Started 11 days ago
Took 4 hr 53 min on green-dragon-02

Failed Build #14375 (Jul 11, 2019 8:02:14 PM)

  • : 365865
  • : 365866
  • : 365863
  • : 365596
  • : 365856
  • : 365849
  1. [X86][PowerPC] Support -mlong-double-128

    This patch makes the driver option -mlong-double-128 available for X86
    and PowerPC. The CC1 option -mlong-double-128 is available on all targets
    for users to test on unsupported targets.

    On PowerPC, -mlong-double-128 uses the IBM extended double format
    because we don't support -mabi=ieeelongdouble yet (D64283).

    Reviewed By: rnk

    Differential Revision: (detail)
    by maskray
  2. docs/GithubMove.rst: Add link to GitHub migration status page (detail)
    by tstellar
  3. Return Undef from isBytewiseValue for empty arrays or structs

    Reviewers: pcc, eugenis

    Subscribers: hiraditya, llvm-commits

    Tags: #llvm

    Differential Revision: (detail)
    by Vitaly Buka
  4. NFC: Unforget a colon in a few CHECK: directives.

    Differential Revision: (detail)
    by dergachev
  5. [PowerPC] Default to -fomit-frame-pointer when optimization is enabled

    NetBSD, Linux, CloudABI and Hurd already omit frame pointer for PowerPC.
    Make it do so for other platforms. (detail)
    by maskray
  6. [analyzer] exploded-graph-rewriter: Improve source location dumps.

    - Correctly display macro expansion and spelling locations.
    - Use the same procedure to display location context call site locations.
    - Display statement IDs for program points. (detail)
    by dergachev
  7. [Driver] Refactor interaction between -f(no-)?omit-frame-pointer and -m(no-)?omit-leaf-frame-pointer

    Use a tri-state enum to represent shouldUseFramePointer() and

    This simplifies the logic and fixes PR9825:
      -fno-omit-frame-pointer doesn't imply -mno-omit-leaf-frame-pointer.

    and PR24003:
      /Oy- /O2 should not omit leaf frame pointer: this matches MSVC x86-32.
      (/Oy- is a no-op on MSVC x86-64.)

      when CC1 option -mdisable-fp-elim if absent, -momit-leaf-frame-pointer
      can also be omitted.

    The new behavior matches GCC:
      -fomit-frame-pointer wins over -mno-omit-leaf-frame-pointer
      -fno-omit-frame-pointer loses out to -momit-leaf-frame-pointer

    The behavior makes lots of sense. We have 4 states:

    - 00) leaf retained, non-leaf retained
    - 01) leaf retained, non-leaf omitted  (this is invalid)
    - 10) leaf omitted, non-leaf retained  (what -momit-leaf-frame-pointer was designed for)
    - 11) leaf omitted, non-leaf omitted

    "omit" options taking precedence over "no-omit" options is the only way
    to make 3 valid states representable with -f(no-)?omit-frame-pointer and

    Reviewed By: ychen

    Differential Revision: (detail)
    by maskray
  8. [MachinePipeliner] Fix order for nodes with Anti dependence in same cycle

    Problem exposed in PowerPC functional testing.

    We did not consider Anti dependence for nodes in same cycle,
    so we may end up generating bad machine code.
    eg: the reduced test won't verify.

    *** Bad machine code: Using an undefined physical register ***
    - function:    lame_encode_buffer_interleaved
    - basic block: %bb.4  (0x4bde4e12928)
    - instruction: %29:gprc = ADDZE %27:gprc, implicit-def dead $carry, implicit $carry
    - operand 3:   implicit $carry

    Reviewers: bcahoon, kparzysz, hfinkel

    Subscribers: MaskRay, wuzish, nemanjai, hiraditya, llvm-commits

    Tags: #llvm

    Differential Revision: (detail)
    by jsji
  9. Handle IntToPtr in isBytewiseValue

    This helps with more efficient use of memset for pattern initialization

    From @pcc prototype for -ftrivial-auto-var-init=pattern optimizations

    Binary size change on CTMark, (with -fuse-ld=lld -Wl,--icf=all, similar results with default linker options)
                       master           patch      diff
    Os           8.238864e+05    8.238864e+05       0.0
    O3           1.054797e+06    1.054797e+06       0.0
    Os zero      8.292384e+05    8.292384e+05       0.0
    O3 zero      1.062626e+06    1.062626e+06       0.0
    Os pattern   8.579712e+05    8.338048e+05 -0.030299
    O3 pattern   1.090502e+06    1.067574e+06 -0.020481

    Zero vs Pattern on master
                   zero       pattern      diff
    Os     8.292384e+05  8.579712e+05  0.036578
    O3     1.062626e+06  1.090502e+06  0.025124

    Zero vs Pattern with the patch
                   zero       pattern      diff
    Os     8.292384e+05  8.338048e+05  0.003333
    O3     1.062626e+06  1.067574e+06  0.003193

    Reviewers: pcc, eugenis

    Subscribers: hiraditya, cfe-commits, llvm-commits

    Tags: #clang, #llvm

    Differential Revision: (detail)
    by Vitaly Buka
  10. Codegen, NFC: 32bit test in auto-var-init.cpp (detail)
    by Vitaly Buka
  11. Mark destroying delete test as UNSUPPORTED with clang 7 (detail)
    by ericwf
  12. Tolerate import errors in "" implementation (detail)
    by ericwf
  13. Reorganize the 'bit' header to make most of the facilities available for internal use pre-C++20. NFC for external users (detail)
    by marshall
  14. NFC: lit: python3 compatibility for functions

    These functions should decode subprocess output (detail)
    by arphaman
  15. [InstCombine] Reorder pow() transformations (NFC)

    Move the transformation from `powf(x, itofp(y))` to `powi(x, y)` to the
    group of transformations related to the exponent. (detail)
    by evandro
  16. Re-Revert Devirtualize destructor of final class.

