RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-27 22:12:47 +01:00
Code Issues Projects Releases Wiki Activity
42,592 Commits 4 Branches 5 Tags 704 MiB
2e352c9bb6
Commit Graph

25745 Commits

Author SHA1 Message Date
Chris Lattner
d85de82f04 simplify loop 
llvm-svn: 59406
 2008-11-16 06:35:18 +00:00
Chris Lattner
652917424d simplify a bunch more instcombines to use m_Specific etc. 
llvm-svn: 59403
 2008-11-16 05:38:51 +00:00
Chris Lattner
c487057a1e factor the code for simplifying (icmp)|(icmp) into its own function. 
llvm-svn: 59402
 2008-11-16 05:20:07 +00:00
Chris Lattner
6b5b2c3606 do some computation with apints instead of ConstantInts. 
llvm-svn: 59401
 2008-11-16 05:14:43 +00:00
Chris Lattner
f47d16afe3 merge a check into a place where it is simpler. 
llvm-svn: 59400
 2008-11-16 05:10:52 +00:00
Mon P Wang
b6661b480b Improved shuffle normalization to avoid using extract/build when we 
can extract using different indexes for two vectors. Added a few tests
for vector shuffles.

llvm-svn: 59399
 2008-11-16 05:06:27 +00:00
Chris Lattner
3b058783bc factor a whole bunch of code out into a helper function. 
llvm-svn: 59398
 2008-11-16 05:06:21 +00:00
Chris Lattner
f9dd858359 simplify the conditions on two gigantic if's, decreasing indentation 
a bit.  Next step is to factor out into their own helper functions.

llvm-svn: 59397
 2008-11-16 04:55:20 +00:00
Chris Lattner
762c52d684 simplify some instcombine matches by using m_Specific 
llvm-svn: 59395
 2008-11-16 04:46:19 +00:00
Chris Lattner
a5aee38775 Use new m_SelectCst template to eliminate macros. 
llvm-svn: 59392
 2008-11-16 04:33:38 +00:00
Chris Lattner
cba75c1b7b simplify code. 
llvm-svn: 59390
 2008-11-16 04:26:55 +00:00
Chris Lattner
21f18c9760 Handle the case where there is no "not". It is possible it got 
folded into the select.

llvm-svn: 59389
 2008-11-16 04:25:26 +00:00
Chris Lattner
6afddeeed1 factor a bunch of copy/paste code out into a helper function. 
Eliminate the cases checking for cond?0:-1, since that is already
handled by commutative checking.

llvm-svn: 59388
 2008-11-16 04:24:12 +00:00
Nick Lewycky
1cddd8346f Don't brute-force analyze cubic or higher polynomials. 
If this patch causes a performance regression for anyone, please let me know,
and it can be fixed in a different way with much more effort.

llvm-svn: 59384
 2008-11-16 04:14:25 +00:00
Chris Lattner
9dd963a73a rearrange some code, no functionality change. 
llvm-svn: 59381
 2008-11-16 03:56:24 +00:00
Chris Lattner
0c0c68bab4 if we're going to use a macro, use it maximally. no functionality change. 
llvm-svn: 59380
 2008-11-16 03:54:57 +00:00
Oscar Fuentes
42942c0bc5 Adds extern "C" ints to the .cpp files that use RegisterTarget, as 
well as 2 files that use "Registrator"s. These are to be used by the
MSVC builds, as the Win32 linker does not include libs that are
otherwise unreferenced, even if global constructors in the lib have
side-effects.

Patch by Scott Graham!

llvm-svn: 59378
 2008-11-15 21:36:30 +00:00
Nick Lewycky
75d57a3bc3 Correct this error message. 
llvm-svn: 59370
 2008-11-15 17:50:47 +00:00
Duncan Sands
52ce276405 When splitting a SHUFFLE_VECTOR, try to have the result 
use SHUFFLE_VECTOR instead.  If not practical, fall back
to the old scheme of building the split result by hand
using a BUILD_VECTOR.

llvm-svn: 59361
 2008-11-15 09:25:38 +00:00
Mon P Wang
4421962b9b Add missing widen operations, fixed widening for extracting a subvector, 
and when loading/storing a widen vector, make sure that they are loaded
and stored in consecutive order.

