Commit Graph

354168 Commits

Author SHA1 Message Date
Hanhan Wang ac691c4fe7 [mlir][StandardToSPIRV] Add support for lowering FPToSIOp to SPIR-V.
Summary: Depends On D79373

Differential Revision: https://reviews.llvm.org/D79374
2020-05-11 01:27:54 -07:00
Hanhan Wang b80da04b44 [mlir] Add FPToSIOp to Standard dialect.
Summary:
Cast from a value interpreted as floating-point to the corresponding signed
integer value. Similar to an element-wise `static_cast` in C++, performs an
element-wise conversion operation.

Differential Revision: https://reviews.llvm.org/D79373
2020-05-11 01:26:02 -07:00
Djordje Todorovic 45e5a32a8b [NFC][DwarfDebug] Avoid default capturing when using lambdas
It is bad practice to capture by default (via [&] in this case) when
using lambdas, so we should avoid that as much as possible.

This patch fixes that in the getForwardingRegsDefinedByMI
from DwarfDebug module.

Differential Revision: https://reviews.llvm.org/D79616
2020-05-11 10:02:13 +02:00
Haojian Wu 507d1eb1ce Add a missing test file for recovery expressions.
The test was missed in 8222107aa9.
2020-05-11 09:23:32 +02:00
Haojian Wu d82538b3f6 Fix -Wunused compiler warning. 2020-05-11 09:20:48 +02:00
Djordje Todorovic 2552dc5317 [NFC][DwarfDebug] Prefer explicit to auto type deduction
We should use explicit type instead of auto type deduction when
the type is so obvious. In addition, we remove ambiguity, since auto
type deduction sometimes is not that intuitive, so that could lead
us to some unwanted behavior.

This patch fixes that in the collectCallSiteParameters() from
DwarfDebug module.

Differential Revision: https://reviews.llvm.org/D79624
2020-05-11 09:12:58 +02:00
Haojian Wu 8222107aa9 [AST] Preserve the type in RecoveryExprs for broken function calls.
RecoveryExprs are modeled as dependent type to prevent bogus diagnostics
and crashes in clang.

This patch allows to preseve the type for broken calls when the
RecoveryEprs have a known type, e.g. a broken non-overloaded call, a
overloaded call when the all candidates have the same return type, so
that more features (code completion still work on "take2args(x).^") still
work.

However, adding the type is risky, which may result in more clang code being
affected leading to new crashes and hurt diagnostic, and it requires large
effort to minimize the affect (update all sites in clang to handle errorDepend
case), so we add a new flag (off by default) to allow us to develop/test
them incrementally.

This patch also has some trivial fixes to suppress diagnostics (to prevent regressions).

Tested:

all existing tests are passed (when both "-frecovery-ast", "-frecovery-ast-type" flags are flipped on);

Reviewed By: sammccall

Subscribers: rsmith, arphaman, cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D79160
2020-05-11 08:46:18 +02:00
Muhammad Omair Javaid 20629ca949 [LLDB] Fix broken testsuite due to Xfail decorators
Following test cases need minor adjustment in order to accomodate xfail
decorator:
  lldb/test/Shell/SymbolFile/NativePDB/break-by-line.cpp
  lldb/test/Shell/SymbolFile/NativePDB/source-list.cpp
2020-05-11 10:25:04 +05:00
Xun Li 44e5aaf911 Remove an unused Module param
Summary:
In D65848 the function getFuncNameInModule was refactored to no longer use module.
This diff removes the parameter and rename the function name to avoid confusion.

Reviewers: wenlei, wmi, davidxl

Reviewed By: wenlei

Subscribers: hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D79310
2020-05-10 22:09:55 -07:00
Xing GUO 1171bef020 [Object] Remove unused variable after D79560. NFC. 2020-05-11 13:03:53 +08:00
Fangrui Song f081150c4d [gcov] Implement --stdout -t
gcov by default prints to a .gcov file. With --stdout, stdout is used.
Some summary information is omitted. There is no separator for multiple
source files.
2020-05-10 21:02:38 -07:00
Johannes Doerfert 3a8740bdd5 [Attributor] Merge the query set into AbstractAttribute
The old QuerriedAAs contained two vectors, one for required one for
optional dependences (=queries). We now use a single vector and encode
the kind directly in the pointer.

