This reverts commit 0be81968a2.
The VFDatabase needs some rework to be able to handle vectorization
and subsequent scalarization of intrinsics in out-of-tree versions of
the compiler. For more details, see the discussion in
https://reviews.llvm.org/D67572.
The initial attempt (rG89633320) botched the logic by reversing
the source/dest types. Added x86 tests for additional coverage.
The vector tests show a potential improvement (fold vector load
instead of broadcasting), but that's a known/existing problem.
This fold is done in IR by instcombine, and we have a special
form of it already here in DAGCombiner, but we want the more
general transform too:
https://rise4fun.com/Alive/3jZm
Name: general
Pre: (C1 + zext(C2) < 64)
%s = lshr i64 %x, C1
%t = trunc i64 %s to i16
%r = lshr i16 %t, C2
=>
%s2 = lshr i64 %x, C1 + zext(C2)
%a = and i64 %s2, zext((1 << (16 - C2)) - 1)
%r = trunc %a to i16
Name: special
Pre: C1 == 48
%s = lshr i64 %x, C1
%t = trunc i64 %s to i16
%r = lshr i16 %t, C2
=>
%s2 = lshr i64 %x, C1 + zext(C2)
%r = trunc %s2 to i16
...because D58017 exposes a regression without this fold.
The big switch in `ARMBaseInstrInfo::getNumMicroOps` is missing cases for
`VLLDM` and `VLSTM`, which are currently defined with itineraries having a
dynamic count of micro-ops.
Assuming an optimistic case in which these instruction do not actually perform
loads or stores, and with the idea that Armv8-m cores are supposed to use the
new style scheduling models, this patch just sets the itinerary for those two
instructions to `NoItinerary`.
Differential Revision: https://reviews.llvm.org/D71266
Summary:
[libomptarget] Build most of common/src for amdgcn
Excluding parallel.cu, which uses an integer min() from cuda,
Excluding support.cu, which calls malloc that is not yet available for amdgcn
Reviewers: jdoerfert, ABataev, grokos
Reviewed By: jdoerfert
Subscribers: gregrodgers, ronlieb, jvesely, mgorny, openmp-commits
Tags: #openmp
Differential Revision: https://reviews.llvm.org/D71446
Turns out that gtest in LLVM is only 1.8.0 (the newest version 1.10.0)
supports the GTEST_SKIP() macro, and apparently I didn't build w/o
GWP-ASan.
Should fix the GN bot, as well as any bots that may spuriously break on
platforms where the code wasn't correctly ifdef'd out as well.
This reverts commit 2bbd32f5e8, it was
causing UBSan failures like the following:
lld/ELF/Target.cpp:103:41: runtime error: applying non-zero offset 24 to null pointer
Fix PR44284. This is probably not valid assembly but we should not crash.
Reviewed By: luporl, #powerpc, steven.zhang
Differential Revision: https://reviews.llvm.org/D71443
When a common symbol is merged with a shared symbol, increase st_size if
the shared symbol has a larger st_size. At runtime, the executable's
symbol overrides the shared symbol. The shared symbol may be created
from common symbols in a previous link. This rule makes sure we pick
the largest size among all common symbols.
This behavior matches GNU ld. See
https://sourceware.org/bugzilla/show_bug.cgi?id=25236 for discussions.
A shared symbol does not hold alignment constraints. Ignore the
alignment update.
Reviewed By: peter.smith
Differential Revision: https://reviews.llvm.org/D71161
Summary:
Adds GWP-ASan to Scudo standalone. Default parameters are pulled across from the
GWP-ASan build. No backtrace support as of yet.
Reviewers: cryptoad, eugenis, pcc
Reviewed By: cryptoad
Subscribers: merge_guards_bot, mgorny, #sanitizers, llvm-commits, cferris, vlad.tsyrklevich, pcc
Tags: #sanitizers, #llvm
Differential Revision: https://reviews.llvm.org/D71229
Summary:
I overstepped my reach and generated too many intrinsics; these never
made it into the tests.
Remove these extras. Some needed to be signed-olny, and there were some
possible but unrequired _x variants that needed an extra argument to
IntrinsicMX to allow [de-]selection at compile-time.
