Gitiles
Code Review Sign In
gerrit-public.fairphone.software / toolchain / llvm-project / a66f42caa988df0c41f8cec486f61a289b44a130 / llvm / lib / Support / Host.cpp
  1. 9709e2b [Support] Fix ErrorOr assertion when /proc/cpuinfo doesn't exist. by Teresa Johnson · 9 years ago
  2. 0b5eed2 Remove xgene1 from host detection by Yi Kong · 9 years ago
  3. 57019dc Implement host CPU detection for AArch64 by Yi Kong · 9 years ago
  4. 77ce4f6 Make naming in Host.h in line with coding standards. by Kristof Beyls · 9 years ago
  5. 7a76b31 Revert "Make naming in Host.h in line with coding standards." by Kristof Beyls · 9 years ago
  6. ca878c9 Make naming in Host.h in line with coding standards. by Kristof Beyls · 9 years ago
  7. 9e46396 Refactor getHostCPUName to allow testing on non-native hardware. by Kristof Beyls · 9 years ago
  8. 3cac763 [X86] Remove the HLE feature flag. by Craig Topper · 9 years ago
  9. 86576bd [X86] Remove INVPCID and SMAP feature flags. They aren't currently used by any instructions and not tested. by Craig Topper · 9 years ago
  10. 50f3d14 [X86] Clzero intrinsic and its addition under znver1 by Craig Topper · 9 years ago
  11. e0ac7f3 [X86] Remove PCOMMIT instruction support since Intel has deprecated this instruction with no plans to release products with it. by Craig Topper · 9 years ago
  12. d55b831 AMD family 17h (znver1) enablement by Craig Topper · 9 years ago
  13. 33c544b [X86] Add Intel Kaby Lake model numbers to getHostCPUName aliased to "skylake" since there are no feature differences. by Craig Topper · 9 years ago
  14. 1ab35fa [X86] Change getHostCPUName to report Intel model 0x4e as "skylake" instead of "skylake-avx512". Add the proper 0x55 model for "skylake-avx512". by Craig Topper · 9 years ago
  15. c08b90d [PowerPC] Add identification for POWER8NVL by Nemanja Ivanovic · 9 years ago
  16. db46b7d Add computeHostNumPhysicalCores() implementation for Darwin by Mehdi Amini · 9 years ago
  17. 4c2582a Reduce global namespace pollution. NFC. by Benjamin Kramer · 9 years ago
  18. 7943fec Add interface to compute number of physical cores on host system by Teresa Johnson · 9 years ago
  19. 9a78ebd [cpu-detection] Copy simplified version of get_cpuid_max to remove dependency to clang's implementation by Alina Sbirlea · 9 years ago
  20. b86aa17 Properly ifdef the use of cpuid. by Alina Sbirlea · 9 years ago
  21. 33588b1 [cpu-detection] Cleanup of Host.cpp. by Alina Sbirlea · 9 years ago
  22. b308f8b [Support] Make helper function static. NFC. by Benjamin Kramer · 9 years ago
  23. d665b41 Reapply 272328 and 272329 as a single patch. by Alina Sbirlea · 9 years ago
  24. e0b7bf4 Revert 272328 and 272329 to recommit as a single patch. by Alina Sbirlea · 9 years ago
  25. 4acea0a Keep barcelona subtype for amdfam10 by Alina Sbirlea · 9 years ago
  26. e76dcd2 [cpu-detection] Return amdfam10 for all subtypes. Address Bug 28067. by Alina Sbirlea · 9 years ago
  27. 080241b [cpu-detection] Add missing break statements in outer switches by Alina Sbirlea · 9 years ago
  28. 76c4a85 [cpu-detection] Substantial refactor of Host CPU detection code (x86) by Alina Sbirlea · 9 years ago
  29. 400eb02 [cpu-detection] Naming convention by Alina Sbirlea · 9 years ago
  30. b820edd 80-column fixup after last formatting change. by Eric Christopher · 9 years ago
  31. d9804bb Fix a couple of misformatted comments spotted in post-commit review. by Eric Christopher · 9 years ago
  32. 5db9d66 This patch is in preparation for a substantial refactoring of the by Eric Christopher · 9 years ago
  33. 5426922 Removing an unused variable introduced in r269911; NFC. by Aaron Ballman · 9 years ago
  34. 348af9c Add new flag and intrinsic support for MWAITX and MONITORX instructions by Ashutosh Nema · 9 years ago
