16a1b9cab6a7386f43d71c6b51dd59600e81c1
|
| ff7d89c0364f6ebd0f0798eb18ef8bd62917de6a |
|
07-Nov-2016 |
Aart Bik <ajcbik@google.com> |
Allow read side effects for removing dead instructions.
Rationale:
Instructions that only have the harmless read side effect may
be removed when dead as well, we were too strict previously.
As proof of concept, this cl also provides more accurate information
on a few string related intrinsics. This removes the dead indexOf
from CaffeineString (17% performance improvement, big bottleneck
of the StringBuffer's toString() still remains in loop).
Test: test-art-host
Change-Id: Id835a8e287e13e1f09be6b46278a039b8865802e
|
| 68db2a9514d67708a21bb0975aee4c5d1c2bf49e |
|
15-Sep-2016 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Fix overlapping use of "in" & "out" registers.
Test: Boot MIPS64 QEMU
Test: 568-checker-onebit
Change-Id: Ifc89fd8df674b1f3ffcdde52256a35b4a3562d45
|
| fc734088e6656a918b6c75094eb942a22bd799e8 |
|
19-Jul-2016 |
Serban Constantinescu <serban.constantinescu@linaro.org> |
Extend the InvokeRuntime() changes to mips64.
Change-Id: I3f825746053b9288ca31ab5e823d6a1648dfd894
|
| 542451cc546779f5c67840e105c51205a1b0a8fd |
|
26-Jul-2016 |
Andreas Gampe <agampe@google.com> |
ART: Convert pointer size to enum
Move away from size_t to dedicated enum (class).
Bug: 30373134
Bug: 30419309
Test: m test-art-host
Change-Id: Id453c330f1065012e7d4f9fc24ac477cc9bb9269
|
| 806f0122e923581f559043e82cf958bab5defc87 |
|
09-Mar-2016 |
Serban Constantinescu <serban.constantinescu@linaro.org> |
Add support for CallKind::kCallOnMainAndSlowPath
Some of the intrinsics call on both the main and slowpath. This patch
adds support for such a CallKind and marks the intrinsics accordingly.
This will be exercised by a later patch that refactors all the runtime
calls to use InvokeRuntime().
Please note that without this patch, the calls to ValidateInvokeRuntime()
exercised by the following patches would fail.
Change-Id: I450571b8b47280a004b714996189ba6db13fb57d
|
| 54ff482710910929900f8348a19c5b875e519237 |
|
07-Jul-2016 |
Serban Constantinescu <serban.constantinescu@linaro.org> |
Rename kCall to kCallOnMainOnly
This patch renames kCall to kCallOnMainOnly in preparation for
the next patch in this series which will be adding kCallOnMainAndSlowPath.
Note: With this patch there will be places where we use kCallOnMainOnly
even though we call on the slow path too. The next patch in this series
will fix that.
Test: ART host tests.
Change-Id: Iabfdb0901990d163be5d780f3bdd2fab6fa17b32
|
| ab922503cee2b105dfd9dbdde9fb60c26a35d2df |
|
15-Apr-2016 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Highest/Lowest Bit Intrinsic Support
- int java.lang.Integer.highestOneBit(int)
- long java.lang.Long.highestOneBit(long)
- int java.lang.Integer.lowestOneBit(int)
- long java.lang.Long.lowestOneBit(long)
Change-Id: I0db7858542130d759ee7d17ecb1eadb7ec3dc04c
|
| 87f3fcbd0db352157fc59148e94647ef21b73bce |
|
28-Apr-2016 |
Vladimir Marko <vmarko@google.com> |
Replace String.charAt() with HIR.
Replace String.charAt() with HArrayLength, HBoundsCheck and
HArrayGet. This allows GVN on the HArrayLength and BCE on
the HBoundsCheck as well as using the infrastructure for
HArrayGet, i.e. better handling of constant indexes than
the old intrinsic and using the HArm64IntermediateAddress.
Bug: 28330359
Change-Id: I32bf1da7eeafe82537a60416abf6ac412baa80dc
|
| 7adaab070bbe9783130e78eea163c459303c980b |
|
21-Apr-2016 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: java.lang.Math.round
- int java.lang.Math.round(float)
- long java.lang.Math.round(double)
BUG=26327751
Change-Id: I8bb7a5f32375b06b886a0babf39eb3e20df3a085
|
| da05108b17b020b28555a8d5db5caa42e4435981 |
|
17-May-2016 |
Vladimir Marko <vmarko@google.com> |
Clean up String.indexOf() intrinsics.
