Enables the MVEGatherScatterLowering pass to build
pre-incrementing gathers. Incrementing writeback gathers
are built when it is possible to replace the loop increment
instruction.
Differential Revision: https://reviews.llvm.org/D76786
Summary:
Correct instruction bitfield addresses to generate machine code correctly. Also
add some variables to represent all instructions correctly and change default
values to use registers by default.
Differential Revision: https://reviews.llvm.org/D79539
Summary:
Conflicting types for the same section name defined in clang section
pragmas and GNU-style section attributes were not properly captured by
Clang's Sema. The lack of diagnostics was caused by the fact the section
specification coming from attributes was handled by Sema as implicit,
even though explicitly defined by the user.
This patch enables the diagnostics for section type conflicts between
those specifications by making sure sections defined in section
attributes are correctly handled as explicit.
Reviewers: hans, rnk, javed.absar
Reviewed By: rnk
Subscribers: cfe-commits
Tags: #clang
Differential Revision: https://reviews.llvm.org/D78573
Summary:
Section names used in clang section pragmas were not validated against
previously defined sections, causing section type conflicts to be
ignored by Sema.
This patch enables Clang to capture these section type conflicts by
using the existing Sema's UnifySection method to validate section names
from clang section pragmas.
Reviewers: hans, rnk, javed.absar
Reviewed By: rnk
Subscribers: cfe-commits
Tags: #clang
Differential Revision: https://reviews.llvm.org/D78572
Summary:
We used getEnclosingNamespaceContext(), which calls getParent() rather
than getLexicalParent(), so we would end up adding the "using" line in
places that do not affect the cursor location, or just return an error
when declaration was in another file.
Patch by Adam Czachorowski!
Reviewers: hokein
Reviewed By: hokein
Subscribers: ilya-biryukov, MaskRay, jkorous, arphaman, kadircet, usaxena95, cfe-commits
Tags: #clang
Differential Revision: https://reviews.llvm.org/D79496
Originally, these operations were folded only if all expressions in their
affine maps could be folded to a constant expression that can be then subject
to numeric min/max computation. This introduces a more advanced version that
partially folds the affine map by lifting individual constant expression in it
even if some of the expressions remain variable. The folding can update the
operation in place to use a simpler map. Note that this is not as powerful as
canonicalization, in particular this does not remove dimensions or symbols that
became useless. This allows for better composition of Linalg tiling and
promotion transformation, where the latter can handle some canonical forms of
affine.min that the folding can now produce.
Differential Revision: https://reviews.llvm.org/D79502
In the Vector to LLVM conversion, the `replaceTransferOp` function calls
into a type converter that may fail and suppresses the status. Change
the function to return the failure status instead, Since it is called
from a pattern, the failure can be readily propagated to the rest of
infrastructure.
Summary:
This patch handles illegal scalable types when lowering IR operations,
addressing several places where the value of isScalableVector() is
ignored.
For types such as <vscale x 8 x i32>, this means splitting the
operations. In this example, we would split it into two
operations of type <vscale x 4 x i32> for the low and high halves.
In cases such as <vscale x 2 x i32>, the elements in the vector
will be promoted. In this case they will be promoted to
i64 (with a vector of type <vscale x 2 x i64>)
Reviewers: sdesmalen, efriedma, huntergr
Reviewed By: efriedma
Subscribers: david-arm, tschuett, hiraditya, rkruppe, psnobl, cfe-commits, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D78812
Splitting critical edges for indirect branches
the SplitIndirectBrCriticalEdges() function may break branch
probabilities if target basic block happens to have unset
a probability for any of its successors. That is because in
such cases the getEdgeProbability(Target) function returns
probability 1/NumOfSuccessors and it is called after Target
was split (thus Target has a single successor). As the result
the correspondent successor of the split block gets
probability 100% but 1/NumOfSuccessors is expected (or better
be left unset).
Reviewers: yamauchi
Differential Revision: https://reviews.llvm.org/D78806
If tail-folding of the scalar remainder loop is applied, the primary induction
variable is splat to a vector and used by the masked load/store vector
instructions, thus the IV does not remain scalar. Because we now mark
that the IV does not remain scalar for these cases, we don't emit the vector IV
if it is not used. Thus, the vectoriser produces less dead code.
Thanks to Ayal Zaks for the direction how to fix this.
Differential Revision: https://reviews.llvm.org/D78911
When calculating the natural alignment for scalable vectors it
is acceptable to calculate an allocation size based on the minimum
number of elements in the vector.
This code path is exercised by an existing test:
CodeGen/AArch64/sve-intrinsics-int-arith.ll
Differential Revision: https://reviews.llvm.org/D79475
The list of destination load ops while evaluating producer-consumer
fusion wasn't being maintained as a set, and as such, duplicate load ops
were being added to it. Although this is harmless correctness-wise, it's
a killer efficiency-wise and it prevents interesting/useful fusions
(including for eg. reshapes into a matmul). The reason the latter
fusions would be missed is that a slice union would be unnecessarily
needed due to the duplicate load ops on a memref added to the 'dst
loads' list. Since slice union is unimplemented for the local var case,
a single destination load op that leads to local vars (like a floordiv /
mod producing fusion), a common case, would not get fused due to an
unnecessary union being tried with itself. (The union would actually be
the same thing but we would bail out.)
Besides the above, this would also significantly speed up fusion as all
the unnecessary slice computations / unions, checks, etc. due to the
duplicates go away.
Differential Revision: https://reviews.llvm.org/D79547
The source file used to test Objective-C data-formatters didn't respected
any formatting (mixed tab and spaces, lines exceed column 80, etc...).
