LowerSELECT sees the CMP with 0 and wants to use a trick with SUB
and SBB. But we can use the flags from the BSF/TZCNT.

Fixes PR46203.

Differential Revision: https://reviews.llvm.org/D81312

Fixes a minor bug that led to finding the wrong register if the definition had more
than one register destination.

Similar to rG42f488b63a04

This is intended to preserve the logic of the existing transform,
but remove unnecessary restrictions on uses and types.

https://rise4fun.com/Alive/oS0

  Name: narrow input
  Pre: C1 <= width(C1) - 24
  %B = sext i8 %A
  %C = lshr %B, C1
  %r = trunc %C to i24
  =>
  %s = ashr i8 %A, trunc(umin(C1, 7))
  %r = sext i8 %s to i24

  Name: wide input
  Pre: C1 <= width(C1) - 24
  %B = sext i24 %A
  %C = lshr %B, C1
  %r = trunc %C to i8
  =>
  %s = ashr i24 %A, trunc(umin(C1, 23))
  %r = trunc i24 %s to i8

Shows missing transforms with extra uses and vectors.

Reviewers: efriedma, kmclaughlin, sdesmalen, MaskRay, JDevlieghere

Reviewed By: sdesmalen

Subscribers: tschuett, rkruppe, psnobl, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D81201

- Now all SalvageDebugInfo() calls will mark undef if the salvage
  attempt fails.

 Reviewed by: vsk, Orlando

 Differential Revision: https://reviews.llvm.org/D78369

__sptr is a keyword for ms-extension. Change it from __sptr to __sinptr.

Use the default target triple configured by the user to determine the
default architecture for `ld64.lld`.  Stash the architecture in the
configuration as when linking against TBDs, we will need to filter out
the symbols based upon the architecture.  Treat the Haswell slice as it
is equivalent to `x86_64` but with the extra Haswell extensions (e.g.
AVX2, FMA3, BMI1, etc).  This will make it easier to add new
architectures in the future.

This change also changes the failure mode where an invalid `-arch`
parameter will result in the linker exiting without further processing.

This patch adds a test to check that we do not use an undef renamable
register for renaming the other operand in a LDP instruction, as
suggested in D81108.

We sometimes have functions with large numbers of sibling basic
blocks (usually with an error path exit from each one). This was
triggering the qudratic behavior in this function - after visiting
each child llvm would re-scan the parent from the beginning again. We
modify the work stack to record the next index to be worked on
alongside the pointer. This avoids the need to linearly search for
the next unfinished child.

Differential Revision: https://reviews.llvm.org/D80029

Reviewers: efriedma, c-rhodes, david-arm, spatel, craig.topper, aqjune, paquette, arsenm, gchatelet

Reviewed By: spatel, gchatelet

Subscribers: wdng, tschuett, hiraditya, rkruppe, psnobl, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D80313

Summary: Following up D78949.

Reviewers: davidxl

Subscribers: hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D81020

All compilers supported by libc++ have rvalues in C++03 mode so, there is no need for this non-rvalue overload.

Differential Revision: https://reviews.llvm.org/D80881

Replace the DisableColors with a ColorMode which can be set to Auto,
Enabled and Disabled. The purpose of this change is to make it possible
to ignore the command line option not only for disabling colors, but
also for enabling them.

Differential revision: https://reviews.llvm.org/D81056

The update_*test_checks scripts miss new stuff added at the end of
lines. Regenerate checks so the new mode register operands don't show
up in the diff of a future patch.

Summary:
Exempt ObjC from arrow/dot fixits since this has limited value for
Objective-C, where properties (referenced by dot syntax) are normally
backed by ivars (referenced by arrow syntax).

In addition, the current implementation doesn't properly mark
the fix it condition for Objective-C.

This was initially added in https://reviews.llvm.org/D41537
for C++ and then later C, don't believe the Objective-C changes
were intentional.

