summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Remove old DSE.Owen Anderson2007-08-011-179/+0
| | | | llvm-svn: 40666
* update this to build with LLVM ToTChris Lattner2007-08-011-2/+2
| | | | llvm-svn: 40665
* Update generated files.David Greene2007-08-017-2733/+2398
| | | | llvm-svn: 40663
* New CallInst interface to address GLIBCXX_DEBUG errors caused byDavid Greene2007-08-0122-66/+158
| | | | | | | | indexing an empty std::vector. Updates to all clients. llvm-svn: 40660
* Print floating point literal values better.Chris Lattner2007-08-011-2/+2
| | | | llvm-svn: 40659
* Indexed loads each has 2 outputs.Evan Cheng2007-08-011-10/+10
| | | | llvm-svn: 40658
* Requires SSE2.Evan Cheng2007-08-011-2/+2
| | | | llvm-svn: 40657
* Tighten up Parser::ParseTypeofSpecifier().Steve Naroff2007-07-312-18/+29
| | | | | | Add some more tests to typeof.c. Also added a couple of missing "expect" attributes that caused the test to fail. llvm-svn: 40656
* Don't let the memory allocator outsmart GVN. ;-)Owen Anderson2007-07-311-0/+6
| | | | llvm-svn: 40655
* simpleregistercoalescing -> regcoalescing. It's too long for me to handle.Evan Cheng2007-07-311-1/+1
| | | | llvm-svn: 40654
* remove more explicit accesses to the canonical type pointer.Chris Lattner2007-07-312-9/+9
| | | | llvm-svn: 40653
* simplify some type checking code, don't explicitly accessChris Lattner2007-07-311-43/+37
| | | | | | canonical types. llvm-svn: 40652
* move trivial type predicates inline.Chris Lattner2007-07-312-17/+25
| | | | llvm-svn: 40651
* Fix a failure I accidentally caused in my last commit by mishandling the Owen Anderson2007-07-312-0/+24
| | | | | | removal of redundant phis. llvm-svn: 40650
* Fix a bug in GetKnownAlignment of packed structs.Lauro Ramos Venancio2007-07-312-3/+32
| | | | llvm-svn: 40649
* Change the x86 assembly output to use tab characters to separate theDan Gohman2007-07-3135-1163/+1163
| | | | | | | | | mnemonics from their operands instead of single spaces. This makes the assembly output a little more consistent with various other compilers (f.e. GCC), and slightly easier to read. Also, update the regression tests accordingly. llvm-svn: 40648
* Fix GLIBCXX_DEBUG error owing to dereference of end iterator. There'sDavid Greene2007-07-312-29/+41
| | | | | | | no guarantee that an instruction returned by getDependency exists in the maps. llvm-svn: 40647
* split the rest of the type predicates into pure predicates:Chris Lattner2007-07-314-50/+73
| | | | | | there is now an isXXXType and a getAsXXXType llvm-svn: 40646
* add internals manual to projectChris Lattner2007-07-311-0/+4
| | | | llvm-svn: 40645
* Owen pointed out that this made no sense :)Chris Lattner2007-07-311-3/+3
| | | | llvm-svn: 40644
* add two missing files to the xcode project.Chris Lattner2007-07-311-0/+8
| | | | llvm-svn: 40643
* Fix a misoptimization in aha.Owen Anderson2007-07-312-11/+338
| | | | llvm-svn: 40642
* Use SCEVExpander::InsertCastOfTo instead of calling new IntToPtrInstDan Gohman2007-07-311-5/+12
| | | | | | | directly, because the insert point used by the SCEVExpander may vary from what LSR originally computes. llvm-svn: 40641
* rename isReferenceType to follow the new scheme.Chris Lattner2007-07-314-6/+9
| | | | llvm-svn: 40640
* make isPointerType() a pure predicate, rename theChris Lattner2007-07-314-7/+11
| | | | | | existing one to getAsPointerType() llvm-svn: 40639
* Add note.Devang Patel2007-07-311-1/+3
| | | | llvm-svn: 40638
