| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| |
|
|
|
|
|
|
|
| |
Add support for customer device extension
Change-Id: I0402a630ba212d1c5e81cda110f61210f7b60384
(cherry picked from commit 11499df326462bfe25890a35c6abbf019ff7784e)
(cherry picked from commit e03b8f8da9cf4eef64cedf39ce9ca90d26ce5124)
(cherry picked from commit fb360be406f35b9591f12c61936657f03cc5880f)
|
| |
|
|
|
|
|
| |
We can just use the existing Math intinsics.
Bug: 7146208
Change-Id: I9e78d33cf65a5dcc5a7c0133e67bd9c3c1e43f23
|
| |
|
|
|
|
|
|
|
|
| |
An leading underscore followed by a capital letter is a reserved
name space in C and C++.
This change also moves any #include directives within the include
guard in some of the compiler/codegen/arm header files.
Change-Id: I9715e2c5301699d31886e61d0fe6e29483555a2a
|
| |
|
|
| |
Change-Id: I236c5a1553a51f82c9bc3eaaab042046c854d3b4
|
| |
|
|
| |
Change-Id: I2ece682bc3b4d3b55ab27c60fd84a0b3243d7ca6
|
| |
|
|
| |
Change-Id: I25d8fa821987a3dd6d7109d07fd42dbf2fe0e589
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This is a restructuring of the Dalvik ARM and x86 interpreters:
o Combine the old portstd and portdbg interpreters into a single
portable interpreter.
o Add debug/profiling support to the fast (mterp) interpreters.
o Delete old mechansim of switching between interpreters. Now, once
you choose an interpreter at startup, you stick with it.
o Allow JIT to co-exist with profiling & debugging (necessary for
first-class support of debugging with the JIT active).
o Adds single-step capability to the fast assembly interpreters without
slowing them down (and, in fact, measurably improves their performance).
o Remove old "polling for safe point" mechanism. Breakouts now achieved
via modifying base of interpreter handler table.
o Simplify interpeter control mechanism.
o Allow thread-granularity control for profiling & debugging
The primary motivation behind this change was to improve the responsiveness
of debugging and profiling and to make it easier to add new debugging and
profiling capabilities in the future. Instead of always bailing out to the
slow debug portable interpreter, we can now stay in the fast interpreter.
A nice side effect of the change is that the fast interpreters
got a healthy speed boost because we were able to replace the
polling safepoint check that involved a dozen or so instructions
with a single table-base reload. When combined with the two earlier CLs
related to this restructuring, we show a 5.6% performance improvement
using libdvm_interp.so on the Checkers benchmark relative to Honeycomb.
Change-Id: I8d37e866b3618def4e582fc73f1cf69ffe428f3c
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Even though execute-inline is now a mandatory optimization, you can't be sure
the inline natives will be invoked that way. There's reflection and JNI, for
example, and there's the special case of String.equals that might be invoked
as Object.equals. This patch adds a regular native method corresponding to
each inline native, so that a corresponding libcore patch can drop its
implementations. (For example, despite the fact that we all believed last week
that the Java implementation of String.equals is never used, that turned out
not to be true: every HashMap lookup will have used it. This pair of patches
brings reality in line with our existing belief.)
Change-Id: I19e64c23bea83e91696206ca40ce4e3faf853040
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This shifts two dexopt optimizations from the "non-essential" category
to "essential", which means they will be performed at class load time
for classes that did not successfully verify in dexopt. (This has an
impact on memory and start time, but measurements have indicated that
it's negligible because dexopt usually succeeds.)
First, invoke-direct --> invoke-direct-empty. This is part of the
work needed for bug 3342343, which needs to do a little extra work
when returning from Object.<init> in a finalizable class.
Second, invoke-* --> execute-inline. We currently have three copies
of methods like String.length(): one in libcore, one in InlineNatives.c,
and one in the JIT's code generator. If we guarantee inlining, we can
get rid of the copy in libcore. We also ensure that certain libcore
tests (which are organized in a way that makes dexopt unhappy) are
using the version that will most likely be used on production.
Note there is currently no support for "jumbo" opcodes here.
Also, made the inline method lookup abort-on-failure. Once upon a time
these were "best effort" optimizations, but now they're mandatory. And
seriously, if you don't have String.length() and Math.min() you
shouldn't be trying to run anyway. dvmInlineNativeCheck() is now
redundant and has been removed.
Change-Id: I4244e011839f77311fea0570195b3b0df4d84dcf
|
| |
|
|
|
|
|
|
|
| |
Also fix a bug where we'd dereference NULL if an inline native's class failed
to resolve.
Also merge this method lookup with Optimize.c's (superior) near-duplicate.
Change-Id: Ic7a95e1f7445b6c9964ddd5e2e1d14d70792a622
|
| |
|
|
|
| |
Bug: 2935622
Change-Id: I0f9e564f1f94ccf6596a37a6f1c10253481d5062
|
| |
|
|
|
|
|
|
|
|
| |
Fixes all known bugs in our handling of supplementary characters. This change
introduces a performance regression on the assumption that it won't be released
without a corresponding JIT change to enable the code to be inlined back to
pretty much what it used to be.
Bug: 2587122
Change-Id: I3449c9718bbe32ebe53b6c10454ae1dc82105b59
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Before:
benchmark ns logarithmic runtime
IsEmpty 115 XXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
LengthEqualsZero 21 XXXXX||||||||||||||
With C intrinsic:
IsEmpty 30 XXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
LengthEqualsZero 20 XXXXXXXXXXXXXXXXXXXX||||||
With assembler intrinsic:
IsEmpty 15 XXXXXXXXXXXXXXXXXXXX||||||
LengthEqualsZero 21 XXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
(All times on passion.)
Change-Id: Ifcc37fe7b8efdd377675a448e0085e490d6767bc
|
| | |
|
| |
|
|
| |
bug fixes.
|
| | |
|
| | |
|
| |
|