    This reverts r365509 (git commit d088720edad9c29ee0d622b5d69092e18a9ac0bd)

    This is a second revert[1] due to failures in internal test cases (shared offline) found during more thorough testing.

    [1] Original patch commited as r364100, reverted as r364359, recommitted as r365509 (detail)
    by rupprecht
  17. [clangd] Add a missing early return in getTypeHierarchy()

    Reviewers: sammccall

    Subscribers: ilya-biryukov, MaskRay, jkorous, arphaman, kadircet, cfe-commits

    Tags: #clang

    Differential Revision: (detail)
    by nridge
  18. Add another buildbot username to the workaround list (detail)
    by ericwf
  19. Attempt to override broken buildbot config for libc++abi.

    The buildbots were changed to pass -DLIBCXX_CXX_ABI=libcxxabi, but
    they don't provide an include path for the library, so cxxabi.h is
    never found while building libc++.

    This is a temporary change until the buildbots are updated or until
    D63883 lands in a form that unbreaks the bots (detail)
    by ericwf
  20. [AMDGPU] Skip calculating callee saved registers for entry function.

    Reviewers: arsenm

    Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits

    Tags: #llvm

    Differential Revision: (detail)
    by hliao
  21. [CMake][Fuchsia] Use RelWithDebInfo to build runtimes

    We want to preserve debug info in our runtimes to aid symbolization and
    debugging; for shared libraries this will be stripped away during
    install-stripped step and distributed via .build-id, for static archives
    it's part of the archive and it's a responsibility of the consumer to
    strip it away in the final binary if not needed.

    Differential Revision: (detail)
    by phosek
  22. [clangd] Fix MSVC build failure. (detail)
    by probinson
  23. AMDGPU: s_waitcnt field should be treated as unsigned

    Also make it an ImmLeaf, so it should work with global isel as well,
    which was part of the point of moving it in the first place. (detail)
    by arsenm
  24. Use clang driver for libfuzzer tests on Windows

    There's no real reason to use clang-cl on Windows, the clang driver
    works just as well. This fixes a test which uses the -O0 flag, which was
    recently removed from clang-cl to match MSVC, which lacks this flag.

    While I'm here, remove the explicit -std=c++11 flag. Previously, this
    flag was necessary when the default C++ standard was C++98. Now that the
    default is C++14, this is no longer necessary. It's problematic on
    Windows, because the Visual C++ standard library relies on C++14
    features, and attempting to compile it with C++11 results in errors.
    Rather than adding logic to conditionally set the standard to C++11 only
    on non-Win, this flag can be removed.

    See and

    Reviewers: morehouse, thakis

    Subscribers: #sanitizers, llvm-commits

    Tags: #sanitizers, #llvm

    Differential Revision: (detail)
    by rnk
  25. Fix memory leak in set and map.

    When assigning an initializer list into set/map, libc++ would
    leak memory if the initializer list contained equivalent keys
    because we failed to check if the insertion was successful. (detail)
    by ericwf
  26. [sancov] Ignore PC samples with value 0

    The sancov runtime for the (Fuchsia) Zircon kernel delivers results
    in the standard format, but as the full array of possible samples
    with 0 in uncovered slots. That runtime delivers "live" data and
    has no final "export" pass to compactify out the uncovered slots,
    and it seems silly to require another offline tool just for that.

    Patch By: mcgrathr
    Differential Revision: (detail)
    by phosek
  27. [NewPM] Port Sancov

    This patch contains a port of SanitizerCoverage to the new pass manager. This one's a bit hefty.


    - Split SanitizerCoverageModule into 2 SanitizerCoverage for passing over
      functions and ModuleSanitizerCoverage for passing over modules.
    - ModuleSanitizerCoverage exists for adding 2 module level calls to initialization
      functions but only if there's a function that was instrumented by sancov.
    - Added legacy and new PM wrapper classes that own instances of the 2 new classes.
    - Update llvm tests and add clang tests.

    Differential Revision: (detail)
    by leonardchan
  28. [AMDGPU] Fixed asan error with agpr spilling

    Instruction was used after it was erased. (detail)
    by rampitec
  29. Fix build errors LLVM tests are disabled.

    Original patch from

    Fixes the error:
    CMake Error in <...>/llvm/cmake/modules/CMakeLists.txt:

    export called with target "LLVMTestingSupport" which requires target
    "gtest" that is not in the export set.

    This occurs when LLVM is embedded in a larger project, but is configured not to
    include tests. If testing is disabled gtest isn't available and LLVM fails to

    Differential revision: (detail)
    by dnovillo

Started by timer (5 times)

This run spent:

  • 4 hr 51 min waiting;
  • 4 hr 53 min build duration;
  • 9 hr 45 min total from scheduled to completion.
Test Result (5 failures / ±0)Show all failed tests >>>

Identified problems

Regression test failed

This build failed because a regression test in the test suite FAILed. See the test report for details.
Indication 1

Ninja target failed

Below is a link to the first failed ninja target.
Indication 2

Compile Error

This build failed because of a compile error. Below is a list of all errors in the build log:
Indication 3