This reduces memory consumption and makes the connection between
abstract attributes and their dependences clearer.

No functional change is intended, changes in the test are due to
different order in the query map. Neither the order before nor now is in
any way special.

---

Single run of the Attributor module and then CGSCC pass (oldPM)
for SPASS/clause.c (~10k LLVM-IR loc):

Before:
```
calls to allocation functions: 543734 (329735/s)
temporary memory allocations: 105895 (64217/s)
peak heap memory consumption: 19.19MB
peak RSS (including heaptrack overhead): 102.26MB
total memory leaked: 269.10KB
```

After:
```
calls to allocation functions: 513292 (341511/s)
temporary memory allocations: 106028 (70544/s)
peak heap memory consumption: 13.35MB
peak RSS (including heaptrack overhead): 95.64MB
total memory leaked: 269.10KB
```

Difference:
```
calls to allocation functions: -30442 (208506/s)
temporary memory allocations: 133 (-910/s)
peak heap memory consumption: -5.84MB
peak RSS (including heaptrack overhead): 0B
total memory leaked: 0B
```

---

Reviewed By: uenoku

Differential Revision: https://reviews.llvm.org/D78729
2020-05-10 22:27:00 -05:00
QingShan Zhang 3c44c441db [DAGCombine] Remove the getNegatibleCost to avoid the out of sync with getNegatedExpression
We have the getNegatibleCost/getNegatedExpression to evaluate the cost and negate the expression.
However, during negating the expression, the cost might change as we are changing the DAG,
and then, hit the assertion if we negated the wrong expression as the cost is not trustful anymore.

This patch is target to remove the getNegatibleCost to avoid the out of sync with getNegatedExpression,
and check the cost during negating the expression. It also reduce the duplicated code between
getNegatibleCost and getNegatedExpression. And fix the crash for the test in D76638

Reviewed By: RKSimon, spatel

Differential Revision: https://reviews.llvm.org/D77319
2020-05-11 02:41:10 +00:00
Muhammad Omair Javaid 8e63f35f86 [LLDB] Decorate tests failing on arm-linux buildbot
Tests impacted by these decorators fail on arm-linux-gnueabihf.

These have been triaged and appropriate bugs have been filed.
2020-05-11 07:31:18 +05:00
Muhammad Omair Javaid e179e7234f Remove XFAIL arm-linux decorator from passing tests 2020-05-11 07:31:18 +05:00
Muhammad Omair Javaid 634b359cf2 XFAIL NativePDB tests on arm-linux
NativePDB tests fail on arm-linux buildbot. clang-cl driver crashes with
-m32 option. Bug files http://llvm.org/pr45867
2020-05-11 07:31:18 +05:00
Fangrui Song f40fc7b8d6 [X86] Fix combineVectorCompareAndMaskUnaryOp regression after 0e8e731449 2020-05-10 19:03:38 -07:00
Lang Hames 689486dc2a [examples] Fix the SpeculativeJIT and ThinLtoJIT examples for 41379f1ec4. 2020-05-10 17:34:31 -07:00
Nico Weber c5647992e5 Remove a comment that is no longer true after d03838343f. 2020-05-10 20:15:29 -04:00
Nico Weber e3a4463446 Remove a variable write that is not needed after d03838343f. 2020-05-10 20:13:45 -04:00
Johannes Doerfert 5e06b2514a [Attributor][FIX] Carefully handle/ignore/forget `argmemonly`
When we have an existing `argmemonly` or `inaccessiblememorargmemonly`
we used to "know" that information. However, interprocedural constant
propagation can invalidate these attributes. We now ignore and remove
these attributes for internal functions (which may be affected by IP
constant propagation), if we are deriving new attributes for the
function.
2020-05-10 19:06:11 -05:00
Johannes Doerfert 713ee3aa77 [Attributor] Use "simplify to constant" in genericValueTraversal
As we replace values with constants interprocedurally, we also need to
do this "look-through" step during the generic value traversal or we
would derive properties from replaced values. While this is often not
problematic, it is when we use the "kind" of a value for reasoning,
e.g., accesses to arguments allow `argmemonly`.
2020-05-10 19:06:11 -05:00
Johannes Doerfert 513ac6e9b0 [Attributor] Ignore illegal accesses to `null`
When we categorize a pointer value we bailed at `null` before. If we
know `null` is not a valid memory location we can ignore it as there
won't be an access at all.
2020-05-10 19:06:10 -05:00
Johannes Doerfert 31c03b9223 [Attributor] Use existing helpers to determine IR facts
We now use getPointerDereferenceableBytes to determine `nonnull` and
`dereferenceable` facts from the IR. We also use getPointerAlignment in
AAAlign for the same reason. The latter can interfere with callbacks so
we do restrict it to non-function-pointers for now.
2020-05-10 19:06:10 -05:00
Johannes Doerfert a9ee8b492c [Attributor][NFC] Clang format Attributor*.cpp 2020-05-10 19:06:10 -05:00
Lang Hames 41379f1ec4 [ORC] Share ownership of JITDylibs between ExecutionSession and
MaterializationResponsibility.

