Commit Graph

280446 Commits

Author SHA1 Message Date
Nico Weber 8321ad9ffc Make DiagnosticsEngine() take DiagOpts as DiagnosticsEngine.
No behavior change, but makes it a bit clearer that DiagnosticsEngine adds a
ref to DiagOpts.

llvm-svn: 322611
2018-01-17 02:55:27 +00:00
Aaron Smith 620a7f765d Fix build error - 'default label in switch which covers all enumeration values'
llvm-svn: 322610
2018-01-17 01:49:01 +00:00
Sam Clegg 51bcdc2d49 [WebAssembly] Define __heap_base global
This is an immutable exported global representing
the start of the heap area.  It is a page aligned.

Differential Revision: https://reviews.llvm.org/D42030

llvm-svn: 322609
2018-01-17 01:34:31 +00:00
Aaron Smith 53a1a1616c Fix pretty printing the unspecified param of a variadic function
Summary:
 - Fix a bug in PrettyBuiltinDumper that returns "void" as the name for
  an unspecified builtin type. Since the unspecified param of a variadic
  function is considered a builtin of unspecified type in PDBs, we set
  "..." for its name.

  - Provide a method to determine if a PDBSymbolFunc is variadic in
  PrettyFunctionDumper since PDBSymbolFunc::getArgument() doesn't return the
  last unspecified-type param.

  - Add a pretty-func-dumper.test to test pretty dumping of variadic
  functions.

Reviewers: zturner, llvm-commits

Reviewed By: zturner

Differential Revision: https://reviews.llvm.org/D41801

llvm-svn: 322608
2018-01-17 01:22:03 +00:00
Peter Collingbourne 7351a22b7d cfi: Add a blacklist entry for MSVC's std::get_temporary_buffer function.
Differential Revision: https://reviews.llvm.org/D42150

llvm-svn: 322607
2018-01-17 01:15:33 +00:00
Sam Clegg 5a11dd9690 [WebAssembly] Create synthetic __dso_handle symbol
This is used by __cxa_ataxit to determine the currently
executing DLL.  Once we fully support DLLs this will need
to be set to some address within the DLL.

The ELF linker added support for this symbol here:
https://reviews.llvm.org/D33856

Differential Revision: https://reviews.llvm.org/D42024

llvm-svn: 322606
2018-01-17 01:10:28 +00:00
Rui Ueyama 2c95e798a0 [LLD][COFF] Report error when file will exceed Windows maximum image size (4GB)
Patch by Colden Cullen.

Currently, when a large PE (>4 GiB) is to be produced, a crash occurs
because:

1. Calling setOffset with a number greater than UINT32_MAX causes the
   PointerToRawData to overflow

2. When adding the symbol table to the end of the file, the last section's
   offset was used to calculate file size. Because this had overflowed,
   this number was too low, and the file created would not be large enough.
   This lead to the actual crash I saw, which was a buffer overrun.

This change:

1. Adds comment to setOffset, clarifying that overflow can occur, but it's
   somewhat safe because the error will be handled elsewhere

2. Adds file size check after all output data has been created This matches
   the MS link.exe error, which looks prints as: "LINK : fatal error
   LNK1248: image size (10000EFC9) exceeds maximum allowable size
   (FFFFFFFF)"

3. Changes calculate of the symbol table offset to just use the existing
   FileSize. This should match the previous calculations, but doesn't rely
   on the use of a u32 that can overflow.

4. Removes trivial usage of a magic number that bugged me while I was
   debugging the issue

I'm not sure how to add a test for this outside of adding 4GB of object
files to the repo. If there's an easier way, let me know and I'll be
happy to add a test.

Differential Revision: https://reviews.llvm.org/D42010

llvm-svn: 322605
2018-01-17 01:08:02 +00:00
Petr Hosek a1b57e694e [libFuzzer] Support using libc++
This is needed in case the users of libFuzzer use libc++ in their
code, which the fuzz target (libFuzzer) will be linked against.
When libc++ source is available, we build a private version of it
and link it against libFuzzer which allows using the same static
library against codebases which use both libc++ and libstdc++.

Differential Revision: https://reviews.llvm.org/D37631

llvm-svn: 322604
2018-01-17 00:42:48 +00:00
Jason Molenda 0af609d17c Remove the hardcoded macos deployment targets altogether
from the xcode project files.  We'll build for the current
OS only, by default.  

llvm-svn: 322603
2018-01-17 00:22:27 +00:00
Yan Zhang 8c298d2ff2 add ID as a special acronym to objc property declaration check for property names like bundleID.allow using acronyms as suffix.
Reviewers: benhamilton, hokein

Reviewed By: benhamilton

Subscribers: klimek, cfe-commits

Differential Revision: https://reviews.llvm.org/D42143

llvm-svn: 322602
2018-01-17 00:19:35 +00:00
Evgeniy Stepanov c07e0bd533 [hwasan] Rename sized load/store callbacks to be consistent with ASan.
Summary: __hwasan_load is now __hwasan_loadN.

