Chris Lattner
284ae75537
get CodeGen/Alpha/mul128.ll to work.
...
llvm-svn: 57318
2008-10-09 04:50:56 +00:00
Dale Johannesen
9c6ffd55b4
Align EH tables before label is emitted, not after,
...
thus aligning the label.
llvm-svn: 57310
2008-10-08 21:50:21 +00:00
Dale Johannesen
817eff07b1
(re)Put const weak strings in appropriate section on Darwin.
...
g++dg/abi/key2.C
llvm-svn: 57309
2008-10-08 21:49:47 +00:00
Nuno Lopes
a4813e472c
dont specialize weak functions and the like
...
llvm-svn: 57305
2008-10-08 18:45:59 +00:00
Jim Grosbach
974799922e
Comment to be explicit that the enumeration values for CondCodes matter.
...
llvm-svn: 57295
2008-10-08 16:24:35 +00:00
Duncan Sands
bc53ce331a
Use template to distinguish between function variants.
...
GCC 4.4.0 gives an error on the "int" declaration for example
saying that it has already been declared (using the "short"
one). Using templates here allow the compiler to distinguish
between the function to choose.
Also, "llvm/Support/DataTypes.h" was not included, leading to
error messages about not knowing "uint32_t" for example.
Patch by Samuel Tardieu.
llvm-svn: 57292
2008-10-08 07:44:52 +00:00
Duncan Sands
8f296a3788
Add <cstdio> include where needed by gcc-4.4.
...
Patch by Samuel Tardieu.
llvm-svn: 57291
2008-10-08 07:23:46 +00:00
Chris Lattner
293590ca07
regenerate
...
llvm-svn: 57290
2008-10-08 06:44:45 +00:00
Chris Lattner
4afce47e9b
Add missing semicolumns in parser rules, those missing semicolumns
...
are required to compile with the latest Bison.
Patch by Samuel Tardieu!
llvm-svn: 57289
2008-10-08 06:44:36 +00:00
Chris Lattner
0aa4423c8c
Add parentheses to avoid warnings in GCC 4.4.0,
...
patch by Samuel Tardieu!
llvm-svn: 57288
2008-10-08 06:42:28 +00:00
Owen Anderson
7f99714393
Fix the case where an instruction is not properly marked as using all registers that alias its inputs.
...
llvm-svn: 57286
2008-10-08 04:30:51 +00:00
Dan Gohman
08e60cee90
Remove -disable-fast-isel. Use cl::boolOrDefault with -fast-isel
...
instead.
So now: -fast-isel or -fast-isel=true enable fast-isel, and
-fast-isel=false disables it. Fast-isel is also on by default
with -fast, and off by default otherwise.
llvm-svn: 57270
2008-10-07 23:00:56 +00:00
Dan Gohman
c65ca09308
Add MBB successors and physreg Uses in the same order that
...
SDISel typically adds them in. This makes it a little easier
to compare FastISel output with SDISel output.
llvm-svn: 57266
2008-10-07 22:10:33 +00:00
Dan Gohman
6d98c5ab31
Avoid emitting redundant materializations of integer constants
...
for things like null pointers, which at this level aren't
different from regular integer constants.
llvm-svn: 57265
2008-10-07 22:03:27 +00:00
Dan Gohman
2561119124
Instead of emitting an implicit use for the super-register of
...
X86::CL that was used, emit an EXTRACT_SUBREG from the CL
super-register to CL. This more precisely describes how the
CL register is being used.
llvm-svn: 57264
2008-10-07 21:50:36 +00:00
Jim Grosbach
8ac554209f
Unconditional branch instruction encoding fix. Needs to use ABI, not AXI, to get the proper opcode bits.
...
llvm-svn: 57262
2008-10-07 21:08:09 +00:00
Jim Grosbach
5fb8bb7434
need ARM.h for ARMCC definition
...
llvm-svn: 57261
2008-10-07 21:01:51 +00:00
Owen Anderson
c9a628af26
Add an option to enable StrongPHIElimination, for ease of testing.
...
llvm-svn: 57259
2008-10-07 20:22:28 +00:00
Jim Grosbach
d44d20be6e
Encode the conditional execution predicate when JITing.
...
llvm-svn: 57258
2008-10-07 19:05:35 +00:00
Dale Johannesen
3d2e449078
Model hardwired inputs & outputs of x86 8-bit divides correctly.
...
