Dan Gohman
4d273f4519
Commit this, which should have accompanied 101531.
...
llvm-svn: 101532
2010-04-16 20:22:43 +00:00
Dan Gohman
148c69a3f6
Eliminate an unnecessary SelectionDAG dependency in getOptimalMemOpType.
...
llvm-svn: 101531
2010-04-16 20:11:05 +00:00
Dan Gohman
9dbe61456a
Fix this code to avoid implicit assumptions about the length of the array.
...
llvm-svn: 101530
2010-04-16 20:08:45 +00:00
Johnny Chen
2b7aba10c2
In the same spirit of r101524, which removed the assert() from printAddrMode2OffsetOperand(),
...
this patch removes the assert() from printAddrMode3OffsetOperand() and adds a test case.
llvm-svn: 101529
2010-04-16 19:57:21 +00:00
Dan Gohman
0591a050ff
Revert 101520, which depended on 101503, which was reverted.
...
llvm-svn: 101528
2010-04-16 19:36:41 +00:00
Johnny Chen
807e1748fc
Multiclass LdStCop was using pre-UAL syntax LDC<c>L for the L fragment. Changed
...
to the UAL syntax of LDCL<c>, instead.
Add a test case for this change which also tests the removal of assert() from
printAddrMode2OffsetOperand().
llvm-svn: 101527
2010-04-16 19:33:23 +00:00
Duncan Sands
7fc8123b37
Revert commit 101503 (johannes), in the hope of fixing the dragonegg build,
...
see http://google1.osuosl.org:8011/builders/dragonegg-x86_64-linux/builds/693
Original commit text:
Use a ValueMap not a std::map for the reason indicated
in the comment. This was causing nondeterministic changes
in inlining decisions.
llvm-svn: 101525
2010-04-16 19:28:59 +00:00
Johnny Chen
88599a42bb
Remove the assert() from printAddrMode2OffsetOperand(). "#0 and #-0" are
...
considered legal instructions.
Refs: A8.6.51 LDC, LDC2 (immediate) -- page A8-107, A8.6.58 LDR (immediate, ARM)
-- page A8-121, and A8.6.194 STR (immediate, ARM) -- page A8-395.
llvm-svn: 101524
2010-04-16 19:10:52 +00:00
Dan Gohman
076a3278a1
Trim a #include.
...
llvm-svn: 101520
2010-04-16 18:45:11 +00:00
Dan Gohman
c1ce91603c
Revert r101455, which fails on the llvm-arm-linux buildbot.
...
llvm-svn: 101515
2010-04-16 18:37:31 +00:00
Dale Johannesen
3104bf1618
Use a ValueMap not a std::map for the reason indicated
...
in the comment. This was causing nondeterministic changes
in inlining decisions.
llvm-svn: 101503
2010-04-16 18:16:08 +00:00
Evan Cheng
954bd598dd
80 col.
...
llvm-svn: 101501
2010-04-16 17:58:41 +00:00
Evan Cheng
d6b0a7c075
80 col.
...
llvm-svn: 101500
2010-04-16 17:57:59 +00:00
Dan Gohman
3a7ee8eead
Avoid creating virtual registers for unused values.
...
llvm-svn: 101480
2010-04-16 17:15:02 +00:00
Dan Gohman
5664b9f1a9
Fix an assertion string.
...
llvm-svn: 101478
2010-04-16 16:55:18 +00:00
Dan Gohman
4572a9f479
Fix a comment.
...
llvm-svn: 101477
2010-04-16 16:52:37 +00:00
Dan Gohman
f13f69f296
Disable inlining of recursive calls. It can complicate tailcallelim and
...
dependent analyses, and increase code size, so doing it profitably would
require more complex heuristics.
llvm-svn: 101471
2010-04-16 16:01:18 +00:00
Dan Gohman
99e5327bfd
Refine the detection of seemingly infinitely recursive calls where the
...
callee is expected to be expanded to something else by codegen, so that
normal infinitely recursive calls are still transformed.
llvm-svn: 101468
2010-04-16 15:57:50 +00:00
Gabor Greif
f375520f7b
reapply r101434
...
with a fix for self-hosting
rotate CallInst operands, i.e. move callee to the back
of the operand array
the motivation for this patch are laid out in my mail to llvm-commits:
more efficient access to operands and callee, faster callgraph-construction,
smaller compiler binary
llvm-svn: 101465
2010-04-16 15:33:14 +00:00
Dan Gohman
b3862ecd48
Make callIsSmall accessible as a utility function.
...
llvm-svn: 101463
2010-04-16 15:14:50 +00:00
Dan Gohman
12293815de
Fix SCEVCommutativeExpr::print to be robust in the case of improper
...
expression canonicalization. Its job is to print what's there, not to
make judgements about it.
llvm-svn: 101461
2010-04-16 15:03:25 +00:00
Dan Gohman
aa4d9ea465
Delete a blank line.
...
llvm-svn: 101459
2010-04-16 13:32:55 +00:00
Bill Wendling
ae4541d758
Add JIT exception handling test.
...
llvm-svn: 101455
2010-04-16 09:04:28 +00:00
Bill Wendling
929f3c0927
The JIT calls TidyLandingPads to tidy up the landing pads. However, because the
...
JIT doesn't use the MC back-end asm printer to emit labels that it uses, the
section for the MCSymbol is never set. And thus the MCSymbol for the EH label
isn't marked as "defined". Because of that, TidyLandingPads removes the needed
landing pads from the JIT output. This breaks EH for every JIT program.