MaterializationResponsibility objects provide a connection between a
materialization process (compiler, jit linker, etc.) and the JIT state held in
the ExecutionSession and JITDylib objects. Switching to shared ownership
extends the lifetime of JITDylibs to ensure they remain accessible until all
materializers targeting them have completed. This will allow (in a follow-up
patch) JITDylibs to be removed from the ExecutionSession and placed in a
pending-destruction state while they are kept alive to communicate errors
to/from any still-runnning materialization processes. The intent is to enable
JITDylibs to be safely removed even if they have running compiles targeting
them.
2020-05-10 16:37:17 -07:00
Fangrui Song 25544ce2df [gcov] Default coverage version to '407*' and delete CC1 option -coverage-cfg-checksum
Defaulting to -Xclang -coverage-version='407*' makes .gcno/.gcda
compatible with gcov [4.7,8)

In addition, delete clang::CodeGenOptionsBase::CoverageExtraChecksum and GCOVOptions::UseCfgChecksum.
We can infer the information from the version.

With this change, .gcda files produced by `clang --coverage a.o` linked executable can be read by gcov 4.7~7.
We don't need other -Xclang -coverage* options.
There may be a mismatching version warning, though.

(Note, GCC r173147 "split checksum into cfg checksum and line checksum"
 made gcov 4.7 incompatible with previous versions.)
2020-05-10 16:14:07 -07:00
Ricky Zhou 6d23f29852 [examples] Fix llvm.memset prototype in BrainF example.
Commit 1e68724d24 removed the alignment
argument from the memset intrinsic. Update the BrainF example to match.

Reviewed By: jyknight
Differential Revision: https://reviews.llvm.org/D79601
2020-05-10 17:20:56 -04:00
Matt Arsenault 856dda3918 AMDGPU/GlobalISel: Remove -global-isel-abort=0 from tests 2020-05-10 17:19:47 -04:00
Richard Smith c7ebf00670 Fix clangd test that depended on a diagnostic removed in Clang. 2020-05-10 14:13:25 -07:00
Richard Smith 8fc12b8698 Enforce the C++11 anonymous enum bitfields check even for
Objective-C++11 and under MS extensions.

This matches the MSVC behavior, and means that Objective-C behaves as a
set of extensions to the base language, rather than replacing the base
language rule with a different one.
2020-05-10 14:03:50 -07:00
Richard Smith 2d3f5a62de Fix typo in enum-base disambiguation. 2020-05-10 13:39:49 -07:00
Martin Storsjö ed0a57f753 [LLD] [COFF] Fix def file exporting of symbols containing periods
This fixes an accidental breakage of exporting symbols using def
files, when the symbol name contains a period, since commit
0ca06f7950, mixing up a symbol name containing a period with
the case of exporting a symbol as a forward to another dll.