Additional cleanup after
https://android-review.googlesource.com/223260
Bug: 28330359
Change-Id: I88def196babec70123896ef581ec8d61bb1b9a9a
|
| fb6c90a1d7c8333c74c09f64f7eb2f402c3ea002 |
|
06-May-2016 |
Vladimir Marko <vmarko@google.com> |
Improve String.indexOf() intrinsics.
If the code point input is a char, we don't need the slow
path. Also improve the slow-path check (if we do need it)
on arm and arm64 to avoid loading 0xffff into a register.
Bug: 28330359
Change-Id: Ie6514c16126717bb0b11e3c7ab2b60eaa70fed4c
|
| 7fda7854ed734c4cdc786e46fcfdaa71ec600ecf |
|
22-Apr-2016 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Implement bitCount intrinsics.
- int java.lang.Integer.bitCount(int)
- int java.lang.Long.bitCount(long)
Change-Id: If2390beeb5b900e8680ead1927e0455b35f1948a
|
| ddc4055abab40740e689d91e9a4fe20a7b8e5d28 |
|
11-Mar-2016 |
Goran Jakovljevic <Goran.Jakovljevic@imgtec.com> |
MIPS: Don't use $t8 for calling entrypoints
When jumping to entrypoints, $t9 register must be used. Value of $gp
is calculated based on value from $t9 and it should contain the
address of the first instruction of the entrypoint.
This CL enables MIPS32 and MIPS64 to boot.
Change-Id: Idf0f7f479cceafabb88b1b087da190dbda86e1c3
|
| f969a209c30e3af636342d2fb7851d82a2529bf7 |
|
09-Mar-2016 |
Roland Levillain <rpl@google.com> |
Fix and enable java.lang.StringFactory intrinsics.
The following intrinsics were not considered by the
intrinsics recognizer:
- StringNewStringFromBytes
- StringNewStringFromChars
- StringNewStringFromString
This CL enables them and add tests for them.
This CL also:
- Fixes the locations of the ARM64 & MIPS64
StringNewStringFromString intrinsics.
- Fixes the definitions of the FOUR_ARG_DOWNCALL macros on
ARM and x86, which are used to implement the
art_quick_alloc_string_from_bytes* runtime entry points.
- Fixes PC info (stack maps) recording in the
StringNewStringFromBytes, StringNewStringFromChars and
StringNewStringFromString ARM, ARM64 & MIPS64 intrinsics.
Bug: 27425743
Change-Id: I38c00d3f0b2e6b64f7d3fe9146743493bef9e45c
|
| 1193259cb37c9763a111825aa04718a409d07145 |
|
08-Mar-2016 |
Aart Bik <ajcbik@google.com> |
Implement the 1.8 unsafe memory fences directly in HIR.
Rationale:
More efficient since it exposes full semantics to
all operations on the graph and allows for proper
code generation for all architectures.
bug=26264765
Change-Id: Ic435886cf0645927a101a8502f0623fa573989ff
|
| cf283daf579e9eda586f312c3fc89444601e2525 |
|
20-Jan-2016 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS32: java.lang.Thread, and java.lang.String intrinsics:
- Thread java.lang.Thread.currentThread()
- int java.lang.String.compareTo(String anotherString)
- int java.lang.String.indexOf(int ch)
- int java.lang.String.indexOf(int ch, int fromIndex)
- java.lang.StringFactory.newStringFromBytes(byte[] data,
int high,
int offset,
int byteCount)
- java.lang.StringFactory.newStringFromChars(int offset,
int charCount,
char[] data)
- java.lang.StringFactory.newStringFromString(String toCopy)
Change-Id: I96a06ff81e1e3bf18d45760282356854efaf4945
|
| 0e54c0160c84894696c05af6cad9eae3690f9496 |
|
04-Mar-2016 |
Aart Bik <ajcbik@google.com> |
Unsafe: Recognize intrinsics for 1.8 java.util.concurrent
With unit test.
Rationale:
Recognizing the 1.8 methods as intrinsics is the first step
towards providing efficient implementation on all architectures.
