1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-29 23:12:55 +01:00
Commit Graph

41716 Commits

Author SHA1 Message Date
Dan Gohman
dc99a744fd Use -1ULL instead of uint64_t(-1), at Anton's suggestion.
llvm-svn: 57021
2008-10-03 17:56:45 +00:00
Devang Patel
2bed4d4ca0 Verify function attributes.
llvm-svn: 57020
2008-10-03 17:50:00 +00:00
Evan Cheng
d572afd76c Fix typos pointed out by Duncan. Also untabify these files.
llvm-svn: 57018
2008-10-03 17:11:58 +00:00
Daniel Dunbar
40fb36a42c Unbreak build.
llvm-svn: 57017
2008-10-03 17:11:57 +00:00
Dan Gohman
00034b1416 Avoid creating two TargetLowering objects for each target.
Instead, just create one, and make sure everything that needs
it can access it. Previously most of the SelectionDAGISel
subclasses all had their own TargetLowering object, which was
redundant with the TargetLowering object in the TargetMachine
subclasses, except on Sparc, where SparcTargetMachine
didn't have a TargetLowering object. Change Sparc to work
more like the other targets here.

llvm-svn: 57016
2008-10-03 16:55:19 +00:00
Dan Gohman
e41ac02dce Remove an unused field.
llvm-svn: 57014
2008-10-03 16:17:33 +00:00
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