Gitiles
Code Review Sign In
gerrit-public.fairphone.software / fp2-dev / platform / external / llvm / ef41ff618f2537539b538e6c7bf471c753391f92 / lib / Target / X86 / X86Subtarget.cpp
  1. ef41ff6 Remove TargetOptions.h dependency from X86Subtarget. by Evan Cheng · 14 years ago
  2. fee2286 Enable autodetect of popcnt by Mon P Wang · 14 years ago
  3. 558692f ADT/Triple: Renambe isOSX... methods to isMacOSX for consistency with the OS by Daniel Dunbar · 14 years ago
  4. 2cf711f Target/X86: Eliminate uses of getDarwinVers(). by Daniel Dunbar · 14 years ago
  5. 4c3ab58 Stack alignment is 16 bytes on FreeBSD/i386 too. by Roman Divacky · 14 years ago
  6. 7331ca8 The stack should be 16 byte aligned on 32 bit solaris. Patch by Yuri. by Duncan Sands · 14 years ago
  7. 04f5079 Experiment with changing the default 32-bit linux stack alignment to by Eric Christopher · 15 years ago
  8. de7f920 Disable auto-detection of AVX support since AVX codegen support is not ready. by Evan Cheng · 15 years ago
  9. 2ea8ee7 Formalize the notion that AVX and SSE are non-overlapping extensions from the compiler's point of view. Per email discussion, we either want to always use VEX-prefixed instructions or never use them, and are taking "HasAVX" to mean "Always use VEX". Passing -mattr=-avx,+sse42 should serve to restore legacy SSE support when desirable. by Nate Begeman · 15 years ago
  10. d643486 Initialize HasPOPCNT. by Bill Wendling · 15 years ago
  11. 1f6efa3 Merge System into Support. by Michael J. Spencer · 15 years ago
  12. 699647c Use rip-rel addressing on win64 by default. For this we just by Anton Korobeynikov · 15 years ago
  13. cdae7e8 Add x86 CLMUL (Carry-less multiplication) cpu feature by Bruno Cardoso Lopes · 15 years ago
  14. 62f35a2 Have the X86 backend use Triple instead of a string and some enums. by Eric Christopher · 15 years ago
  15. 6b60153 fix a nasty bug where we were not treating available_externally by Chris Lattner · 15 years ago
  16. 4d3d6e1 FastISel doesn't yet handle callee-pop functions. by Dan Gohman · 15 years ago
  17. 2bce5f4b Enable i16 to i32 promotion by default. by Evan Cheng · 15 years ago
  18. 5528e7b isel (i32 anyext i16) as insert_subreg when 16-bit ops are being promoted. by Evan Cheng · 15 years ago
  19. 6d1cd1c Separate out the AES-NI instructions from the SSE4.2 instructions. Add by Eric Christopher · 15 years ago
  20. 48c58bb Nehalem unaligned memory access is fast. by Evan Cheng · 15 years ago
  21. bdc652b Turning off post-ra scheduling for x86. It isn't a consistent win. by Evan Cheng · 15 years ago
  22. 1c436d0 no really, all 64-bit cpu's have cmov support. This should by Chris Lattner · 15 years ago
  23. f0356fe Kill ModuleProvider and ghost linkage by inverting the relationship between by Jeffrey Yasskin · 16 years ago
  24. 95eb2ee by David Greene · 16 years ago
  25. bd7b845 Change errs() to dbgs(). by David Greene · 16 years ago
  26. 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
  27. 400073d On recent Intel u-arch's, folding loads into some unary SSE instructions can by Evan Cheng · 16 years ago
  28. d84ea47 Don't enable the post-RA scheduler on x86 except at -O3. In its by Dan Gohman · 16 years ago
  29. 29cbade Target-independent support for TargetFlags on BlockAddress operands, by Dan Gohman · 16 years ago
  30. 067d024 Add llvm::sys::getHostCPUName, for detecting the LLVM name for the host CPU. by Daniel Dunbar · 16 years ago
  31. 87d21b9 Allow target to specify regclass for which antideps will only be broken along the critical path. by David Goodwin · 16 years ago
  32. c2e8a7e Fixed to address code review. No functional changes. by David Goodwin · 16 years ago
  33. 79f7400 Remove X86Subtarget::IsLinux. It's no longer being used. by Evan Cheng · 16 years ago