Where not implemented (everywhere for now), the methods fall back
to the JNI native or reference implementation.
NOTE: needs iam's CL first!
bug=26264765
Change-Id: Ife65e81689821a16cbcdd2bb2d35641c6de6aeb6
|
| ddec7f9c117baa2b90d06ccfdb3460a4c5caf35f |
|
16-Feb-2016 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Implement isInfinite intrinsics.
- boolean java.lang.Float.isInfinite(float)
- boolean java.lang.Double.isInfinite(double)
Change-Id: I8e94a9cc462e6b1cf99bb14b17c1ff009c9c29a4
|
| 2f9fcc999fab4ba6cd86c30e664325b47b9618e5 |
|
02-Mar-2016 |
Aart Bik <ajcbik@google.com> |
Simplified intrinsic macro mechanism.
Rationale:
Reduces boiler-plate code in all intrinsics code generators.
Also, the newly introduced "unreachable" macro provides a
static verifier that we do not have unreachable and thus
redundant code in the generators. In fact, this change
exposes that the MIPS32 and MIPS64 rotation intrinsics
(IntegerRotateRight, LongRotateRight, IntegerRotateLeft,
LongRotateLeft) are unreachable, since they are handled
as HIR constructs for all architectures. Thus the code
can be removed.
Change-Id: I0309799a0db580232137ded72bb8a7bbd45440a8
|
| 42ad288254e660ad091d03fad8c8fbad1d34ec89 |
|
29-Feb-2016 |
Roland Levillain <rpl@google.com> |
Fix the signature of the IndexOf entry point.
The IndexOf entry point was declared as taking four
arguments (void*, uint32_t, uint32_t, uint32_t) whereas all
actual implementations use three arguments (void*, uint32_t,
uint32_t). As that fourth argument is not documented, drop
it from the intrinsic declaration to have it match the
implementations.
Change-Id: I65d747033192025ccd2b9a5e8f8ed05b77a21941
|
| cc3839c15555a2751e13980638fc40e4d3da633e |
|
29-Feb-2016 |
Roland Levillain <rpl@google.com> |
Improve documentation about StringFactory.newStringFromChars.
Make it clear that the native method requires its third
argument to be non-null, and therefore that the intrinsics
do not need a null check for it.
Bug: 27378573
Change-Id: Id2f78ceb0f7674f1066bc3f216b738358ca25542
|
| 2a6aad9d388bd29bff04aeec3eb9429d436d1873 |
|
25-Feb-2016 |
Aart Bik <ajcbik@google.com> |
Implement fp to bits methods as intrinsics.
Rationale:
Better optimization, better performance.
Results on libcore benchmark:
Most gain is from moving the invariant call out of the loop
after we detect everything is a side-effect free intrinsic.
But generated code in general case is much cleaner too.
Before:
timeFloatToIntBits() in 181 ms.
timeFloatToRawIntBits() in 35 ms.
timeDoubleToLongBits() in 208 ms.
timeDoubleToRawLongBits() in 35 ms.
After:
timeFloatToIntBits() in 36 ms.
timeFloatToRawIntBits() in 35 ms.
timeDoubleToLongBits() in 35 ms.
timeDoubleToRawLongBits() in 34 ms.
bug=11548336
Change-Id: I6e001bd3708e800bd75a82b8950fb3a0fc01766e
|
| 9cd6d378bd573cdc14d049d32bdd22a97fa4d84a |
|
09-Feb-2016 |
David Srbecky <dsrbecky@google.com> |
Associate slow paths with the instruction that they belong to.
Almost all slow paths already know the instruction they belong to,
this CL just moves the knowledge to the base class as well.
This is needed to be be able to get the corresponding dex pc for
slow path, which allows us generate better native line numbers,
which in turn fixes some native debugging stepping issues.
Change-Id: I568dbe78a7cea6a43a4a71a014b3ad135782c270
|
| b74353a6765447b1551b337fd76803eb6aa86b8b |
|
20-Nov-2015 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS32: Implement intrinsics from java.lang.Math:
- abs(double) - abs(float) - abs(int)
- abs(long) - max(double, double) - max(float, float)
- max(int, int) - max(long, long) - min(double, double)
- min(float, float) - min(int, int) - min(long, long)
- sqrt(double)
The math intrinsics:
- ceil(double) - floor(double) - rint(double)
- round(double) - round(float)
aren't implemented because they require instructions which only exist
for MIPS64, or for MIPS32r6.