llvm-svn: 59357
 2008-11-15 06:05:52 +00:00
Evan Cheng
7ac8120105 Fix fuitos encoding. 
llvm-svn: 59344
 2008-11-15 00:40:57 +00:00
Dan Gohman
95967fc7b7 Correct a comment. 
llvm-svn: 59341
 2008-11-15 00:24:23 +00:00
Dan Gohman
b4151fd731 Move ScheduleDAGList's LatencyPriorityQueue class out to a separate file. 
llvm-svn: 59340
 2008-11-15 00:23:40 +00:00
Devang Patel
86c9f12e47 Refactor code. 
Strip debug information before stripping symbol names. 

llvm-svn: 59328
 2008-11-14 22:49:37 +00:00
Dan Gohman
521cee6a9c Add support for building a ScheduleDAG from MachineInstrs. This is currently 
fairly conservative; it doesn't do alias-analysis queries and it doesn't
attempt to break anti-dependencies.

llvm-svn: 59324
 2008-11-14 21:47:58 +00:00
Evan Cheng
626e85dfc2 Fix MOVrx, MOVsrl_flag, and MOVsra_flag encodings. 
llvm-svn: 59314
 2008-11-14 20:09:11 +00:00
Dale Johannesen
29e1b2e9fd Remove unneeded stuff from GRAD register class. 
llvm-svn: 59311
 2008-11-14 18:10:48 +00:00
Richard Osborne
e30cb5908e [XCore] Remove whitespace in the description used when 
registering XCoreTargetMachine.

llvm-svn: 59308
 2008-11-14 16:19:56 +00:00
Richard Osborne
c2b2d5e6cf [XCore] Fix expansion of 64 bit add/sub. Don't custom expand 
these operations if ladd/lsub are not available on the current
subtarget.

llvm-svn: 59305
 2008-11-14 15:59:19 +00:00
Richard Osborne
8f86bb4d20 Add XCore intrinsics for getid (returns thread id) and bitrev (reverses 
bits in a word).

llvm-svn: 59296
 2008-11-14 10:12:16 +00:00
Lang Hames
ed5d29fea5 Test commit. 
llvm-svn: 59293
 2008-11-14 06:51:35 +00:00
Evan Cheng
c6f581034a ARM / Mac OS X also wants to invalidate icache after jitting. 
llvm-svn: 59291
 2008-11-14 02:33:17 +00:00
Dan Gohman
bab393fdff For post-regalloc scheduling, remove the instructions from the block 
before re-inserting them.

llvm-svn: 59281
 2008-11-14 00:33:17 +00:00
Dan Gohman
5b7b7b416b Check in the correct version of the patch in r59279. 
llvm-svn: 59280
 2008-11-14 00:32:34 +00:00
Dan Gohman
ad452993b0 Debug printing for SUnits that carry MachineInstrs. 
llvm-svn: 59279
 2008-11-14 00:28:56 +00:00
Dan Gohman
f92f2d0c97 Initial support for carrying MachineInstrs in SUnits. 
llvm-svn: 59278
 2008-11-14 00:06:09 +00:00
Dan Gohman
2e0edf0617 Change DOTGraphTraits<ScheduleDAG*>::getGraphName how to find the name of 
the current function on its own, rather than relying on the SelectionDAG.

llvm-svn: 59277
 2008-11-13 23:45:55 +00:00
Evan Cheng
f7c1da41a1 Handle the rest of pseudo instructions. 
llvm-svn: 59275
 2008-11-13 23:36:57 +00:00
Evan Cheng
feb7615798 Lazy compilation callback save / restore VFP registers. 
llvm-svn: 59274
 2008-11-13 23:28:54 +00:00
Dan Gohman
0a3ae5c0f2 Remove the FlaggedNodes member from SUnit. Instead of requiring each SUnit 
to carry a SmallVector of flagged nodes, just calculate the flagged nodes
dynamically when they are needed.

