[X86] Add helper function to reduce some code duplication when shrinking a vector load to a vzext_load.

There's more code for calling CombineTo and replacing the nodes
that I'd like to share, but its complicated by the getNode call
in the middle that needs to be specific to each opcode.

While there are also make sure we recursively delete the load
we're replacing. It eventually gets removed by a RemoveDeadNodes
call at the end of DAG combine, but we should be more eager about
it. We were inconsistently doing this in some places but not all.

Summary:
This patch implements dynamic stack allocation for the VE target. Changes:
* compiler-rt: `__ve_grow_stack` to request stack allocation on the VE.
* VE: base pointer support, dynamic stack allocation.

Differential Revision: https://reviews.llvm.org/D79084

Summary:
Allow AMDGCN as a GPU offloading target for OpenMP during compiler
invocation and allow setting CUDAMode for it.

Originally authored by Greg Rodgers (@gregrodgers).

Reviewers: ronlieb, yaxunl, b-sumner, scchan, JonChesterfield, jdoerfert, sameerds, msearles, hliao, arsenm

Reviewed By: sameerds

Subscribers: sstefan1, jvesely, wdng, arsenm, guansong, dexonsmith, cfe-commits, llvm-commits, gregrodgers

Tags: #clang, #llvm

Differential Revision: https://reviews.llvm.org/D79754

This is more friendly than the "Unknown CMake command “mlir_tablegen”."
that would be issued instead.

Differential Revision: https://reviews.llvm.org/D80359

And bump its version number accordingly.

This is a patched recommit of 7c298c10

Previous hash implementation was incorrectly passing an uint64_t, that got converted
to an uint8_t, to finalize the hash computation. This led to different functions
having the same hash if they only differ by the remaining statements, which is
incorrect.

Added a new test case that trivially tests that a small function change is
reflected in the hash value.

Not that as this patch fixes the hash computation, it would invalidate all hashes
computed before that patch applies, this is why we bumped the version number.

Update profile data hash entries due to hash function update, except for binary
version, in which case we keep the buggy behavior for backward compatibility.

Differential Revision: https://reviews.llvm.org/D79961

Isel match that instead of the intrinsic. Similar to what we do
for avx512.

Trying to move more intrinsics to target specific ISD opcodes.
Hoping to add DAG combines to shrink simple loads going into
scalar intrinsics that only read 32 or 64 bits.

Summary:
Some instruction like VPMULDQ is NOT the variant of VPMULD but a new
one.
So we should make sure the suffix matcher only works for memory variant
that has the same size with the suffix.
Currently we only check for SSE/AVX* instructions, because many legacy
instructions didn't declare the alias instructions of their variants.

Differential Revision: https://reviews.llvm.org/D80608

IE throws errors while using key and mouse navigation through the error path tips.
querySelectorAll method returns NodeList. NodeList belongs to browser API. IE doesn't have forEach among NodeList's methods. At the same time Array is a JavaScript object and can be used instead. The fix is in the converting NodeList into Array and keeps using forEach method as before.

Checked in IE11, Chrome and Opera.

Differential Revision: https://reviews.llvm.org/D80444

This was suggested in https://reviews.llvm.org/D79149.

alloc/dealloc/copies.

Add options to LinalgPromotion to use callbacks for implementating the
allocation, deallocation of buffers used for the promoted subviews,
and to copy data into and from the original subviews to the allocated
buffers.
Also some misc. cleanup of the code.

Differential Revision: https://reviews.llvm.org/D80365

Modifying the loop nest builder for generating scf.parallel loops to
not generate scf.parallel loops for non-parallel iterator types in
Linalg operations. The existing implementation incorrectly generated
scf.parallel for all tiled loops. It is rectified by refactoring logic
used while lowering to loops that accounted for this.

Differential Revision: https://reviews.llvm.org/D80188

A few testcases are still using deprecated options.

warning: argument '-fsanitize-coverage=[func|bb|edge]' is deprecated,
use '-fsanitize-coverage=[func|bb|edge],[trace-pc-guard|trace-pc]'
instead [-Wdeprecated]

Reviewed By: vitalybuka

Differential Revision: https://reviews.llvm.org/D79741

as it's causing crashes on code generation and https://bugs.llvm.org/show_bug.cgi?id=46084

This reverts commit 98cad555.

Mirror the note on G_LOAD. We probably do need to add an explicit
G_TRUNCSTORE opcode for the vector case, although I do not have a use
for it.

Probably NFC.

Remove const from some parameters as upcoming changes in ScalarEvolution
calls will need non const pointers.

This fixes a bug in `tryOptArithImmedIntegerCompare`.

It is unsafe to update the predicate on a MachineOperand when optimizing a
G_ICMP, because it may be used in more than one place.

For example, when we are optimizing G_SELECT, we allow compares which are used
in more than one G_SELECT. If we modify the G_ICMP, then we'll break one of
the G_SELECTs.

Since the compare is being produced to either

1) Select a G_ICMP
2) Fold a G_ICMP into an instruction when profitable

there's no reason to actually modify it. The change is local to the specific
compare.

Instead, pass a `CmpInst::Predicate` to `tryOptArithImmedIntegerCompare` which
can be modified by reference.

Differential Revision: https://reviews.llvm.org/D80585

This was discussed on llvm-dev thread "Transferring code ownership for SCEV and IndVars" a few months back.  I just forgot to make the actual change.

This used to be part of the man page but got lost when we moved to
generating it with Sphinx.

