Jim Grosbach
a49386d8e7
On Darwin ARM, memory needs special handling to do JIT. This patch expands
...
this handling to work properly for modifying stub functions, relocations
back to entry points after JIT compilation, etc..
llvm-svn: 57013
2008-10-03 16:17:20 +00:00
Jim Grosbach
d9ff019d3e
Indexing off by one resulted in errant encoding of source register for
...
reg->reg moves.
llvm-svn: 57011
2008-10-03 15:53:56 +00:00
Jim Grosbach
e398f553b2
NeedStub/DoesntNeedStub logic was reversed, leading to not using a stub
...
for global relocations that do need them (libc calls, for example).
llvm-svn: 57010
2008-10-03 15:52:42 +00:00
Nuno Lopes
3fbdc238d6
regenerate
...
llvm-svn: 57009
2008-10-03 15:52:39 +00:00
Nuno Lopes
5cb07eb550
fix more memleaks in ResolveTypeTo() and ParseGlobalVariable()
...
llvm-svn: 57008
2008-10-03 15:51:46 +00:00
Nuno Lopes
263d218cd1
regenerate with bison 2.3
...
llvm-svn: 57007
2008-10-03 15:45:58 +00:00
Dan Gohman
30c5ce1b7d
Switch the MachineOperand accessors back to the short names like
...
isReg, etc., from isRegister, etc.
llvm-svn: 57006
2008-10-03 15:45:36 +00:00
Nuno Lopes
949c7ea3e7
fix memleak in FunctionHeaderH
...
llvm-svn: 57005
2008-10-03 15:44:21 +00:00
Mikhail Glushenkov
733e709a06
Rename llvmc2/src to llvmc2/core.
...
llvm-svn: 57000
2008-10-03 10:27:23 +00:00
Mikhail Glushenkov
b68c72d987
Fix build breakage when objdir!=srcdir (proper fix).
...
llvm-svn: 56999
2008-10-03 10:26:37 +00:00
Mikhail Glushenkov
e7dbeecd74
Fix build breakage (again) when srcdir != objdir, other small fixes.
...
llvm-svn: 56998
2008-10-03 09:09:34 +00:00
Duncan Sands
00b25fea88
The result of getSetCCResultType (eg: i32) may be larger
...
than the type an i1 is promoted to (eg: i8). Account
for this. Noticed by Tilmann Scheller on CellSPU; he
will hopefully take care of fixing this in LegalizeDAG
and adding a testcase!
llvm-svn: 56997
2008-10-03 07:41:46 +00:00
Duncan Sands
5edd9b2350
Teach internalize to preserve the callgraph.
...
Why? Because it was there!
llvm-svn: 56996
2008-10-03 07:36:09 +00:00
Nicolas Geoffray
c3efec61f5
Acquire the lock only when necessary. More precisely, do not acquire
...
the lock when calling a method which may materialize the llvm::Function.
llvm-svn: 56995
2008-10-03 07:27:08 +00:00
Owen Anderson
e98ca283b0
SplitBlock should only attempt to update LoopInfo if it is actually being used.
...
llvm-svn: 56994
2008-10-03 06:55:35 +00:00
Dan Gohman
68e27d0b27
Implement fast-isel support for zero-extending from i1.
...
It turns out that this is a fairly common operation,
and it's easy enough to handle.
llvm-svn: 56990
2008-10-03 01:28:47 +00:00
Dan Gohman
78ef9889c9
Fix X86FastISel to handle dynamic allocas that have avoided
...
getting inserted into the ValueMap. This avoids infinite
recursion in some rare cases.
llvm-svn: 56989
2008-10-03 01:27:49 +00:00
Bill Wendling
5b82095bcd
Unbreak the build.
...
llvm-svn: 56988
2008-10-03 00:26:49 +00:00
Dan Gohman
3ad9361680
Fix a typo.
