| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Add intrinsics for log, log2, log10, exp, exp2. | Dale Johannesen | 2008-09-04 | 4 | -0/+328 |
| * | Do trivial local CSE for constants and other non-Instruction values | Dan Gohman | 2008-09-03 | 1 | -12/+15 |
| * | Put RegsForValue in the llvm namespace to avoid warnings about | Dan Gohman | 2008-09-03 | 1 | -1/+1 |
| * | Create HandlePHINodesInSuccessorBlocksFast, a version of | Dan Gohman | 2008-09-03 | 3 | -187/+226 |
| * | Do not emit a UsedDirective for things in the llvm.used | Dale Johannesen | 2008-09-03 | 1 | -3/+32 |
| * | Oops, I accidentally broke the fallback case with my last commit. | Owen Anderson | 2008-09-03 | 1 | -0/+2 |
| * | Fix an issue where we were reusing materializations of constants in blocks no... | Owen Anderson | 2008-09-03 | 1 | -9/+15 |
| * | Split the SelectionDAG-building code, including the FunctionLoweringInfo | Dan Gohman | 2008-09-03 | 3 | -5134/+5303 |
| * | Separate MachineInstr-emitting routines from actual scheduling | Dan Gohman | 2008-09-03 | 2 | -751/+772 |
| * | Fix addRegisterDead and addRegisterKilled to be more thorough | Dan Gohman | 2008-09-03 | 1 | -19/+34 |
| * | If TargetSelectInstruction returns true, move to next instruction. | Evan Cheng | 2008-09-03 | 1 | -1/+3 |
| * | 80 col violations. | Evan Cheng | 2008-09-02 | 1 | -2/+4 |
| * | Ensure that HandlePHINodesInSuccessorBlocks is run for all blocks, | Dan Gohman | 2008-09-02 | 1 | -3/+9 |
| * | Provide two overloads of AnalyzeNewNode. | Gabor Greif | 2008-09-01 | 2 | -17/+24 |
| * | Even though no caller actually uses the new value | Duncan Sands | 2008-09-01 | 1 | -1/+2 |
| * | Cosmetic changes to Machine LICM. No functionality change. | Bill Wendling | 2008-08-31 | 1 | -31/+36 |
| * | Another situation where ROTR is cheaper than ROTL. | Bill Wendling | 2008-08-31 | 1 | -3/+3 |
| * | For this pattern, ROTR is the cheaper option. | Bill Wendling | 2008-08-31 | 1 | -4/+4 |
| * | - Fix comment so that it describes how the code really works: | Bill Wendling | 2008-08-31 | 1 | -6/+6 |
| * | typo | Gabor Greif | 2008-08-30 | 1 | -1/+1 |
| * | fix some 80-col violations | Gabor Greif | 2008-08-30 | 1 | -19/+23 |
| * | Re-apply 55467 with fix. If copy is being replaced by remat'ed def, transfer ... | Evan Cheng | 2008-08-30 | 2 | -4/+83 |
| * | Fold isRematerializable checks into isSafeToReMat. | Evan Cheng | 2008-08-30 | 1 | -1/+3 |
| * | Transform (x << (y&31)) -> (x << y). This takes advantage of the fact x86 shi... | Evan Cheng | 2008-08-30 | 1 | -0/+60 |
| * | Fix an issue where a use might be selected before a def, and then we didn't r... | Owen Anderson | 2008-08-30 | 1 | -8/+23 |
| * | Fix 80 col. violations. | Evan Cheng | 2008-08-29 | 1 | -2/+4 |
| * | Back out 55498. It broken Apple style bootstrapping. | Evan Cheng | 2008-08-29 | 1 | -106/+81 |
| * | Add a target callback for FastISel. | Dan Gohman | 2008-08-28 | 1 | -2/+7 |
| * | erect abstraction boundaries for accessing SDValue members, rename Val -> Nod... | Gabor Greif | 2008-08-28 | 14 | -696/+704 |
| * | Implement null and undef values for FastISel. | Dan Gohman | 2008-08-28 | 1 | -0/+5 |
| * | Optimize DAGCombiner's worklist processing. Previously it started | Dan Gohman | 2008-08-28 | 1 | -77/+102 |
| * | Move CaseBlock, JumpTable, and BitTestBlock to be members of | Dan Gohman | 2008-08-28 | 1 | -80/+77 |
| * | Fix a FastISel bug where the instructions from lowering the arguments | Dan Gohman | 2008-08-28 | 1 | -12/+16 |
| * | Reduce the size of the Parts vector. | Rafael Espindola | 2008-08-28 | 1 | -3/+4 |
| * | Hook up support for fast-isel of trunc instructions, using the newly working ... | Owen Anderson | 2008-08-28 | 1 | -1/+4 |
| * | FastEmitInst_extractsubreg doesn't need to be passed the register class. It ... | Owen Anderson | 2008-08-28 | 1 | -2/+2 |
| * | Revert r55467; it causes regressions in UnitTests/Vector/divides, | Dan Gohman | 2008-08-28 | 2 | -68/+4 |
| * | Correctly resize the Parts array. | Rafael Espindola | 2008-08-28 | 1 | -1/+1 |
| * | If a copy isn't coalesced, but its src is defined by trivial computation. Re-... | Evan Cheng | 2008-08-28 | 2 | -4/+68 |
| * | Split the ATOMIC NodeType's to include the size, e.g. | Dale Johannesen | 2008-08-28 | 3 | -75/+424 |
| * | Reorganize the lifetimes of the major objects SelectionDAGISel | Dan Gohman | 2008-08-27 | 2 | -232/+345 |
| * | Add a helper method that will be used to support EXTRACT_SUBREG for selecting... | Owen Anderson | 2008-08-27 | 1 | -0/+11 |
| * | Move the check whether it's worth remating to caller. | Evan Cheng | 2008-08-27 | 2 | -3/+2 |
| * | Fix FastISel's bitcast code for the case where getRegForValue fails. | Dan Gohman | 2008-08-27 | 1 | -1/+4 |
| * | Refactor isSafeToReMat out of 2addr pass. | Evan Cheng | 2008-08-27 | 2 | -29/+26 |
| * | Use TargetLowering to get the types in fast isel, which handles pointer types... | Owen Anderson | 2008-08-27 | 1 | -4/+4 |
| * | Don't check TLI.getOperationAction. The FastISel way is to | Dan Gohman | 2008-08-27 | 1 | -6/+2 |
| * | Add a new FastISel method, getRegForValue, which takes care of | Dan Gohman | 2008-08-27 | 1 | -133/+95 |
| * | Add a comment about the current floating-point constant code in FastISel. | Dan Gohman | 2008-08-27 | 1 | -0/+6 |
| * | Optimize ScheduleDAGRRList's topological sort to use one pass instead | Dan Gohman | 2008-08-27 | 1 | -19/+8 |
