| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Fix a bug reported by Kelly Wilson, where we incorrectly | Chris Lattner | 2008-06-30 | 2 | -4/+17 |
| | | | | | | | rejected FP immediates like 08.123 llvm-svn: 52890 | ||||
| * | refactor some code out into a new method. | Chris Lattner | 2008-06-30 | 2 | -83/+106 |
| | | | | | llvm-svn: 52889 | ||||
| * | check in anton's patch to make inlining happen in a determinstic order | Chris Lattner | 2008-06-30 | 1 | -4/+6 |
| | | | | | | | | and fix the bug that it uncovers: inlining a pattern fragment could bring in other pattern fragments if the inlinee hadn't already been inlined. llvm-svn: 52888 | ||||
| * | Implement split and scalarize for SELECT_CC, fixing PR2504 | Chris Lattner | 2008-06-30 | 2 | -0/+32 |
| | | | | | llvm-svn: 52887 | ||||
| * | Because of the laziness, the required passes must exist even after | Nick Lewycky | 2008-06-30 | 1 | -2/+2 |
| | | | | | | | | | | LoopVR::runOnFunction runs. This should accomplish that, but it doesn't. I think that's a PassManager bug, but without a consumer of LoopVR in the tree, I can't give steps to reproduce. llvm-svn: 52886 | ||||
| * | Add a value range analysis that lazily computes ranges using ScalarEvolutions. | Nick Lewycky | 2008-06-30 | 3 | -0/+381 |
| | | | | | llvm-svn: 52885 | ||||
| * | Revert (52748 and friends): | Anton Korobeynikov | 2008-06-29 | 11 | -141/+158 |
| | | | | | | | | | | | | | Move GetConstantStringInfo to lib/Analysis. Remove string output routine from Constant. Update all callers. Change debug intrinsic api slightly to accomodate move of routine, these now return values instead of strings. This unbreaks llvm-gcc bootstrap. llvm-svn: 52884 | ||||
| * | make type attribute processing static instead of methods on Sema. | Chris Lattner | 2008-06-29 | 2 | -48/+43 |
| | | | | | llvm-svn: 52881 | ||||
| * | make the rest of the decl attribute processing methods be | Chris Lattner | 2008-06-29 | 2 | -179/+160 |
| | | | | | | | static functions instead of methods on sema. llvm-svn: 52880 | ||||
| * | make most of Sema public. Sema is a class private to the Sema library | Chris Lattner | 2008-06-29 | 2 | -39/+37 |
| | | | | | | | | anyway, so there is no real loss here. Start making attribute processing methods static functions instead of methods on Sema. llvm-svn: 52879 | ||||
| * | move a few methods, no other change. | Chris Lattner | 2008-06-29 | 1 | -74/+75 |
| | | | | | llvm-svn: 52878 | ||||
| * | handle type attributes when converting types, not when processing decls. | Chris Lattner | 2008-06-29 | 2 | -16/+6 |
| | | | | | llvm-svn: 52877 | ||||
| * | Make ProcessDeclAttributes walk the declarator structure pulling | Chris Lattner | 2008-06-29 | 4 | -21/+60 |
| | | | | | | | | | | | | | | decl attributes out of the various places they can hide. This makes us correctly reject things like this: t.c:2:22: error: mode attribute only supported for integer and floating-point types int **__attribute((mode(HI)))* i32; ^ because you can't make a pointer be HImode. llvm-svn: 52876 | ||||
| * | move some code from all callers of ProcessDeclAttributes into | Chris Lattner | 2008-06-29 | 3 | -18/+11 |
| | | | | | | | the implementation of ProcessDeclAttributes. llvm-svn: 52875 | ||||
| * | more attribute refactoring/renaming, no functionality change. | Chris Lattner | 2008-06-28 | 3 | -48/+53 |
| | | | | | llvm-svn: 52874 | ||||
| * | more minor tidiness. | Chris Lattner | 2008-06-28 | 1 | -17/+12 |
| | | | | | llvm-svn: 52873 | ||||
| * | more cleanups, refactor HandleVectorTypeAttribute | Chris Lattner | 2008-06-28 | 3 | -44/+46 |
| | | | | | | | | | to work list the rest of the attr handlers. Also, rename it to HandleVectorSizeAttribute to match its attr name. No functionality change. llvm-svn: 52872 | ||||
| * | adjust the prototypes of a bunch of decl processing methods to take | Chris Lattner | 2008-06-28 | 3 | -157/+158 |
| | | | | | | | | | | | | the single attribute they look at by reference instead of by pointer. This is a subtle indicator that they take the specified attribute, not a whole list of them. This also make HandleExtVectorTypeAttribute work the same way as the rest of the attributes, adds some comments etc. No functionality change. llvm-svn: 52871 | ||||
| * | Start refactoring of asmprinters: provide a TAI hook, which will select a ↵ | Anton Korobeynikov | 2008-06-28 | 2 | -2/+69 |
| | | | | | | | 'section kind' for a global. llvm-svn: 52868 | ||||
| * | Unbreak | Anton Korobeynikov | 2008-06-28 | 1 | -2/+2 |
| | | | | | llvm-svn: 52866 | ||||
| * | Temporary rever invalid commit | Anton Korobeynikov | 2008-06-28 | 2 | -7/+9 |