This is a work-around for this limitation. We pass in the label locations
map. If the label has a non-zero value, then it was "emitted" by the JIT and
TidyLandingPads shouldn't remove that label.
A nicer solution would be to mark the MCSymbol as "used" by the JIT and not rely
upon the section being set to determine if it's defined or not.
llvm-svn: 101453
2010-04-16 08:46:10 +00:00
Chris Lattner
408f79197c
completed my pass over all 6+ months of commits, next step, format and make comprehendable.
...
llvm-svn: 101449
2010-04-16 06:20:22 +00:00
Evan Cheng
af56facacd
Adding support for dag combiner to promote operations for profit. This requires target specific queries. For example, x86 should promote i16 to i32 when it does not impact load folding.
...
x86 support is off by default. It can be enabled with -promote-16bit.
Work in progress.
llvm-svn: 101448
2010-04-16 06:14:10 +00:00
Evan Cheng
3da64f7672
Use getAL() rather than a major constant.
...
llvm-svn: 101446
2010-04-16 05:46:06 +00:00
Eric Christopher
dea3bda860
Add a check for posix_spawn.
...
Regenerate configure and other autoconf files.
llvm-svn: 101444
2010-04-16 05:14:21 +00:00
Dan Gohman
5563473062
Refine further the scope where the global DebugLoc value is active.
...
llvm-svn: 101443
2010-04-16 05:06:56 +00:00
Nick Lewycky
bb2ec7de9c
Revert r64616 which worked around http://gcc.gnu.org/PR42757 , we just didn't
...
know it at the time.
llvm-svn: 101439
2010-04-16 04:32:20 +00:00
Eric Christopher
206d7ce582
Silence an unused variable warning.
...
llvm-svn: 101438
2010-04-16 04:02:04 +00:00
Chris Lattner
bd2d9430d6
fix comment noticed by Bob
...
llvm-svn: 101437
2010-04-16 02:32:17 +00:00
Gabor Greif
403e9694f9
back out r101423 and r101397, they break llvm-gcc self-host on darwin10
...
llvm-svn: 101434
2010-04-16 01:16:20 +00:00
Chris Lattner
393e08536d
move comment.
...
llvm-svn: 101433
2010-04-16 01:05:52 +00:00
Chris Lattner
1146d326a7
fix PR6832: we were using the alignment of a pointer when we
...
wanted the alignment of the pointee.
llvm-svn: 101432
2010-04-16 01:05:38 +00:00
Dan Gohman
0977358509
Create an exports file, so that the plugin only exports the onload symbol.
...
llvm-svn: 101431
2010-04-16 00:43:25 +00:00
Dan Gohman
ebb4ae0912
Make things static that don't need to be referenced from outside the file.
...
llvm-svn: 101430
2010-04-16 00:42:57 +00:00
Chris Lattner
b73552908e
improve comments.
...
llvm-svn: 101429
2010-04-16 00:38:19 +00:00
Chris Lattner
78d7dbbc30
pull all the ConvertToScalarInfo code together into one
...
place.
llvm-svn: 101427
2010-04-16 00:24:57 +00:00
Chris Lattner
d69c3ee958
more refactoring: suck some stuff out of SRoA into
...
ConvertToScalarInfo.
llvm-svn: 101425
2010-04-16 00:20:00 +00:00
Gabor Greif
6af0ad846e
shift intrinsic operand
...
llvm-svn: 101423
2010-04-16 00:06:45 +00:00
Chris Lattner
9ef4eae6e6
introduce a new ConvertToScalarInfo struct to simplify
...
CanConvertToScalar/MergeInType. Eliminate a pointless
LLVMContext argument to MergeInType.
llvm-svn: 101422
2010-04-15 23:50:26 +00:00
Jakob Stoklund Olesen
cdc3df4888
Avoid sinking machine instructions into a loop.
...
MachineLoopInfo is already available when MachineSinking runs, so the check is
free.
There is no test case because it would require a critical edge into a loop, and
CodeGenPrepare splits those. This check is just to be extra careful.
llvm-svn: 101420
2010-04-15 23:41:02 +00:00
Johnny Chen
1d3ee607b3
Added another test case for am3offset operand, testing Rn, #+/-imm8.
...
Previous checkin tested Rn, #+/-Rm.
llvm-svn: 101418
2010-04-15 23:23:40 +00:00
Jakob Stoklund Olesen
dc6d42dbf8
Add test case for machine-sink on critical edges
...
llvm-svn: 101416
2010-04-15 23:19:16 +00:00
Johnny Chen
acbc06c2a3
Fixed a bug in ARM disassembly where LDRSBT should have am3offset operand, not
...
am2offset. Modified the instruction table entry and added a new test case.
llvm-svn: 101415
2010-04-15 23:12:47 +00:00
Dan Gohman
ff9ecb2824
Make the export files absolute paths, and change Makefile.rules
...
to expect them this way, to fix srcdir!=objdir builds.
llvm-svn: 101414
2010-04-15 23:08:00 +00:00
Dan Gohman
1639265421
Add a dependency on the .dir file to make sure that the directory
...
is created before the native exports file is built in a parallel build.
llvm-svn: 101413
2010-04-15 22:46:27 +00:00
Evan Cheng
f7f97b4bbd
Use default lowering of DYNAMIC_STACKALLOC. As far as I can tell, ARM isle is doing the right thing and codegen looks correct for both Thumb and Thumb2.
...
llvm-svn: 101410
2010-04-15 22:20:34 +00:00
Chris Lattner
9c1172d848
tidy interface to isOnlyCopiedFromConstantGlobal
...
llvm-svn: 101405
2010-04-15 21:59:20 +00:00