| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Fix the string for ISD::UDIVREM. | Dan Gohman | 2008-09-08 | 1 | -1/+1 |
| | | | | | llvm-svn: 55917 | ||||
| * | Delete an unused variable. | Dan Gohman | 2008-09-08 | 1 | -1/+0 |
| | | | | | llvm-svn: 55915 | ||||
| * | Remove OptimizeIVType() | Devang Patel | 2008-09-08 | 1 | -206/+0 |
| | | | | | llvm-svn: 55913 | ||||
| * | Didn't mean to commit this change to how the | Duncan Sands | 2008-09-08 | 1 | -8/+4 |
| | | | | | | | callgraph is printed. llvm-svn: 55912 | ||||
| * | Avoid redefinition and nnbreak windows build. | Evan Cheng | 2008-09-08 | 1 | -16/+16 |
| | | | | | llvm-svn: 55911 | ||||
| * | Unbreak and fix indentation | Anton Korobeynikov | 2008-09-08 | 1 | -37/+33 |
| | | | | | llvm-svn: 55904 | ||||
| * | Drop unused variable | Anton Korobeynikov | 2008-09-08 | 1 | -1/+0 |
| | | | | | llvm-svn: 55901 | ||||
| * | We do support EH on x86-64! | Anton Korobeynikov | 2008-09-08 | 1 | -2/+1 |
| | | | | | llvm-svn: 55900 | ||||
| * | First draft of EH support on x86/64-linux | Anton Korobeynikov | 2008-09-08 | 3 | -32/+60 |
| | | | | | llvm-svn: 55899 | ||||
| * | Implement FRAME_TO_ARGS_OFFSET for x86-64 | Anton Korobeynikov | 2008-09-08 | 1 | -11/+7 |
| | | | | | llvm-svn: 55898 | ||||
| * | Update the callgraph correctly. | Duncan Sands | 2008-09-08 | 1 | -1/+4 |
| | | | | | llvm-svn: 55896 | ||||
| * | Update the callgraph correctly in ArgumentPromotion. | Duncan Sands | 2008-09-08 | 1 | -0/+7 |
| | | | | | llvm-svn: 55895 | ||||
| * | Reapply 55859. This doesn't change anything as | Duncan Sands | 2008-09-08 | 3 | -27/+19 |
| | | | | | | | | long as the callgraph is correct. It checks for wrong callgraphs more strictly. llvm-svn: 55894 | ||||
| * | Add fast isel physical register definition support. | Evan Cheng | 2008-09-08 | 1 | -7/+64 |
| | | | | | llvm-svn: 55892 | ||||
| * | Add support to extend call operands when needed. Enable x86 fastisel call ↵ | Evan Cheng | 2008-09-08 | 1 | -24/+33 |
| | | | | | | | support. llvm-svn: 55891 | ||||
| * | Revert my previous change -- the subtraction of two constants was a no-op | Bill Wendling | 2008-09-08 | 1 | -1/+1 |
| | | | | | | | | | | before. This is taken care of in the selection DAG pass. In my opinion, this should be in one place or the other. I.e., it should probably be removed from the DAG combiner (along with the other arithmetic transformations on constants that are essentially no-ops). llvm-svn: 55889 | ||||
| * | Convert | Bill Wendling | 2008-09-07 | 1 | -1/+1 |
| | | | | | | | | | // fold (sub c1, c2) -> c1-c2 from a no-op into an actual transformation. llvm-svn: 55886 | ||||
| * | Correct a comment and strip trailing whitespace. | Duncan Sands | 2008-09-07 | 1 | -25/+25 |
| | | | | | llvm-svn: 55883 | ||||
| * | Initial fastisel call support for C, Fast, and X86_FastCall calling ↵ | Evan Cheng | 2008-09-07 | 1 | -42/+308 |
| | | | | | | | | | conventions. It's meant to handle "simple" calls, i.e. no byval, structret, etc. It doesn't support multi-result returns either. Not yet turned on, it needs to support sext / zext of arguments and result. llvm-svn: 55882 | ||||
| * | Some code clean up. | Evan Cheng | 2008-09-07 | 1 | -26/+21 |
| | | | | | llvm-svn: 55881 | ||||
| * | Indentation. | Evan Cheng | 2008-09-07 | 1 | -2/+2 |
| | | | | | llvm-svn: 55880 | ||||
| * | - Doh. Pass vector by value is bad. | Evan Cheng | 2008-09-07 | 1 | -1/+11 |
| | | | | | | | - Add a AnalyzeCallResult specialized for calls which produce a single value. This is used by fastisel. llvm-svn: 55879 | ||||
| * | Handle x86 truncate to i8 with target hook for now. | Evan Cheng | 2008-09-07 | 1 | -0/+38 |
| | | | | | llvm-svn: 55877 | ||||
| * | fix crash when the malloc/free function is defined or is a declaration with ↵ | Nuno Lopes | 2008-09-06 | 1 | -4/+2 |
| | | | | | | | | | 0 parameters. this pass doesnt seem to be used, but still it's now a little more correct llvm-svn: 55873 | ||||
| * | When PruneEH turned an invoke into an ordinary | Duncan Sands | 2008-09-06 | 2 | -1/+20 |
| | | | | | | | | | | | | | call (thus changing the call site) it didn't inform the callgraph about this. But the call site does matter - as shown by the testcase, the callgraph become invalid after the inliner ran (with an edge between two functions simply missing), resulting in wrong deductions by GlobalsModRef. llvm-svn: 55872 | ||||
