Gitiles
Code Review Sign In
gerrit-public.fairphone.software / toolchain / llvm-project / a9a7bf68ee35ffbe2fd6a8ac06290f24f94e16f9 / llvm / lib / Target / ARM / ARMISelLowering.cpp
  1. 453f4aa [ARM] fix initialization of PredictableSelectIsExpensive by Junmo Park · 10 years ago
  2. 1108ab0 Minor code cleanups. NFC. by Junmo Park · 10 years ago
  3. 93cff7f [CodeGen] Document and use getConstant's splat-building feature. NFC. by Ahmed Bougacha · 10 years ago
  4. f8dfb47 [CodeGen] Prefer "if (SDValue R = ...)" to "if (R.getNode())". NFCI. by Ahmed Bougacha · 10 years ago
  5. f36005a ARM: support TLS for WoA by Saleem Abdulrasool · 10 years ago
  6. 6027dd38e [ARM] Move GNUEABI divmod to __aeabi_divmod* by Renato Golin · 10 years ago
  7. b30f2f51 Avoid overly large SmallPtrSet/SmallSet by Matthias Braun · 10 years ago
  8. 042a6c1 ARMv7k: base ABI decision on v7k Arch rather than watchos OS. by Tim Northover · 10 years ago
  9. e5f807f CXX_FAST_TLS calling convention: fix issue on ARM. by Manman Ren · 10 years ago
  10. 433c22e [ARM] Add ARMv8-A semaphore/atomic instructions to ARMv8-M Baseline/Mainline by Bradley Smith · 10 years ago
  11. 519563e [ARM] Add SDIV/UDIV instructions to ARMv8-M Baseline by Bradley Smith · 10 years ago
  12. 5e9e65e CXX_FAST_TLS calling convention: performance improvement for ARM. by Manman Ren · 10 years ago
  13. 1602605 CXX_FAST_TLS calling convention: Add support for ARM on Darwin. by Manman Ren · 10 years ago
  14. 4b3b13d RBIT Instruction only available for ARMv6t2 and above. by Weiming Zhao · 10 years ago
  15. b793230 Add some testing for thumb1 and thumb2 inline asm immediate constraints by Eric Christopher · 10 years ago
  16. bd41cf8 ARM: support TLS accesses on Darwin platforms by Tim Northover · 10 years ago
  17. 353d719 Remove extra whitespace. NFC. by Chad Rosier · 10 years ago
  18. c106989 Normalize MBB's successors' probabilities in several locations. by Cong Hou · 10 years ago
  19. cd8664c Revert r248483, r242546, r242545, and r242409 - absdiff intrinsics by Hal Finkel · 10 years ago
  20. 97564c3 [AArch64][ARM] Don't base interleaved op legality on type alloc size. by Ahmed Bougacha · 10 years ago
  21. 901f036 [ARM] When a bitcast is about to be turned into a VMOVDRR, try to combine it by Quentin Colombet · 10 years ago
  22. f520eff AArch64: use ldxp/stxp pair to implement 128-bit atomic loads. by Tim Northover · 10 years ago
  23. d97c100 Replace all weight-based interfaces in MBB with probability-based interfaces, and update all uses of old interfaces. by Cong Hou · 10 years ago
  24. 1dbaf67 Revert r254348: "Replace all weight-based interfaces in MBB with probability-based interfaces, and update all uses of old interfaces." by Hans Wennborg · 10 years ago
  25. fa1917c Replace all weight-based interfaces in MBB with probability-based interfaces, and update all uses of old interfaces. by Cong Hou · 10 years ago
  26. d122924 ARM: address WOA unsigned division overflow crash by Martell Malone · 10 years ago
  27. 314ee04 Expose isXxxConstant() functions from SelectionDAGNodes.h (NFC) by Artyom Skrobov · 10 years ago
  28. a6b867e ARM: address WoA division overflow crash by Martell Malone · 10 years ago
  29. 2018091 Properly check if a CMPZ node is in fact comparing against zero by James Molloy · 10 years ago
  30. b564098 [ARM] Replace ARMISD::RBIT with ISD::BITREVERSE by James Molloy · 10 years ago
  31. 8e99e97 [ARM] CMOV->BFI combining: handle both senses of CMPZ by James Molloy · 10 years ago
