Gitiles
Code Review Sign In
gerrit-public.fairphone.software / fp2-dev / platform / external / llvm / 96dc115ef3ee019cb91d7c112358a77536c38a53 / lib / Target / X86 / X86InstrInfo.cpp
  1. 96dc115 Add two target hooks to determine whether two loads are near and should be scheduled together. by Evan Cheng · 16 years ago
  2. 94da721 Fix a minor issue in x86 load / store folding table. movups does an unaligned load so it doesn't require 16-byte alignment. by Evan Cheng · 16 years ago
  3. 73e884b make findDebugLoc a class method by Dale Johannesen · 16 years ago
  4. 918f0f0 Move findDebugLoc somewhere more central. Fix by Dale Johannesen · 16 years ago
  5. e45ab8a For aligned load/store instructions, it's only required to know whether a by Jim Grosbach · 16 years ago
  6. 57d1d93 For now, avoid issuing extract_subreg to reuse lower 8-bit, it's not safe in 32-bit. by Evan Cheng · 16 years ago
  7. 7da9ecf Add a quick pass to optimize sign / zero extension instructions. For targets where the pre-extension values are available in the subreg of the result of the extension, replace the uses of the pre-extension value with the result + extract_subreg. by Evan Cheng · 16 years ago
  8. f1b4d26 Reapply the MOV64r0 patch, with a fix: MOV64r0 clobbers EFLAGS. by Dan Gohman · 16 years ago
  9. a5a81d7 Add TargetInstrInfo::isCoalescableInstr. It returns true if the specified by Evan Cheng · 16 years ago
  10. 05920b8 Revert 93158. It's breaking quite a few x86_64 tests. by Evan Cheng · 16 years ago
  11. 71c25b7 Re-instate MOV64r0 and MOV16r0, with adjustments to work with the by Dan Gohman · 16 years ago
  12. 5b90132 Change errs() to dbgs(). by David Greene · 16 years ago
  13. c41b638 Remove dead variable. by Bill Wendling · 16 years ago
  14. 9e32383 completely eliminate the MOV16r0 'instruction'. The only by Chris Lattner · 16 years ago
  15. b1f4981 Remove target attribute break-sse-dep. Instead, do not fold load into sse partial update instructions unless optimizing for size. by Evan Cheng · 16 years ago
  16. 400073d On recent Intel u-arch's, folding loads into some unary SSE instructions can by Evan Cheng · 16 years ago
  17. 108934c Instruction fixes, added instructions, and AsmString changes in the by Sean Callanan · 16 years ago
  18. 85de1e5 Whitespace changes, comment clarification. No functional changes. by Bill Wendling · 16 years ago
  19. dd99f3a Disable r91104 for x86. It causes partial register stall which pessimize code in 32-bit. by Evan Cheng · 16 years ago
  20. 04ab19c Add comment about potential partial register stall. by Evan Cheng · 16 years ago
  21. 656e514 Add support to 3-addressify 16-bit instructions. by Evan Cheng · 16 years ago
  22. 864e2ef Remove the target hook TargetInstrInfo::BlockHasNoFallThrough in favor of by Dan Gohman · 16 years ago
  23. adbc23c by David Greene · 16 years ago
  24. 29dbf50 by David Greene · 16 years ago
  25. 7896c9f improve portability to avoid conflicting with std::next in c++'0x. by Chris Lattner · 16 years ago
  26. 735afe1 Remove ISD::DEBUG_LOC and ISD::DBG_LABEL, which are no longer used. by Dan Gohman · 16 years ago
  27. d15ac2f Re-apply 89011. It's not to be blamed. by Evan Cheng · 16 years ago
  28. 6db07ea Revert 89011. Buildbot thinks it might be breaking stuff. by Evan Cheng · 16 years ago
  29. 574186f A few more instructions that should be marked re-materializable. by Evan Cheng · 16 years ago
  30. 600c043 - Check memoperand alignment instead of checking stack alignment. Most load / store folding instructions are not referencing spill stack slots. by Evan Cheng · 16 years ago
  31. d57cdd5 - Change TargetInstrInfo::reMaterialize to pass in TargetRegisterInfo. by Evan Cheng · 16 years ago
  32. dda3978 by David Greene · 16 years ago
  33. b87bc95 by David Greene · 16 years ago
  34. 81cf432 Fix DenseMap iterator constness. by Jeffrey Yasskin · 16 years ago