Reviewers: simon_tatham
Subscribers: kristof.beyls, dmgreen, cfe-commits
Tags: #clang
Differential Revision: https://reviews.llvm.org/D71466
Test writing and reading benchmark instructions to and from disc, and
check calculations of min, max and avg values from a list of benchmark
measures.
Differential Revision: https://reviews.llvm.org/D71265
Summary:
The problem:
LSP specifies that Positions are between characters. Therefore when a position
(or an empty range) is used to target elements of the source code, there is an
ambiguity - should we look left or right of the cursor?
Until now, SelectionTree resolved this to the right except in trivial cases
(where there's whitespace, semicolon, or eof on the right).
This meant that it's unable to e.g. out-line `int foo^()` today.
Complicating this, LSP notwithstanding the cursor is *on* a character in many
editors (mostly terminal-based). In these cases there's no ambiguity - we must
"look right" - but there's also no way to tell in LSP.
(Several features currently resolve this by using getBeginningOfIdentifier,
which tries to rewind and supports end-of-identifier. But this relies on
raw lexing and is limited and buggy).
Precedent: well - most other languages aren't so full of densely packed symbols
that we might want to target. Bias-towards-identifier works well enough.
MS C++ for vscode seems to mostly use bias-toward-identifier too.
The problem with this solution is it doesn't provide any way to target some
things such as the constructor call in Foo^(bar());
Presented solution:
When an ambiguous selection is found, we generate *both* possible selection
trees. We try to run the feature on the rightward tree first, and then on the
leftward tree if it fails.
This is basically do-what-I-mean, the main downside is the need to do this on
a feature-by-feature basis (because each feature knows what "fail" means).
The most complicated instance of this is Tweaks, where the preferred selection
may vary tweak-by-tweak.
Wrinkles:
While production behavior is pretty consistent, this introduces some
inconsistency in testing, depending whether the interface we're testing is
inside or outside the "retry" wrapper.
In particular, for many features like Hover, the unit tests will show production
behavior, while for Tweaks the harness would have to run the loop itself if
we want this.
Subscribers: ilya-biryukov, MaskRay, jkorous, arphaman, kadircet, usaxena95, cfe-commits
Tags: #clang
Differential Revision: https://reviews.llvm.org/D71345
Summary: Useful when positions are used to target nodes, with before/after ambiguity.
Reviewers: ilya-biryukov, kbobyrev
Subscribers: cfe-commits
Tags: #clang
Differential Revision: https://reviews.llvm.org/D71356
Summary:
I overstepped my reach and generated too many intrinsics; these never
made it into the tests.
Remove these extras. Some needed to be signed-olny, and there were some
possible but unrequired _x variants that needed an extra argument to
IntrinsicMX to allow [de-]selection at compile-time.
Reviewers: simon_tatham
Subscribers: kristof.beyls, dmgreen, cfe-commits
Tags: #clang
Differential Revision: https://reviews.llvm.org/D71466
We've been marking VPT incompatible instructions as invalid for tail
predication too, though this may not strictly be true. VPT are
incompatible and, unless its the first predicate def in a loop,
they shouldn't be compatible for tail predication either.
Differential Revision: https://reviews.llvm.org/D71410
Summary:
This is a follow up for D70548.
Currently, variables with debug info coverage between 0% and 1% are put into
zero-bucket. D70548 changed the way statistics calculate a variable's coverage:
we began to use enclosing scope rather than a possible variable life range.
Thus more variables might be moved to zero-bucket despite they have some debug
info coverage.
The patch is to distinguish between a variable that has location info but
it's significantly less than its enclosing scope and a variable that doesn't
have it at all.
Reviewers: djtodoro, aprantl, dblaikie, avl
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71070
GEP index size can be specified in the DataLayout, introduced in D42123. However, there were still places
in which getIndexSizeInBits was used interchangeably with getPointerSizeInBits. This notably caused issues
with Instcombine's visitPtrToInt; but the unit tests was incorrect, so this remained undiscovered.
This fixes the buildbot failures.
