2666f59322
Fix pre- and post-indexed load / store encoding bugs.
...
llvm-svn: 59230
2008-11-13 07:34:59 +00:00
9a04b9dd8b
Refactor the code that does the type checking for intrinsics.
...
llvm-svn: 59228
2008-11-13 07:11:27 +00:00
ed90e701f0
Add Binary flag to raw_fd_ostream constructor.
...
Document raw_fd_ostream's treatment of "-".
llvm-svn: 59219
2008-11-13 05:01:07 +00:00
9aa657663a
Added testcase for r59214.
...
llvm-svn: 59218
2008-11-13 04:09:04 +00:00
3dd51c5c62
Really remove all debug information.
...
llvm-svn: 59208
2008-11-13 01:28:40 +00:00
1a0f1d88ff
Regenerated
...
llvm-svn: 59204
2008-11-13 01:03:00 +00:00
a813017b41
Update docs for ssp and sspreq function attributes.
...
llvm-svn: 59203
2008-11-13 01:02:51 +00:00
ccb67a3d85
Implement stack protectors as function attributes: "ssp" and "sspreq".
...
llvm-svn: 59202
2008-11-13 01:02:14 +00:00
6cd8ad06d6
Revert the part of r59145 that changed the comment about
...
virtual registers possibly having multiple kills while still
being defined and killed in the same block. If LiveIntervals
is manually re-run after two-address lowering, it currently
does add extra kills to two-address instructions, but this
is considered a bug.
llvm-svn: 59194
2008-11-12 23:24:15 +00:00
88ba5f0b96
Move the code that inserts X87 FP_REG_KILL instructions from a
...
special-purpose hook to a new pass. Also, add check to see if any
x87 virtual registers are used, to avoid doing any work in the
common case that no x87 code is needed.
llvm-svn: 59190
2008-11-12 22:55:05 +00:00
287a25d636
Remove the incorrect assertion. We don't have enough information before relocation to set U bit.
...
llvm-svn: 59170
2008-11-12 21:37:59 +00:00
0c6b786ab2
CMake: when bulding shared libraries on non-WIN32 systems, link dl to
...
LLVMSystem.
llvm-svn: 59159
2008-11-12 20:40:56 +00:00
38d6c9a817
Tell GenLibDeps.pl to inspect .so and .dylib shared files.
...
llvm-svn: 59158
2008-11-12 20:39:06 +00:00
6467858be1
Fix unsigned char->ppcf128 conversion.
...
llvm-svn: 59150
2008-11-12 18:38:44 +00:00
0df957e09d
Do the LiveVariables update before printing the instruction in
...
the debug output, so that the updated liveness flags are
reflected in the debug output.
llvm-svn: 59147
2008-11-12 17:15:19 +00:00
5efcb61337
Remove some debugging code made redundant by the change to do
...
coalescing as a separate pass rather than inside of
LiveIntervalAnalysis.
llvm-svn: 59146
2008-11-12 17:09:23 +00:00
da82aa3e0d
Update VarInfo's comments to reflect the current code. LiveVar
...
no longer records a unique defining instruction, and virtual
registers may have multiple kills while still being defined
and killed in the same block.
llvm-svn: 59145
2008-11-12 17:02:24 +00:00
8a46117376
Correct a function name in a comment.
...
llvm-svn: 59143
2008-11-12 16:53:40 +00:00
129f4febd2
Add test case for ptr annotation.
...
llvm-svn: 59142
2008-11-12 16:12:27 +00:00
a2909684b6
Check the return value of std::getenv.
...
When constructing std::strings from C strings, we should check the input
value to be not NULL so that the std::string constructor does not
segfault.
Fixes #3047 .
llvm-svn: 59131
2008-11-12 12:41:18 +00:00
d85a1669b9
Correct these links.
...
llvm-svn: 59126
2008-11-12 10:10:25 +00:00
2907b0085c
Simplify SplitVecRes_EXTRACT_SUBVECTOR. This means
...
that it no longer handles non-power-of-two vectors.
However it previously only handled them sometimes,
depending on obscure numerical relationships between
the index and vector type. For example, for a vector
of length 6, it would succeed if and only if the
index was an even multiple of 6. I consider this
more confusing than useful.
llvm-svn: 59122
2008-11-12 08:37:57 +00:00
aa7060c885
Correct some thinkos in the expansion of ADD/SUB
...
when the target does not support ADDC/SUBC. This
fixes PR3044.
llvm-svn: 59120
2008-11-12 08:23:26 +00:00
e4df875dd6
Change binary dump format.
...
llvm-svn: 59119
2008-11-12 08:22:43 +00:00
45d030a05a
Address mode immediate offset has already been divided by 4.
