maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
8,995 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

626 Commits

Author SHA1 Message Date
Chris Lattner 64d88bc788 Do not use BasicBlock::succ_iterator 
llvm-svn: 8700
 2003-09-24 22:03:22 +00:00
Misha Brukman cd1d0e31f5 * No longer initialize the module, a subclass is more suitable to do this 
because it can add a module ID which we do not have at this time.
* Check to see if the module has been initialized when materializing it.

llvm-svn: 8674
 2003-09-22 23:44:13 +00:00
Chris Lattner 5dac64f629 Rename Function::getEntryNode -> getEntryBlock 
llvm-svn: 8625
 2003-09-20 14:39:18 +00:00
Chris Lattner 3284ed725a Reject "llvm." as a function name 
llvm-svn: 8608
 2003-09-19 19:31:41 +00:00
Misha Brukman 3d72faddeb Minimal implementation of the abstract ModuleProvider interface. 
llvm-svn: 8594
 2003-09-18 16:17:06 +00:00
Chris Lattner c1b1651210 Change the semancics of the dropallrefs method 
llvm-svn: 8572
 2003-09-17 04:58:59 +00:00
Chris Lattner bb9d03b9c0 Renamed DominatorTree::Node::getNode() -> getBlock() 
llvm-svn: 8469
 2003-09-11 16:26:13 +00:00
Chris Lattner 630d2954be Rework dominator interfaces to handle changes in the post-dominance 
construction.  Now there may be multiple root blocks, and null is a
special node used to mark the "virtual" exit node of a CFG.

llvm-svn: 8461
 2003-09-10 20:37:51 +00:00
Brian Gaeke ff713ae819 Make createVerifierPass return a FunctionPass *. 
llvm-svn: 8449
 2003-09-10 19:37:04 +00:00
Chris Lattner 216c7b8aed Fix spell-o's 
llvm-svn: 8431
 2003-09-10 05:29:43 +00:00
John Criswell f711d34e98 Reverting back to the previous revision. 
We want to check for length 5 because we might get the "llvm." string as the
name.  That string is in the LLVM namespace and should be checked as such.
We also don't have to worry about garbage data because (I believe) the string
class will return a valid value.  So, the switch statement will work and we
don't have to worry about the code wandering into segfault land.

llvm-svn: 8419
 2003-09-09 16:58:41 +00:00
John Criswell 8d575cb2e1 Modified the check for intrinsic functions. All intrinsic functions have to 
be at least 6 characters, since something must follow the "llvm." string in the
function name.
This seems to fix an assertion failure with the SingleSource tests, too.

llvm-svn: 8418
 2003-09-09 16:36:09 +00:00
Chris Lattner 04ecefe232 Eliminate support for the llvm.unwind intrinisic, using the Unwind instruction instead 
llvm-svn: 8411
 2003-09-08 19:44:26 +00:00
Chris Lattner 66d5f575ba Add support for unwind 
llvm-svn: 8407
 2003-09-08 18:54:36 +00:00
Chris Lattner 504f9242c3 Add support for volatile loads/stores 
llvm-svn: 8393
 2003-09-08 17:45:59 +00:00
Misha Brukman 730e047678 Spell `occurrence' correctly. 
llvm-svn: 8388
 2003-09-08 03:08:43 +00:00
Chris Lattner 20b98d2c93 Add asserts, move code around. This gets the dropAllTypeUses partially implemented 
llvm-svn: 8361
 2003-09-05 05:10:04 +00:00
Chris Lattner d15598bfe0 Move functionality preserving changes. 
Inline containsEquivalent
Remove some //'s

llvm-svn: 8358
 2003-09-05 02:39:52 +00:00
Chris Lattner 5ac07d2221 Refactor what has effectively become copy-and-pasted code 
llvm-svn: 8357
 2003-09-05 02:30:47 +00:00
Chris Lattner 3f695ff02e Check in a bunch of minor fixes, plus a whole lot of #if 0'd out code, which will hopefully be enabled in the near future 
This does not make any functionality changes