  35. 0115e16 Fix MachineLICM to use the correct virtual register class when by Dan Gohman · 16 years ago
  36. 1b1764b Make isSafeToClobberEFLAGS more aggressive. Teach it to scan backwards by Dan Gohman · 16 years ago
  37. 4e6f7a0 Remove a no-longer-necessary #include. by Dan Gohman · 16 years ago
  38. 3731bc0 Replace X86's CanRematLoadWithDispOperand by calling the target-independent by Dan Gohman · 16 years ago
  39. 91e69c3 Add basic infrastructure and x86 support for preserving MachineMemOperand by Dan Gohman · 16 years ago
  40. e33f44c Replace TargetInstrInfo::isInvariantLoad and its target-specific by Dan Gohman · 16 years ago
  41. 26207e5 Introduce the TargetInstrInfo::KILL machine instruction and get rid of the by Jakob Stoklund Olesen · 16 years ago
  42. c76909a Improve MachineMemOperand handling. by Dan Gohman · 16 years ago
  43. 602b0c8 Rename getTargetNode to getMachineNode, for consistency with the by Dan Gohman · 16 years ago
  44. 00133a7 Fix X86's unfoldMemoryOperand to properly handle MachineMemOperands. by Dan Gohman · 16 years ago
  45. 4a0b3e1 Add support for rematerializing FsFLD0SS and FsFLD0SD as constant-pool by Dan Gohman · 16 years ago
  46. 879caea Follow up to 81494. When the folded reload is narrowed to a 32-bit load then change the destination register to a 32-bit one or add a sub-register index. by Evan Cheng · 16 years ago
  47. 9cef48e It's not legal to fold a load from a narrower stack slot into a wider instruction. If done, the instruction does a 64-bit load and that's not by Evan Cheng · 16 years ago
  48. 31e2c7b Remove Offset from ExternalSybmol MachineOperands, this is unused (and at least partly unsupported, in X86 encoding at least). by Daniel Dunbar · 16 years ago
  49. 6f9bb6f Short-term workaround for frame-related weirdness on win64. by Anton Korobeynikov · 16 years ago
  50. 705e07f remove various std::ostream version of printing methods from by Chris Lattner · 16 years ago
  51. af76e59 Rename TargetAsmInfo (and its subclasses) to MCAsmInfo. by Chris Lattner · 16 years ago
  52. 24f20e0 Record variable debug info at ISel time directly. by Devang Patel · 16 years ago
  53. 1d0be15 Push LLVMContexts through the IntegerType APIs. by Owen Anderson · 16 years ago
  54. 825b72b Split EVT into MVT and EVT, the former representing _just_ a primitive type, while by Owen Anderson · 16 years ago
  55. 3108222 Simplify this code. The case where one class is GR64RegClass and the by Dan Gohman · 16 years ago
  56. e50ed30 Rename MVT to EVT, in preparation for splitting SimpleValueType out into its own struct type. by Owen Anderson · 16 years ago
  57. b4dc13c Add crc32 instruction and intrinsics. Add a new class of prefix by Eric Christopher · 16 years ago
  58. 59e3492 Use GR32 for copies between GR32_NOSP and GR32_NOREX, as neither by Dan Gohman · 16 years ago
  59. be0cf7d hasSuperClass tests for a strict superset relation, rather than by Dan Gohman · 16 years ago
  60. d90183d Move the getInlineAsmLength virtual method from TAI to TII, where by Chris Lattner · 16 years ago
  61. a7235ea Move a few more APIs back to 2.5 forms. The only remaining ones left to change back are by Owen Anderson · 16 years ago
  62. a4714e0 Add a new register class to describe operands that can't be SP, by Dan Gohman · 16 years ago
  63. cb778a8 1. Introduce a new TargetOperandInfo::getRegClass() helper method by Chris Lattner · 16 years ago
  64. e922c02 Get rid of the Pass+Context magic. by Owen Anderson · 16 years ago
  65. 93e55de Silence warning in Linux builds: by Jakob Stoklund Olesen · 16 years ago
  66. 2b48ab9 With recent MC changes, RIP base register is explicitly modeled. Make sure we add it when x86 V_SET0 / V_SETALLONES (by transforming it into a constpool load) into the use instruction. by Evan Cheng · 16 years ago
  67. 3784453 Let callers decide the sub-register index on the def operand of rematerialized instructions. by Evan Cheng · 16 years ago
