maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
48,718 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

25215 Commits

Author SHA1 Message Date
Matthijs Kooijman c8d7988da8 Make MachineFunction not crash when TargetMachine::getRegisterInfo() returns 
NULL, but just hide some debug output then.

llvm-svn: 57437
 2008-10-13 12:37:16 +00:00
Gabor Greif cf1d1b7fbc do not use deprecated interfaces 
llvm-svn: 57433
 2008-10-13 10:21:17 +00:00
Nick Lewycky 707663eda8 Disallow the construction of SCEVs with could-not-compute operands. Catch CNCs 
returned by BinomialCoefficient and don't try to operate with them. This
replaces the previous fix for PR2857.

llvm-svn: 57431
 2008-10-13 03:58:02 +00:00
Chris Lattner c52af45304 calls can be supported. 
llvm-svn: 57428
 2008-10-13 01:59:13 +00:00
Dale Johannesen cc98e28f37 Change TAG_ names to DW_TAG for gcc (testsuite) compatibility. 
llvm-svn: 57425
 2008-10-12 21:23:01 +00:00
Owen Anderson fe1f3d6e08 Fix a bug in live-in detection that caused lost-copy problems to show up. 
llvm-svn: 57424
 2008-10-12 20:39:30 +00:00
Anton Korobeynikov 46a9c01fff Update size of inst correctly with segment override. 
llvm-svn: 57414
 2008-10-12 10:30:11 +00:00
Owen Anderson de9812de43 Add special-case code to allow null-guards on calls to malloc. 
llvm-svn: 57413
 2008-10-12 08:10:46 +00:00
Owen Anderson f2699bb57d Make Escape Analysis work for any pointer. 
llvm-svn: 57412
 2008-10-12 07:33:29 +00:00
Dale Johannesen ba074c0fed Change Dwarf comments starting with AT_ to DW_AT_ to 
match gcc.  Helps with the testsuite.

llvm-svn: 57410
 2008-10-12 06:20:47 +00:00
Owen Anderson 198966dbef Fix crashes and infinite loops. 
llvm-svn: 57408
 2008-10-12 06:03:38 +00:00
Owen Anderson 36b48de43c Duncan convinced me that it's not possible to transform control-based escapes into 
data-based ones.  Just be conservative when analyzing control-based escapes.

llvm-svn: 57400
 2008-10-12 03:59:45 +00:00
Chris Lattner c46186e890 fix typo 
llvm-svn: 57388
 2008-10-11 23:59:03 +00:00
Chris Lattner da435910e8 Fix PR2697 by rewriting the '(X / pos) op neg' logic. This also changes 
a couple other cases for clarity, but shouldn't affect correctness.

Patch by Eli Friedman!

llvm-svn: 57387
 2008-10-11 22:55:00 +00:00
Chris Lattner 2753955fc0 Change CALLSEQ_BEGIN and CALLSEQ_END to take TargetConstant's as 
parameters instead of raw Constants.  This prevents the constants from
being selected by the isel pass, fixing PR2735.

llvm-svn: 57385
 2008-10-11 22:08:30 +00:00
Chris Lattner d57b7603f9 rearrange some code. 
llvm-svn: 57384
 2008-10-11 22:07:19 +00:00
Duncan Sands 23ee981e8e Fix comment typo. 
llvm-svn: 57381
 2008-10-11 19:34:24 +00:00
Anton Korobeynikov 2589777f3f Add ability to override segment (mostly for code emitter purposes). 
llvm-svn: 57380
 2008-10-11 19:09:15 +00:00
Daniel Dunbar d94184395f Unbreak DbgStopPointInst::getFileName(). 
llvm-svn: 57373
 2008-10-11 06:40:56 +00:00
Chris Lattner fb1f4a1329 simplify comparison 
llvm-svn: 57371
 2008-10-11 00:08:02 +00:00
Dale Johannesen 05b54c2af4 Fix SSE4.1 roundss, roundsd. While the instructions have 
the same pattern as roundpd/roundps, the Intel compiler 
builtins do not:  rounds* has an extra operand.  Fixes
gcc.target/i386/sse4_1-rounds[sd]-[1234].c