Reviewers: kcc

Subscribers: hiraditya, llvm-commits

Differential Revision: https://reviews.llvm.org/D42138

llvm-svn: 322601
2018-01-16 23:15:08 +00:00
Simon Pilgrim a8e6b885bd [X86][BTVER2] Fix scheduling of VCMPSD/VCMPSS instructions
For some reason they don't have a trailing i like the packed equivalents.

llvm-svn: 322600
2018-01-16 22:15:41 +00:00
Florian Hahn c6c89bffdc [CallSiteSplitting] Pass list of (BB, Conditions) pairs to splitCallSite.
This removes some duplication from splitCallSite and makes it easier to
add additional code dealing with each predecessor. It also allows us to
split for more than 2 predecessors, although that is not enabled for
now.

Reviewers: junbuml, mcrosier, davidxl, davide

Reviewed By: junbuml

Differential Revision: https://reviews.llvm.org/D41858

llvm-svn: 322599
2018-01-16 22:13:15 +00:00
Simon Pilgrim 3c66e2c541 [X86][BTVER2] Use instrs instead of instregex for low match counts (PR35955)
llvm-svn: 322598
2018-01-16 22:08:43 +00:00
Simon Pilgrim e9a2832f32 [X86][BTVER2] Use instrs instead of instregex for single use matches (PR35955)
llvm-svn: 322597
2018-01-16 21:44:48 +00:00
Martin Storsjo 89e636c87c [PPC64] Added vector registers.
The Registers_ppc64 class needed a couple of changes, both to accommodate the
new registers as well as to handle the overlaps of VS register set
without wasting space.

The save/restore code of V and VS registers was added.
As VS registers depend on the VMX extension, they are processed only if
VMX support is detected (_ARCH_PWR8 for now).

Patch by Leandro Lupori!

Differential Revision: https://reviews.llvm.org/D41906

llvm-svn: 322596
2018-01-16 20:54:10 +00:00
Rui Ueyama af4ddd5a6e Specify inline for isWhitespace in CommandLine.cpp
Patch by Takuto Ikuta.

In chromium's component build, there are many directive sections and
commandline parsing takes much time.
This patch is for speed up of lld in RelWithDebInfo build by forcing
inline heavily called isWhitespace function.

10 times link perf stats of blink_core.dll changed like below.

master:
TotalSeconds: 9.8764878
TotalSeconds: 10.1455242
TotalSeconds: 10.075279
TotalSeconds: 10.3397347
TotalSeconds: 9.8361665
TotalSeconds: 9.9544441
TotalSeconds: 9.8960686
TotalSeconds: 9.8877865
TotalSeconds: 10.0551879
TotalSeconds: 10.0492254
Avg: 10.01159047

with this patch:
TotalSeconds: 8.8696762
TotalSeconds: 9.1021585
TotalSeconds: 9.0233893
TotalSeconds: 9.1886175
TotalSeconds: 9.156954
TotalSeconds: 9.0978564
TotalSeconds: 9.1316824
TotalSeconds: 8.8354606
TotalSeconds: 9.2549431
TotalSeconds: 9.4473085
Avg: 9.11080465

llvm-svn: 322595
2018-01-16 20:52:32 +00:00
Lang Hames 4a793c0667 [ExecutionEngine] Rename JITSymbol::isStrongDefinition to isStrong.
For symmetry with isWeak, isCommon.

llvm-svn: 322594
2018-01-16 20:39:51 +00:00
Richard Trieu cc64266f53 Add context to why test was disabled on Windows
test/Modules/odr_hash-Friend.cpp triggers an assertion in MicrosoftMangle.cpp
This has been reported in PR35939

llvm-svn: 322593
2018-01-16 19:53:06 +00:00
Erich Keane 0a6fde4895 Move target MV resolver to COMDAT
As reported here: https://bugs.llvm.org/show_bug.cgi?id=35921
The resolver functions should be in their own
COMDAT regions. This patch sets that up.

Differential Revision: https://reviews.llvm.org/D42110

llvm-svn: 322592
2018-01-16 19:49:52 +00:00
Guozhi Wei e6fb4e1f8a [PPC] Add a new register XER aliased to CARRY
When "xer" is specified as clobbered register in inline assembler, clang can accept it, but llvm simply ignore it when lowered to machine instructions. It may cause problems later in scheduler.

This patch adds a new register XER aliased to CARRY, and adds it to register class CARRYRC. Now PPCTargetLowering::getRegForInlineAsmConstraint can return correct register number for inline asm constraint "{xer}", and scheduler behave correctly.