Summary:
Objective-C names are stored in m_demangled, not in m_mangled. The
method in the condition will never return true.

Differential Revision: https://reviews.llvm.org/D79823

Work around global module caching during reproducer replay. See inline
comment for the details.

Summary:
This op extracts an extent from a shape.

This also is the first op which constant folds to shape.const_size,
which revealed that shape.const_size needs a folder (ConstantLike ops
seem to always need folders for the constant folding infra to work).

Differential Revision: https://reviews.llvm.org/D80394

cctools strip has the option "-T" which removes Swift symbols.
This diff implements this option in llvm-strip for MachO.

Test plan: make check-all

Differential revision: https://reviews.llvm.org/D80099

Summary:
preallocated and musttail can work together, but we don't want to call
@llvm.call.preallocated.setup() to modify the stack in musttail calls.
So we shouldn't have the "preallocated" operand bundle when a
preallocated call is musttail.

Also disallow use of preallocated on calls without preallocated.

Codegen not yet implemented.

Subscribers: hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D80581

Summary:
Based on comments received in D80415 pertinent to test case format, the following fixes are provided to other tests in 'aix-ld.c' for the sake of consistency and readability,
  - Align flags in RUN directives vertically.
  - Align patterns in CHECK directives vertically.
  - Remove the ‘-o %t.o’ as it’s unnecessary for tests with ‘-###’.
  - Fix typos in comments.

Reviewers: ZarkoCA, hubert.reinterpretcast, daltenty

Reviewed By: hubert.reinterpretcast

Subscribers: cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D80532

If you remember the mail [1] I sent out about how I envision the future of the
already existing checkers to look dependencywise, one my main points was that no
checker that emits diagnostics should be a dependency. This is more problematic
for some checkers (ahem, RetainCount [2]) more than for others, like this one.

The MallocChecker family is a mostly big monolithic modeling class some small
reporting checkers that only come to action when we are constructing a warning
message, after the actual bug was detected. The implication of this is that
NewDeleteChecker doesn't really do anything to depend on, so this change was
relatively simple.

The only thing that complicates this change is that FreeMemAux (MallocCheckers
method that models general memory deallocation) returns after calling a bug
reporting method, regardless whether the report was ever emitted (which may not
always happen, for instance, if the checker responsible for the report isn't
enabled). This return unfortunately happens before cleaning up the maps in the
GDM keeping track of the state of symbols (whether they are released, whether
that release was successful, etc). What this means is that upon disabling some
checkers, we would never clean up the map and that could've lead to false
positives, e.g.:

error: 'warning' diagnostics seen but not expected:
  File clang/test/Analysis/NewDelete-intersections.mm Line 66: Potential leak of memory pointed to by 'p'
  File clang/test/Analysis/NewDelete-intersections.mm Line 73: Potential leak of memory pointed to by 'p'
  File clang/test/Analysis/NewDelete-intersections.mm Line 77: Potential leak of memory pointed to by 'p'

error: 'warning' diagnostics seen but not expected:
  File clang/test/Analysis/NewDelete-checker-test.cpp Line 111: Undefined or garbage value returned to caller
  File clang/test/Analysis/NewDelete-checker-test.cpp Line 200: Potential leak of memory pointed to by 'p'

error: 'warning' diagnostics seen but not expected:
  File clang/test/Analysis/new.cpp Line 137: Potential leak of memory pointed to by 'x'
There two possible approaches I had in mind:

Make bug reporting methods of MallocChecker returns whether they succeeded, and
proceed with the rest of FreeMemAux if not,
Halt execution with a sink node upon failure. I decided to go with this, as
described in the code.
As you can see from the removed/changed test files, before the big checker
dependency effort landed, there were tests to check for all the weird
configurations of enabled/disabled checkers and their messy interactions, I
largely repurposed these.

[1] http://lists.llvm.org/pipermail/cfe-dev/2019-August/063070.html
[2] http://lists.llvm.org/pipermail/cfe-dev/2019-August/063205.html

Differential Revision: https://reviews.llvm.org/D77474

[analyzer][RetainCount] Tie diagnostics to osx.cocoa.RetainCount rather then RetainCountBase, for the most part

Similarly to other patches of mine, I'm trying to uniformize the checker
interface so that dependency checkers don't emit diagnostics. The checker that
made me most anxious so far was definitely RetainCount, because it is definitely
impacted by backward compatibility concerns, and implements a checker hierarchy
that is a lot different to other examples of similar size. Also, I don't have
authority, nor expertise regarding ObjC related code, so I welcome any
objection/discussion!

Differential Revision: https://reviews.llvm.org/D78099

Previous commit: bd7ff5d9

- Added missing x86 triples
- Added missing asserts

Differential Revision: https://reviews.llvm.org/D80436

Summary:
This patch makes the following changes to SanCov and its complementary Python script in order to resolve issues pertaining to non-UNIX file paths in JSON symbolization information:
* Convert all paths to use forward slash.
* Update `coverage-report-server.py` to correctly handle paths to sources which contain spaces.
* Remove Linux platform restriction for all SanCov unit tests. All SanCov tests passed when ran on my local Windows machine.

Patch by Douglas Gliner.

Reviewers: kcc, filcab, phosek, morehouse, vitalybuka, metzman

Reviewed By: vitalybuka

Subscribers: vsk, Dor1s, llvm-commits

Tags: #sanitizers, #llvm

Differential Revision: https://reviews.llvm.org/D51018