  32. 0767ae5 Properly fix unused variable in disable-assert builds. by Diego Novillo · 10 years ago
  33. 29f88a2 Remove unused variable in disable-assert builds. NFC. by Diego Novillo · 10 years ago
  34. ce12c92 [ARM] Combine BFIs together by James Molloy · 10 years ago
  35. af1b48b [ARM] add overrides for isCheapToSpeculateCttz() and isCheapToSpeculateCtlz() by Sanjay Patel · 10 years ago
  36. 9d55f19 Reapply "[ARM] Combine CMOV into BFI where possible" by James Molloy · 10 years ago
  37. 6d435f1 [EABI] Add LLVM support for -meabi flag by Renato Golin · 10 years ago
  38. 1d8a2c9 Revert "[ARM] Combine CMOV into BFI where possible" by Renato Golin · 10 years ago
  39. f748c89 [WinEH] Update exception pointer registers by Joseph Tremoulet · 10 years ago
  40. bef6e431 [ARM] Compute known bits for ARMISD::CMOV by James Molloy · 10 years ago
  41. e7d679c [ARM] Combine CMOV into BFI where possible by James Molloy · 10 years ago
  42. f8e47e4 ARM: add support for WatchOS's compact unwind information. by Tim Northover · 10 years ago
  43. 8b40366 ARM: teach backend about WatchOS and TvOS libcalls. by Tim Northover · 10 years ago
  44. 458e79b [ARM] Expand ROTL and ROTR of vector value types by Charlie Turner · 10 years ago
  45. 99fac80 ARM/ELF: Restore original (pre-r251322) logic for deciding whether to use GOT. by Peter Collingbourne · 10 years ago
  46. 97aae40 ARM/ELF: Better codegen for global variable addresses. by Peter Collingbourne · 10 years ago
  47. 8fe40e0 Change makeLibCall to take an ArrayRef<SDValue> instead of pointer and size. This removes the need to pass a hardcoded size in many places. NFC by Craig Topper · 10 years ago
  48. 7fd67e2 Adding support for TargetLoweringBase::LibCall by Artyom Skrobov · 10 years ago
  49. 9f9559e ARM: Remove implicit ilist iterator conversions, NFC by Duncan P. N. Exon Smith · 10 years ago
  50. 2626094 Make a bunch of static arrays const. by Craig Topper · 10 years ago
  51. 169865f [ARM] Promote helper function to SelectionDAG. by Chad Rosier · 10 years ago
  52. d3d114b [ARM] Use correct half-precision functions in EABI mode by Oliver Stannard · 10 years ago
  53. 17436bf [ARM] Prevent PerformVDIVCombine from combining a vcvt/vdiv with 8 lanes. by Chad Rosier · 10 years ago
  54. aebca09 [ARM][AArch64] Only lower to interleaved load/store if the target has NEON by Jeroen Ketema · 10 years ago
  55. db71abf [ARM] Push more complex check down to reduce compile time. NFC. by Chad Rosier · 10 years ago
  56. dca46b4 [ARM] Minor refactoring. NFC. by Chad Rosier · 10 years ago
  57. aed910b [ARM] Minor refactoring. NFC. by Chad Rosier · 10 years ago
  58. 9df4aff [ARM] Minor refactoring. NFC. by Chad Rosier · 10 years ago
  59. a087fd2 [ARM] Minor refactoring to improve readability. NFC. by Chad Rosier · 10 years ago
  60. 953f908 [ARM] Modify codegen for memcpy intrinsic to prefer LDM/STM. by Scott Douglass · 10 years ago
  61. ab99b59 [ARM][NEON] Use address space in vld([1234]|[234]lane) and vst([1234]|[234]lane) instructions by Jeroen Ketema · 10 years ago
  62. ad8a063 [ARM] Avoid redundant checks for isThumb1Only() after supportsTailCall() by Artyom Skrobov · 10 years ago
  63. e81610f [ARM] Don't generate clrex for pre-v7 targets. by Ahmed Bougacha · 10 years ago
  64. 8e99f50 ARM: make -Asserts,-Werror=unused-variable build happy by Saleem Abdulrasool · 10 years ago
  65. fe83b50 ARM: address WoA division limitation by Saleem Abdulrasool · 10 years ago
  66. cf29644 [ARM] Handle +t2dsp feature as an ArchExtKind in ARMTargetParser.def by Artyom Skrobov · 10 years ago
