Convert subtensor and subtensor_insert operations to use their
rank-reduced versions to drop unit dimensions.

Differential Revision: https://reviews.llvm.org/D101495

Add function to create the offload_maptypes and the offload_mapnames globals. These two functions
are used in clang. They will be used in the Flang/MLIR lowering as well.

Reviewed By: Meinersbur

Differential Revision: https://reviews.llvm.org/D101503

atomicrmw instructions are expanded by AtomicExpandPass before register allocation
into cmpxchg loops. Register allocation can insert spills between the exclusive loads
and stores, which invalidates the exclusive monitor and can lead to infinite loops.

To avoid this, reimplement atomicrmw operations as pseudo-instructions and expand them
after register allocation.

Floating point legalisation:
f16 ATOMIC_LOAD_FADD(*f16, f16) is legalised to
f32 ATOMIC_LOAD_FADD(*i16, f32) and then eventually
f32 ATOMIC_LOAD_FADD_16(*i16, f32)

Differential Revision: https://reviews.llvm.org/D101164

Originally submitted as 3338290c.
Reverted in c7df6b12.

The current implementation had a bug as it was relying on the target vector
dimension sizes to calculate where to insert broadcast. If several dimensions
have the same size we may insert the broadcast on the wrong dimension. The
correct broadcast cannot be inferred from the type of the source and
destination vector.

Instead when we want to extend transfer ops we calculate an "inverse" map to the
projected permutation and insert broadcast in place of the projected dimensions.

Differential Revision: https://reviews.llvm.org/D101738

Differential Revision: https://reviews.llvm.org/D101771

Add dedicated pass `convert-linalg-tiled-loops-to-scf` to lower
`linalg.tiled_loop`s.

Differential Revision: https://reviews.llvm.org/D101768

[AsmParser][SystemZ][z/OS] Implement HLASM location counter syntax ("*") for Z PC-relative instructions.

- This patch attempts to implement the location counter syntax (*) for the HLASM variant for PC-relative instructions.
- In the HLASM variant, for purely constant relocatable values, we expect a * token preceding it, with special support for " *" which is parsed as "<pc-rel-insn 0>"
- For combinations of absolute values and relocatable values, we don't expect the "*" preceding the token.

When you have a " * "  what’s accepted is:

```
*<space>.*{.*} -> <pc-rel-insn> 0
*[+|-][constant-value] -> <pc-rel-insn> [+|-]constant-value
```

When you don’t have a " * " what’s accepted is:

```
brasl  1,func           is allowed (MCSymbolRef type)
brasl  1,func+4         is allowed (MCBinary type)
brasl  1,4+func         is allowed (MCBinary type)
brasl  1,-4+func        is allowed (MCBinary type)
brasl  1,func-4         is allowed (MCBinary type)
brasl  1,*func          is not allowed (* cannot be used for non-MCConstantExprs)
brasl  1,*+func         is not allowed (* cannot be used for non-MCConstantExprs)
brasl  1,*+func+4       is not allowed (* cannot be used for non-MCConstantExprs)
brasl  1,*+4+func       is not allowed (* cannot be used for non-MCConstantExprs)
brasl  1,*-4+8+func     is not allowed (* cannot be used for non-MCConstantExprs)
```

Reviewed By: Kai

Differential Revision: https://reviews.llvm.org/D100987

The Scudo C unit tests are currently non-hermetic. In particular, adding
or removing a transfer batch is a global state of the allocator that
persists between tests. This can cause flakiness in
ScudoWrappersCTest.MallInfo, because the creation or teardown of a batch
causes mallinfo's uordblks or fordblks to move up or down by the size of
a transfer batch on malloc/free.

It's my opinion that uordblks and fordblks should track the statistics
related to the user's malloc() and free() usage, and not the state of
the internal allocator structures. Thus, excluding the transfer batches
from stat collection does the trick and makes these tests pass.

Repro instructions of the bug:
 1. ninja ./projects/compiler-rt/lib/scudo/standalone/tests/ScudoCUnitTest-x86_64-Test
 2. ./projects/compiler-rt/lib/scudo/standalone/tests/ScudoCUnitTest-x86_64-Test --gtest_filter=ScudoWrappersCTest.MallInfo

Reviewed By: cryptoad

Differential Revision: https://reviews.llvm.org/D101653

This makes the libc++ tests more portable -- almost all of them should
now work on Windows, except for some tests that assume a shell is
available on the target. We should probably provide a way to exclude
those anyway for the purpose of running tests on embedded targets.

Differential Revision: https://reviews.llvm.org/D89495

This fixes the issue by implementing _And using the short-circuiting
SFINAE trick that we previously used only in std::tuple. One thing we
could look into is use the naive recursive implementation for disjunctions
with a small number of arguments, and use that trick with larger numbers
of arguments. It might be the case that the constant overhead for setting
up the SFINAE trick makes it only worth doing for larger packs, but that's
left for further work.

This problem was raised in https://reviews.llvm.org/D96523.

Differential Revision: https://reviews.llvm.org/D101661

* NFC but has some fixes for CMake glitches discovered along the way (things not cleaning properly, co-mingled depends).
* Includes previously unsubmitted fix in D98681 and a TODO to fix it more appropriately in a smaller followup.

Differential Revision: https://reviews.llvm.org/D101493

This patch gets rid of technical debt around std::pointer_safety which,
I claim, is entirely unnecessary. I don't think anybody has used
std::pointer_safety in actual code because we do not implement the
underlying garbage collection support. In fact, P2186 even proposes
removing these facilities entirely from a future C++ version. As such,
I think it's entirely fine to get rid of complex workarounds whose goals
were to avoid breaking the ABI back in 2017.