  35. 6e29baf [Power9] Add support for -mcpu=pwr9 in the back end by Nemanja Ivanovic · 9 years ago
  36. de4318b [Support][X86] Add a few more Intel model numbers to getHostCPUName for airmont and knl. by Craig Topper · 10 years ago
  37. e7d743c [Support][X86] Change the case values in the Intel family 6 code to hex so its easier to compare with Intel's docs. NFC by Craig Topper · 10 years ago
  38. 0e2f14f [Support][X86] Add a couple more Broadwell CPU models numbers to getHostCPUName. by Craig Topper · 10 years ago
  39. 91d3cfe Revert "Fix Clang-tidy modernize-deprecated-headers warnings in remaining files; other minor fixes." by Duncan P. N. Exon Smith · 10 years ago
  40. 1760dc2 Fix Clang-tidy modernize-deprecated-headers warnings in remaining files; other minor fixes. by Eugene Zelenko · 10 years ago
  41. aa63dc0 Fix LLVM's handling and detection of skylake and cannonlake CPUs by Sanjoy Das · 10 years ago
  42. 29cde35 Added Skylake client to X86 targets and features by Elena Demikhovsky · 10 years ago
  43. 9c47e06 [AVX512] adding AVXVBMI feature flag by Michael Zuckerman · 10 years ago
  44. 97b6a692 [AVX512] adding AVXVBMI feature flag by Michael Zuckerman · 10 years ago
  45. 5acf66f [x86] adding PKU feature flag by Asaf Badouh · 10 years ago
  46. b84b126 [X86] Update CPU detection to only enable XSAVE features if the OS has enabled them and the saving of YMM state. This seems to be consistent with gcc behavior. by Craig Topper · 10 years ago
  47. 1db6d7a [X86] Add XSAVE intrinsic family by Amjad Aboud · 10 years ago
  48. e4405e9 [ADT] Switch a bunch of places in LLVM that were doing single-character by Chandler Carruth · 10 years ago
  49. 68ba18f Add model numbers for Skylake CPUs and an additional Broadwell model. by Craig Topper · 10 years ago
  50. f7ce754 Add Intel family 6 model 93 as Silvermont. by Craig Topper · 10 years ago
  51. a3db7d2 Add Intel family 6 model 90 as Silvermont. Fixes PR24392. by Craig Topper · 10 years ago
  52. a8b04e1 [SystemZ] Add z13 vector facility and MC support by Ulrich Weigand · 11 years ago
  53. 545b951 [X86] Stop changing result of getHostCPUName based on whether the processor supports AVX. getHostCPUFeatures should be used instead to determine whether to support AVX. by Craig Topper · 11 years ago
  54. 1214bdc [X86] Be more robust against unknown Intel family 6 models. Use feature flags to guess what it might be. by Craig Topper · 11 years ago
  55. 5d28b90 [X86] In getHostCPUFeatures, disable xop, f16c, fma, and fma4 if OS does not support saving ymm state. by Craig Topper · 11 years ago
  56. 3c2e758 [X86] Use the more specific CPU names like 'nehalem', 'westmere', 'haswell', etc. Split Nehalem and Westmere CPUs. by Craig Topper · 11 years ago
  57. 0668285 [X86] Move family 6 model 21 to 'pentium-m'. Near as I can tell this is a Dothan based SOC. by Craig Topper · 11 years ago
  58. 4e78a92 [X86] Family 6 model 29 is a Penryn based processor not a Nehalem based processor. by Craig Topper · 11 years ago
  59. 7db49fd Fix a variable name in MSVC specific part of rr233487. by Craig Topper · 11 years ago
  60. 798a260 [X86] Implement getHostCPUFeatures for X86. by Craig Topper · 11 years ago
  61. 3b1c350 Fix typo 'AVX too' instead of 'AVX2' by Craig Topper · 11 years ago
  62. 1e1b0f7 [X86] Add one stepping of Broadwell to the CPU name autodetection for march=native. by Craig Topper · 11 years ago
  63. b664e2a We require MSVC 1800 as our minimum, so these checks can safely go away; NFC. by Aaron Ballman · 11 years ago
  64. 5f06030 Remove a debugging assert. by Rafael Espindola · 11 years ago
  65. 81adfb5 Fix the windows build. by Rafael Espindola · 11 years ago
  66. 97935a9 Refactor and simplify the code reading /proc/cpuinfo. NFC. by Rafael Espindola · 11 years ago