...
llvm-svn: 59117
2008-11-12 08:21:12 +00:00
052f20d3b1
Fix a VFP binary arithmetic instruction encoding bug.
...
llvm-svn: 59116
2008-11-12 08:14:21 +00:00
2836d91630
Fix address mode 3 immediate offset mode encoding.
...
llvm-svn: 59109
2008-11-12 07:34:37 +00:00
af644b50b4
Consolidate formats; fix FCMPED etc. encodings.
...
llvm-svn: 59107
2008-11-12 07:18:38 +00:00
9c9abe5936
Add ptr annotation intrinsic.
...
llvm-svn: 59106
2008-11-12 07:17:57 +00:00
4b6c7efbde
Fix VFP conversion instruction encodings.
...
llvm-svn: 59104
2008-11-12 06:41:41 +00:00
a0e2f26320
Fix encoding of single-precision VFP registers.
...
llvm-svn: 59102
2008-11-12 02:19:38 +00:00
ffc67df2aa
Fix the testb optimization so x86 also bootstraps.
...
Reenable test.
llvm-svn: 59101
2008-11-12 02:00:35 +00:00
bfcee5b863
VFP fld / fst immediate field is multiplied by 4.
...
llvm-svn: 59100
2008-11-12 01:02:24 +00:00
1b504d5372
CMake: Remove removed source file.
...
llvm-svn: 59098
2008-11-12 00:14:12 +00:00
1cb041242f
Add a bit of lazy evaluation to PopulateCompilationGraph().
...
Only the tools that are mentioned in the compilation graph definition
are now inserted by PopulateCompilationGraph(). This should cut down
plugin loading time a little.
llvm-svn: 59097
2008-11-12 00:05:17 +00:00
c1e7dbb1f7
Some cosmetic changes.
...
llvm-svn: 59096
2008-11-12 00:04:46 +00:00
4f02a0b740
Remove
...
llvm-svn: 59093
2008-11-11 23:58:15 +00:00
bf0835706c
Undo previous check-in.
...
llvm-svn: 59092
2008-11-11 23:57:33 +00:00
7d8b884b12
This shouldn't be necessary
...
llvm-svn: 59090
2008-11-11 23:19:51 +00:00
97ccab888a
Fix FMDRR encoding.
...
llvm-svn: 59088
2008-11-11 22:46:12 +00:00
ad519bbe54
Handle floating point constpool_entry's.
...
llvm-svn: 59087
2008-11-11 22:19:31 +00:00
fd395eb801
Don't walk into predecessors in which the vreg is not live when doing shrinkwrapping.
...
This lets several failing tests get farther along, but doesn't completely fix any of them.
llvm-svn: 59086
2008-11-11 22:11:27 +00:00
8cbbcb1f2f
Encode VFP load / store instructions.
...
llvm-svn: 59084
2008-11-11 21:48:44 +00:00
e52e0897e2
In ScheduleDAGRRList::CopyAndMoveSuccessors, create the SUnit for the load
...
before creating the SUnit for the operation that it was unfolded from. This
allows each SUnit to have all of its predecessor SUnits available at the time
it is created. I don't know yet if this will be absolutely required, but it
is a little tidier to do it this way.
llvm-svn: 59083
2008-11-11 21:34:44 +00:00
fb78ef9fd3
Avoid relying on the SelectionDAG for initializing the MachineFunction and
...
TargetLoweringInfo variables for the scheduler.
llvm-svn: 59082
2008-11-11 21:31:56 +00:00
7ae7d91ee0
CMake: Updated library dependency info used for MSVC++.
...
llvm-svn: 59079
2008-11-11 20:04:40 +00:00
2353ef3e91
CMake: Updated list of source files for lib/Transforms/Utils.
...
llvm-svn: 59077
2008-11-11 19:51:36 +00:00
38c9a14a88
Encode VFP conversion instructions.
...
llvm-svn: 59074
2008-11-11 19:40:26 +00:00
7db0a21b7b
last validation errors
...
llvm-svn: 59072
2008-11-11 19:36:31 +00:00
50759f2dad
Remove incomplete lto-bugpoint tool. If there is an interest then we can resurrect this tool later on and finish implementation.
...
llvm-svn: 59071
2008-11-11 19:35:38 +00:00
97a5bb1157
fix some validation errors <it> -> <i>
...
llvm-svn: 59070
2008-11-11 19:35:15 +00:00
5f04ce98f2
fix some validation errors.
...
llvm-svn: 59069
2008-11-11 19:34:28 +00:00
6096f26bd4
Add utility pass to remove dbg info.
