mirrors/llvm-project
0
0
Fork 0
mirror of https://github.com/llvm/llvm-project.git synced 2025-05-19 06:26:07 +00:00
Code Issues Projects Releases Wiki Activity
50,136 Commits 1,258 Branches 288 Tags
Commit Graph

4596 Commits

Author SHA1 Message Date
Devang Patel
aa3d68d301 Handle floating point ivs during doInitialization(). 
llvm-svn: 59466
 2008-11-17 21:32:02 +00:00
Devang Patel
b63c74730c Let AnalyzeAlloca() remove debug intrinsics. 
llvm-svn: 59454
 2008-11-17 18:37:53 +00:00
Torok Edwin
026259faeb If SI->size() is 0, we are not allowed to dereference ->begin(). 
This fixed PR3078.

llvm-svn: 59416
 2008-11-16 17:21:25 +00:00
Chris Lattner
7917b43a28 eliminate some std::set's. 
llvm-svn: 59409
 2008-11-16 07:17:51 +00:00
Chris Lattner
f8f6270f14 simplify loop 
llvm-svn: 59406
 2008-11-16 06:35:18 +00:00
Chris Lattner
44152742a0 simplify a bunch more instcombines to use m_Specific etc. 
llvm-svn: 59403
 2008-11-16 05:38:51 +00:00
Chris Lattner
d397fef50d factor the code for simplifying (icmp)|(icmp) into its own function. 
llvm-svn: 59402
 2008-11-16 05:20:07 +00:00
Chris Lattner
909b969b18 do some computation with apints instead of ConstantInts. 
llvm-svn: 59401
 2008-11-16 05:14:43 +00:00
Chris Lattner
feaea9bdf7 merge a check into a place where it is simpler. 
llvm-svn: 59400
 2008-11-16 05:10:52 +00:00
Chris Lattner
269cbd5770 factor a whole bunch of code out into a helper function. 
llvm-svn: 59398
 2008-11-16 05:06:21 +00:00
Chris Lattner
b37b6e7e96 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
f1be285134 simplify some instcombine matches by using m_Specific 
llvm-svn: 59395
 2008-11-16 04:46:19 +00:00
Chris Lattner
fae5e33111 Use new m_SelectCst template to eliminate macros. 
llvm-svn: 59392
 2008-11-16 04:33:38 +00:00
Chris Lattner
569d78cbb5 simplify code. 
llvm-svn: 59390
 2008-11-16 04:26:55 +00:00
Chris Lattner
c3f3b059d0 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
5f6d9a313b 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
Chris Lattner
68d2da2a19 rearrange some code, no functionality change. 
llvm-svn: 59381
 2008-11-16 03:56:24 +00:00
Chris Lattner
e02c7c7ad2 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
Devang Patel
8ada1d5de5 Refactor code. 
Strip debug information before stripping symbol names. 

llvm-svn: 59328
 2008-11-14 22:49:37 +00:00
Devang Patel
3dd51c5c62 Really remove all debug information. 
llvm-svn: 59208
 2008-11-13 01:28:40 +00:00
Oscar Fuentes
1b504d5372 CMake: Remove removed source file. 
llvm-svn: 59098
 2008-11-12 00:14:12 +00:00
Devang Patel
4f02a0b740 Remove 
llvm-svn: 59093
 2008-11-11 23:58:15 +00:00
Devang Patel
bf0835706c Undo previous check-in. 
llvm-svn: 59092
 2008-11-11 23:57:33 +00:00
Oscar Fuentes
2353ef3e91 CMake: Updated list of source files for lib/Transforms/Utils. 
llvm-svn: 59077
 2008-11-11 19:51:36 +00:00
Devang Patel
6096f26bd4 Add utility pass to remove dbg info. 
llvm-svn: 59068
 2008-11-11 19:33:39 +00:00
Devang Patel
95b18126ee Use actual function name in comments. 
llvm-svn: 59063
 2008-11-11 19:16:41 +00:00
Cedric Venet
8cb2e28e43 Update CMakeLists.txt 
llvm-svn: 59039
 2008-11-11 09:55:48 +00:00
Devang Patel
53b39b5467 Cleanup debug info. assocated with deleted instructions. 
llvm-svn: 59012
 2008-11-11 00:54:10 +00:00
Devang Patel
dc6699e82f Add utility routines to remove dead debug info. 
llvm-svn: 59011
 2008-11-11 00:53:02 +00:00
Devang Patel
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
Bill Wendling
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
Mon P Wang
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
Bill Wendling
4fb13c051d Correction for the last patch. Should match the conditional in the first part 
of the select match, not the select instruction itself.

llvm-svn: 58947
 2008-11-09 23:37:53 +00:00
Bill Wendling
1579287550 The method of doing the matching with a 'select' instruction was wrong. The 
original code was matching like this:

	if (match(A, m_Not(m_Value(B))))

B was already matched as a 'select' instruction. However, this isn't matching
what we think it's matching. It would match B as a 'Value', so basically
anything would match to it. In this case, a Constant matched. B was replaced
with a constant representation. And then the wrong value would be used in the
SelectInst::Create statement, causing a crash.