  67. 81616a7 [ARM] Emit clrex in the expanded cmpxchg fail block. by Ahmed Bougacha · 10 years ago
  68. 41681a5 [ARM] Do not scale vext with a factor by Jeroen Ketema · 10 years ago
  69. 4966f58 ARM: cleanup formatting by Saleem Abdulrasool · 10 years ago
  70. a260701 propagate fast-math-flags on DAG nodes by Sanjay Patel · 10 years ago
  71. 5246867 [CodeGen] Refactor TLI/AtomicExpand interface to make LLSC explicit. by Ahmed Bougacha · 10 years ago
  72. 9d67713 [CodeGen] Rename AtomicRMWExpansionKind to AtomicExpansionKind. by Ahmed Bougacha · 10 years ago
  73. 8c995a9 [ARM] Do not use vtrn for vectorshuffle if the order is reversed by James Molloy · 10 years ago
  74. 699a9dd [ARM] Don't abort on variable-idx extractelt in ReconstructShuffle. by Ahmed Bougacha · 10 years ago
  75. f9c19da [CodeGen] Support (and default to) expanding READCYCLECOUNTER to 0. by Ahmed Bougacha · 10 years ago
  76. 0e28823 [WinEH] Add some support for code generating catchpad by Reid Kleckner · 10 years ago
  77. bdef604 [ARM] Use AEABI helpers for i64 div and rem by Scott Douglass · 10 years ago
  78. d2974a6 [ARM] Refactor LowerDivRem before adding LowerREM (nfc) by Scott Douglass · 10 years ago
  79. bf17009 [ARM] Don't try and custom lower a vNi64 SETCC. by James Molloy · 10 years ago
  80. ad1b19f [ARM] Add instruction selection patterns for vmin/vmax by Silviu Baranga · 10 years ago
  81. 974838f [ARM] Fix crash when targetting CPU without NEON by James Molloy · 10 years ago
  82. c617be5 Rip out hand-rolled matching code for VMIN, VMAX, VMINNM and VMAXNM by James Molloy · 10 years ago
  83. 3111787 [ARM] FMINNAN/FMAXNAN of f64 are not legal. by James Molloy · 10 years ago
  84. e40c8a2 PseudoSourceValue: Replace global manager with a manager in a machine function. by Alex Lorenz · 10 years ago
  85. d616c64 [ARM] Match fminnan/fmaxnan for vector vmin/vmax instead of an intrinsic by James Molloy · 10 years ago
  86. ee868b2 [ARM] Match fminnum/fmaxnum for vector vminnm/vmaxnm instead of an intrinsic by James Molloy · 10 years ago
  87. ea3a687 [ARM] Replace ARMISD::VMINNM/VMAXNM with ISD::FMINNUM/FMAXNUM by James Molloy · 10 years ago
  88. db8ee4b [ARM] Replace ARMISD::FMIN/FMAX with the shiny new ISD::FMINNAN/FMAXNAN. by James Molloy · 10 years ago
  89. df005cb Fix some comment typos. by Benjamin Kramer · 10 years ago
  90. a07090f Fix unused variable warning introduced in r244314 by Silviu Baranga · 10 years ago
  91. 3e8e51c [ARM] Update ReconstructShuffle to handle mismatched types by Silviu Baranga · 10 years ago
  92. 924879a wrap OptSize and MinSize attributes for easier and consistent access (NFCI) by Sanjay Patel · 10 years ago
  93. 0a2672b ARM: support windows division routines by Saleem Abdulrasool · 10 years ago
  94. 67697a7 ARM: make Darwin libcall registration table driven (NFC) by Saleem Abdulrasool · 10 years ago
  95. e3dcce9 De-constify pointers to Type since they can't be modified. NFC by Craig Topper · 10 years ago
  96. 532a136 [ARM] Lower modulo operation to generate __aeabi_divmod on Android by Sumanth Gundapaneni · 10 years ago
  97. 1166f2f fix memcpy/memset/memmove lowering when optimizing for size by Sanjay Patel · 10 years ago
  98. 1e85958 Implement target independent TLS compatible with glibc's emutls.c. by Chih-Hung Hsieh · 10 years ago
  99. 4d45ff2 [ARM] - Fix lowering of shufflevectors in AArch32 by Luke Cheeseman · 10 years ago
  100. b5c627a When lowering vector shifts a check is performed to see if the value to shift by by Luke Cheeseman · 10 years ago