Fixes local RA miscompilation of gcc.c-torture/execute/20020904-1.c -O0.
llvm-svn: 57257
2008-10-07 18:54:28 +00:00
Andrew Lenharth
66cc9d5e53
Use Dan's supperior check
...
llvm-svn: 57255
2008-10-07 18:27:23 +00:00
Andrew Lenharth
c83731e00a
Correctly set attributes when removing args during cloning. Fixes PR2765
...
llvm-svn: 57254
2008-10-07 18:08:38 +00:00
Jim Grosbach
61f8207ac9
Clarify naming and correct conditional so that CMP and CMN instructions get the Rn operand encoded properly
...
llvm-svn: 57252
2008-10-07 17:42:09 +00:00
Jim Grosbach
a52546fec4
Fix Opcode values of CMP and CMN
...
llvm-svn: 57251
2008-10-07 17:40:46 +00:00
Andrew Lenharth
950618a347
No need for |=
...
llvm-svn: 57249
2008-10-07 17:11:29 +00:00
Andrew Lenharth
2399c6cb95
Use ADDC if it is valid at any smaller size. Do it right this time
...
llvm-svn: 57248
2008-10-07 17:09:16 +00:00
Andrew Lenharth
84166420cc
Use ADDC if it is valid at any smaller size. fixes test/Codegen/Generic/i128-addsub.ll on x86
...
llvm-svn: 57247
2008-10-07 17:03:15 +00:00
Anders Carlsson
a9c42526f8
Certain patterns involving the "movss" instruction were marked as requiring SSE2, when in reality movss is an SSE1 instruction.
...
llvm-svn: 57246
2008-10-07 16:14:11 +00:00
Andrew Lenharth
c00c2a0058
Expand arith on machines without carry flags
...
llvm-svn: 57243
2008-10-07 14:15:42 +00:00
Andrew Lenharth
7a997d1cfd
Note that ADDC and company don't actually expand yet (missing in legalize
...
llvm-svn: 57226
2008-10-07 02:10:26 +00:00
Dale Johannesen
3b86d974bc
Mark negative-zero-to-int conversion as Inexact,
...
since -0.0 can't be represented as an int.
This prevents llvm from reducing -0.0 to a
load-and-convert of int 0. Fixes
ieee.exp/mzero[2356].c in gcc testsuite.
llvm-svn: 57224
2008-10-07 00:40:01 +00:00
Dan Gohman
188af3ae0d
Correctly handle calls with no return values. This fixes
...
2006-01-23-UnionInit on x86-64 when inlining is not enabled.
llvm-svn: 57223
2008-10-07 00:12:37 +00:00
Devang Patel
378c8633e5
Fix typo, fix PR 2865.
...
llvm-svn: 57221
2008-10-06 23:22:54 +00:00
Dale Johannesen
40d00c0979
Be more precise about which conversions of NaNs
...
are Inexact. (These are not Inexact as defined
by IEEE754, but that seems like a reasonable way
to abstract what happens: information is lost.)
llvm-svn: 57218
2008-10-06 22:59:10 +00:00
Evan Cheng
88d76ffe8a
Fix PR2850 and PR2863. Only generate movddup for 128-bit SSE vector shuffles.
...
llvm-svn: 57210
2008-10-06 21:13:08 +00:00
Dale Johannesen
24ea5f2be7
Temporarily revert functionality change from my previous patch;
...
it is too aggressive.
llvm-svn: 57203
2008-10-06 20:43:48 +00:00
Devang Patel
ca66d093c0
Remove interfaces implemented by dead pass from the list of available passes.
...
Patch By Matthijs Kooijman.
llvm-svn: 57202
2008-10-06 20:36:36 +00:00
Dale Johannesen
89329a1d0a
Mark shortening NaN conversions as Inexact. PR 2856.
...
Improve description of unsupported formats.
llvm-svn: 57185
2008-10-06 18:22:29 +00:00
Devang Patel
07a9ce22e4
It is possible that all functions in one module are not being
...
optimized for size. Set OptForSize for each function separately.
llvm-svn: 57182
2008-10-06 18:03:39 +00:00
Dan Gohman
8b33abdd5b
Don't dereference the end() iterator. Thanks to
...
ENABLE_EXPENSIVE_CHECKS for finding this.
llvm-svn: 57181
2008-10-06 18:00:07 +00:00
Devang Patel
4f91b766d2
Remove unncessary isDeclaration() checks.
...
llvm-svn: 57179
2008-10-06 17:30:07 +00:00
Matthijs Kooijman
12cd5d041d
Allow scalarrepl to treat an all-zero GEP just as bitcast.
...
This includes not marking a GEP involving a vector as unsafe, but only when it
has all zero indices. This allows scalarrepl to work in a few more cases.
llvm-svn: 57177
2008-10-06 16:23:31 +00:00
Chris Lattner
8e41e3ac13
reorder #include order, patch by Kenneth Boyd!
...
llvm-svn: 57148
2008-10-06 03:54:25 +00:00
Chris Lattner
5d6871b940
Add #include to get alloca, patch by Kenneth Boyd!