The local-liveness change is due to a trivial scheduling change where
the scheduler arbitrary decision differently.

llvm-svn: 59273
 2008-11-13 23:24:17 +00:00
Owen Anderson
aa9f1836d9 Don't allow the restore point to be placed after terminators. With this change, 
MultiSource/Applications is clean with the prealloc splitter.  Some failures
remain in SPEC.

llvm-svn: 59267
 2008-11-13 21:53:14 +00:00
Dale Johannesen
de9fdff884 Extend InlineAsm::C_Register to allow multiple specific registers 
(actually, code already all worked, only the comment
changed).  Use this to implement 'A' constraint on x86.
Fixes PR 1779.

llvm-svn: 59266
 2008-11-13 21:52:36 +00:00
Evan Cheng
f8ba919d76 Always emit a function pointer as a pointer to the function stub (if there is one). This makes it possible to compare function pointer values in lazy compilation mode. This fixes PR3043. 
llvm-svn: 59265
 2008-11-13 21:50:50 +00:00
Dan Gohman
0cefa8f2ff Make the Node member of SUnit private, and add accessors. 
llvm-svn: 59264
 2008-11-13 21:36:12 +00:00
Dan Gohman
df9f75e981 Change ScheduleDAG's DAG member from a reference to a pointer, to prepare 
for the possibility of scheduling without a SelectionDAG being present.

llvm-svn: 59263
 2008-11-13 21:21:28 +00:00
Evan Cheng
4c8297e12b Don't forget to emit stubs for function GV's emitted in CONSTPOOL_ENTRY's. 
llvm-svn: 59258
 2008-11-13 19:22:28 +00:00
Dan Gohman
f63a02ae6c Use find_first/find_next to iterate through all the set bits in a 
BitVector, instead of manually testing each bit.

llvm-svn: 59246
 2008-11-13 16:31:27 +00:00
Bill Wendling
9dc2bd7973 Modify the intrinsics pattern to separate out the "return" types from the 
"parameter" types. An intrinsic can now return a multiple return values like
this:

  def add_with_overflow : Intrinsic<[llvm_i32_ty, llvm_i1_ty],
                                    [LLVMMatchType<0>, LLVMMatchType<0>]>;

llvm-svn: 59237
 2008-11-13 09:08:33 +00:00
Evan Cheng
997eb67c20 fsub{d|s} encoding bugs. 
llvm-svn: 59234
 2008-11-13 07:59:48 +00:00
Evan Cheng
d67d6c4571 Missed a break statement. 
llvm-svn: 59231
 2008-11-13 07:46:59 +00:00
Evan Cheng
3c0113820b Fix pre- and post-indexed load / store encoding bugs. 
llvm-svn: 59230
 2008-11-13 07:34:59 +00:00
Bill Wendling
0eb23711fb Refactor the code that does the type checking for intrinsics. 
llvm-svn: 59228
 2008-11-13 07:11:27 +00:00
Daniel Dunbar
a830cb14f3 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
Devang Patel
2876af73db Really remove all debug information. 
llvm-svn: 59208
 2008-11-13 01:28:40 +00:00
Bill Wendling
dedf359e39 Regenerated 
llvm-svn: 59204
 2008-11-13 01:03:00 +00:00
Bill Wendling
f5b264a64b Implement stack protectors as function attributes: "ssp" and "sspreq". 
llvm-svn: 59202
 2008-11-13 01:02:14 +00:00
Dan Gohman
229c65c05b 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
Evan Cheng
4768468ec1 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
Oscar Fuentes
dc2008cb1a CMake: when bulding shared libraries on non-WIN32 systems, link dl to 
LLVMSystem.

llvm-svn: 59159
 2008-11-12 20:40:56 +00:00
Dale Johannesen
5ad71e113e Fix unsigned char->ppcf128 conversion. 
llvm-svn: 59150
 2008-11-12 18:38:44 +00:00
Dan Gohman
5f3e5a75b4 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
Dan Gohman
ceb5b7477b 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
Duncan Sands
4e70a21580 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
Duncan Sands
117397c8dd 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
Evan Cheng
b6c760349e Change binary dump format. 
llvm-svn: 59119
 2008-11-12 08:22:43 +00:00
Evan Cheng
9cb6f40f8f Address mode immediate offset has already been divided by 4. 
llvm-svn: 59117
 2008-11-12 08:21:12 +00:00
Evan Cheng
80d0d5cfa8 Fix a VFP binary arithmetic instruction encoding bug. 
llvm-svn: 59116
 2008-11-12 08:14:21 +00:00
Evan Cheng
a4dc0e304e Fix address mode 3 immediate offset mode encoding. 
llvm-svn: 59109
 2008-11-12 07:34:37 +00:00
Evan Cheng
7fef8cfe75 Consolidate formats; fix FCMPED etc. encodings. 
llvm-svn: 59107
 2008-11-12 07:18:38 +00:00
Evan Cheng
0966883093 Fix VFP conversion instruction encodings. 
llvm-svn: 59104
 2008-11-12 06:41:41 +00:00
Evan Cheng
39d8bf295d Fix encoding of single-precision VFP registers. 
llvm-svn: 59102
 2008-11-12 02:19:38 +00:00
Dale Johannesen
a2cd0724ea Fix the testb optimization so x86 also bootstraps. 
Reenable test.