Differential Revision: https://reviews.llvm.org/D41967

llvm-svn: 322591
2018-01-16 19:28:50 +00:00
Rafael Espindola 62003fbb02 Inline foot gun into only valid use.
Symbol had both Visibility and getVisibility() and they had different
meanings. That is just too easy to get wrong.

getVisibility() would compute the visibility of a particular symbol
(foo in bar.o), and Visibility stores the computed value we will put
in the output.

There is only one case when we want what getVisibility() provides, so
inline it.

llvm-svn: 322590
2018-01-16 19:28:28 +00:00
Alexey Bataev 9675302866 [DOCS] Updated current status of OpenMP support, NFC.
llvm-svn: 322589
2018-01-16 19:22:49 +00:00
Evgeniy Stepanov d96b06f2c2 [hwasan] Build runtime library with -fPIC, not -fPIE.
Summary: -fPIE can not be used when building a shared library.

Reviewers: alekseyshl, peter.smith

Subscribers: kubamracek, llvm-commits, mgorny

Differential Revision: https://reviews.llvm.org/D42121

llvm-svn: 322588
2018-01-16 19:21:45 +00:00
Alexey Bataev 9350fc3987 [OPENMP] Add support for `depend` clauses on `target teams distribute
parallel for simd` directives.

Added codegen for `depend` clauses on `#pragma omp target teams
distribute parallel for simd` directives.

llvm-svn: 322587
2018-01-16 19:18:24 +00:00
Rafael Espindola 7e6aeb614c Fix another case we used the wrong visibility.
In here too we want the computed output visibility.

llvm-svn: 322586
2018-01-16 19:02:46 +00:00
Alexey Bataev 9f9fb0ba35 [OPENMP] Add support for `depend` on `target teams distribute parallel
for` directives.

Added codegen for `depend` clauses on `#pragma omp target teams
distribute parallel for` directives.

llvm-svn: 322585
2018-01-16 19:02:33 +00:00
Francis Visoiu Mistrih 54a9e7a400 [CodeGen] Skip some instructions that shouldn't affect shrink-wrapping
r320606 checked for MI.isMetaInstruction which skips all DBG_VALUEs.

This also skips IMPLICIT_DEFs and other instructions that may def / read
a register.

Differential Revision: https://reviews.llvm.org/D42119

llvm-svn: 322584
2018-01-16 18:55:26 +00:00
Rafael Espindola d3ec3e5684 Add an extra test. NFC.
Without this all test would pass if the visibility checks were removed
from SymbolTable::addShared and SymbolTable::addUndefined.

llvm-svn: 322583
2018-01-16 18:53:09 +00:00
Volkan Keles f7f2568613 [GlobalISel][TableGen] Add support for SDNodeXForm
Summary:
This patch adds CustomRenderer which renders the matched
operands to the specified instruction.

Targets can enable the matching of SDNodeXForm by adding
a definition that inherits from GICustomOperandRenderer and
GISDNodeXFormEquiv as follows.

def gi_imm8 : GICustomOperandRenderer<"renderImm8”>,
                       GISDNodeXFormEquiv<imm8_xform>;

Custom renderer functions should be of the form:
void render(MachineInstrBuilder &MIB, const MachineInstr &I);

Reviewers: dsanders, ab, rovka

Reviewed By: dsanders

Subscribers: kristof.beyls, javed.absar, llvm-commits, mgrang, qcolombet

Differential Revision: https://reviews.llvm.org/D42012

llvm-svn: 322582
2018-01-16 18:44:05 +00:00
Michael Kruse a0db63a195 [IslTools] dumpPw: Dump same structure pieces together.
Print same or similar structure elements together. Previously, the
value could take more importance that the space structure if visited
first in the space nest tree.

Before:
{
  Left[0] -> Right[i]: i >= 0;
  Left[1] -> AnotherRight[i];
  Left[2] -> Right[-1]
}

After:
{
  Left[0] -> Right[i]: i >= 0;
  Left[2] -> Right[-1];
  Left[1] -> AnotherRight[i]
}

llvm-svn: 322581
2018-01-16 18:39:42 +00:00
Rafael Espindola 3c3544652b Fix another case we were using the wrong visibility.
llvm-svn: 322580
2018-01-16 18:21:23 +00:00
Alexey Bataev 6977dbcc7b [SLP] Fix for PR32164: Improve vectorization of reverse order of extract operations.
Summary: Sometimes vectorization of insertelement instructions with extractelement operands may produce an extra shuffle operation, if these operands are in the reverse order. Patch tries to improve this situation by the reordering of the operands to remove this extra shuffle operation.