I'm putting this up both to get reviews and to discuss this proposal for
a breaking change. I think we should be comfortable with making these
tiny breaks if we are confident they won't hurt anyone, which I'm fairly
confident is the case here.

Differential Revision: https://reviews.llvm.org/D100410

The comment about how to make use of debugger tuning within DwarfDebug
really belongs inside the DwarfDebug declaration, where it will be
easier to find.

Differential Revision: https://reviews.llvm.org/D101511

Extend the legalization of global SADDR loads and stores
with changing to VADDR to the FLAT scratch instructions.

Differential Revision: https://reviews.llvm.org/D101408

The previous implementation of the default AltiVec ABI marked registers V20-V31
as reserved.  This failed to prevent reserved VFRC registers being allocated.
In this patch instead of marking the registers reserved we remove unallowed
registers from the allocation order completely.

This is a slight rework of an implementation by @nemanjai

Reviewed By: jsji

Differential Revision: https://reviews.llvm.org/D100050

Remove an early return from an `else` block that's immediately followed
by an equivalent early return after the `else` block.

Differential Revision: https://reviews.llvm.org/D101671

Differential Revision: https://reviews.llvm.org/D101637

Differential Revision: https://reviews.llvm.org/D101643

In the overwrite branch of MutationDispatcher::ApplyDictionaryEntry in
FuzzerMutate.cpp, the index Idx at which W.size() bytes are overwritten
with the word W is chosen uniformly at random in the interval
[0, Size - W.size()). This means that Idx + W.size() will always be
strictly less than Size, i.e., the last byte of the current unit will
never be overwritten.

This is fixed by adding 1 to the exclusive upper bound.

Addresses https://bugs.llvm.org/show_bug.cgi?id=49989.

Reviewed By: morehouse

Differential Revision: https://reviews.llvm.org/D101625

Instead of legalizing saddr operand with a readfirstlane
when address is moved from SGPR to VGPR we can just
change the opcode.

Differential Revision: https://reviews.llvm.org/D101405

Reviewed By: jdoerfert

Differential Revision: https://reviews.llvm.org/D101739

The converter assumed that all operands have the same type, that's not
true for select.

Differential Revision: https://reviews.llvm.org/D101767

Move TransposeOp lowering in its own populate function as in some cases
it is better to keep it during ContractOp lowering to better
canonicalize it rather than emiting scalar insert/extract.

Differential Revision: https://reviews.llvm.org/D101647

Reviewed By: asbirlea, ychen

Differential Revision: https://reviews.llvm.org/D100912

Add missing check in -test-affine-data-copy without which a test case
that has no affine.loads at all would crash this test pass. Fix two
clang-tidy warnings in the file while at this. (Not adding a test case
given the triviality.)

Differential Revision: https://reviews.llvm.org/D101719

* This makes them consistent with custom types/attributes, whose constructors will do a type checked conversion. Of course, the base classes can represent everything so never error.
* More importantly, this makes it possible to subclass Type and Attribute out of tree in sensible ways.

Differential Revision: https://reviews.llvm.org/D101734

This avoids the non-trivial overhead of creating a TaskGroup in these degenerate
cases, but also exposes parallelism.  It turns out that the default executor
underlying TaskGroup prevents recursive parallelism - so an instance of a task
group being alive will make nested ones become serial.

This is a big issue in MLIR in some dialects, if they have a single instance of
an outer op (e.g. a firrtl.circuit) that has many parallel ops within it (e.g.
a firrtl.module).  This patch side-steps the problem by avoiding creating the
TaskGroup in the unneeded case.  See this issue for more details:
https://github.com/llvm/circt/issues/993

Note that this isn't a really great solution for the general case of nested
parallelism.  A redesign of the TaskGroup stuff would be better, but would be
a much more invasive change.

Differential Revision: https://reviews.llvm.org/D101699

This fixes another bogus build error on gcc, e.g. https://lab.llvm.org/buildbot/#/builders/118/builds/2504.

/home/ssglocal/clang-cmake-x86_64-avx2-linux/clang-cmake-x86_64-avx2-linux-perf/llvm/clang/lib/Format/UnwrappedLineFormatter.cpp:424:42: error: binding ‘clang::format::FormatToken* const’ to reference of type ‘clang::format::FormatToken*&’ discards qualifiers
     auto IsElseLine = [&First = TheLine->First]() -> bool {
                                          ^

Differential Revision: https://reviews.llvm.org/D101747

This can come up in rare situations, where a csel is created with
identical operands. These can be folded simply to the original value,
allowing the csel to be removed and further simplification to happen.

This patch also removes FCSEL as it is unused, not being produced
anywhere or lowered to anything.

Differential Revision: https://reviews.llvm.org/D101687

This fixes the bug http://llvm.org/pr50019.

Reviewed By: MyDeveloperDay

Differential Revision: https://reviews.llvm.org/D100727

Fix PR50111

Differential Revision: https://reviews.llvm.org/D101698

Differential Revision: https://reviews.llvm.org/D101705

- Previously, https://reviews.llvm.org/D101308 removed prefixes from register while printing them out. This was especially needed for inline asm statements which used input/output operands.
- However, the backend SystemZAsmParser, accepts both prefixed registers and prefix-less registers as part of its implementation
- This patch aims to change that by ensuring that prefixed registers are only allowed for the ATT dialect.

Reviewed By: uweigand

Differential Revision: https://reviews.llvm.org/D101665