  67. 5106ce7 Remove StringMap::GetOrCreateValue in favor of StringMap::insert by David Blaikie · 11 years ago
  68. 579e402 Add support for ppc64/power8 as a host by Will Schmidt · 11 years ago
  69. cfe341f Fix .cpp files claiming to be header files by Hans Wennborg · 11 years ago
  70. da0c793 Fix typos by Alp Toker · 11 years ago
  71. 63c8b1b Fixup sys::getHostCPUFeatures crypto names so it doesn't clash with kernel headers by Bradley Smith · 11 years ago
  72. 9288b21 Extend sys::getHostCPUFeatures to work on AArch64 platforms by Bradley Smith · 11 years ago
  73. a39d2a0 Select bdver2 instead of bdver1 if TBM support is present on models < 0x10. by Kaelyn Takata · 12 years ago
  74. 6004573 Add a description for AMD's bdver4 (aka Excavator). by Benjamin Kramer · 12 years ago
  75. 66f38db [Modules] Followup to r206822 to add a DEBUG_TYPE which is used on ARM by Chandler Carruth · 12 years ago
  76. b38bf96 Add support for krait cpu in llvm::sys::getHostCPUName() by Kai Nacke · 12 years ago
  77. b75ea01 Fix Typo. by Rafael Espindola · 12 years ago
  78. 1f58e4d Convert the other getHostByName implementations to StringRef. by Rafael Espindola · 12 years ago
  79. 74f444c Return a StringRef from getHostCPUName. by Rafael Espindola · 12 years ago
  80. 583b00e Make helper function static. by Benjamin Kramer · 12 years ago
  81. 89ccb61 X86: enable AVX2 under Haswell native compilation by Tim Northover · 12 years ago
  82. d114def X86: Add a description for AMD bdver3 aka Steamroller. by Benjamin Kramer · 12 years ago
  83. f834ea1 [SystemZ] Automatically detect zEC12 and z196 hosts by Richard Sandiford · 12 years ago
  84. 3fe264d Adds support for Atom Silvermont (SLM) - -march=slm by Preston Gurd · 12 years ago
  85. 8f42938 X86: Add a description of the Intel Atom Silvermont CPU. by Benjamin Kramer · 12 years ago
  86. bf4f9eb Actually, use GNU inline asm for cpuid with clang by Reid Kleckner · 12 years ago
  87. be85cb9 Use the MSVC __cpuid intrinsic instead of inline asm by Reid Kleckner · 12 years ago
  88. fb34989 Some Intel Penryn CPUs come with SSE4 disabled. Detect them as core 2. by Benjamin Kramer · 12 years ago
  89. e2cd139 Ensure sys::getProcessTriple always uses a normalized triple. Patch by by Duncan Sands · 12 years ago
  90. bd9e549 Make host ARM CPU feature detection independent of the vendor by Tobias Grosser · 12 years ago
  91. fee13d1 Allow host triple to be correctly overridden in CMake builds by Tim Northover · 13 years ago
  92. b44c427 X86: Add target description for btver2; make autodetection logic aware of AVX. by Benjamin Kramer · 13 years ago
  93. 31c0adc Testing for _XCR_XFEATURE_ENABLED_MASK instead of a specific MSVC version because some MSVC 2010 SP1 installations do not have the _xgetbv intrinsic. Patch thanks to Serge Pavlov! by Aaron Ballman · 13 years ago
  94. 7af39d7 Convert windows line endings to linux/unix line endings. by Craig Topper · 13 years ago
  95. 5e6d205 Ensuring that both bits are set, and not just a combination of one or the other. by Aaron Ballman · 13 years ago
  96. edc03c6 Testing for Visual Studio 2010 SP1 or greater before calling the _xgetbv intrinsic. This also fixes a minor code formatting issue. by Aaron Ballman · 13 years ago
  97. 5f7c680 Second pass at addressing PR15351 by explicitly checking for AVX support by Aaron Ballman · 13 years ago
  98. 9c0f0af Rolling back the AVX support patch due to breaking a gcc 4.6 build bot that doesn't understand the xgetbv instruction for some reason. Will revisit when time permits. by Aaron Ballman · 13 years ago
  99. 56be6ba Attempting to fix the build on older GCC versions. by Aaron Ballman · 13 years ago
  100. 6bc0dfc This patch addresses PR15351 by explicitly checking for AVX support by Aaron Ballman · 13 years ago