...
llvm-svn: 56986
2008-10-03 00:07:11 +00:00
Jim Grosbach
659f1ab77f
Add support for Canadian Cross builds where the host executables are not
...
runnable on the build machine.
There are a few bits that need built for the build environment (TableGen).
This patch builds those bits, and the associated libraries, for the build
environment as well as the (usual) host environment.
Thanks to Eric C. and Devang P. for pre-commit review.
llvm-svn: 56975
2008-10-02 22:56:44 +00:00
Mikhail Glushenkov
acf37039b0
Fix build breakage.
...
Forgot to include Makefile.plugins.
llvm-svn: 56970
2008-10-02 22:41:42 +00:00
Dan Gohman
e75d14f8b0
Optimize conditional branches in X86FastISel. This replaces
...
sequences like this:
sete %al
testb %al, %al
jne LBB11_1
with this:
je LBB11_1
llvm-svn: 56969
2008-10-02 22:15:21 +00:00
Dan Gohman
bf63ae1e29
Add a new MachineBasicBlock utility function, isLayoutSuccessor, that
...
can be used when deciding if a block can transfer control to another
via a fall-through instead of a branch.
llvm-svn: 56968
2008-10-02 22:09:09 +00:00
Mikhail Glushenkov
016196513e
Build system tweaks to make it more convenient for the plugin authors.
...
Plugins can be now compiled in with a slight Makefile change.
For example, to compile the new Clang driver, use:
cd $LLVMC2_DIR
make TOOLNAME=ccc2 BUILTIN_PLUGINS=Clang
llvm-svn: 56967
2008-10-02 21:15:05 +00:00
Andrew Lenharth
106090d2a6
fix build gcc 4.3
...
llvm-svn: 56965
2008-10-02 20:15:08 +00:00
Owen Anderson
1c171e1d1c
Use a multimap rather than a map for holding the list of copies to insert, so we don't lose copies when two of them have
...
the same source. I don't know what I was thinking when I wrote this originally.
Note: There's probably a more efficient way to do this, but I need to think about it some more, and about what determinism
guarantees need to be present.
llvm-svn: 56964
2008-10-02 19:40:33 +00:00
Dale Johannesen
dbd7b1bd33
Handle some 64-bit atomics on x86-32, some of the time.
...
llvm-svn: 56963
2008-10-02 18:53:47 +00:00
Bill Wendling
7434efae89
Avoid name shadowing with E variable defined in for(). This was giving VC++
...
grief.
llvm-svn: 56961
2008-10-02 18:39:11 +00:00
Devang Patel
92bd02d528
Remove redundant check.
...
llvm-svn: 56960
2008-10-02 18:38:23 +00:00
Evan Cheng
c589085710
A Partitioned Boolean Quadratic Programming (PBQP) based register allocator.
...
Contributed by Lang Hames.
llvm-svn: 56959
2008-10-02 18:29:27 +00:00
Oscar Fuentes
c1d88c3b68
CMake: Added Host.cpp to lib/System/CMakeLists.txt.
...
llvm-svn: 56957
2008-10-02 17:39:29 +00:00
Daniel Dunbar
553c69eecd
Rename IRBuilder::IsNonNull -> IsNotNull in response to feedback.
...
llvm-svn: 56953
2008-10-02 17:05:03 +00:00
Dan Gohman
c48242640d
Fix a think-o in isSafeToMove. This fixes it from thinking that
...
volatile memory references are safe to move.
llvm-svn: 56948
2008-10-02 15:04:30 +00:00
Dan Gohman
bba3fb6d18
Work around an interaction between fast-isel and regalloc=local. The
...
local register allocator's physreg liveness doesn't recognize subregs,
so it doesn't know that defs of %ecx that are immediately followed by
uses of %cl aren't dead. This comes up due to the way fast-isel emits
shift instructions.
This is a temporary workaround. Arguably, local regalloc should
handle subreg references correctly. On the other hand, perhaps
fast-isel should use INSERT_SUBREG instead of just assigning to the
most convenient super-register of %cl when lowering shifts.