...
llvm-svn: 57147
2008-10-06 03:53:16 +00:00
Chris Lattner
4622ca2262
fix an incorrect and extremely confusing error message
...
llvm-svn: 57123
2008-10-05 18:24:03 +00:00
Chris Lattner
1e4f7de3b6
make the autoupgrade code for ret attributes dramatically simpler
...
and actually work. We can now read the llvm 2.3 bc file from PR2849
llvm-svn: 57122
2008-10-05 18:22:09 +00:00
Nuno Lopes
4cf7f0e3cd
regenerate
...
llvm-svn: 57114
2008-10-05 16:49:34 +00:00
Nuno Lopes
9e274c3532
clean ArgTypeListI production: free the PATypeHolder
...
llvm-svn: 57113
2008-10-05 16:49:03 +00:00
Anton Korobeynikov
8106145480
Emit type-correct constant null. Also fix a typo.
...
Patch by Robert G. Jakabosky!
llvm-svn: 57110
2008-10-05 15:07:06 +00:00
Anton Korobeynikov
1f7e8162d9
Fix weird think-o and unbreak build on all gcc-3.4.x-based platforms (e.g. mingw)
...
llvm-svn: 57106
2008-10-05 08:53:29 +00:00
Chris Lattner
ed0f84ee2d
this case is matched now.
...
llvm-svn: 57096
2008-10-05 02:16:12 +00:00
Chris Lattner
107e8f8b60
rewrite bswap matching to be more general, allowing arbitrary
...
shifting and masking inside a bswap expr. This allows it to handle
the cases from PR2842, which involve the intermediate 'or'
expressions being shifted, not just the input value.
llvm-svn: 57095
2008-10-05 02:13:19 +00:00
Chris Lattner
6fae76bbf3
fix a bug where the bswap matcher could match a case involving
...
ashr. It should only apply to lshr.
llvm-svn: 57089
2008-10-05 00:50:57 +00:00
Chris Lattner
576e29c87d
wrap some long lines and expand i32 mul's to libcalls, inspired by a
...
patch by Mikael Lepisto!
llvm-svn: 57077
2008-10-04 21:27:46 +00:00
Oscar Fuentes
4bf1c53073
CMake: Reflected changes on source file structure. New plugin support
...
for llvmc2 incomplete.
llvm-svn: 57076
2008-10-04 21:18:50 +00:00
Duncan Sands
e22385630e
Ignore loads from and stores to local memory (i.e. allocas)
...
when deciding whether to mark a function readnone/readonly.
Since the pass is currently run before SROA, this may be
quite helpful. Requested by Chris on IRC.
llvm-svn: 57050
2008-10-04 13:24:24 +00:00
Nick Lewycky
53e751fcba
Allow the construction of SCEVs with SCEVCouldNotCompute operands, by
...
implementing folding. Fixes PR2857.
llvm-svn: 57049
2008-10-04 11:19:07 +00:00
Anton Korobeynikov
4cc9051fbb
Revert r56675 - it breaks unwinding runtime everywhere.
...
llvm-svn: 57048
2008-10-04 11:09:36 +00:00
Argyrios Kyrtzidis
8614f628d2
Add implementations for sys::Memory::setWritable and sys::Memory::setExecutable on Win32 platform.
...
llvm-svn: 57047
2008-10-04 08:15:32 +00:00
Argyrios Kyrtzidis
b9e76c172c
Fix compilation error on MSVC.
...
llvm-svn: 57046
2008-10-04 08:11:49 +00:00
Dan Gohman
5944450d5f
Fix fast-isel's handling of atomic instructions. They may
...
expand to multiple basic blocks, in which case fast-isel
needs to informed of which block to use as it resumes
inserting instructions.
llvm-svn: 57040
2008-10-04 00:56:36 +00:00
Dan Gohman
638a8001c8
Fix a bug in the local allocator's liveness computation where it
...
was setting kill flags on tied uses in two-address instructions.
The kill flags were causing the allocator to think it could
allocate the use and its tied def in different registers.
llvm-svn: 57039
2008-10-04 00:31:14 +00:00
Dale Johannesen
dc83b95ba5
Make atomic Swap work, 64-bit on x86-32.
...
Make it all work in non-pic mode.
llvm-svn: 57034
2008-10-03 22:25:52 +00:00
Dan Gohman
700611dfc6
Clean up some multiple-return-value code that is no longer
...
applicable.
llvm-svn: 57033
2008-10-03 22:21:24 +00:00
Devang Patel
0d22d8ebdb
Fix function attribute verification check.
...
Thanks Duncan!
llvm-svn: 57029
2008-10-03 21:11:02 +00:00
Dale Johannesen
27d8955b8f
Pass MemOperand through for 64-bit atomics on 32-bit,
...
incidentally making the case where the memop is a
pointer deref work. Fix cmp-and-swap regression.
llvm-svn: 57027
2008-10-03 19:41:08 +00:00
Devang Patel
55401473f9
Nick Lewycky's patch.
...
While hosting instruction check PHI node.
llvm-svn: 57025
2008-10-03 18:57:37 +00:00
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
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
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
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
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
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
Devang Patel
d90556aed0
Attributes noinline alwaysinline are incompatible
...
llvm-svn: 56939
2008-10-01 23:41:25 +00:00