  34. 63476a8 Reference to hidden symbols do not have to go through non-lazy pointer in non-pic mode. rdar://7187172. by Evan Cheng · 16 years ago
  35. 8481138 Make these functions static and local. by Daniel Dunbar · 16 years ago
  36. d0da6ff X86JITInfo::getLazyResolverFunction() should not read cpu id to determine whether sse is available. Just use consult subtarget. by Evan Cheng · 16 years ago
  37. 7008416 Add support for modeling whether or not the processor has support for by Chris Lattner · 16 years ago
  38. 6f9bb6f Short-term workaround for frame-related weirdness on win64. by Anton Korobeynikov · 16 years ago
  39. ce914b8 change the -x86-asm-syntax=intel/att flag to be in X86TAI by Chris Lattner · 16 years ago
  40. e22f4da Remove some dead code. by Daniel Dunbar · 16 years ago
  41. 0ea8bf3 - s/DOUT/DEBUG(errs()/g - Tidy up some headers. by Bill Wendling · 16 years ago
  42. 3be0340 Normalize Subtarget constructors to take a target triple string instead of by Daniel Dunbar · 16 years ago
  43. cfb8a1b Fix some minor MSVC compiler warnings. by Daniel Dunbar · 16 years ago
  44. a82b22c GV with ghost linkage (module being lazily streamed in in JIT lazy compilation mode) do not require extra load from stub. This fixes ExecutionEngine/2005-12-02-TailCallBug.ll. by Evan Cheng · 16 years ago
  45. c782232 fix indentation by Chris Lattner · 16 years ago
  46. e2c9208 remove the now-dead TM argument to these methods. by Chris Lattner · 16 years ago
  47. 8097b65 make PIC vs DynamicNoPIC be explicit in PICStyles. by Chris Lattner · 16 years ago
  48. 84853a1 some minor simplifications. by Chris Lattner · 16 years ago
  49. 3b67e9b add a couple of predicates to test for "stub style pic in PIC mode" and "stub style pic in dynamic-no-pic" mode. by Chris Lattner · 16 years ago
  50. 0d786dd simplify fast isel by using ClassifyGlobalReference. This by Chris Lattner · 16 years ago
  51. dfed413 eliminate GVRequiresRegister, replacing it with predicates we by Chris Lattner · 16 years ago
  52. d392bd9 move some classification logic around. Now GVRequiresExtraLoad by Chris Lattner · 16 years ago
  53. ed0dca6 GVRequiresExtraLoad is now never used for calls, simplify it based on this. by Chris Lattner · 16 years ago
  54. 754b765 actually, just eliminate PCRelGVRequiresExtraLoad. It makes the code by Chris Lattner · 16 years ago
  55. e6c07b5 There is only one case where GVRequiresExtraLoad returns true for calls: by Chris Lattner · 16 years ago
  56. 04b304c the "isDirectCall" operand of GVRequiresRegister is always false, eliminate it. by Chris Lattner · 16 years ago
  57. 15a380a simplify some code based on the fact that picstyles != none are only valid by Chris Lattner · 16 years ago
  58. 73b5b71 Reduce indentation in GVRequiresExtraLoad. Return true for windows by Chris Lattner · 16 years ago
  59. 343dadb by David Greene · 16 years ago
  60. 0eebf65 The attached patches implement most of the ARM AAPCS-VFP hard float by Anton Korobeynikov · 16 years ago
  61. 8cf5ab1 Update CPU capabilities for AMD machines by Stefanus Du Toit · 16 years ago
  62. d7f666a Try again. Allow call to immediate address for ELF or when in static relocation mode. by Evan Cheng · 16 years ago
  63. bc58322 add support for detecting process features on win64, patch by Nicolas Capens! by Chris Lattner · 16 years ago
  64. 667d4b8 Introduce new linkage types linkonce_odr, weak_odr, common_odr by Duncan Sands · 16 years ago
  65. 9feb5dd Added another darwin subtarget by Mon P Wang · 16 years ago
  66. 605679f Tevert part of the x86 subtarget logic changes: when -march=x86-64 by Dan Gohman · 17 years ago
  67. f75e5b4 Change Feature64Bit to not imply FeatureSSE2. All x86-64 hardware has by Dan Gohman · 17 years ago