Differential Revision: https://reviews.llvm.org/D79619
2020-05-10 23:30:14 +03:00
Richard Smith d6425e2c14 Properly implement 'enum class' parsing.
The 'class' or 'struct' keyword is only permitted as part of either an
enum definition or a standalone opaque-enum-declaration, not as part of
an elaborated type specifier. We previously failed to diagnose this, and
generally didn't properly implement the restrictions on elaborated type
specifiers for enumeration types.

In passing, also fixed incorrect parsing for enum-bases, which we
previously parsed as a type-name, but are actually a type-specifier-seq.
This matters for cases like 'enum E : int *p;', which is valid as a
Microsoft extension.

Plus some minor parse diagnostic improvements.

Bumped the recently-added ExtWarn for 'enum E : int x;' to be
DefaultError; this is not an intentional extension, so producing an
error by default seems appropriate, but the warning flag to disable it
may still be useful for code written against old Clang. The same
treatment is given here to the diagnostic for 'enum class E x;', which
we similarly have incorrectly accepted for many years. These diagnostics
continue to be suppressed under -fms-extensions and when compiling
Objective-C code. We will need to decide separately whether Objective-C
should follow the C++ rules or the (older) MSVC rules.
2020-05-10 13:21:04 -07:00
Fangrui Song 13a633b438 [gcov] Delete CC1 option -coverage-no-function-names-in-data
rL144865 incorrectly wrote function names for GCOV_TAG_FUNCTION
(this might be part of the reasons the header says
"We emit files in a corrupt version of GCOV's "gcda" file format").

rL176173 and rL177475 realized the problem and introduced -coverage-no-function-names-in-data
to work around the issue. (However, the description is wrong.
libgcov never writes function names, even before GCC 4.2).

In reality, the linker command line has to look like:

clang --coverage -Xclang -coverage-version='407*' -Xclang -coverage-cfg-checksum -Xclang -coverage-no-function-names-in-data

Failing to pass -coverage-no-function-names-in-data can make gcov 4.7~7
either produce wrong results (for one gcov-4.9 program, I see "No executable lines")
or segfault (gcov-7).
(gcov-8 uses an incompatible format.)

This patch deletes -coverage-no-function-names-in-data and the related
function names support from libclang_rt.profile
2020-05-10 12:37:44 -07:00
Craig Topper e4c454b065 [X86] Add a few more shuffles to hasUndefRegUpdate.
Mostly found by asserting on tests that have undef operands. I'm
sure this isn't an exhaustive list.
2020-05-10 12:30:16 -07:00
Tyker 5957e058e4 [AssumeBundles] Remove non-determinisme from assume builder
Summary:
The assume builder was non-deterministic when working on unamed values.
this patch fixes this.

Reviewers: jdoerfert

Reviewed By: jdoerfert

Subscribers: hiraditya, mgrang, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D78616
2020-05-10 21:18:33 +02:00
Andrea Di Biagio 47b95d7cf4 [MCA][InstrBuilder] Correctly mark reserved resources in initializeUsedResources.
This fixes a bug reported by Alex Renda on LLVMDev where mca did not correctly
mark a resource group as "reserved".
(See http://lists.llvm.org/pipermail/llvm-dev/2020-May/141485.html).

The issue was caused by a wrong check in function `initializeUsedResources`.
As a consequence of this, a resource group was left unreserved, and its field
`NumUnits` incorrectly reported an unrealistic number of consumed resource
units.

