Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / llvm / d0eeeeb5580622d8700fd1009bbf2465789303a8 / lib / Target / X86 / X86InstrInfo.cpp
  1. d0eeeeb Remove the x86 MOV{32,64}{rr,rm,mr}_TC instructions. by Jakob Stoklund Olesen · 14 years ago
  2. 15df55d reapply: Use the new TB_NOT_REVERSABLE flag instead of special by Chris Lattner · 14 years ago
  3. 99ae665 reapply the patch reverted in r116033: by Chris Lattner · 14 years ago
  4. b88b00b Revert "Reimplement (part of) the or -> add optimization. Matching 'or' into by Daniel Dunbar · 14 years ago
  5. b38109f Revert "Use the new TB_NOT_REVERSABLE flag instead of special ", which depends by Daniel Dunbar · 14 years ago
  6. 32f0cdb Revert "reimplement the second half of the or/add optimization. We should now", by Daniel Dunbar · 14 years ago
  7. cd3167b reimplement the second half of the or/add optimization. We should now by Chris Lattner · 14 years ago
  8. 05e27c5 Use the new TB_NOT_REVERSABLE flag instead of special by Chris Lattner · 14 years ago
  9. a228376 simplify some map operations. by Chris Lattner · 14 years ago
  10. 122e2ea Reimplement (part of) the or -> add optimization. Matching 'or' into 'add' by Chris Lattner · 14 years ago
  11. 45a1cb2 Reduce casting in various tables by defining the table with the right types. by Chris Lattner · 14 years ago
  12. afcd543 simplify code: don't build up vector only to assert it is empty. by Chris Lattner · 14 years ago
  13. 635127a Constrain the offset register to a *_NOSP register class when inserting LEA by Jakob Stoklund Olesen · 14 years ago
  14. 25cbf50 Use #NAME# to have the CMOV multiclass define things with the same names as before by Chris Lattner · 14 years ago
  15. d350e47 switch CMOVBE to the multipattern: 21 insertions(+), 53 deletions(-) by Chris Lattner · 14 years ago
  16. b2ef4c1 add basic avx support to the disassembler, also teach it about ssmem/sdmem by Chris Lattner · 14 years ago
  17. bf6018a add asmparser support for cvttpd2dq by removing some Int_ prefixes. by Chris Lattner · 14 years ago
  18. 0c04e4f implement rdar://8456382 - cvtsd2si support, by removing some Int_ prefixes. by Chris Lattner · 14 years ago
  19. bc57c6d fix rdar://8456412 - llvm-mc crash in encoder on "mov %rdx, %cr8" by Chris Lattner · 14 years ago
  20. d8c0a51 Avoid emitting a PIC base register if no PIC addresses are needed. by Dan Gohman · 14 years ago
  21. c52bedb Properly handle passing of FP stuff to varargs function on Win64: by Anton Korobeynikov · 14 years ago
  22. 5dad73c Revert part of one of the prev. patches - tailjmp will follow later. by Anton Korobeynikov · 14 years ago
  23. e9df15e Enable more win64 calls folding opportunities. Patch by Cameron Esfahani! by Anton Korobeynikov · 14 years ago
  24. 642eb02 - Teach SSEDomainFix to switch between different levels of AVX instructions. Here we guess that AVX will have domain issues, so just implement them for consistency and in the future we remove if it's unnecessary. by Bruno Cardoso Lopes · 14 years ago
  25. 4d04362 Fix comment order by Bruno Cardoso Lopes · 14 years ago
  26. d29583b Fix <rdar://problem/8282498> even if it doesn't reproduce on trunk. by Jakob Stoklund Olesen · 14 years ago
  27. 90c579d Reapply r110396, with fixes to appease the Linux buildbot gods. by Owen Anderson · 14 years ago
  28. 1f74590 Revert r110396 to fix buildbots. by Owen Anderson · 14 years ago
  29. 9ccaf53 Don't use PassInfo* as a type identifier for passes. Instead, use the address of the static by Owen Anderson · 14 years ago
  30. b2eeed7 Revert r109652, and remove the offending assert in loadRegFromStackSlot instead. by Jakob Stoklund Olesen · 14 years ago
  31. 81c7b19 The isLoadFromStackSlot and isStoreToStackSlot have no way of reporting by Jakob Stoklund Olesen · 14 years ago