Differential Revision: https://reviews.llvm.org/D68328
Patch by Joseph Faulls!
Summary:
This patch adds intrinsics for the following MVE instructions:
* VABAV
* VMLADAV, VMLSDAV
* VMLALDAV, VMLSLDAV
* VRMLALDAVH, VRMLSLDAVH
Each of the above 4 groups has a corresponding new LLVM IR intrinsic,
since the instructions cannot be easily represented using
general-purpose IR operations.
Reviewers: simon_tatham, ostannard, dmgreen, MarkMurrayARM
Reviewed By: MarkMurrayARM
Subscribers: merge_guards_bot, kristof.beyls, hiraditya, cfe-commits, llvm-commits
Tags: #clang, #llvm
Differential Revision: https://reviews.llvm.org/D71062
Summary:
This changes the representation of 'coverage buckets' in llvm-dwarfdump and
llvm-locstats to one that makes more clear what the buckets contain.
See some related details in D71070.
Reviewers: djtodoro, aprantl, cmtice, jhenderson
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71366
Summary:
This fills in the remaining shift operations that take a single vector
input and an immediate shift count: the `vqshl`, `vqshlu`, `vrshr` and
`vshll[bt]` families.
`vshll[bt]` (which shifts each input lane left into a double-width
output lane) is the most interesting one. There are separate MC
instruction ids for shifting by exactly the input lane width and
shifting by less than that, because the instruction encoding is so
completely different for the lane-width special case. So I had to
write two sets of patterns to match based on the immediate shift
count, which involved adding a ComplexPattern matcher to avoid the
general-case pattern accidentally matching the special case too. For
that family I've made sure to add an llc codegen test for both
versions of each instruction.
I'm experimenting with a new strategy for parametrising the isel
patterns for all these instructions: adding extra fields to the
relevant `Instruction` subclass itself, which are ignored by the
Tablegen backends that generate the MC data, but can be retrieved from
each instance of that instruction subclass when it's passed as a
template parameter to the multiclass that generates its isel patterns.
A nice effect of that is that I can fill in those informational fields
using `let` blocks, rather than having to type them out once per
instruction at `defm` time.
(As a result, quite a lot of existing instruction `def`s are
reindented by this patch, so it's clearer to read with whitespace
changes ignored.)
Reviewers: dmgreen, MarkMurrayARM, miyuki, ostannard
Reviewed By: MarkMurrayARM
Subscribers: kristof.beyls, hiraditya, cfe-commits, llvm-commits
Tags: #clang, #llvm
Differential Revision: https://reviews.llvm.org/D71458
We have custom lowering for operations converting to/from floating-point types
when we don't have hardware support for those types, and this doesn't interact
well with the target-independent legalization of the strict versions of these
operations. Fix this by adding similar custom lowering of the strict versions.
This fixes the last of the assertion failures in the CodeGen/ARM/fp-intrinsics
test, with the remaining failures due to poor instruction selection.
Differential Revision: https://reviews.llvm.org/D71127
This reverts commit 69fcfb7d35.
As shown in the test I attached to this commit, the change I reverted
causes a problem with "zext(cc1) - zext(cc2)". It commuted
the operands to the sub and used different logic to select the addc/subc
instruction:
sub zext (setcc), x => addcarry 0, x, setcc
sub sext (setcc), x => subcarry 0, x, setcc
... but that is bogus. I believe it is not possible to fold those commuted
patterns into any form of addcarry or subcarry. It may have worked as
intended before "AMDGPU: Change boolean content type to 0 or 1" because
the setcc was considered to be -1 rather than 1.
Differential Revision: https://reviews.llvm.org/D70978
Change-Id: If2139421aa6c935cbd1d925af58fe4a4aa9e8f43
If the total number of PC range bytes in each variable's enclosing scope
('scope bytes total') is 0, we will have division by zero.
Differential Revision: https://reviews.llvm.org/D71415
Allow sending address spaces into diagnostics to simplify and improve
error reporting. Improved wording of diagnostics for address spaces
in overloading.