llvm-svn: 59101
 2008-11-12 02:00:35 +00:00
Evan Cheng
cc9323ac73 VFP fld / fst immediate field is multiplied by 4. 
llvm-svn: 59100
 2008-11-12 01:02:24 +00:00
Oscar Fuentes
444fd3cc2d CMake: Remove removed source file. 
llvm-svn: 59098
 2008-11-12 00:14:12 +00:00
Devang Patel
0a73799659 Remove 
llvm-svn: 59093
 2008-11-11 23:58:15 +00:00
Devang Patel
0616706919 Undo previous check-in. 
llvm-svn: 59092
 2008-11-11 23:57:33 +00:00
Andrew Lenharth
0e7b77369c This shouldn't be necessary 
llvm-svn: 59090
 2008-11-11 23:19:51 +00:00
Evan Cheng
8b7fefc126 Fix FMDRR encoding. 
llvm-svn: 59088
 2008-11-11 22:46:12 +00:00
Evan Cheng
95bad0db94 Handle floating point constpool_entry's. 
llvm-svn: 59087
 2008-11-11 22:19:31 +00:00
Owen Anderson
3ef1e1ff3f 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
Evan Cheng
35f1477c5a Encode VFP load / store instructions. 
llvm-svn: 59084
 2008-11-11 21:48:44 +00:00
Dan Gohman
291ea92cc4 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
Dan Gohman
51db591eac 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
Oscar Fuentes
ac819d0394 CMake: Updated list of source files for lib/Transforms/Utils. 
llvm-svn: 59077
 2008-11-11 19:51:36 +00:00
Evan Cheng
91e4ef91c5 Encode VFP conversion instructions. 
llvm-svn: 59074
 2008-11-11 19:40:26 +00:00
Devang Patel
c9fdfd2f0b Add utility pass to remove dbg info. 
llvm-svn: 59068
 2008-11-11 19:33:39 +00:00
Devang Patel
9e6295b55c Silence unused variable warning. 
llvm-svn: 59064
 2008-11-11 19:17:41 +00:00
Devang Patel
ef6a48b56f Use actual function name in comments. 
llvm-svn: 59063
 2008-11-11 19:16:41 +00:00
Dan Gohman
ec3b31e7eb 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
Evan Cheng
82b17df2b0 Add a README entry. 
llvm-svn: 59052
 2008-11-11 17:35:52 +00:00
Oscar Fuentes
e4e9531262 CMake: corrected split of Alpha and Sparc AsmPrinters. 
llvm-svn: 59050
 2008-11-11 17:10:13 +00:00
Anton Korobeynikov
fe80f44b35 Separate sparc asmprinter. This should unbreak the native build 
llvm-svn: 59047
 2008-11-11 16:42:57 +00:00
Anton Korobeynikov
e3e227b40b Separate alpha asmprinter. This should unbreak native build. 
llvm-svn: 59046
 2008-11-11 16:42:17 +00:00
Dan Gohman
fd00e20872 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
Cedric Venet
49a701ae17 Update CMakeLists.txt 
llvm-svn: 59039
 2008-11-11 09:55:48 +00:00
Bill Wendling
9da4535062 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
Andrew Lenharth
d096adcb5f fix another libgcc blocker 
llvm-svn: 59026
 2008-11-11 06:06:07 +00:00
Mon P Wang
c4bf9b94d5 Cleaned up and fix bugs in convert_rndsat node 
llvm-svn: 59025
 2008-11-11 05:40:06 +00:00
Scott Michel
2ab73cf730 Unbreak the buildbot and back out (inadvertant) casting edits in CellSPU 
backend.

llvm-svn: 59018
 2008-11-11 03:06:06 +00:00
Evan Cheng
3c62bb7471 Encode VFP arithmetic instructions. 
llvm-svn: 59016
 2008-11-11 02:11:05 +00:00