* update nameChris Lattner2007-07-311-1/+1
| | | | llvm-svn: 40637
* new testcaseChris Lattner2007-07-311-0/+8
| | | | llvm-svn: 40636
* Revert overly aggressive interpretation of noaliasChristopher Lamb2007-07-312-44/+1
| | | | llvm-svn: 40635
* Regenerate.Reid Spencer2007-07-312-954/+954
| | | | llvm-svn: 40634
* fp2uint -> fptouiReid Spencer2007-07-311-8/+8
| | | | llvm-svn: 40633
* After a discussion with Anton, it turns out that the InReg attribute is notReid Spencer2007-07-312-2/+2
| | | | | | permitted on function results. So, revert the last patch to make it illegal. llvm-svn: 40632
* Add parsing and AST support for GNU "typeof".Steve Naroff2007-07-3112-4/+147
| | | | | | | Many small changes to lot's of files. Still some FIXME's, however the basic support is in place. llvm-svn: 40631
* Bunch of tests to check loop passes.Devang Patel2007-07-319-0/+204
| | | | llvm-svn: 40629
* Redo and generalize previously removed opt for pinsrw: (vextract (v4i32 bc ↵Evan Cheng2007-07-317-235/+264
| | | | | | (v4f32 s2v (f32 load ))), 0) -> (i32 load ) llvm-svn: 40628
* Loop unswitch preserves dom info.Devang Patel2007-07-311-18/+33
| | | | | | Use simple analysis interface to preserve analysis info maintained by other loop passes. llvm-svn: 40627
* Implement Simple Analysis interfaces - cloneBasicBlockAnalysis and ↵Devang Patel2007-07-311-0/+26
| | | | | | deleteAnalysisValue. llvm-svn: 40626
* Introduce Simple Analysis interface for loop passes.Devang Patel2007-07-312-0/+50
| | | | | | Right now, this interface provides hooks for only to operations, 1) clone basic block 2) delete value. llvm-svn: 40625
* Teach BasicAA about noalias function parameters. Passes all of DejaGNU and ↵Christopher Lamb2007-07-312-1/+44
| | | | | | test-suite. llvm-svn: 40624
* Un-XFAIL these tests after r40622 fixed them.Christopher Lamb2007-07-312-2/+0
| | | | llvm-svn: 40623
* Regenerate.Reid Spencer2007-07-312-954/+954
| | | | llvm-svn: 40621
* Oops, I committed the wrong file before. This expands the description ofChris Lattner2007-07-311-34/+70
| | | | | | type. llvm-svn: 40620
* Allow the INREG parameter attribute to be added to functions. This permits theReid Spencer2007-07-311-0/+1
| | | | | | | | function result to be passed in a register. This implements the GCC regparm function attribute for llvm by translation to the InReg parameter attribute and fixes test/CFrontend/2002-07-30-SubregSetAssertion.c llvm-svn: 40619
* The InReg parameter attribute is valid on function results. The llvm-gcc-4.0Reid Spencer2007-07-311-2/+1
| | | | | | | front end converts regparm attribute on the gcc function into InReg attribute on the llvm function. This fixes test/CFrontend/2002-07-30-SubrefSetAssertion.c llvm-svn: 40618
* This isn't safe when there are uses of load's chain result.Evan Cheng2007-07-311-11/+4
| | | | llvm-svn: 40617
* Fix PR1581, patch by Timo SavolaChris Lattner2007-07-311-1/+1
| | | | llvm-svn: 40616
* Add a start at a clang internals manual, documenting someChris Lattner2007-07-311-0/+395
| | | | | | of the more subtle and interesting classes. llvm-svn: 40615
* add a linkChris Lattner2007-07-311-0/+2
| | | | llvm-svn: 40614
* Regenerate (again).Reid Spencer2007-07-312-148/+146
| | | | llvm-svn: 40613
* Don't include newlines in the whitespace before newline (WSNL) rule.Reid Spencer2007-07-311-2/+2
| | | | | | Fix the comment for WSNL to describe its actual function. llvm-svn: 40612
OpenPOWER on IntegriCloud