Change-Id: I943be3592b52a423fcb7ac40f46f38a5e2a58c50
|
| 75a38b24801bd4d27c95acef969930f626dd11da |
|
17-Feb-2016 |
Aart Bik <ajcbik@google.com> |
Implement isNaN intrinsic through HIR equivalent.
Rationale:
Efficient implementation on all platforms.
Subject to better compiler optimizations.
Change-Id: Ie8876bf5943cbe1138491a25d32ee9fee554043c
|
| a19616e3363276e7f2c471eb2839fb16f1d43f27 |
|
02-Feb-2016 |
Aart Bik <ajcbik@google.com> |
Implemented compare/signum intrinsics as HCompare
(with all code generation for all)
Rationale:
At HIR level, many more optimizations are possible, while ultimately
generated code can take advantage of full semantics.
Change-Id: I6e2ee0311784e5e336847346f7f3c4faef4fd17e
|
| d967266cdfc8011c81ba6e9857a247c4a73bd0fc |
|
03-Sep-2015 |
Lazar Trsic <Lazar.Trsic@imgtec.com> |
MIPS64: Remove unaligned memory access from art generated code
Unaligned memory access was caused by sd, ld, ldc1 and sdc1
instructions. Check if offset is unaligned and replace it
with two 32 bit memory accesses, if so.
Added assembler tests for new instructions, as well as assembler
tests for LoadFromOffset, LoadFpuFromOffset, StoreToOffset and
StoreFpuToOffset.
Change-Id: I0228a4a2ce6c801eeb5b46952b8330e14468deb3
|
| 59c9454b92c2096a30a2bbdffb64edf33dbdd916 |
|
25-Jan-2016 |
Aart Bik <ajcbik@google.com> |
Recognize common utilities as intrinsics.
Rationale:
Recognizing these method calls as intrinsics already has
major advantages (compiler knows about no-side-effects/no-throw
properties). Next step is, of course, to implement these
with native instructions on each architecture.
Change-Id: I06fd12973238caec00d67b31b195d7f8807a538e
|
| 8ed1826a9da054920f2d39d34dfc7ba43337e4c9 |
|
22-Jan-2016 |
Goran Jakovljevic <Goran.Jakovljevic@imgtec.com> |
Fix MIPS64 booting problem
Add missing MarkGCCard in compareAndSwapObject intinsic.
Additionaly, don't do a null test in MarkGCCard if the value
cannot be null for MIPS64.
Change-Id: Iad50f9e6be8cd27fedb31abb00d5829498941696
|
| 3f67e692860d281858485d48a4f1f81b907f1444 |
|
15-Jan-2016 |
Aart Bik <ajcbik@google.com> |
Implemented BitCount as an intrinsic. With unit test.
Rationale:
Recognizing this important operation as an intrinsic has
various advantages:
(1) having the no-side-effects/no-throw allows for
much more GVN/LICM/BCE.
(2) Some architectures, like x86_64, provide direct
support for this operation.
Performance improvements on X86_64:
CheckersEvalBench (32-bit bitboard): 27,210KNS -> 36,798KNS = + 35%
ReversiEvalBench (64-bit bitboard): 52,562KNS -> 89,086KNS = + 69%
Change-Id: I65d549b0469b7909b12c6611cdc34a8640a5751f
|
| 391b866ce55b8e78b1f9a6b98321d837256e8d66 |
|
18-Dec-2015 |
Roland Levillain <rpl@google.com> |
Disable the UnsafeCASObject intrinsic with read barriers.
The current implementations of the UnsafeCASObject
intrinsics are missing a read barrier. Temporarily disable
them when read barriers are enabled.
Also re-enable the jsr166.LinkedTransferQueueTest tests that
were failing on the concurrent collector configuration, as
the UnsafeCASObject JNI implementation now correctly
implements the read barrier which was missing.