llvm-svn: 8355
 2003-09-05 02:21:39 +00:00
Chris Lattner e4fdce4235 containsEquivalent never returns its argument 
llvm-svn: 8353
 2003-09-04 23:49:53 +00:00
Chris Lattner cd27235b23 Remove needless usage of getDescription() 
llvm-svn: 8351
 2003-09-04 23:46:03 +00:00
Chris Lattner 59be7695ef Inline method 
llvm-svn: 8350
 2003-09-04 23:43:40 +00:00
Chris Lattner b8b10b5c54 Don't try to be sneaky, breaking recursive types in the process 
llvm-svn: 8348
 2003-09-04 23:41:03 +00:00
Chris Lattner 50745187ef This is now unnecessary 
llvm-svn: 8347
 2003-09-04 23:38:22 +00:00
Chris Lattner 13651f0c46 Fix bug where we couldn't print a function without a name 
llvm-svn: 8341
 2003-09-03 17:56:43 +00:00
Chris Lattner b89d2afab1 No need to rescan types when they are created. 
llvm-svn: 8339
 2003-09-03 14:44:53 +00:00
Chris Lattner cc61a136f7 Another small speedup, this one to: 2.42s 
llvm-svn: 8335
 2003-09-02 22:52:49 +00:00
Chris Lattner 188afa5feb Don't return bogus references, and don't add an entry to the Concrete map 
unless it's not empty!

llvm-svn: 8334
 2003-09-02 22:50:02 +00:00
Chris Lattner 39e5095c8e Another optimization, speed up the testcase to 2.7s 
llvm-svn: 8333
 2003-09-02 22:15:15 +00:00
Chris Lattner 835499277b Removal of explicit stack, which requires the method to be a member (so it can 
call setAbstract).  Now that we just compute abstractness we can also return
the computed value by value instead of as an argument.

llvm-svn: 8332
 2003-09-02 21:56:34 +00:00
Chris Lattner 9a61bbf1d3 Remove the "recursive bit", not only is it unused by anyone, it was also 
not correctly calculated, and calculating it wrong for fun seems rather
pointless.  This also speeds up my favorite testcase by .25 seconds.

llvm-svn: 8330
 2003-09-02 21:41:05 +00:00
Chris Lattner ce35f14050 Don't bother doing an exhaustive recursive walk if we are at the limit of what 
we need to know anyway.  This reduces the 2002-07-08-HugePerformanceProblem.llx
down to 3.210u:0.010s, which is back in the acceptable range again

llvm-svn: 8323
 2003-09-02 20:06:29 +00:00
Chris Lattner 99b9ddead7 Ugh, fix bugs. Ok, so the last fix wasn't as great as I thought it was. 
Now we're back to: 131.730u, 0.330s, which is still quite an improvement,
but still quite unacceptable

llvm-svn: 8322
 2003-09-02 19:14:12 +00:00
Chris Lattner 2a36482e74 Further simplifications 
llvm-svn: 8321
 2003-09-02 16:46:41 +00:00
Chris Lattner e0703ff161 Change the code to no longer compute the "type description" immediately when 
the type is analyzed.  Instead, only compute it when requested (with
getDescription), and cached for reuse later.

This dramatically speeds up LLVM in general because these descriptions almost
_never_ need to be constructed.  The only time they are used is when a type is
<<'d.  Printing of modules by themselves uses other code to print symbolic
types when possible, so these descriptions are really only used for debugging.

Also, this fixes the particularly bad case when lots of types get resolved to
each other, such as during linking of large programs.  In these cases, the type
descriptions would be repeatedly recomputed and discarded even though: A. noone
reads the description before it gets resolved, and B. many many resolutions
happen at intermediate steps, causing a HUGE waste of time.