llvm-svn: 57370
 2008-10-10 23:51:03 +00:00
Devang Patel 647a1e532b Check loop exit predicate properly while eliminating one iteration loop. 
This patch fixes PR 2869

llvm-svn: 57369
 2008-10-10 22:02:57 +00:00
Anton Korobeynikov 58deb69040 Fix a thinko and unbreak sparc default CC 
llvm-svn: 57368
 2008-10-10 21:47:37 +00:00
Dale Johannesen 4f2791617e Remove some overzealous checks that were rejecting 
valid comments in inline assembly.
gcc.target/i386/20011009-1.c

llvm-svn: 57365
 2008-10-10 21:04:42 +00:00
Anton Korobeynikov f8a4a0e959 Extend set of return registers on sparc until someone will implement MRV support there. At least, this will allow libgcc compile, however we are not ABI-compatible with stuff compiled with native gcc. 
llvm-svn: 57364
 2008-10-10 20:30:14 +00:00
Anton Korobeynikov b80b485264 Ignore extra 'r' modifier for now 
llvm-svn: 57363
 2008-10-10 20:29:50 +00:00
Anton Korobeynikov 76baad1ffc Use expand for smul_lohi for now 
llvm-svn: 57362
 2008-10-10 20:29:31 +00:00
Anton Korobeynikov 281cf247a5 Add rudimentary support for 'r' register operand 
llvm-svn: 57359
 2008-10-10 20:28:10 +00:00
Anton Korobeynikov b8736566c2 Cleanup 
llvm-svn: 57358
 2008-10-10 20:27:31 +00:00
Oscar Fuentes 45fde6fc4f CMake: updated lib/Analysis/CMakeLists.txt. 
llvm-svn: 57357
 2008-10-10 18:51:36 +00:00
Mon P Wang 297364cd3b Revert r57340 move guard mutex in getPointerToFunction as this can cause 
deadlock issues with java

llvm-svn: 57356
 2008-10-10 18:07:10 +00:00
Nuno Lopes e3127f3f80 fix memleak by cleaning the global sets on pass exit 
llvm-svn: 57353
 2008-10-10 16:25:50 +00:00
Anton Korobeynikov 3db2173021 Add rudimentary asmprinter support for printing inline asm operands for sparc. 
llvm-svn: 57346
 2008-10-10 10:15:03 +00:00
Anton Korobeynikov 9aaaa4035e Add dummy 'm' inline asm constraint handler for Sparc. I'm not sure, whether it is correct, however :) 
llvm-svn: 57345
 2008-10-10 10:14:47 +00:00
Anton Korobeynikov 1f9487b916 Cleanup 
llvm-svn: 57344
 2008-10-10 10:14:15 +00:00
Owen Anderson 45d41c6741 Add a basic intra-procedural escape analysis. This hasn't be extensively tested yet, but feedback is welcome. 
llvm-svn: 57342
 2008-10-10 08:36:25 +00:00
Mon P Wang 6e5eccf86b Moved guard mutex upwards to guard materializing a function 
in getPointerToFunction

llvm-svn: 57340
 2008-10-10 01:47:42 +00:00
Mon P Wang dfcc1ff8f8 Added missing print functions that take a raw_ostream 
llvm-svn: 57339
 2008-10-10 01:43:55 +00:00
Dale Johannesen 62a2e5cb2f Generated files for previous checkin. 
llvm-svn: 57331
 2008-10-09 23:01:34 +00:00
Dale Johannesen 4f0bd68cfe Add a "loses information" return value to APFloat::convert 
and APFloat::convertToInteger.  Restore return value to
IEEE754.  Adjust all users accordingly.

llvm-svn: 57329
 2008-10-09 23:00:39 +00:00
Dale Johannesen 54306fe499 Rename APFloat::convertToAPInt to bitcastToAPInt to 
make it clearer what the function does.  No functional
change.