Bug: 25883050
Bug: 26205973
Change-Id: Iaf5d515532949662d0ac6702c9452a00aa0a23e6
|
| a4f1220c1518074db18ca1044e9201492975750b |
|
06-Aug-2015 |
Mark Mendell <mark.p.mendell@intel.com> |
Optimizing: Add direct calls to math intrinsics
Support the double forms of:
cos, sin, acos, asin, atan, atan2, cbrt, cosh, exp, expm1,
hypot, log, log10, nextAfter, sinh, tan, tanh
Add these entries to the vector addressed off the thread pointer. Call
the libc routines directly, which means that we have to implement the
native ABI, not the ART one. For x86_64, that includes saving XMM12-15
as the native ABI considers them caller-save, while the ART ABI
considers them callee-save. We save them by marking them as used by the
call to the math function. For x86, this is not an issue, as all the XMM
registers are caller-save.
Other architectures will call Java as before until they are ready to
implement the new intrinsics.
Bump the OAT version since we are incompatible with old boot.oat files.
Change-Id: Ic6332c3555c09393a17d1ad4daf62932488722fb
Signed-off-by: Mark Mendell <mark.p.mendell@intel.com>
|
| bf84a3d2aa29c0975b4ac0f6f983d56724b2cc57 |
|
04-Dec-2015 |
Roland Levillain <rpl@google.com> |
Annotate Boolean literals more uniformly in Optimizing's intrinsics.
Change-Id: Ida40309b4bc170a18b4e5db552b77f021a7b89df
|
| a0e87b0a97fadd54540ec7e8331b61bebd82d378 |
|
25-Sep-2015 |
Alexey Frunze <Alexey.Frunze@imgtec.com> |
MIPS64: Support short and long branches
Change-Id: I618c960bd211048166d9fde78d4106bd3ca42b3a
|
| 972d6d7b3b36c48ead6d95fa6a2a936390b868ac |
|
20-Oct-2015 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Add java.lang.String.equals intrinsic.
Change-Id: I71e41b20ebaf7640b2c72c590455eb0be4cbc5b7
|
| 53afca191ace3d7447b09097f9ea82a513075c52 |
|
06-Nov-2015 |
Alexey Frunze <Alexey.Frunze@imgtec.com> |
MIPS64: Implement virtual intrinsic slow path
This fixes a crash in dex2oat while compiling boot.oat.
Change-Id: I44fc92809902d7fc226c88b3e3f081b72cc19ce5
|
| 36427494be5700bc8adba514b5c67dc3ac429176 |
|
23-Oct-2015 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Add "Compare and Swap" intrinsic support.
Add following functions from sun.misc.Unsafe:
- boolean compareAndSwapInt(Object, long, int expected, int)
- boolean compareAndSwapLong(Object, long, long expected, long)
- boolean compareAndSwapObject(Object, long, Object expected, Object)
Change-Id: Iea0bf486ce1fc0d77ce349dfd6c089c9835fbe92
|
| 8128437353f34648fc11c5501800cd2ce7156dce |
|
22-Oct-2015 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Clean-up intrinsics code
- Wrap lines longer that 100 characters.
- Fix return type in comments for various Long intrinsics.
- Add Location::OutputOverlap parameter to CreateFPToFP() function;
wrong value was being used for floor()/ceil() intrinsics.
Change-Id: I998b647e1c20521a72da89cfe2d5a4c27e3ab85c
|
| 0f8f8643bc10160a9034b9e3ccfd81e9e6ed8e74 |
|
03-Oct-2015 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Add intrinsic support for bit rotation
- int java.lang.Integer.rotateLeft(int i, int distance)
- int java.lang.Long.rotateLeft(long i, int distance)
Change-Id: I048ebf310265c6b20a80108673a7931cbeee0513
|
| 9aebff2f19b605bff864308be51b604b7191163e |
|
23-Sep-2015 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Add intrinsic support for bit rotation
- int java.lang.Integer.rotateRight(int i, int distance)
- int java.lang.Long.rotateRight(long i, int distance)
Assembler tests for new MIPS instructions will be provided in a
separate patch.
