| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Undo r50574. We are already ensuring the folded load address is 16-byte aligned. | Evan Cheng | 2008-05-02 | 1 | -0/+8 |
| * | Not safe folding a load + FsXORPSrr into FsXORPSrm. It's loading a FR64 value... | Evan Cheng | 2008-05-02 | 1 | -8/+0 |
| * | Don't forget to update the current operand when getting the size of an instru... | Nicolas Geoffray | 2008-04-20 | 1 | -4/+14 |
| * | Don't forget about sub-register indices when rematting instructions. | Evan Cheng | 2008-04-16 | 1 | -0/+13 |
| * | Infrastructure for getting the machine code size of a function and an instruc... | Nicolas Geoffray | 2008-04-16 | 1 | -0/+540 |
| * | Rename MemOperand to MachineMemOperand. This was suggested by | Dan Gohman | 2008-04-07 | 1 | -1/+1 |
| * | ReMat of load from stub in pic mode extends the life of pic base. Currently s... | Evan Cheng | 2008-04-01 | 1 | -0/+6 |
| * | Remove unnecessary and non-deterministic checking code. Re-enable remat of lo... | Evan Cheng | 2008-04-01 | 1 | -11/+0 |
| * | Disabling remat of load from gv stub (temporarily) again to fix llvmgcc boots... | Evan Cheng | 2008-04-01 | 1 | -0/+3 |
| * | It's not safe to fold a load from GV stub or constantpool into a two-address ... | Evan Cheng | 2008-03-31 | 1 | -0/+8 |
| * | Move reMaterialize() from TargetRegisterInfo to TargetInstrInfo. | Evan Cheng | 2008-03-31 | 1 | -0/+28 |
| * | Re-apply 48911. | Evan Cheng | 2008-03-31 | 1 | -8/+12 |
| * | Backing out 48911 for now. It's breaking stuff. | Evan Cheng | 2008-03-28 | 1 | -12/+8 |
| * | Load from stub is already re-materializable. | Evan Cheng | 2008-03-28 | 1 | -8/+12 |
| * | Code clean up. | Evan Cheng | 2008-03-27 | 1 | -14/+16 |
| * | Allow certain lea instructions to be rematerialized. | Evan Cheng | 2008-03-27 | 1 | -35/+66 |
| * | Remove an unused command line option. | Evan Cheng | 2008-03-27 | 1 | -6/+0 |
| * | Add CMP32mr and friends to the load-unfolding table. Among | Dan Gohman | 2008-03-25 | 1 | -0/+4 |
| * | Add support for calls that return two FP values in | Chris Lattner | 2008-03-21 | 1 | -5/+7 |
| * | Make insert_subreg a two-address instruction, vastly simplifying LowerSubregs... | Christopher Lamb | 2008-03-16 | 1 | -2/+4 |
| * | Get rid of a pseudo instruction and replace it with subreg based operation on... | Christopher Lamb | 2008-03-13 | 1 | -3/+3 |
| * | coalesce away 80-bit floating point copies. | Chris Lattner | 2008-03-11 | 1 | -4/+6 |
| * | convert a massive if statement to a switch. | Chris Lattner | 2008-03-11 | 1 | -19/+32 |
| * | Missed part of recommit. | Christopher Lamb | 2008-03-11 | 1 | -4/+7 |
| * | abort with an assert instead of a cerr to get line# | Chris Lattner | 2008-03-10 | 1 | -1/+1 |
| * | Revert 48125, 48126, and 48130 for now to unbreak some x86-64 tests. | Evan Cheng | 2008-03-10 | 1 | -8/+4 |
| * | Allow insert_subreg into implicit, target-specific values. | Christopher Lamb | 2008-03-10 | 1 | -4/+8 |
| * | teach X86InstrInfo::copyRegToReg how to copy into ST(0) from | Chris Lattner | 2008-03-09 | 1 | -1/+18 |
| * | add some code to support cross-register class copying from | Chris Lattner | 2008-03-09 | 1 | -4/+22 |
| * | rearrange some code, no functionality change. | Chris Lattner | 2008-03-09 | 1 | -58/+59 |
| * | Turning on remat of pic loads. | Evan Cheng | 2008-02-23 | 1 | -1/+1 |
| * | No need recognize load from a fixed argument slot as re-materializable. LiveI... | Evan Cheng | 2008-02-23 | 1 | -12/+0 |
| * | Allow re-materialization of pic load (controlled by -remat-pic-load for now). | Evan Cheng | 2008-02-22 | 1 | -3/+23 |
| * | commuteInstr() can now commute non-ssa machine instrs. | Evan Cheng | 2008-02-13 | 1 | -0/+9 |
| * | It's not always safe to fold movsd into xorpd, etc. Check the alignment of th... | Evan Cheng | 2008-02-08 | 1 | -3/+51 |
| * | Added missing entries in X86 load / store folding tables. | Evan Cheng | 2008-02-08 | 1 | -0/+8 |
| * | In some cases, e.g. ADD32ri, no transformation is made. Guide against it. | Evan Cheng | 2008-02-07 | 1 | -0/+2 |
| * | fix a wordo that gordon noticed :) | Chris Lattner | 2008-01-12 | 1 | -1/+1 |
| * | Any x86 instruction that reads from an invariant location is invariant. | Chris Lattner | 2008-01-12 | 1 | -43/+24 |
| * | rename MachineInstr::setInstrDescriptor -> setDesc | Chris Lattner | 2008-01-11 | 1 | -4/+4 |
| * | remove xchg and shift-reg-by-1 instructions, which are dead. | Chris Lattner | 2008-01-11 | 1 | -14/+2 |
| * | Simplify the side effect stuff a bit more and make licm/sinking | Chris Lattner | 2008-01-10 | 1 | -10/+13 |
| * | verify that the frame index is immutable before remat'ing (still disabled) | Chris Lattner | 2008-01-10 | 1 | -7/+10 |
| * | add a testcase | Chris Lattner | 2008-01-09 | 1 | -5/+4 |
| * | Operand 1 should be a register. We don't care if it's a preg, vreg, or 0. | Bill Wendling | 2008-01-07 | 1 | -13/+9 |
| * | rename TargetInstrDescriptor -> TargetInstrDesc. | Chris Lattner | 2008-01-07 | 1 | -13/+13 |
| * | Move a bunch more accessors from TargetInstrInfo to TargetInstrDescriptor | Chris Lattner | 2008-01-07 | 1 | -7/+7 |
| * | remove MachineOpCode typedef. | Chris Lattner | 2008-01-07 | 1 | -1/+1 |
| * | Add predicates methods to TargetOperandInfo, and switch all clients | Chris Lattner | 2008-01-07 | 1 | -4/+4 |
| * | Rename MachineInstr::getInstrDescriptor -> getDesc(), which reflects | Chris Lattner | 2008-01-07 | 1 | -12/+11 |