Overall, this makes the getTypeDesc function much more light-weight, and fixes
bug: Assembler/2002-07-08-HugePerformanceProblem.llx, which went from taking
1048.770u/19.150s (which is 17.5 MINUTES, on apoc), to taking 0.020u/0.000s,
which is a nice little speedup.  :)

llvm-svn: 8320
 2003-09-02 16:35:17 +00:00
Brian Gaeke e248195b22 Remove assertion which is never reached. 
llvm-svn: 8318
 2003-09-02 06:45:34 +00:00
Chris Lattner bd717d897f Implement new method 
llvm-svn: 8238
 2003-08-31 00:19:28 +00:00
Chris Lattner a38adaa88f Fix bug: Linker/2003-08-28-TypeResolvesGlobal3.ll 
Use new replaceAllUsesWith stuff in a way that works even though types have not yet been propagated

llvm-svn: 8210
 2003-08-29 05:37:22 +00:00
Chris Lattner c27038d7b5 Implement "unsafe" replaceAllUsesWWith stuff for use during type resolution. 
llvm-svn: 8209
 2003-08-29 05:36:46 +00:00
Chris Lattner 6097d94295 Fix bug: Linker/2003-08-28-TypeResolvesGlobal2.ll 
llvm-svn: 8206
 2003-08-29 05:11:34 +00:00
Chris Lattner 9f15812e88 Refactor code to make it useful outside of Constants.cpp 
llvm-svn: 8205
 2003-08-29 05:09:37 +00:00
Chris Lattner ae77242011 Fix bug: Linker/2003-08-28-TypeResolvesGlobal.ll 
llvm-svn: 8202
 2003-08-29 04:49:54 +00:00
Chris Lattner ea9891311a As it turns out, things will be simpler than I first expected. We no longer 
need any exception handling intrinsics beyond llvm.unwind. (yaay)

llvm-svn: 8145
 2003-08-25 22:35:01 +00:00
Chris Lattner 8068e0cd17 Support new 'any' support for pointer size and endianness 
llvm-svn: 8119
 2003-08-24 13:48:48 +00:00
Chris Lattner 7da3571af9 rethrow is really the language independent primitive here. "throw" can be written 
in terms of it and llvm.exc.setcurrent.

Rework the intrinsics.

llvm-svn: 8110
 2003-08-24 12:24:08 +00:00
Chris Lattner ca3e569269 Fix copy-and-paste-o 
llvm-svn: 8104
 2003-08-24 06:57:53 +00:00
Chris Lattner ade9410c99 Initial support for recognizing LLVM exception handling intrinsics 
llvm-svn: 8102
 2003-08-24 05:30:29 +00:00
Chris Lattner 6d5693566f Allow specifying the name for the newly split basic block 
llvm-svn: 8097
 2003-08-24 03:41:39 +00:00
Chris Lattner 180e14cb87 Rename SwitchInst::dest_push_back -> addCase 
Add new removeCase method

llvm-svn: 8088
 2003-08-23 23:14:37 +00:00
Chris Lattner 1c3430491e If an "LLVM name" has wierd characters in it, print it out in double quotes instead of prefixing it with % 
llvm-svn: 8049
 2003-08-22 05:40:38 +00:00
Misha Brukman be372b91e1 The word `dependent' has no `a'. 
llvm-svn: 8030
 2003-08-21 22:14:26 +00:00
Chris Lattner 941b06bf3c Implement Assembler/2003-08-21-ConstantExprCast-Fold.llx 
llvm-svn: 8015
 2003-08-21 19:45:55 +00:00
Chris Lattner ddab239262 Implement testcase: Assembler/2003-08-20-ConstantExprGEP-Fold.llx 
llvm-svn: 7983
 2003-08-20 16:11:27 +00:00
Chris Lattner f8a77578a2 Do not even attempt to compute dominator information for unreachable blocks 
llvm-svn: 7963
 2003-08-18 22:11:16 +00:00
Chris Lattner ab69ecc6d5 Fix linking bug in xboard 
llvm-svn: 7952
 2003-08-18 16:54:48 +00:00
Chris Lattner 748e9e143b Add intrinsics for the llvm.sig(set|long)jmp functions 
llvm-svn: 7949
 2003-08-18 15:41:24 +00:00
Misha Brukman 7eb05a170a Spell `necessary' correctly. 
llvm-svn: 7944
 2003-08-18 14:43:39 +00:00
Brian Gaeke 2cc4b9dd2c Add new method to FunctionPassManager to add ImmutablePasses. 
llvm-svn: 7838
 2003-08-14 06:07:57 +00:00
Chris Lattner e7e094467d Dramatically simplify how -time-passes works. 
This also enables -time-passes for FunctionPassManagers, which allows it to
be used for the JIT