Change-Id: I6dd4786e2d5f674bf56ff3d5afd321bb1bef589e
|
| 0646da7c04e4744c84d1b0a03df33ccae1d6d477 |
|
23-Sep-2015 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Add intrinsics support for trailing zeros
- int java.lang.Integer.numberOfTrailingZeros(int i)
- int java.lang.Long.numberOfTrailingZeros(long i)
Change-Id: I0fc1c2629738de9047313b6511b490639eef68f3
|
| 1360adac0b8f523e3de7da58f6b85f724ec6e42e |
|
05-Sep-2015 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Implement intrinsics from sun.misc.Unsafe:
- int getInt(Object, long)
- int getIntVolatile(Object, long)
- long getLong(Object, long)
- long getLongVolatile(Object, long)
- Object getObject(Object, long)
- Object getObjectVolatile(Object, long)
- void putInt(Object, long, int)
- void putOrderedInt(Object, long, int)
- void putIntVolatile(Object, long, int)
- void putObject(Object, long, Object)
- void putOrderedObject(Object, long, Object)
- void putObjectVolatile(Object, long, Object)
- void putLong(Object, long, long)
- void putOrderedLong(Object, long, long)
- void putLongVolatile(Object, long, long)
The compareAndSwap*() functions will be delivered in a separate patch.
Change-Id: I94238254b2f9df017d58fa9a4bb38632f6479472
|
| ee3cf0731d0ef0787bc2947c8e3ca432b513956b |
|
06-Oct-2015 |
Nicolas Geoffray <ngeoffray@google.com> |
Intrinsify System.arraycopy.
Currently on x64, will do the other architectures in
different changes.
Change-Id: I15fbbadb450dd21787809759a8b14b21b1e42624
|
| 9701c2ee2dde033e2269dcfc592a09f21151e97e |
|
05-Sep-2015 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Implement intrinsics from java.lang.String:
- char charAt(int index)
- int compareTo(String anotherString)
- int indexOf(int ch)
- int indexOf(int ch, int fromIndex)
- String(byte[] bytes)
- String(char[] value)
- String(String original)
Change-Id: I9c309b62580b42ae08a09cb1c2b4ebd1a203c5d2
|
| 145008296e80b8ac5affa4fb9bc20e411bf0bd92 |
|
01-Oct-2015 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Code cleanup.
1. Add comment to explain logic for GenMinMax in intrinsics code.
2. Declare enumerated type for class.s/class.d mask values.
3. Change intrinsics code to use the enumerated values described in
item 2.
4. Change "CLASS_MASK" to "kFPLeaveUnchanged" to match ART coding
standards.
Change-Id: Ib1fe4b01515595b46e5f101e0082bb9bbcf0c688
|
| 49e553927a70704cd6a29c7c8b96861e63808470 |
|
05-Sep-2015 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Implement intrinsic java.lang.Thread.currentThread()
Change-Id: I45378414e5b6071dce9663ee42a2136874eba6ff
|
| 0b7ac98ecdb891797a282c508b41238451d6c770 |
|
04-Sep-2015 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Implement intrinsics from java.lang.Math:
- abs(double) - abs(float) - abs(int)
- abs(long) - ceil(double) - floor(double)
- max(double, double) - max(float, float) - max(int, int)
- max(long, long) - min(double, double) - min(float, float)
- min(int, int) - min(long, long) - rint(double)
- sqrt(double)
The math intrinsics:
- round(double) - round(float)
aren't implemented because there is no simple mapping from these Java
functions into MIPS assembly code.
Change-Id: I37ee5224d3d64f7162ed98521ba566fbc58d7905
|
| 70fb1f447970548555c3a994de880be2a17a146a |
|
04-Sep-2015 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Implement intrinsics from libcore.io.Memory:
- peekByte(long address)
- peekShort(long address)
- peekInt(long address)
- peekLong(long address)
- pokeByte(long address, byte value)
- pokeShort(long address, short value)
- pokeInt(long address, int value)
- pokeLong(long address, long value)
Change-Id: Ic5996ea035bf7e622b6fc85b9526ee8318cb6b1f
|
| 3039e381b79ac1ef01c420511f6629f639d40ab4 |
|
26-Aug-2015 |
Chris Larsen <chris.larsen@imgtec.com> |
MIPS64: Implement miscellaneous bit manipulation intrinsics
// java.lang.Double
- doubleToRawLongBits(double) - longBitsToDouble(long)
// java.lang.Float
- floatToRawIntBits(float) - intBitsToFloat(int)
// java.lang.Integer
- numberOfLeadingZeros(int) - reverseBytes(int)
- reverse(int)
// java.lang.Long
- numberOfLeadingZeros(long) - reverseBytes(long)
- reverse(long)
// java.lang.Short
- reverseBytes(short)
Change-Id: Ic8f8c4e7b584132e2282b4fd267453870fefbaaa
|