Reviewers: sammccall, yvvan

Subscribers: jfb, cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D81263

With a fix to use -triple %itanium_abi_triple

Differential Revision: https://reviews.llvm.org/D80979

This commit updates the 'CLion Integration' section in ClangFormat docs.
Key changes:
- clang-format is enabled automatically when there is a config file;
- formatting now works for indentations;
- if clang-format is enabled without a config file, CLion suggests creating it based on the IDE settings or uses the LLVM style by default.

Patch by Marina Kalashina!

Reviewers: sylvestre.ledru, ilya-biryukov

Reviewed By: ilya-biryukov

Subscribers: ilya-biryukov, klimek, MyDeveloperDay, sammccall, gribozavr2

Differential Revision: https://reviews.llvm.org/D80721

Move the color handling code from raw_fd_ostream to raw_ostream. This
makes it possible to use colors with any ostream when enabled. The
existing behavior where only raw_fd_ostream supports colors by default
remains unchanged.

Differential revision: https://reviews.llvm.org/D81110

This is intended to preserve the logic of the existing transform,
but remove unnecessary restrictions on uses and types.

https://rise4fun.com/Alive/pYfR

  Pre: C1 <= width(C1) - 8
  %B = sext i8 %A
  %C = lshr %B, C1
  %r = trunc %C to i8
   =>
  %r = ashr i8 %A, trunc(umin(C1, 7))

This bit was assumed to be always false for ParmVarDecls, but attribute
objc_externally_retained now can produce it.

Differential revision: https://reviews.llvm.org/D74417

Differential Revision: https://reviews.llvm.org/D81344

Summary:
crash stack:

```
llvm-project/clang/lib/AST/ASTContext.cpp:2248: clang::TypeInfo clang::ASTContext::getTypeInfoImpl(const clang::Type *) const: Assertion `!A->getDeducedType().isNull() && "cannot request the size of an undeduced or dependent auto type"' failed.
PLEASE submit a bug report to https://bugs.llvm.org/ and include the crash backtrace, preprocessed source, and associated run script.
Stack dump:
 #0 0x00000000025bb0bf llvm::sys::PrintStackTrace(llvm::raw_ostream&) llvm-project/llvm/lib/Support/Unix/Signals.inc:564:13
 #1 0x00000000025b92b0 llvm::sys::RunSignalHandlers() llvm-project/llvm/lib/Support/Signals.cpp:69:18
 #2 0x00000000025bb535 SignalHandler(int) llvm-project/llvm/lib/Support/Unix/Signals.inc:396:3
 #3 0x00007f9ef9298110 __restore_rt (/lib/x86_64-linux-gnu/libpthread.so.0+0x14110)
 #4 0x00007f9ef8d72761 raise /build/glibc-M65Gwz/glibc-2.30/signal/../sysdeps/unix/sysv/linux/raise.c:51:1
 #5 0x00007f9ef8d5c55b abort /build/glibc-M65Gwz/glibc-2.30/stdlib/abort.c:81:7
 #6 0x00007f9ef8d5c42f get_sysdep_segment_value /build/glibc-M65Gwz/glibc-2.30/intl/loadmsgcat.c:509:8
 #7 0x00007f9ef8d5c42f _nl_load_domain /build/glibc-M65Gwz/glibc-2.30/intl/loadmsgcat.c:970:34
 #8 0x00007f9ef8d6b092 (/lib/x86_64-linux-gnu/libc.so.6+0x34092)
 #9 0x000000000458abe0 clang::ASTContext::getTypeInfoImpl(clang::Type const*) const llvm-project/clang/lib/AST/ASTContext.cpp:0:5
```

Reviewers: sammccall

Subscribers: cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D81384

Summary:
This fixes a reported bug: if clang and libc++ are installed under
/usr/lib/llvm-11/...  but there'- a symlink /usr/bin/clang++-11, then a
compile_commands.json with "/usr/bin/clang++-11 -stdlib=libc++" would previously
look for libc++ under /usr/include instead of /usr/lib/llvm-11/include.
The PATH change makes this work if the compiler is just "clang++-11" too.

