aboutsummaryrefslogtreecommitdiff
path: root/lib/Target/X86/X86InstrInfo.cpp
AgeCommit message (Expand)Author
2009-03-13Fix some significant problems with constant pools that resulted in unnecessar...Evan Cheng
2009-03-04Correct this comment.Dan Gohman
2009-03-04When using MachineInstr operand indices on SDNodes, the numberDan Gohman
2009-02-22Do not consider MMX_MOVD64rr a move instructions. The source register is in G...Evan Cheng
2009-02-18Factor out the code to add a MachineOperand to a MachineInstrBuilder.Dan Gohman
2009-02-13Remove non-DebugLoc versions of BuildMI from X86.Dale Johannesen
2009-02-12Eliminate a couple of non-DebugLoc BuildMI variants.Dale Johannesen
2009-02-11Propagate DebugLoc info for spiller call-backs.Bill Wendling
2009-02-09Implement FpSET_ST1_*.Evan Cheng
2009-02-09Turns out AnalyzeBranch can modify the mbb being analyzed. This is a nastyEvan Cheng
2009-02-06Move getPointerRegClass from TargetInstrInfo to TargetRegisterInfo.Evan Cheng
2009-02-06Add TargetInstrInfo::isSafeToMoveRegisterClassDefs. It returns true if it's s...Evan Cheng
2009-02-06Get rid of one more non-DebugLoc getNode andDale Johannesen
2009-02-03Create DebugLoc information in FastISel. Several temporary methods wereBill Wendling
2009-01-20Change TargetInstrInfo::isMoveInstr to return source and destination sub-regi...Evan Cheng
2009-01-15Add load-folding table entries for BT*ri8 instructions.Dan Gohman
2009-01-09Add load-folding table entries for MOVDQA.Dan Gohman
2009-01-07Add load-folding table entries for cmovno too.Dan Gohman
2009-01-07Define instructions for cmovo and cmovno.Dan Gohman
2009-01-07X86_COND_C and X86_COND_NC are alternate mnemonics forDan Gohman
2009-01-06Revert r42653 and forward-port the code that lets INC64_32r beDan Gohman
2009-01-05Tidy up #includes, deleting a bunch of unnecessary #includes.Dan Gohman
2008-12-23Make the fuse-failed debug output human-readable.Dan Gohman
2008-12-18Fixed x86 code generation of multiple for v2i64. It was incorrect for SSE4.1.Mon P Wang
2008-12-05Reason #3 from 60595 doesn't hold true. If we can fold a PIC load from constp...Evan Cheng
2008-12-05Effectively undo 60461 in PIC mode which simply transform V_SET0 / V_SETALLON...Evan Cheng
2008-12-03Split foldMemoryOperand into public non-virtual and protected virtualDan Gohman
2008-12-03Mark x86's V_SET0 and V_SETALLONES with isSimpleLoad, and teach X86'sDan Gohman
2008-12-02Reapply r60382. This time, don't mark "ADC" nodes with "implicit EFLAGS".Bill Wendling
2008-12-01Temporarily revert r60382. It caused CodeGen/X86/i2k.ll and others to fail.Bill Wendling
2008-12-01- Have "ADD" instructions return an implicit EFLAGS.Bill Wendling
2008-11-26Generate something sensible for an [SU]ADDO op when the overflow/carry flag isBill Wendling
2008-11-26Fish kill flag annotations in PUSH instructions.Dan Gohman
2008-11-18Add more const qualifiers. This fixes build breakage from r59540.Dan Gohman
2008-10-27For now, don't split live intervals around x87 stack register barriers. FpGET...Evan Cheng
2008-10-25Generate code for TLS instructions.Nicolas Geoffray
2008-10-21Optimized FCMP_OEQ and FCMP_UNE for x86.Dan Gohman
2008-10-21When the coalescer is doing rematerializing, have it removeDan Gohman
2008-10-17Define patterns for shld and shrd that match immediateDan Gohman
2008-10-16Const-ify several TargetInstrInfo methods.Dan Gohman
2008-10-12Update size of inst correctly with segment override.Anton Korobeynikov
2008-10-04Revert r56675 - it breaks unwinding runtime everywhere.Anton Korobeynikov
2008-10-03Switch the MachineOperand accessors back to the short names likeDan Gohman
2008-09-30Move the GlobalBaseReg field out of X86ISelDAGToDAG.cppDan Gohman
2008-09-26Mark lea fi# as being really rematerializable.Dan Gohman
2008-09-26Avoid spilling EBP / RBP twice in the prologue.Evan Cheng
2008-09-23Move the code for initializing the global base reg out ofDan Gohman
2008-09-13Remove isImm(), isReg(), and friends, in favor of Dan Gohman
2008-08-29Use static_cast instead of C style cast.Evan Cheng
2008-08-29Backing out 55521. Not safe.Evan Cheng