Tags: #clang
Differential Revision: https://reviews.llvm.org/D71111
Summary:
The use of a boolean isInteger flag (generally initialized using
VT.isInteger()) caused errors in our out-of-tree CHERI backend
(https://github.com/CTSRD-CHERI/llvm-project).
In our backend, pointers use a separate ValueType (iFATPTR) and therefore
.isInteger() returns false. This meant that getSetCCInverse() was using the
floating-point variant and generated incorrect code for us:
`(void *)0x12033091e < (void *)0xffffffffffffffff` would return false.
Committing this change will significantly reduce our merge conflicts
for each upstream merge.
Reviewers: spatel, bogner
Reviewed By: bogner
Subscribers: wuzish, arsenm, sdardis, nemanjai, jvesely, nhaehnle, hiraditya, kbarton, jrtc27, atanasyan, jsji, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70917
Summary:
So far it seems like the only test affected by this change is the one I
recently added for R_MIPS_JALR relocations since the other test cases that
use this function early (unknown-relocation-*) do not have a valid input
section for the relocation offset.
Reviewers: ruiu, grimar, MaskRay, espindola
Reviewed By: ruiu, MaskRay
Subscribers: emaste, sdardis, jrtc27, atanasyan, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70659
This reverts commit 9468e3334b.
There's a test that doesn't like this change. The RDA analysis
gets invalided by changes in the block, which is not taken into
account. Revert while I work on a fix for this.
Summary:
Better use of multiclass is used, and this helped find some existing
bugs in the predicated VMULL* intrinsics, which are now fixed.
The refactored VMULL[TB]Q_(INT|POLY)_M() intrinsics were discovered
to have an argument ("inactive") with incorrect type, and this required
a fix that is included in this whole patch. The argument "inactive"
should have been the same width (per vector element) as the return
type of the intrinsic, but was not in the case where the return type
was double the element width of the input types.
To assist in testing the multiclassing , and to thwart further gremlins,
the unit tests are improved in scope.
The *.ll tests are all generated by a small bit of throw-away scripting
from the corresponding *.c tests, and as such the diffs are large and
nasty. Look at the file rather than the diff.
Reviewers: dmgreen, miyuki, ostannard, simon_tatham
Subscribers: kristof.beyls, hiraditya, cfe-commits, llvm-commits
Tags: #clang, #llvm
Differential Revision: https://reviews.llvm.org/D71421
Summary:
A lot of our tests copied the setUp code from our TestSampleTest.py:
```
def setUp(self):
# Call super's setUp().
TestBase.setUp(self)
```
This code does nothing unless we actually do any setUp work in there, so let's remove all these method definitions.
Reviewers: labath, JDevlieghere
Reviewed By: labath
Subscribers: lldb-commits
Tags: #lldb
Differential Revision: https://reviews.llvm.org/D71454
Summary:
A lot of tests do this trick but the vast majority of them don't even call `print()`.
Most of this patch was generated by a script that just looks at all the files and deletes the line if there is no `print (` or `print(` anywhere else in the file.
I checked the remaining tests manually and deleted the import if we never call print (but instead do stuff like `expr print(...)` and similar false-positives).
I also corrected the additional empty lines after the import in the files that I manually edited.
Reviewers: JDevlieghere, labath, jfb
Reviewed By: labath
Subscribers: dexonsmith, wuzish, nemanjai, kbarton, christof, arphaman, abidh, lldb-commits
Tags: #lldb
Differential Revision: https://reviews.llvm.org/D71452
The target feature matrix in the code generator documentation is
outdated. This PR fixes some entries for PowerPC and SystemZ.
Both have:
- assembly parser
- disassembler
- .o file writing
Reviewers: uweigand
Differential Revision: https://reviews.llvm.org/D71004
Summary:
LLDB associates additional information with Types and Declarations which it calls ClangASTMetadata.
ClangASTMetadata is stored by the ClangASTSourceCommon which is implemented by having a large map of
`void *` keys to associated `ClangASTMetadata` values. To make this whole mechanism even unsafer
we also decided to use `clang::Decl *` as one of pointers we throw in there (beside `clang::Type *`).