As this is now doing IO potentially on every getCompileCommand(), we cache
the results for each distinct driver.

While here:
- Added a Memoize helper for this as multithreaded caching is a bit noisy.
- Used this helper to simplify QueryDriverDatabase and reduce blocking there.
  (This makes use of the fact that llvm::Regex is now threadsafe)

Reviewers: kadircet

Subscribers: jyknight, ormris, ilya-biryukov, MaskRay, jkorous, arphaman, jfb, usaxena95, cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D75414

Shows missing transforms with extra uses and vectors.

Summary:
The macro `INSTANTIATE_TEST_CASE_P` is defined as
```
\# define INSTANTIATE_TEST_CASE_P(prefix, test_case_name, generator, ...) \
...
```

If we build the test case with -werror, we will get an error like
```
error: ISO C++11 requires at least one argument for the "..." in a
variadic macro

testing::ValuesIn(TestClangConfig::allConfigs()));
                                                ^
```
This patch fixes that.

Reviewers: gribozavr, hlopko, eduucaldas, gribozavr2

Reviewed By: gribozavr2

Subscribers: cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D81388

Summary:
When getting a warning that we release a capability that isn't held it's
sometimes not clear why. So just like we do for double locking, we add a
note on the previous release operation, which marks the point since when
the capability isn't held any longer.

We can find this previous release operation by looking up the
corresponding negative capability.

Reviewers: aaron.ballman, delesley

Reviewed By: aaron.ballman

Differential Revision: https://reviews.llvm.org/D81352

Summary:
The standard std::unique_lock can be constructed to manage a lock without
initially acquiring it by passing std::defer_lock as second parameter.
It can be acquired later by calling lock().

To support this, we use the locks_excluded attribute. This might seem
like an odd choice at first, but its consistent with the other
annotations we support on scoped capability constructors. By excluding
the lock we state that it is currently not in use and the function
doesn't change that, which is exactly what the constructor does.

Along the way we slightly simplify handling of scoped capabilities.

Reviewers: aaron.ballman, delesley

Reviewed By: aaron.ballman

Differential Revision: https://reviews.llvm.org/D81332

Removing the include was probably just forgotten after
f13ba222.

Summary: This is a followup on D81196.

Reviewers: courbet

Subscribers: hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D81362

With the race_debug_openbsd_amd64.syso file created via this diff,
Go's race detector is able to detect a race in the example code
from this link: https://golang.org/doc/articles/race_detector.html

Reviewed-in: https://reviews.llvm.org/D80469
Author: qbit (Aaron Bieber)

This patch intends to be an NFC-patch. Test cases will be added in a follow-up patch.

Reviewed By: jhenderson, grimar

Differential Revision: https://reviews.llvm.org/D81356

Summary:
The only difference is that LLVM_ENABLE_WERROR is set to OFF
by default, but we enable this in a standalone flang build

This commit fixes some windows issues with the flags

Reviewers: DavidTruby, jdoerfert, sscalpone

Reviewed By: DavidTruby, sscalpone

Subscribers: ormris, richard.barton.arm, mehdi_amini, Meinersbur, ChinouneMehdi, tskeith, mgorny, llvm-commits

Tags: #llvm, #flang

Differential Revision: https://reviews.llvm.org/D78306

Adding type checks into the other backends that call
getTypeLegalizationCost.

Differential Revision: https://reviews.llvm.org/D80984

These have very few users to begin with, and have been marked
deprecated for 2 months which should be long enough for out of tree
targets.

When the input to a wide compare instruction is a DUP or SPLAT_VECTOR
node we should deal with cases where the DUP/SPLAT_VECTOR input
operand is not an immediate value. I've fixed the code to return
SDValue() in such cases and added a couple of tests - one each to
represent the signed and unsigned cases.

Differential Revision: https://reviews.llvm.org/D81167