  68. b68a88b Only force SSE level if it is not correct. by Torok Edwin · 17 years ago
  69. 38870ed remove #if 0 code on Bill's request. by Torok Edwin · 17 years ago
  70. 3f142c3 Implement -mno-sse: if SSE is disabled on x86-64, don't store XMM on stack for by Torok Edwin · 17 years ago
  71. afb564c should have removed the + when manually applying a patch! by Torok Edwin · 17 years ago
  72. c8ad2d2 revert this patch for now, because Codegen does still want to generate SSE code, by Torok Edwin · 17 years ago
  73. 7f1d525 If user explicitly asks not to use SSE, don't force it. This fixes LLVM part of PR3402. by Torok Edwin · 17 years ago
  74. bb46f52 Add the private linkage. by Rafael Espindola · 17 years ago
  75. 7877112 Atom and Core i7 do not have same model number after all. by Evan Cheng · 17 years ago
  76. 0be6d3f Add Intel processors core i7 and atom. by Evan Cheng · 17 years ago
  77. 5b925c0 Fix PR3210: Detect more Intel processors. Patch by Torok Edwin. by Evan Cheng · 17 years ago
  78. ccb6976 Do not isel load folding bt instructions for pentium m, core, core2, and AMD processors. These are significantly slower than a load followed by a bt of a register. by Evan Cheng · 17 years ago
  79. 018b7ee Fix x86 CPU id detection to identify Penryn (and future processors). by Evan Cheng · 17 years ago
  80. 8749b61 Add initial support for back-scheduling address computations, by Dan Gohman · 17 years ago
  81. e4d1082 Re-apply 60689 now my head is screwed on right. by Evan Cheng · 17 years ago
  82. 2d4e9bc Revert 60689. It caused many regressions on Darwin targets. by Dan Gohman · 17 years ago
  83. dda346a Perform cheap checks first. by Evan Cheng · 17 years ago
  84. 203af58 Make LoopStrengthReduce smarter about hoisting things out of by Dale Johannesen · 17 years ago
  85. ae94e59 Re-did 60519. It turns out Darwin's handling of hidden visibility symbols are a bit more complicate than I expected. Both declarations and weak definitions still need a stub indirection. However, the stubs are in data section and they contain the addresses of the actual symbols. by Evan Cheng · 17 years ago
  86. a8103da Temporarily revert r60519. It was causing a bootstrap failure: by Bill Wendling · 17 years ago
  87. eb83dfd Visibility hidden GVs do not require extra load of symbol address from the GOT or non-lazy-ptr. by Evan Cheng · 17 years ago
  88. f9a67a8 Fix build with gcc-4.4: it doesn't like PICStyle by Duncan Sands · 17 years ago
  89. b8cab92 Fix command-line option printing to print two spaces where needed, by Dan Gohman · 17 years ago
  90. 6e08738 Just don't transform this memset into "bzero" if no-builtin is specified. by Bill Wendling · 17 years ago
  91. 6f287b2 Add the new `-no-builtin' flag. This flag is meant to mimic the GCC by Bill Wendling · 17 years ago
  92. 817a6a9 x86-64 PIC JIT fixes: do not generate the extra load for external GV's. by Evan Cheng · 17 years ago
  93. 3b48591 Revert accidentially added stuff by Anton Korobeynikov · 17 years ago
  94. e87f52d Switch to new section name handling facility by Anton Korobeynikov · 17 years ago
  95. cb26273 Back out 53091 for now. by Evan Cheng · 17 years ago
  96. f550f47 llvm-gcc sometimes marks external declarations hidden, because intializers are by Anton Korobeynikov · 17 years ago
  97. da5860f Don't use the GOT for symbols that are not externally visible. by Rafael Espindola · 17 years ago
  98. aafce77 Add CommonLinkage; currently tentative definitions by Dale Johannesen · 17 years ago
  99. 844731a Clean up the use of static and anonymous namespaces. This turned up by Dan Gohman · 17 years ago
  100. 63307c3 Added addition atomic instrinsics and, or, xor, min, and max. by Mon P Wang · 17 years ago