This fixes MultiSource/Benchmarks/MallocBench/espresso,
MultiSource/Applications/hexxagon, and others, under -fast.
llvm-svn: 56947
2008-10-02 14:56:12 +00:00
Bill Wendling
1c97db4090
"The original bug was a complaint that _mm_srli_si128 mis-compiled when passed
...
a constant vector ("{0x123, 0x456}" syntax). The fix is to simplify the
_mm_srli_si128 macro, and move the "* 8" from the macro into the compiler
back-end. I can't change the existing __builtins because so many people are
using them :-(."
Patch by Stuart Hastings!
llvm-svn: 56944
2008-10-02 05:56:52 +00:00
Daniel Dunbar
1fab10702e
Add llvm::sys::{osName,osVersion} for retrieving operating system name
...
& version as strings.
- Win32 code is untested.
llvm-svn: 56942
2008-10-02 01:17:28 +00:00
Dan Gohman
595edc380a
Disable fast-isel for this test, as it doesn't emit the same
...
number of instructions.
llvm-svn: 56940
2008-10-01 23:48:35 +00:00
Devang Patel
d90556aed0
Attributes noinline alwaysinline are incompatible
...
llvm-svn: 56939
2008-10-01 23:41:25 +00:00
Devang Patel
a5cda569d3
Remove OptimizeForSize global. Use function attribute optsize.
...
llvm-svn: 56937
2008-10-01 23:18:38 +00:00
Dan Gohman
cd111d96c6
Enable FastISel by default (on x86 and x86-64) with the -fast option.
...
llvm-svn: 56930
2008-10-01 20:39:19 +00:00
Chris Lattner
91e5279de1
add a new form of Type::dump that takes a module for type names,
...
patch provided by Tomas Lindquist Olsen!
llvm-svn: 56929
2008-10-01 20:16:19 +00:00
Dan Gohman
e1d0930044
Make some implicit conversions explicit, to avoid compiler warnings.
...
llvm-svn: 56927
2008-10-01 19:58:59 +00:00
Dan Gohman
be88cf29b6
Split this test and move it into target-specific directories.
...
This fixes failures on configurations that don't have one or the
other targets enabled.
llvm-svn: 56926
2008-10-01 19:46:30 +00:00
Dan Gohman
4aacc3ab83
Split x86's ADJCALLSTACK instructions into 32-bit and 64-bit forms.
...
This allows the 64-bit forms to use+def RSP instead of ESP. This
doesn't fix any real bugs today, but it is more precise and it
makes the debug dumps on x86-64 look more consistent.
Also, add some comments describing the CALL instructions' physreg
operand uses and defs.
llvm-svn: 56925
2008-10-01 18:28:06 +00:00
Jim Grosbach
0268ee4c25
Fix typo s/ther/there/
...
llvm-svn: 56924
2008-10-01 18:16:49 +00:00
Duncan Sands
88d8323743
Factorize code: remove variants of "strip off
...
pointer bitcasts and GEP's", and centralize the
logic in Value::getUnderlyingObject. The
difference with stripPointerCasts is that
stripPointerCasts only strips GEPs if all
indices are zero, while getUnderlyingObject
strips GEPs no matter what the indices are.
llvm-svn: 56922
2008-10-01 15:25:41 +00:00
Dan Gohman
6466b44315
Fold trivial two-operand tokenfactors where the operands are equal
...
immediately.
llvm-svn: 56921
2008-10-01 15:11:19 +00:00
Dan Gohman
8ba73d6d60
Don't prepend a space character for constants in Value::print.
...
llvm-svn: 56920
2008-10-01 15:09:37 +00:00
Dan Gohman
81ade97fe0
Fix typos in comments.
...
llvm-svn: 56919
2008-10-01 15:07:49 +00:00
Dan Gohman
5508abb3bf
nounwind-ify this test.
...
llvm-svn: 56918
2008-10-01 15:07:14 +00:00