llvm-svn: 7834
 2003-08-14 05:20:28 +00:00
Chris Lattner cea4d8c2f5 Implement constant folding of casts from boolean constants to other values 
llvm-svn: 7812
 2003-08-13 15:52:25 +00:00
Brian Gaeke b7a8388b8c Add FunctionPassManager - it's like a PassManager, but it only deals in 
FunctionPasses.

llvm-svn: 7778
 2003-08-12 17:22:39 +00:00
Chris Lattner 4159fdaef2 Add a bunch of new Alpha Intrinsics for Rahul Joshi 
llvm-svn: 7646
 2003-08-06 20:08:25 +00:00
Chris Lattner 463d6a5e7c Implement TODO: print out short form of Invoke if possible 
llvm-svn: 7595
 2003-08-05 15:34:45 +00:00
Tanya Lattner f8c563f76c *** empty log message *** 
llvm-svn: 7447
 2003-07-31 05:06:09 +00:00
Tanya Lattner a93c7aeb7e Added function to determine if an Instruction may trap. 
llvm-svn: 7442
 2003-07-31 04:05:50 +00:00
Chris Lattner 3a5c2826d5 Fix a bug that brian reported 
llvm-svn: 7428
 2003-07-30 19:04:37 +00:00
Chris Lattner 60104f00c7 Add support for Alpha intrinsics, contributed by Rahul Joshi 
llvm-svn: 7373
 2003-07-28 21:20:57 +00:00
Chris Lattner 4b4dacd838 Make Module::getNamedFunction prefer non-external functions if there is more than 
one function of the same name

llvm-svn: 7274
 2003-07-23 20:21:30 +00:00
Chris Lattner f26a8ee580 Remove redundant const qualifiers from cast<> expressions 
llvm-svn: 7253
 2003-07-23 15:30:06 +00:00
Chris Lattner 6077c3195f Simplify code by using ConstantInt::getRawValue instead of checking to see 
whether the constant is signed or unsigned, then casting

llvm-svn: 7252
 2003-07-23 15:22:26 +00:00
Misha Brukman 7fdaab4f68 The word `separate' only has one `e'. 
llvm-svn: 7173
 2003-07-14 17:20:40 +00:00
John Criswell 3ef61afb76 Merged in autoconf branch. This provides configuration via the autoconf 
system.

llvm-svn: 7014
 2003-06-30 21:59:07 +00:00
Chris Lattner d401f39872 Avoid printing out huge structures or arrays if they are just filled with zeros 
llvm-svn: 6938
 2003-06-28 20:08:24 +00:00
Chris Lattner 4ede64e304 Implement more aggressive folding of constant GEP instructions 
llvm-svn: 6913
 2003-06-26 05:22:45 +00:00
Chris Lattner 8bd8bc8399 Make assertion more descriptive 
llvm-svn: 6889
 2003-06-24 22:20:19 +00:00
Chris Lattner 4c9cd8262a Add support for GCC 3.3 
llvm-svn: 6865
 2003-06-23 19:16:20 +00:00
Chris Lattner 22ced56476 Fix bug: InstCombine/2003-06-22-ConstantExprCrash.ll 
llvm-svn: 6857
 2003-06-22 20:48:30 +00:00
Chris Lattner 0cfcaf0cc3 Remove usage of sys/unistd.h 
llvm-svn: 6788
 2003-06-19 18:42:09 +00:00
Chris Lattner 8826647168 Detemplatize the PATypeHandle class, which was only really instantiated on 'Type'. 
llvm-svn: 6774
 2003-06-18 19:22:36 +00:00
Brian Gaeke 87b4f0765c lib/CWriter/Writer.cpp: Copy AsmWriter's ConstantFP checking code here 
into a new function FPCSafeToPrint(), and use it in printConstant()
and printFunction() to decide whether we should output ConstantFPs as
floating-point constants or as references to stack-allocated variables.