After thinking on this for a moment, and after Nick L. told me how the pattern
matching stuff was supposed to work, the solution was to match NOT an m_Value,
but an m_Select.

llvm-svn: 58946
 2008-11-09 23:17:42 +00:00
Nuno Lopes
2e42927e7c fix leakage of ValueNumbering 
llvm-svn: 58933
 2008-11-09 12:45:23 +00:00
Bill Wendling
3f547be28f If the LHS of the FCMP is coming from a UIToFP instruction, then we don't want 
to generate signed ICMP instructions to replace the FCMP. This would violate
the following:

define i1 @test1(i32 %val) {
  %1 = uitofp i32 %val to double
  %2 = fcmp ole double %1, 0.000000e+00
  ret i1 %2
}

would be transformed into:

define i1 @test1(i32 %val) {
  %1 = icmp slt i33 %val, 1
  ret i1 %1
}

which is obviously wrong. This patch modifes InstCombiner::FoldFCmp_IntToFP_Cst
to handle when the LHS comes from UIToFP.

llvm-svn: 58929
 2008-11-09 04:26:50 +00:00
Daniel Dunbar
2b9dce2669 Rework r58829, allowing removal of dbg info intrinsics during alloca 
promotion.
 - Eliminate uses after free and simplify tests.

Devang: Please check that this is still doing what you intended.
llvm-svn: 58887
 2008-11-08 04:12:17 +00:00
Bill Wendling
b9656df4ac BCUI + 1 doesn't work. Use next instead. 
llvm-svn: 58830
 2008-11-07 01:59:41 +00:00
Devang Patel
b8e0d59ceb Handle (delete) dbg intrinsics while promoting alloca. 
llvm-svn: 58826
 2008-11-07 01:30:07 +00:00
Mon P Wang
5ca2ec65bd Fixed scalarizing an extract subvector and prevent an infinite loop 
when simplify a vector. 

llvm-svn: 58820
 2008-11-06 22:52:21 +00:00
Devang Patel
5a5ab730e0 InstructionNamer preserves everything. 
llvm-svn: 58787
 2008-11-06 01:00:16 +00:00
Devang Patel
f0ef35738c Do now allow InlineAlways pass to remove dead functions. 
llvm-svn: 58744
 2008-11-05 01:39:16 +00:00
Devang Patel
7a848b0ee3 Check Attribute::NoInline. 
llvm-svn: 58742
 2008-11-05 01:37:05 +00:00
Oscar Fuentes
076e048cf7 CMake: updated list of source files. 
llvm-svn: 58736
 2008-11-05 00:11:22 +00:00
Dan Gohman
8cdea717a3 Add a new pass to simplify specific half_powr function calls. This is 
a specialized pass that it not likely to be generally useful.

llvm-svn: 58732
 2008-11-04 23:41:45 +00:00
Dale Johannesen
0a7b4f5800 Allow SROA of vectors. Removing this caused a 
huge performance regression in something we care
about.  This may not be final fix.

llvm-svn: 58718
 2008-11-04 20:54:03 +00:00
Devang Patel
f33f8a8606 Fix unused variable warnings. 
llvm-svn: 58651
 2008-11-03 23:14:09 +00:00
Devang Patel
fe57d109b6 Ignore conditions that are outside the loop. 
llvm-svn: 58631
 2008-11-03 19:38:07 +00:00
Andrew Lenharth
348f3fa6a7 add a period at the end of the comment, ignoring the fact that the comment would be hard pressed to be considered a sentence, but if it makes Bill happy... 
llvm-svn: 58630
 2008-11-03 19:29:29 +00:00
Devang Patel
c1631db93b Turn floating point IVs into integer IVs where possible. 
This allows SCEV users to effectively calculate trip count.
LSR later on transforms back integer IVs to floating point IVs
later on to avoid int-to-float casts inside the loop.

llvm-svn: 58625
 2008-11-03 18:32:19 +00:00