...
llvm-svn: 59068
2008-11-11 19:33:39 +00:00
6ce09d73f0
remove an extraneous tag
...
llvm-svn: 59067
2008-11-11 19:31:26 +00:00
d402cc7b6a
Make this document *substantially* better and cover a lot more territory.
...
Document written by Mason Woo (http://www.woo.com )!
llvm-svn: 59066
2008-11-11 19:30:41 +00:00
38d2c7e0e8
Silence unused variable warning.
...
llvm-svn: 59064
2008-11-11 19:17:41 +00:00
95b18126ee
Use actual function name in comments.
...
llvm-svn: 59063
2008-11-11 19:16:41 +00:00
5499e89d06
Change the scheduler accessor methods to accept an explicit TargetMachine
...
argument instead of taking the SelectionDAG's TargetMachine. This is
needed for some upcoming scheduler changes.
llvm-svn: 59055
2008-11-11 17:50:47 +00:00
2d1937ede5
Add a README entry.
...
llvm-svn: 59052
2008-11-11 17:35:52 +00:00
93bf988701
CMake: forces rebuild of llvm-config's library dependency info when a
...
library is added or changed.
llvm-svn: 59051
2008-11-11 17:10:58 +00:00
a08c2905ad
CMake: corrected split of Alpha and Sparc AsmPrinters.
...
llvm-svn: 59050
2008-11-11 17:10:13 +00:00
90cf22e013
CMake: Removed unnecessary library path setting that was breaking the
...
build on OS X.
Fix by Jjgod Jiang!
llvm-svn: 59048
2008-11-11 16:56:52 +00:00
03e084d482
Separate sparc asmprinter. This should unbreak the native build
...
llvm-svn: 59047
2008-11-11 16:42:57 +00:00
f4caceb668
Separate alpha asmprinter. This should unbreak native build.
...
llvm-svn: 59046
2008-11-11 16:42:17 +00:00
059c4fa8d8
The 32-bit displacement field in an x86 address is signed. Arrange for it
...
to be sign-extended when it is promoted to 64 bits for intermediate
offset calculations. The offset calculations are done as uint64_t so that
overflow conditions are well defined.
This fixes a problem which is currently hidden by the x86 AsmPrinter but
which was exposed by r58917 (which is temporarily reverted). See PR3027
for details.
llvm-svn: 59044
2008-11-11 15:52:29 +00:00
8cb2e28e43
Update CMakeLists.txt
...
llvm-svn: 59039
2008-11-11 09:55:48 +00:00
49a5ce863e
Fix for PR3040:
...
The CC was changed, but wasn't checked to see if it was legal if the DAG
combiner was being run after legalization. Threw in a couple of checks just to
make sure that it's okay. As far as the PR is concerned, no back-end target
actually exhibited this problem, so there isn't an associated testcase.
llvm-svn: 59035
2008-11-11 08:25:46 +00:00
2126a6d3c4
fix another libgcc blocker
...
llvm-svn: 59026
2008-11-11 06:06:07 +00:00
774e9ac433
Cleaned up and fix bugs in convert_rndsat node
...
llvm-svn: 59025
2008-11-11 05:40:06 +00:00
4942f296c9
Un-XFAIL tests now that they're fixed.
...
llvm-svn: 59023
2008-11-11 04:44:42 +00:00
aab89ca749
Unbreak the buildbot and back out (inadvertant) casting edits in CellSPU
...
backend.
llvm-svn: 59018
2008-11-11 03:06:06 +00:00
ac2af2fdb2
Encode VFP arithmetic instructions.
...
llvm-svn: 59016
2008-11-11 02:11:05 +00:00
53b39b5467
Cleanup debug info. assocated with deleted instructions.
...
llvm-svn: 59012
2008-11-11 00:54:10 +00:00
dc6699e82f
Add utility routines to remove dead debug info.
...
llvm-svn: 59011
2008-11-11 00:53:02 +00:00
6fcefa065e
r59009 broke these tests. XFAIL for now.
...
llvm-svn: 59010
2008-11-11 00:36:10 +00:00
abad22cf45
CellSPU: Fix bug 3606, as well as some ongoing work.
...
llvm-svn: 59009
2008-11-10 23:43:06 +00:00
cfa3e287bb
Small simplification. Use the iterator already present as the insertion point.
...
llvm-svn: 59008
2008-11-10 23:38:59 +00:00
b172c66af3
Comments and indentation.
...
llvm-svn: 59007
2008-11-10 23:26:16 +00:00
02771dc473
Correct PIC function stub codegen.
...
llvm-svn: 59006
2008-11-10 23:14:47 +00:00
54c1dedd42
CMake: Fixed cross-compiling.
...