The Decl class hierarchy uses multiple inheritance which means that not all pointers have the
same address when they are implicitly converted to pointers of their parent classes. For example
`clang::Decl *` and `clang::DeclContext *` won't end up being the same address when they
are implicitly converted from one of the many Decl-subclasses that inherit from both.
As we use the addresses as the keys in our Metadata map, this means that any implicit type
conversions to parent classes (or anything else that changes the addresses) will break our metadata tracking
in obscure ways.
Just to illustrate how broken this whole mechanism currently is:
```lang=cpp
// m_ast is our ClangASTContext. Let's double check that from GetTranslationUnitDecl
// in ClangASTContext and ASTContext return the same thing (one method just calls the other).
assert(m_ast->GetTranslationUnitDecl() == m_ast->getASTContext()->getTranslationUnitDecl());
// Ok, both methods have the same TU*. Let's store metadata with the result of one method call.
m_ast->SetMetadataAsUserID(m_ast->GetTranslationUnitDecl(), 1234U);
// Retrieve the same Metadata for the TU by using the TU* from the other method... which fails?
EXPECT_EQ(m_ast->GetMetadata(m_ast->getASTContext()->getTranslationUnitDecl())->GetUserID(), 1234U);
// Turns out that getTranslationUnitDecl one time returns a TranslationUnitDecl* but the other time
// we return one of the parent classes of TranslationUnitDecl (DeclContext).
```
This patch splits up the `void *` API into two where one does the `clang::Type *` tracking and one the `clang::Decl *` mapping.
Type and Decl are disjoint class hierarchies so there is no implicit conversion possible that could influence
the address values.
I had to change the storing of `clang::QualType` opaque pointers to their `clang::Type *` equivalents as
opaque pointers are already `void *` pointers to begin with. We don't seem to ever set any qualifier in any of these
QualTypes to this conversion should be NFC.
Reviewers: labath, shafik, aprantl
Reviewed By: labath
Subscribers: JDevlieghere, lldb-commits
Tags: #lldb
Differential Revision: https://reviews.llvm.org/D71409
Updated pred_load patterns added to AArch64SVEInstrInfo.td by this patch
to use reg + imm non-temporal loads to fix previous test failures.
Original commit message:
Adds the following intrinsics:
- llvm.aarch64.sve.ldnt1
- llvm.aarch64.sve.stnt1
This patch creates masked loads and stores with the
MONonTemporal flag set when used with the intrinsics above.
Summary:
This is a quickfix for PR44275. An assertion that checks that the
DIExpression is valid failed due to attempting to create an entry value
for an indirect parameter. This started appearing after D69028, as the
indirect parameter started being represented using an DW_OP_deref,
rather than with the DBG_VALUE's second operand, meaning that the
isIndirectDebugValue() check in LiveDebugValues did not exclude such
parameters. A DIExpression that has an entry value operation can
currently not have any other operation, leading to the failed isValid()
check.
This patch simply makes us stop considering emitting entry values
for such parameters. To support such cases I think we at least need
to do the following changes:
* In DIExpression::isValid(): Remove the limitation that a
DW_OP_LLVM_entry_value operation can be the only operation in a
DIExpression.
* In LiveDebugValues::emitEntryValues(): Create an entry value of size
1, so that it only wraps the register operand, and not the whole
pre-existing expression (the DW_OP_deref).
* In LiveDebugValues::removeEntryValue(): Check that the new debug
value has the same debug expression as the original, rather than
checking that the debug expression is empty.
* In DwarfExpression::addMachineRegExpression(): Modify the logic so
that a DW_OP_reg* expression is emitted for the entry value.
That is how GCC emits entry values for indirect parameters. That will
currently not happen to due the DW_OP_deref causing the
!HasComplexExpression to fail. The LocationKind needs to be changed
also, rather than always emitting a DW_OP_stack_value for entry values.
There are probably more things I have missed, but that could hopefully
be a good starting point for emitting such entry values.
Reviewers: djtodoro, aprantl, jmorse, vsk
Reviewed By: aprantl, vsk
Subscribers: hiraditya, llvm-commits
Tags: #debug-info, #llvm
Differential Revision: https://reviews.llvm.org/D71416
Francesco Petrogalli