| * | Fix constant pool loads, and remove broken versions of addConstantPoolReference. | Owen Anderson | 2008-09-06 | 5 | -45/+10 |
| | | | | | llvm-svn: 55868 | ||||
| * | Fix the X86 addConstantPoolReference, which had the operands in the wrong order. | Owen Anderson | 2008-09-06 | 1 | -1/+2 |
| | | | | | llvm-svn: 55867 | ||||
| * | Next limited float precision expansion (log2 12 bits) | Dale Johannesen | 2008-09-05 | 1 | -3/+43 |
| | | | | | llvm-svn: 55866 | ||||
| * | Revert r55859. This is breaking the build in the abscence of its companion ↵ | Owen Anderson | 2008-09-05 | 4 | -15/+35 |
| | | | | | | | commit. llvm-svn: 55865 | ||||
| * | Fix for PR2687: Add patterns to match sint_to_fp and fp_to_sint for <2 x | Eli Friedman | 2008-09-05 | 1 | -0/+4 |
| | | | | | | | | | | i32>. This is a little messy, but it works. We should really get rid of the intrinsics, though, since they map perfectly well to standard LLVM instructions. llvm-svn: 55864 | ||||
| * | Move the code that inserts copies for function livein registers | Dan Gohman | 2008-09-05 | 2 | -109/+113 |
| | | | | | | | | | | out of ScheduleDAGEmit.cpp and into SelectionDAGISel.cpp. This allows it to be run exactly once per function, even if multiple SelectionDAG iterations happen in the entry block, as may happen with FastISel. llvm-svn: 55863 | ||||
| * | Remove unused map. | Devang Patel | 2008-09-05 | 1 | -1/+0 |
| | | | | | llvm-svn: 55861 | ||||
| * | Delete the removeCallEdgeTo callgraph method, | Duncan Sands | 2008-09-05 | 3 | -23/+11 |
| | | | | | | | | | | | | | | | | because it does not maintain a correct list of callsites. I discovered (see following commit) that the inliner will create a wrong callgraph if it is fed a callgraph with correct edges but incorrect callsites. These were created by Prune-EH, and while it wasn't done via removeCallEdgeTo, it could have been done via removeCallEdgeTo, which is an accident waiting to happen. Use removeCallEdgeFor instead. llvm-svn: 55859 | ||||
| * | Fix X86FastISel's shift and select code to reject illegal types. | Dan Gohman | 2008-09-05 | 1 | -1/+9 |
| | | | | | llvm-svn: 55857 | ||||
| * | Add the next limited-precision expansion. | Dale Johannesen | 2008-09-05 | 1 | -3/+42 |
| | | | | | llvm-svn: 55856 | ||||
| * | Fix the opcodes used by X86FastISel for shifts and conditional moves. | Dan Gohman | 2008-09-05 | 1 | -11/+11 |
| | | | | | llvm-svn: 55855 | ||||
| * | Factor out code that emits load and store instructions. | Evan Cheng | 2008-09-05 | 1 | -111/+138 |
| | | | | | llvm-svn: 55854 | ||||
| * | Rename method. | Owen Anderson | 2008-09-05 | 1 | -3/+3 |
| | | | | | llvm-svn: 55853 | ||||
| * | FastISel support for AND and OR with type i1. | Dan Gohman | 2008-09-05 | 1 | -2/+10 |
| | | | | | llvm-svn: 55846 | ||||
| * | Add hooks for other intrinsics to get low-precision expansions. | Dale Johannesen | 2008-09-05 | 2 | -12/+60 |
| | | | | | llvm-svn: 55845 | ||||
| * | X86FastISel support for shifts and conditional moves. | Dan Gohman | 2008-09-05 | 1 | -0/+99 |
| | | | | | llvm-svn: 55844 | ||||
| * | FastISel support for ConstantExprs. | Dan Gohman | 2008-09-05 | 1 | -5/+17 |
| | | | | | llvm-svn: 55843 | ||||
| * | Revert r55817. It broke PIC. FastISel will need to find a different | Dan Gohman | 2008-09-05 | 1 | -3/+1 |
| | | | | | | | approach here. llvm-svn: 55842 | ||||
| * | If SSE2 is available, x86 should pass first 3 f32/f64 arguments in XMM ↵ | Evan Cheng | 2008-09-05 | 1 | -0/+6 |
| | | | | | | | registers for fastcc calls. llvm-svn: 55840 | ||||
| * | Add a variant of AnalyzeCallOperands that can be used by fast isel. | Evan Cheng | 2008-09-05 | 1 | -0/+17 |
| | | | | | llvm-svn: 55838 | ||||
| * | Use removeAllCalledFunctions rather than removing | Duncan Sands | 2008-09-05 | 1 | -5/+3 |
| | | | | | | | edges one by one by hand. llvm-svn: 55836 | ||||
| * | Remove trailing whitespace. | Duncan Sands | 2008-09-05 | 1 | -36/+36 |
| | | | | | llvm-svn: 55835 | ||||
| * | Make this pass return that it made a change if | Duncan Sands | 2008-09-05 | 1 | -1/+5 |
| | | | | | | | it modifies a functions attributes. llvm-svn: 55831 | ||||
| * | "Fix" PR2762. The testcase now crashes codegen | Duncan Sands | 2008-09-05 | 1 | -1/+19 |
| | | | | | | | | elsewhere due to a missing pattern for v2f64 = sint_to_fp v2i32. That is PR2687. llvm-svn: 55828 | ||||
| * | Fix a search+replace-o. | Dan Gohman | 2008-09-05 | 1 | -1/+1 |
| | | | | | llvm-svn: 55824 | ||||