`clean' makefile target removes add-hoc directory created for building
the native tablegen.
llvm-svn: 59005
2008-11-10 22:09:59 +00:00
d3b33fea65
Fix indentation.
...
llvm-svn: 59004
2008-11-10 22:09:58 +00:00
b85755c829
Temporarily revert r58979 and related patch. It's causing a failure in X86 bootstrap:
...
Comparing stages 2 and 3
warning: ./cc1-checksum.o differs
warning: ./cc1obj-checksum.o differs
warning: ./cc1objplus-checksum.o differs
warning: ./cc1plus-checksum.o differs
Bootstrap comparison failure!
./alias.o differs
./alloc-pool.o differs
./attribs.o differs
./bb-reorder.o differs
./bitmap.o differs
./build/errors.o differs
./build/genattrtab.o differs
./build/genautomata.o differs
./build/genemit.o differs
./build/genextract.o differs
...
-bw
llvm-svn: 59003
2008-11-10 21:22:06 +00:00
747f59f0f7
- Make sure that we don't over-increment the iterator when going through the
...
basic blocks.
- Minor code clean-up.
llvm-svn: 59002
2008-11-10 21:13:10 +00:00
58fb9135e2
Added CONVERT_RNDSAT (conversion with rounding and saturation) SDNode to
...
support targets that support these conversions. Users should avoid using
this node as the current targets don't generating code for it.
llvm-svn: 59001
2008-11-10 20:54:11 +00:00
74eefb5722
Update VC++ project file.
...
llvm-svn: 58997
2008-11-10 20:03:21 +00:00
d0ce981372
If the sign of exit condition and split condition does not match
...
then do not split loop index.
llvm-svn: 58995
2008-11-10 19:48:34 +00:00
ddacbb39ab
Fix PR2667: add soft float support for sint_to_fp/uint_to_fp
...
where the argument is an apint, or smaller than the minimum
size for which there is a libcall (i32).
llvm-svn: 58994
2008-11-10 17:36:26 +00:00
13b2e3634b
Tweak some comments.
...
llvm-svn: 58993
2008-11-10 17:31:56 +00:00
7da4b44dd1
Small cleanups. No functionality change intended!
...
llvm-svn: 58992
2008-11-10 17:29:56 +00:00
d5b53e1c6c
When promoting the result of fp_to_uint/fp_to_sint,
...
inform the optimizers that the result must be zero/
sign extended from the smaller type. For example,
if a fp to unsigned i16 is promoted to fp to i32,
then we are allowed to assume that the extra 16 bits
are zero (because the result of fp to i16 is undefined
if the result does not fit in an i16). This is
quite aggressive, but should help the optimizers
produce better code. This requires correcting a
test which thought that fp_to_uint is some kind
of truncation, which it is not: in the testcase
(which does fp to i1), either the fp value converts
to 0 or 1 or the result is undefined, which is
quite different to truncation.
llvm-svn: 58991
2008-11-10 17:28:30 +00:00
0a758fae91
Work around PR1000.
...
llvm-svn: 58984
2008-11-10 10:05:09 +00:00
8e58c52b37
Proper way of doing llvm canadian-cross compilation.
...
Patch by Jim Grosbach!
llvm-svn: 58981
2008-11-10 07:33:13 +00:00
23be3fd970
Reenable test.
...
llvm-svn: 58980
2008-11-10 07:30:32 +00:00
671743369c
Really fix testb optimization on big-endian.
...
Fixes ppc32 bootstrap.
llvm-svn: 58979
2008-11-10 07:16:42 +00:00
7ef7314d1a
Third time's a charm.
...
The previous patches didn't match correctly. Also, we need to make sure that
the conditional is the same before doing the transformation.
llvm-svn: 58978
2008-11-10 06:59:06 +00:00
2a09239563
final edits
...
llvm-svn: 58966
2008-11-10 05:40:34 +00:00
25f0106fd9
Added support for the following definition of shufflevector
...
<result> = shufflevector <n x <ty>> <v1>, <n x <ty>> <v2>, <m x i32> <mask>
llvm-svn: 58964
2008-11-10 04:46:22 +00:00
09487cd437
eliminate a couple more uses of utohexstr.
...
llvm-svn: 58963
2008-11-10 04:35:24 +00:00
5505eed5ac
Use utohex_buffer instead of utohexstr to avoid creating a temporary
...
string in the .ll and .s printers.
llvm-svn: 58962
2008-11-10 04:30:26 +00:00
90cdddec75
split out the functionality of utohexstr into a new utohex_buffer
...
helper. This allows us to convert numbers to hex without necessarily
needing to make a std::string to hold the result.
llvm-svn: 58961
2008-11-10 04:22:46 +00:00
Evan Cheng