  68. f9b36f0 Move load / store folding alignment require into the table(s). by Evan Cheng · 16 years ago
  69. 9ac7542 reapply r75408, which eliminates MOV64r0 in favor of using by Chris Lattner · 16 years ago
  70. c23197a llvm_unreachable->llvm_unreachable(0), LLVM_UNREACHABLE->llvm_unreachable. by Torok Edwin · 16 years ago
  71. 73c6b71 Move more functionality over to LLVMContext. by Owen Anderson · 16 years ago
  72. 0a5372e Begin the painful process of tearing apart the rat'ss nest that is Constants.cpp and ConstantFold.cpp. by Owen Anderson · 16 years ago
  73. 69600ca Temporarily revert r75408. It appears to break the Apple-style builds: by Bill Wendling · 16 years ago
  74. a6d16ae eliminate MOV64r0 in favor of a Pat<> pattern. This is only nontrivial because by Chris Lattner · 16 years ago
  75. c25e758 assert(0) -> LLVM_UNREACHABLE. by Torok Edwin · 16 years ago
  76. 19a2011 Undo my brain cramp. by Evan Cheng · 16 years ago
  77. 84853a1 some minor simplifications. by Chris Lattner · 16 years ago
  78. 49ddb61 CMOVxx doesn't swap operands which it's commuted. by Evan Cheng · 16 years ago
  79. 3b6b36d change isGlobalStubReference to take target flags instead of a MachineOperand. by Chris Lattner · 16 years ago
  80. 0740634 convert some late code (called by regalloc and code emission) by Chris Lattner · 16 years ago
  81. ed0dca6 GVRequiresExtraLoad is now never used for calls, simplify it based on this. by Chris Lattner · 16 years ago
  82. 910139f Targets sometimes assign fixed stack object to spill certain callee-saved by Evan Cheng · 16 years ago
  83. 15a380a simplify some code based on the fact that picstyles != none are only valid by Chris Lattner · 16 years ago
  84. ab7c09b Start converting to new error handling API. by Torok Edwin · 16 years ago
  85. 4784f1f Add a bit IsUndef to MachineOperand. This indicates the def / use register operand is defined by an implicit_def. That means it can def / use any register and passes (e.g. register scavenger) can feel free to ignore them. by Evan Cheng · 16 years ago
  86. 74d3f50 factor some logic out into a helper function, allow remat of loads from constant by Chris Lattner · 16 years ago
  87. 18c5987 Reimplement rip-relative addressing in the X86-64 backend. The new by Chris Lattner · 16 years ago
  88. ac5e887 Use target-specific machine operand flags to eliminate a gross hack by Chris Lattner · 16 years ago
  89. b1fb84d just eliminate the code entirely! by Chris Lattner · 16 years ago
  90. bccf4b3 PR3739, part 2: Use an explicit store to spill XMM registers. (Previously, by Eli Friedman · 16 years ago
  91. 2265ba0 The MONITOR and MWAIT instructions have insufficient information for by Bill Wendling · 16 years ago
  92. 587daed Change MachineInstrBuilder::addReg() to take a flag instead of a list of by Bill Wendling · 16 years ago
  93. 6ed3491 Avoid unneeded SIB byte encoding. Patch by Zoltan Varga. by Evan Cheng · 16 years ago
  94. 45e0010 Optimize code placement in loop to eliminate unconditional branches or move unconditional branch to the outside of the loop. e.g. by Evan Cheng · 16 years ago
  95. ef18401 Revert part of 70929 that has to do with determining whether a SIB byte is needed. It causes a lot of x86_64 JIT failures. by Evan Cheng · 16 years ago
  96. b0030dd - Avoid the longer SIB encoding on x86_64 when it's not needed. by Evan Cheng · 16 years ago
  97. 4af325d Rename GR8_ABCD to GR8_ABCD_L and create GR8_ABCD_H, and use these by Dan Gohman · 16 years ago
  98. 6241762 Rename GR8_, GR16_, GR32_, and GR64_ to GR8_ABCD, GR16_ABCD, by Dan Gohman · 16 years ago
  99. 70bc17d Make X86's copyRegToReg able to handle copies to and from subclasses. by Dan Gohman · 16 years ago
  100. 0bd07fc Fixed a few 64 bit cases in X86InstrInfo::commuteInstruction by Mon P Wang · 16 years ago