  32. 516cd45 Add assertions that expose the PR7713 miscompilation: Accessing a stack slot by Jakob Stoklund Olesen · 14 years ago
  33. 134d8ee remove the JIT "NeedsExactSize" feature and supporting logic. by Chris Lattner · 14 years ago
  34. 456fdaf instead of migrating it to the MC instruction encoder, just by Chris Lattner · 14 years ago
  35. fcbd1a7 Fixes win64. It was broken by a previous patch where I missed the !isWin64 by Rafael Espindola · 14 years ago
  36. c8ea673 Fix a couple issues with Win64 ABI by Nate Begeman · 14 years ago
  37. 78e6e00 Remove the isMoveInstr() hook. by Jakob Stoklund Olesen · 14 years ago
  38. 7431bea Rename DBG_LABEL PROLOG_LABEL, because it's only used during prolog emission and by Bill Wendling · 14 years ago
  39. 468a2a4 Remove the X86::FP_REG_KILL pseudo-instruction and the X86FloatingPointRegKill by Jakob Stoklund Olesen · 14 years ago
  40. ed42f1e Check begin!=end, rather than !begin. by Dan Gohman · 14 years ago
  41. 5a717a3 Convert getLoadStoreRegOpcode to use a switch. by Rafael Espindola · 14 years ago
  42. 0bfd092 Convert the last getPhysicalRegisterRegClass in VirtRegRewriter.cpp to by Rafael Espindola · 14 years ago
  43. 4ea8771 X86InstrInfo::copyRegToReg is dead. Long live copyPhysReg! by Jakob Stoklund Olesen · 14 years ago
  44. 2b336bc Don't emit st(0)/st(1) copies as FpMOV instructions. Use FpSET_ST? instead. by Jakob Stoklund Olesen · 14 years ago
  45. 84023e0 Reapply bottom-up fast-isel, with several fixes for x86-32: by Dan Gohman · 14 years ago
  46. 61905c8 Remember the *_TC opcodes for load/store by Jakob Stoklund Olesen · 14 years ago
  47. 1f32340 Automatically fold COPY instructions into stack load/store. by Jakob Stoklund Olesen · 14 years ago
  48. 9c50e8b Fix a few tests by Jakob Stoklund Olesen · 14 years ago
  49. e86b01c Start the support for AVX instructions with 256-bit %ymm registers. A couple of by Bruno Cardoso Lopes · 14 years ago
  50. 599b531 Change LEA to have 5 operands for its memory operand, just by Chris Lattner · 14 years ago
  51. ac0ed5d add some long-overdue enums to refer to the parts of the 5-operand by Chris Lattner · 14 years ago
  52. 61c8ecc Remember the VR64 register class by Jakob Stoklund Olesen · 14 years ago
  53. 320bdcb Implement X86InstrInfo::copyPhysReg by Jakob Stoklund Olesen · 14 years ago
  54. 0bc25f4 Convert EXTRACT_SUBREG to COPY when emitting machine instrs. by Jakob Stoklund Olesen · 14 years ago
  55. 5c00e07 Remove references to INSERT_SUBREG after de-SSA. by Jakob Stoklund Olesen · 14 years ago
  56. 5febd07 fix copies to/from GR8_ABCD_H even more by Jakob Stoklund Olesen · 14 years ago
  57. f2e4afd Allow copies between GR8_ABCD_L and GR8_ABCD_H. by Jakob Stoklund Olesen · 14 years ago
  58. 98ec91e - Two-address pass should not assume unfolding is always successful. by Evan Cheng · 14 years ago
  59. 19d8597 Fix the formatting of the switch statement and add a missing break. by Bill Wendling · 14 years ago
  60. c2b3e00 Fix an unintentional commit. I think I typed "git svn dcommit" in the wrong branch. by Rafael Espindola · 14 years ago
  61. f0efafa wip by Rafael Espindola · 14 years ago
  62. 3bf9125 Add a DebugLoc parameter to TargetInstrInfo::InsertBranch(). This by Stuart Hastings · 14 years ago
  63. 21d238f Merge getStoreRegOpcode and getLoadRegOpcode. by Rafael Espindola · 14 years ago
  64. 9edf7de Slightly change the meaning of the reMaterialize target hook when the original by Jakob Stoklund Olesen · 14 years ago
  65. 42d075c Remove the TargetRegisterClass member from CalleeSavedInfo by Rafael Espindola · 14 years ago
  66. 22c0e97 Use enums instead of literals for X86 subregisters. by Jakob Stoklund Olesen · 14 years ago
  67. 3458e9e Rename X86 subregister indices to something shorter. by Jakob Stoklund Olesen · 14 years ago