Reviewers: mkuper, hfinkel, RKSimon, spatel

Subscribers: mzolotukhin, llvm-commits

Differential Revision: https://reviews.llvm.org/D33954

llvm-svn: 322579
2018-01-16 18:17:01 +00:00
Alexey Bataev d60d1baadb [OPENMP] Add support for `depend` clauses on `target parallel for simd`
directives.

Added codegen for `depend` clauses on `#pragma omp target parallel for
simd` directives.

llvm-svn: 322578
2018-01-16 17:55:15 +00:00
Alexey Bataev 8ed89551e2 [OPENMP] Add support for `depend` clauses on `target parallel for`
directives.

Added codegen for `depend` clause on `#pragma omp target parallel for`
directives.

llvm-svn: 322577
2018-01-16 17:41:04 +00:00
Rafael Espindola 37e4e695e9 Use the combined visibility when computing dso_local.
We track both the combined visibility that will be used for the output
symbol and the original input visibility of the selected symbol.

Almost everything should use the computed visibility.

I will make the names less confusing an a followup patch.

llvm-svn: 322576
2018-01-16 17:34:26 +00:00
Alexey Bataev 8d16a43416 [OPENMP] Add support for `depend` clauses on `target teams distribute
simd` directives.

Added codegen for `depend` clauses on `#pragma omp target teams
distribute simd` directives.

llvm-svn: 322575
2018-01-16 17:22:50 +00:00
Simon Pilgrim 3e0aafbfcc [X86][MMX] Accept UNDEF upper bits for MOVD GR32->MMX
llvm-svn: 322574
2018-01-16 17:01:31 +00:00
Nico Weber dab736f16d Add va_start()/va_copy()/va_end to Builtins.def
That way, clang suggests including stdarg.h when these are used in C files.
https://reviews.llvm.org/D42085

llvm-svn: 322573
2018-01-16 16:55:41 +00:00
Rafael Espindola c6df38c985 Set dso_local in lld.
We were already doing this in gold, but not in lld.

llvm-svn: 322572
2018-01-16 16:49:05 +00:00
Alexey Bataev 79df756d1f [OPENMP] Add support for `depend` clause on `target teams distribute`.
Added codegen for `depend` clauses on `#pragma omp target teams
distribute` directives.

llvm-svn: 322571
2018-01-16 16:46:46 +00:00
Alexey Bataev 54d5c7dc44 [OPENMP] Add support for `depend` clauses on `target parallel` directive.
Added codegen for `depend` clauses on `#pragma omp target parallel`
directives.

llvm-svn: 322570
2018-01-16 16:27:49 +00:00
Alexey Bataev 0c869ef21c [OPENMP] Add support for `depend` clauses on `target teams`.
Added codegen for `depend` clause on `#pragma omp target teams`
directives.

llvm-svn: 322569
2018-01-16 15:57:07 +00:00
Petar Jovanovic 76d619b509 [LiveDebugValues] update kill-after-spill test with target triple
Set target triple to "x86_64-unknown-linux-gnu".

llvm-svn: 322568
2018-01-16 15:57:03 +00:00
Marshall Clow 12f0a77902 More constexpr algorithms from P0202. search/search_n
llvm-svn: 322566
2018-01-16 15:48:27 +00:00
Ulrich Weigand e1d2d22d2a [SystemZ] Support vector registers with inline asm
Allow using vector register names and the "v" constraint
in inline asm to ensure compatibility with GCC.

llvm-svn: 322562
2018-01-16 15:39:23 +00:00
Alexey Bataev f41c88fd50 [OPENMP] Add support for `depend` clauses on `target simd`.
Added codegen for `depend` clauses on `#pragma omp target simd`
directives.

llvm-svn: 322559
2018-01-16 15:05:16 +00:00
Marshall Clow a58bdf9f69 Change an internal table of constants for the poisson distribution from
type 'result_type' to 'double'. The only thing that we ever do with
these numbers is to promote them to 'double' and use them in a division.
For small result_types, the values were getting truncated, skewing the
results. Thanks to James Nagurne for the suggestion.

llvm-svn: 322556
2018-01-16 14:54:36 +00:00
Petar Jovanovic 0b464e4f0e [LiveDebugValues] recognize spilled reg killed in instruction after spill
Current condition for spill instruction recognition in LiveDebugValues does
not recognize case when register is spilled and killed in next instruction.

Patch by Nikola Prica.

Differential Revision: https://reviews.llvm.org/D41226

llvm-svn: 322554
2018-01-16 14:46:05 +00:00
Simon Pilgrim 85e6139633 [X86][MMX] Improve MMX constant generation
Extend the MMX zero code to take any constant with zero'd upper 32-bits

llvm-svn: 322553
2018-01-16 14:21:28 +00:00