| | | | | | llvm-svn: 52865 | ||||
| * | Move printing of module-level GVs into dedicated helper | Anton Korobeynikov | 2008-06-28 | 2 | -197/+200 |
| | | | | | llvm-svn: 52864 | ||||
| * | Use common naming convention | Anton Korobeynikov | 2008-06-28 | 2 | -4/+4 |
| | | | | | llvm-svn: 52863 | ||||
| * | Factor out stuff into helper function | Anton Korobeynikov | 2008-06-28 | 2 | -33/+39 |
| | | | | | llvm-svn: 52862 | ||||
| * | Cleanup | Anton Korobeynikov | 2008-06-28 | 1 | -6/+3 |
| | | | | | llvm-svn: 52861 | ||||
| * | Remove X86SharedAsmPrinter | Anton Korobeynikov | 2008-06-28 | 4 | -529/+487 |
| | | | | | llvm-svn: 52860 | ||||
| * | whitespace cleanup | Anton Korobeynikov | 2008-06-28 | 2 | -25/+25 |
| | | | | | llvm-svn: 52859 | ||||
| * | Make intel asmprinter child of generic asmprinter, not x86 shared asm ↵ | Anton Korobeynikov | 2008-06-28 | 4 | -27/+138 |
| | | | | | | | printer. This leads to some code duplication, which will be resolved later. llvm-svn: 52858 | ||||
| * | Cleanup | Anton Korobeynikov | 2008-06-28 | 1 | -10/+5 |
| | | | | | llvm-svn: 52857 | ||||
| * | Whitespace cleanup | Anton Korobeynikov | 2008-06-28 | 1 | -22/+22 |
| | | | | | llvm-svn: 52856 | ||||
| * | Handle unnamed bitfields when parsing C++ classes. | Argyrios Kyrtzidis | 2008-06-28 | 2 | -26/+31 |
| | | | | | llvm-svn: 52855 | ||||
| * | Really fix the bootstrap failure. | Chris Lattner | 2008-06-28 | 1 | -9/+5 |
| | | | | | llvm-svn: 52854 | ||||
| * | Fix for PR2501; this patch makes usual arithmetic conversions for | Eli Friedman | 2008-06-28 | 6 | -5/+97 |
| | | | | | | | | | integers which have the same width and different signedness work correctly. (The testcase in PR2501 uses a comparison between long and unsigned int). llvm-svn: 52853 | ||||
| * | Replace CurFunctionDecl and CurMethodDecl with methods getCurFunctionDecl() ↵ | Argyrios Kyrtzidis | 2008-06-28 | 8 | -52/+50 |
| | | | | | | | and getCurMethodDecl() that return the appropriate Decl through CurContext. llvm-svn: 52852 | ||||
| * | Add back the capability to include nul characters in strings with | Chris Lattner | 2008-06-28 | 3 | -8/+14 |
| | | | | | | | | GetConstantStringInfo. This will hopefully restore llvm-gcc to happy bootstrap land. llvm-svn: 52851 | ||||
| * | Tighten up checking. | Chris Lattner | 2008-06-28 | 1 | -4/+10 |
| | | | | | llvm-svn: 52850 | ||||
| * | When folding a bitcast into a load or store, preserve the alignment | Dan Gohman | 2008-06-28 | 1 | -2/+2 |
| | | | | | | | | information of the original load or store, which is checked to be at least as good, and possibly better. llvm-svn: 52849 | ||||
| * | Updated checker build to checker-47. | Ted Kremenek | 2008-06-28 | 1 | -1/+1 |
| | | | | | llvm-svn: 52848 | ||||
| * | Fix GetMainExecutable. Patch by Sam Bishop. | Seo Sanghyeon | 2008-06-27 | 1 | -4/+2 |
| | | | | | llvm-svn: 52847 | ||||
| * | Fix a bug where we didn't promote 'const float' (or typedefs) to | Chris Lattner | 2008-06-27 | 2 | -5/+12 |
| | | | | | | | double in some places. llvm-svn: 52846 | ||||
| * | the 'mode' attribute is a decl attribute, not a type attribute. Move it to | Chris Lattner | 2008-06-27 | 4 | -137/+132 |
| | | | | | | | SemaDeclAttr, and do some cleanups. llvm-svn: 52844 | ||||
| * | Looks like this condition is inverted. | Evan Cheng | 2008-06-27 | 1 | -2/+2 |
| | | | | | llvm-svn: 52841 | ||||
| * | Nuno points out that my numbers were out of date | Chris Lattner | 2008-06-27 | 1 | -1/+1 |
| | | | | | llvm-svn: 52840 | ||||
| * | Add a NextPowerOf2 function to calculate the next power of two greater than ↵ | Owen Anderson | 2008-06-27 | 1 | -0/+12 |
| | | | | | | | a given integer. llvm-svn: 52839 | ||||
| * | implement some fixme's by making "autorenaming" in the value symbol table not | Chris Lattner | 2008-06-27 | 2 | -32/+11 |
| | | | | | | | thrash the heap with string stuff (e.g. utostr). llvm-svn: 52838 | ||||
| * | simplify some code to avoid string thrashing. | Chris Lattner | 2008-06-27 | 1 | -3/+5 |
| | | | | | llvm-svn: 52837 | ||||
| * | Use StringSet instead of std::set<std::string> | Anton Korobeynikov | 2008-06-27 | 3 | -26/+25 |
| | | | | | llvm-svn: 52836 | ||||
| * | add a helper. | Chris Lattner | 2008-06-27 | 1 | -0/+2 |
| | | | | | llvm-svn: 52835 | ||||
| * | Add a new version of Module::getFunction that takes a const char* instead | Chris Lattner | 2008-06-27 | 4 | -0/+15 |
| | | | | | | | | of a std::string. This avoids copying the string to the heap in common cases. Patch by Pratik Solanki! llvm-svn: 52834 | ||||
| * | making progress! | Chris Lattner | 2008-06-27 | 1 | -1/+1 |
| | | | | | llvm-svn: 52833 | ||||