llvm-svn: 57325
 2008-10-09 18:53:47 +00:00
Nick Lewycky 03c5fa18f1 Don't drop alignment on globals when cloning. 
llvm-svn: 57320
 2008-10-09 06:27:14 +00:00
Chris Lattner 1a84f86271 get CodeGen/Alpha/mul128.ll to work. 
llvm-svn: 57318
 2008-10-09 04:50:56 +00:00
Dale Johannesen d796164e89 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 66e08292aa (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 06c67f88d7 dont specialize weak functions and the like 
llvm-svn: 57305
 2008-10-08 18:45:59 +00:00
Jim Grosbach d83529e8c4 Comment to be explicit that the enumeration values for CondCodes matter. 
llvm-svn: 57295
 2008-10-08 16:24:35 +00:00
Duncan Sands 32052e8272 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 26ff6f9c54 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 9b1300ba55 regenerate 
llvm-svn: 57290
 2008-10-08 06:44:45 +00:00
Chris Lattner 152acb5325 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 42d5785dbd 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 bfe12ee668 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 60ad173dfe 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 b3ba449cfb 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 c1d47c56f9 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 d3917157d5 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 f311fe142c 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 b53acd8caa need ARM.h for ARMCC definition 
llvm-svn: 57261
 2008-10-07 21:01:51 +00:00
Owen Anderson 1d338fc6a4 Add an option to enable StrongPHIElimination, for ease of testing. 
llvm-svn: 57259
 2008-10-07 20:22:28 +00:00
Jim Grosbach c084e84028 Encode the conditional execution predicate when JITing. 
llvm-svn: 57258
 2008-10-07 19:05:35 +00:00
Dale Johannesen 422ef88f31 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 21dca9cbb1 Use Dan's supperior check 
llvm-svn: 57255
 2008-10-07 18:27:23 +00:00
Andrew Lenharth 5aa1cc4065 Correctly set attributes when removing args during cloning. Fixes PR2765 
llvm-svn: 57254
 2008-10-07 18:08:38 +00:00
Jim Grosbach 2fb5c3938b 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 1d54d4f375 Fix Opcode values of CMP and CMN 
llvm-svn: 57251
 2008-10-07 17:40:46 +00:00
Andrew Lenharth d69bdaef64 No need for |= 
llvm-svn: 57249
 2008-10-07 17:11:29 +00:00
Andrew Lenharth 6d409f08be 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 6606f17e50 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 1699ad9030 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 3a9be150be Expand arith on machines without carry flags 
llvm-svn: 57243
 2008-10-07 14:15:42 +00:00
Andrew Lenharth 64861a7181 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 7221af384d 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 bef9b0bef0 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 40aafce00d Fix typo, fix PR 2865. 
llvm-svn: 57221
 2008-10-06 23:22:54 +00:00
Dale Johannesen 6c6729f3a8 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 94d14f2d45 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 6271b0a83c 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 c3e3ca9a45 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 fff2995532 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 c0f3b52e65 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 dfe979bcb0 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 ab379c905b Remove unncessary isDeclaration() checks. 
llvm-svn: 57179
 2008-10-06 17:30:07 +00:00
Matthijs Kooijman cbe5e16eb5 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 7875876e46 reorder #include order, patch by Kenneth Boyd! 
llvm-svn: 57148
 2008-10-06 03:54:25 +00:00
Chris Lattner 0c41861f39 Add #include to get alloca, patch by Kenneth Boyd! 
llvm-svn: 57147
 2008-10-06 03:53:16 +00:00
Chris Lattner 851e72cd22 fix an incorrect and extremely confusing error message 
llvm-svn: 57123
 2008-10-05 18:24:03 +00:00
Chris Lattner 4744ed5f94 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 0ea0fce8fe regenerate 
llvm-svn: 57114
 2008-10-05 16:49:34 +00:00
Nuno Lopes 33b90e3f59 clean ArgTypeListI production: free the PATypeHolder 
llvm-svn: 57113
 2008-10-05 16:49:03 +00:00
Anton Korobeynikov 37e560cde1 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 d2aded08ac 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 f9325e5f67 this case is matched now. 
llvm-svn: 57096
 2008-10-05 02:16:12 +00:00
Chris Lattner 917a6c1343 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 ca91f265c4 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 2416896b3c 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 b5abd78ab5 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 1d35e9aebe 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 fc9bc3cf23 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 b52ef06c8c Revert r56675 - it breaks unwinding runtime everywhere. 
llvm-svn: 57048
 2008-10-04 11:09:36 +00:00