lib/VMCore/AsmWriter.cpp: Fix an apparent typo in the code mentioned above.

llvm-svn: 6762
 2003-06-17 23:55:35 +00:00
Chris Lattner cc7d6ff656 Fix bug: Linker/2003-06-02-TypeResolveProblem2.ll 
llvm-svn: 6699
 2003-06-16 12:11:33 +00:00
Chris Lattner d295d99664 Fix (bogus) possibly uninitialized warning 
llvm-svn: 6634
 2003-06-05 21:01:26 +00:00
Chris Lattner 93c8f14906 * Make assertion message useful 
* Kill dead conditional

llvm-svn: 6544
 2003-06-02 17:42:47 +00:00
Chris Lattner 7fa6783a01 Fix bug: Linker/2003-06-02-TypeResolveProblem.ll 
llvm-svn: 6542
 2003-06-02 17:25:46 +00:00
Chris Lattner 39adbfca5b Don't print out unique identifier for opaque types 
llvm-svn: 6511
 2003-06-01 03:45:51 +00:00
Chris Lattner 8acf346e20 Fix constant folding to ALWAYS work. 
llvm-svn: 6355
 2003-05-27 19:16:07 +00:00
Chris Lattner 20ec7bc0db Fix problem with last checkin. 
llvm-svn: 6328
 2003-05-25 16:15:32 +00:00
Chris Lattner 98fa07b1d5 Fix Bug: Linker/2003-04-26-NullPtrLinkProblem.ll 
This was a problem with constants having their types resolved to some new type,
but there was already a constant of the new type created.  Before, these types
were never merged together, now they are.

llvm-svn: 6314
 2003-05-23 20:03:32 +00:00
Chris Lattner f31a257bfb Remove using declarations and extraneous #includes 
llvm-svn: 6303
 2003-05-22 21:47:17 +00:00
Chris Lattner ef76b27a19 Fix static constructor ordering problem 
llvm-svn: 6302
 2003-05-22 21:31:52 +00:00
Chris Lattner 5eef9ffc27 Remove using declarations 
llvm-svn: 6300
 2003-05-22 21:21:43 +00:00
Chris Lattner 38a9bcde76 Add support for shift constant expressions 
llvm-svn: 6260
 2003-05-21 17:49:25 +00:00
Misha Brukman e5838c4d72 s/convertable/convertible/g 
llvm-svn: 6248
 2003-05-20 18:45:36 +00:00
Chris Lattner 192623ec93 Add support for setjmp/longjmp primitives 
Patch checked in for Bill Wendling :)

llvm-svn: 6241
 2003-05-17 22:26:33 +00:00
Chris Lattner cb4d26fb95 Fix bug: Assembler/2003-05-15-AssemblerProblem.llx 
llvm-svn: 6234
 2003-05-15 19:37:21 +00:00
Chris Lattner 55ed6561a1 Remove unnecessary casts 
llvm-svn: 6201
 2003-05-14 17:51:05 +00:00
Chris Lattner 15285abcbe Print opaque types 
llvm-svn: 6200
 2003-05-14 17:50:47 +00:00
Chris Lattner 69f6af1604 Fix bug 
llvm-svn: 6184
 2003-05-14 02:47:13 +00:00
Chris Lattner c2ceed1b38 Implement another getelementptr folding opportunity that arises when 
linking stuff with appending linkage

llvm-svn: 6180
 2003-05-13 21:50:52 +00:00