  68. 73ea7bf Add the SubRegIndex TableGen class. by Jakob Stoklund Olesen · 14 years ago
  69. 2457f2c Implement @llvm.returnaddress. rdar://8015977. by Evan Cheng · 15 years ago
  70. e5e4ff9 Fix assembly parsing and encoding of the pushf and popf family of instructions. by Dan Gohman · 15 years ago
  71. f8c1ef0 Teach mode load folding and unfolding code about CMP32ri8 and friends. by Dan Gohman · 15 years ago
  72. e5efbaf When converting a test to a cmp to fold a load, use the cmp that has an by Dan Gohman · 15 years ago
  73. 0d88104 When rematerializing, use the debug location of the original by Dan Gohman · 15 years ago
  74. 34dcc6f Add a DebugLoc argument to TargetInstrInfo::copyRegToReg, so that it by Dan Gohman · 15 years ago
  75. 746ad69 Add argument TargetRegisterInfo to loadRegFromStackSlot and storeRegToStackSlot. by Evan Cheng · 15 years ago
  76. 8601a3d Frame index can be negative. by Evan Cheng · 15 years ago
  77. ee9eb41 on darwin empty functions need to codegen into something of non-zero length, by Chris Lattner · 15 years ago
  78. fc4d530 Remove a redundant comment. by Evan Cheng · 15 years ago
  79. 962021b - Move TargetLowering::EmitTargetCodeForFrameDebugValue to TargetInstrInfo and rename it to emitFrameIndexDebugValue. by Evan Cheng · 15 years ago
  80. 46510a7 Add const qualifiers to CodeGen's use of LLVM IR constructs. by Dan Gohman · 15 years ago
  81. fc5a03e Re-apply 101075 and fix it properly. Just reuse the debug info of the branch instruction being optimized. There is no need to --I which can deref off start of the BB. by Evan Cheng · 15 years ago
  82. 97e6992 Temporarily revert r101075, it's causing invalid iterator assertions by Eric Christopher · 15 years ago
  83. 2aae6ae Micro-optimization: by Bill Wendling · 15 years ago
  84. 75361b6 rename llvm::llvm_report_error -> llvm::report_fatal_error by Chris Lattner · 15 years ago
  85. 375be77 Educate GetInstrSizeInBytes implementations that by Dale Johannesen · 15 years ago
  86. fc8e1c3 Properly enable load clustering. by Jakob Stoklund Olesen · 15 years ago
  87. c7f3ace use DebugLoc default ctor instead of DebugLoc::getUnknownLoc() by Chris Lattner · 15 years ago
  88. 93d6a7e Teach AnalyzeBranch, RemoveBranch and the branch by Dale Johannesen · 15 years ago
  89. d363b4e Replace V_SET0 with variants for each SSE execution domain. by Jakob Stoklund Olesen · 15 years ago
  90. 357be7f Renumber SSE execution domains for better code size. by Jakob Stoklund Olesen · 15 years ago
  91. 8258d0b Remove the pmulld intrinsic and autoupdate it as a vector multiply. by Eric Christopher · 15 years ago
  92. e4b94b4 Basic implementation of SSEDomainFix pass. by Jakob Stoklund Olesen · 15 years ago
  93. 352aa50 Add a late SSEDomainFix pass that twiddles SSE instructions to avoid domain crossings. by Jakob Stoklund Olesen · 15 years ago
  94. fe4b92b Revert "Add a late SSEDomainFix pass that twiddles SSE instructions to avoid domain crossings." by Jakob Stoklund Olesen · 15 years ago
  95. c75c5fa Add a late SSEDomainFix pass that twiddles SSE instructions to avoid domain crossings. by Jakob Stoklund Olesen · 15 years ago
  96. 8d1f0dd Teach isSafeToClobberEFLAGS to ignore dbg_value's. We need a MachineBasicBlock::iterator that does this automatically? by Evan Cheng · 15 years ago
  97. f48ef03 Do not force indirect tailcall through fixed registers: eax, r11. Add support to allow loads to be folded to tail call instructions. by Evan Cheng · 15 years ago
  98. 81d0c36 Don't try to fold V_SET0 and V_SETALLONES to loads in medium and by Dan Gohman · 15 years ago
  99. 18ce64e Revert r97766. It's deleting a tag. by Bill Wendling · 15 years ago
  100. 37b52ee Micro-optimization: by Bill Wendling · 15 years ago