summaryrefslogtreecommitdiff
path: root/lib/Target/X86/X86InstrInfo.cpp
AgeCommit message (Expand)AuthorFilesLines
2015-08-08[x86] enable machine combiner reassociations for 128-bit vector single/double...Sanjay Patel1-0/+4
2015-08-06MIR Serialization: Initial serialization of the machine operand target flags.Alex Lorenz1-0/+35
2015-08-05Revert "Fix MO's analyzePhysReg, it was confusing sub- and super-registers. P...JF Bastien1-48/+26
2015-08-05Fix MO's analyzePhysReg, it was confusing sub- and super-registers. Problem p...JF Bastien1-26/+48
2015-08-04wrap OptSize and MinSize attributes for easier and consistent access (NFCI)Sanjay Patel1-2/+3
2015-08-04[x86] machine combiner reassociation: mark EFLAGS operand as 'dead'Sanjay Patel1-4/+43
2015-07-31[x86] reassociate integer multiplies using machine combiner passSanjay Patel1-10/+30
2015-07-30push fast-math check for machine-combiner reassociations into instruction-typ...Sanjay Patel1-7/+4
2015-07-28fix invalid load folding with SSE/AVX FP logical instructions (PR22371)Sanjay Patel1-12/+3
2015-07-23[X86] Allow load folding into PUSH instructionsMichael Kuperstein1-4/+11
2015-07-19Remove TargetInstrInfo::canFoldMemoryOperandSimon Pilgrim1-56/+0
2015-07-14[MMX] Use the appropriate instructions for GR64 <-> VR64 copies.Bruno Cardoso Lopes1-2/+2
2015-07-09[x86] enable machine combiner reassociations for scalar double-precision mult...Sanjay Patel1-1/+3
2015-07-09[x86] enable machine combiner reassociations for scalar double-precision addsSanjay Patel1-0/+2
2015-07-08[x86] enable machine combiner reassociations for scalar single-precision mult...Sanjay Patel1-2/+4
2015-07-08[X86][SSE] Added (V)ROUNDSD + (V)ROUNDSS stack folding supportSimon Pilgrim1-4/+8
2015-07-07use range-based for loops; NFCISanjay Patel1-35/+17
2015-07-06[x86] extend machine combiner reassociation optimization to SSE scalar addsSanjay Patel1-13/+19
2015-06-23Revert r240137 (Fixed/added namespace ending comments using clang-tidy. NFC)Alexander Kornienko1-2/+2
2015-06-23[x86] generalize reassociation optimization in machine combiner to 2 instruct...Sanjay Patel1-77/+87
2015-06-22[X86][FMA4] FMA4 ops can perform unaligned folded loads.Simon Pilgrim1-64/+64
2015-06-22[X86] Teach load folding to accept scalar _Int users of MOVSS/MOVSD.Ahmed Bougacha1-10/+46
2015-06-19name change: hasPattern() -> getMachineCombinerPatterns() ; NFCSanjay Patel1-3/+3
2015-06-19Fixed/added namespace ending comments using clang-tidy. NFCAlexander Kornienko1-2/+2
2015-06-15[TargetInstrInfo] Add new hook: AnalyzeBranchPredicate.Sanjoy Das1-5/+85
2015-06-15[TargetInstrInfo] Rename getLdStBaseRegImmOfs and implement for x86.Sanjoy Das1-0/+30
2015-06-13MachineLICM: Use TargetSchedModel instead of just itinerariesMatthias Braun1-1/+1
2015-06-11[CodeGen] ArrayRef'ize cond/pred in various TII APIs. NFC.Ahmed Bougacha1-5/+3
2015-06-10change assert that will never fire to llvm_unreachableSanjay Patel1-1/+1
2015-06-10[x86] Add a reassociation optimization to increase ILP via the MachineCombine...Sanjay Patel1-0/+204
2015-06-08[InstrInfo] Refactor foldOperandImpl to thread through InsertPt. NFCKeno Fischer1-41/+44
2015-06-08AVX-512: Implemented 256/128bit VALIGND/Q instructions for SKX and KNLIgor Breger1-2/+2
2015-06-07[X86] Added BitScanForward/BitScanReverse memory folding + testsSimon Pilgrim1-0/+6
2015-05-19MachineInstr: Remove unused parameter.Matthias Braun1-1/+1
2015-05-13MC: Modernize MCOperand API naming. NFC.Jim Grosbach1-1/+1
2015-05-07[x86] eliminate unnecessary shuffling/moves with unary scalar math ops (PR21507)Sanjay Patel1-0/+6
2015-04-28[x86] remove RCPPS and RSQRTPS intrinsic instruction definitionsSanjay Patel1-6/+0
2015-04-17[X86, AVX] add an exedepfix entry for vmovq == vmovlps == vmovlpdSanjay Patel1-1/+1
2015-04-15[X86] add an exedepfix entry for movq == movlps == movlpdSanjay Patel1-0/+2
2015-04-03[X86] Added SSE4.2 CRC32 memory folding patterns + testsSimon Pilgrim1-0/+2
2015-04-03[X86][3DNow] Added 3DNow! memory folding patterns + testsSimon Pilgrim1-0/+28
2015-03-12Remove the need to cache the subtarget in the X86 TargetRegisterInfoEric Christopher1-1/+1
2015-02-28Convert push_back loops into append calls.Benjamin Kramer1-2/+2
2015-02-28ArrayRefize memory operand folding. NFC.Benjamin Kramer1-26/+21
2015-02-28Replace std::copy with a back inserter with vector append where feasibleBenjamin Kramer1-1/+1
2015-02-25[X86][MMX] Reapply: Add MMX instructions to foldable tablesBruno Cardoso Lopes1-0/+84
2015-02-23Revert "[X86][MMX] Add MMX instructions to foldable tables"Bruno Cardoso Lopes1-82/+0
2015-02-23[X86][MMX] Add MMX instructions to foldable tablesBruno Cardoso Lopes1-0/+82
2015-02-17rename variables again because these tables also deal with stores; NFCSanjay Patel1-31/+31
2015-02-17Add comment to explain a non-obvious setting; NFC.Sanjay Patel1-0/+6
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-18 08:55:29 +0000