This patch reformats the file using clang-format to make it easier to
work with.
Signed-off-by: Med Ismail Bennani <medismail.bennani@gmail.com>
This patch adds statistics about the contribution of each object file to
the linked debug info. When --statistics is passed to dsymutil, it
prints a table after linking as illustrated below.
It lists the object file name, the size of the debug info in the object
file in bytes, and the absolute size contribution to the linked dSYM and
the percentage difference. The table is sorted by the output size, so
the object files contributing the most to the link are listed first.
.debug_info section size (in bytes)
-------------------------------------------------------------------------------
Filename Object dSYM Change
-------------------------------------------------------------------------------
basic2.macho.x86_64.o 210b 165b -24.00%
basic3.macho.x86_64.o 177b 150b -16.51%
basic1.macho.x86_64.o 125b 129b 3.15%
-------------------------------------------------------------------------------
Total 512b 444b -14.23%
-------------------------------------------------------------------------------
Differential revision: https://reviews.llvm.org/D79513
f8990feb12 enabled installing PIC version of both libclang.a and
libclang.so when LIBCLANG_BUILD_STATIC is ON. But it broke the no-PIC
build when LLVM_ENABLE_PIC=OFF with the following error:
```
CMake Error at
/b/s/w/ir/cache/builder/src/third_party/llvm/clang/tools/libclang/CMakeLists.txt:123
(target_compile_definitions):
target_compile_definitions called with non-compilable target type
```
This is because as the code loops through ${name} and ${name}_static, it
introduced a side effect, which is adding an empty libclang_static to
targets. Later target_compile_definitions is called on libclang_static.
That function requires that target must have been created by a command
such as add_executable() or add_library(), so it crashed.
The solution is to not naively loop through both libclang and
libclang_static, but only the ones that are actually added by
llvm_add_library(). Here's the library build type to library target name
mapping:
| SHARED only | libclang |
| STATIC only | libclang |
| SHARED and STATIC | libclang and libclang_static |
So only when SHARED and STATIC are both set should we loop through two
targets. Explicitly parse the STATIC argument and set the list
accordingly.
Reviewed By: smeenai
Differential Revision: https://reviews.llvm.org/D79059
When reporting diagnostics from ASan's (and other sanitizer's) signal
handlers we should strip the "invalid signature" bit before printing
addresses. This makes the report less confusing and let's the user
focus on the real issue.
rdar://62615826
Reviewed By: kubamracek, delcypher
Differential Revision: https://reviews.llvm.org/D79132
Now using patterns, since there's a single-instruction lowering. (We
could convert to VSELECT and pattern-match that, but there doesn't seem
to be much point.)
I think this might be the first instruction to use nested multiclasses
this way? It seems like a good way to reduce duplication between
different integer widths. Let me know if it seems like an improvement.
Also, while I'm here, fix the return type of SETCC so we don't try to
merge a sign-extend with a SETCC.
Differential Revision: https://reviews.llvm.org/D79193
For Swift LLDB (but potentially also for module support in Clang-land)
we need a way to accumulate the path remappings produced by
Module::RegisterXcodeSDK(). In order to make this work for
SymbolFileDebugMaps, registering the search path remapping with both
modules is necessary.
Differential Revision: https://reviews.llvm.org/D79384
<rdar://problem/62750529>
Summary:
Add --relative to the suggested git-diff one liner. If the user does not
pass this argument, then git will produce a diff with the path relative
to the repository root. If the user's working directory is not the
repository root, then clang-format will complain that the file is not
found. The --relative argument makes git produce a diff with the files
relative to the working directory.
Add note to doc string to warn users about the fact that filenames
embedded in the diff are used as-is with no attempts to "do what they
mean, not what they say"
Reviewers: djasper, alexfh, efriedma, klimek, thakis
Reviewed By: efriedma
Subscribers: cfe-commits
Tags: #clang
Differential Revision: https://reviews.llvm.org/D79054
Summary: I updated the code that produces the message and the associated test.
Reviewers: sscalpone, DavidTruby, kiranchandramohan
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D79514
Neither gcc or icc support this. Split out from D79472. I want
to remove more, but it looks like icc does support some things
gcc doesn't and I need to double check our internal test suites.
The Python used to run lit can be different from the Python LLDB was
build with. One scenario where this happens is when LLVM can find the
Python 3 interpreter, but not the Python 3 libraries, in which case LLDB
build and links against Python 3. Without this change, you end up with
an ModuleNotFoundError because of the mismatch.
Instead of looking at the Python interpreter that's used to run lit,
lldbtest should use the interpreter that matches the Python version LLDB
was build against.
Differential revision: https://reviews.llvm.org/D79519
loop nest.
Summary: As discussed in https://reviews.llvm.org/D73129.
Example
Before unroll and jam:
for
A
for
B
for
C
D
E
After unroll and jam (currently):
for
A
A'
for
B
for
C
D
B'
for
C'
D'
E
E'
After unroll and jam (Ideal):
for
A
A'
for
B
B'
for
C
C'
D
D'
E
E'
This is the first patch to change unroll and jam to work in the ideal
way.
This patch change the safety checks needed to make sure is safe to
unroll and jam in the ideal way.
Reviewer: dmgreen, jdoerfert, Meinersbur, kbarton, bmahjour, etiotto
Reviewed By: Meinersbur
Subscribers: fhahn, hiraditya, zzheng, llvm-commits, anhtuyen, prithayan
Tag: LLVM
Differential Revision: https://reviews.llvm.org/D76132