This patch fixes the issue with the handling of reserved resources in the
InstrBuilder class, and adds a simple test for it.  Ideally, as suggested by
Andy Trick, most of these problems will disappear if in the future we will
introduce a (optional) DelayCycles vector for SchedWriteRes.
2020-05-10 19:25:54 +01:00
Fangrui Song 93d5ae3af1 [gcov] Temporarily unsupport host-byteorder-big-endian 2020-05-10 11:17:17 -07:00
Fangrui Song 415c689dd2 [compiler-rt][test] Add feature host-byteorder-big-endian
This is needed to make 5a9b792d72 "[gcov] Temporarily unsupport host-byteorder-big-endian"
work.
2020-05-10 11:02:25 -07:00
Fangrui Song 5a9b792d72 [gcov] Temporarily unsupport host-byteorder-big-endian
llvm-cov gcov does not support host-byteorder-big-endian yet.
2020-05-10 10:29:09 -07:00
Tyker 821a0f23d8 [AssumeBundles] Prevent generation of some redundant assumes
Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information.

Reviewers: jdoerfert

Reviewed By: jdoerfert

Subscribers: hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D78014
2020-05-10 19:23:59 +02:00
Fangrui Song 7f22ceeaae [gcov] Don't skip leading zeros when reading a string
Even a 2003 version of gcov_read_string does not have the behavior
described by rL204881. The wrong impression might come from
libclang_rt.profile (GCDAProfiling.c)'s corrupted output (since the
initial import rL144865). Note, the corrupted output crashes gcov.
2020-05-10 10:16:34 -07:00
Fangrui Song 2d00eb17ca [gcov] Fix .gcda decoding and support GCC 8, 9 and 10
GCDAProfiling.c unnecessarily writes function names to .gcda files.
GCC 4.2 gcc/libgcov.c (now renamed to libgcc/libgcov*) did not write function
names. gcov-7 (compatible) crashes on .gcda produced by libclang_rt.profile
rL176173 realized the problem and introduced a mode to remove function
names.

llvm-cov code apparently takes GCDAProfiling.c output format as truth
and tries to decode function names.  Additionally, llvm-cov tries to
decode tags in certain order which does not match libgcov emitted .gcda
files.

This patch fixes the .gcda decoder and makes it work with GCC 8 and 9
(10 is compatible with 9). Note, line statistics are broken and not
fixed by this patch.

Add test/tools/llvm-cov/gcov-{4.7,8,9}.c to test compatibility.
2020-05-10 09:55:23 -07:00
Florian Hahn 8528186b9b [LAA] Move runtime-check generation to Transforms/Utils/loopUtils (NFC)
Currently LAA's uses of ScalarEvolutionExpander blocks moving the
expander from Analysis to Transforms. Conceptually the expander does not
fit into Analysis (it is only used for code generation) and
runtime-check generation also seems to be better suited as a
transformation utility.

Reviewers: Ayal, anemet

Reviewed By: Ayal

Differential Revision: https://reviews.llvm.org/D78460
2020-05-10 17:39:26 +01:00
Simon Pilgrim d5a2870a6e CodeMetrics.cpp - remove unused includes. NFC. 2020-05-10 16:59:55 +01:00
Simon Pilgrim 4874f263c8 LoopUtils.h - remove unused forward declarations. NFC. 2020-05-10 16:59:54 +01:00
Simon Pilgrim e303b92620 Local.h - remove unused forward declaration. NFC. 2020-05-10 16:59:54 +01:00
Sanjay Patel 856cc60bc1 [InstCombine] canonicalize bitcast after insertelement into undef
We have a transform in the opposite direction only for the x86 MMX type,
Other types are not handled either way before this patch.

The motivating case from PR45748:
https://bugs.llvm.org/show_bug.cgi?id=45748
...is the last test diff. In that example, we are triggering an existing
bitcast transform, so we reduce the number of casts, and that should give
us the ideal x86 codegen.

Differential Revision: https://reviews.llvm.org/D79171
2020-05-10 11:37:47 -04:00
Sanjay Patel d02b3aba37 [CodeGen] fix test to be (mostly) independent of LLVM optimizer; NFC
This test would break with the proposed change to IR canonicalization
in D79171.

The test tried to do the right thing by only using -mem2reg with opt,
but it was using -O3 before that step, so the opt part was meaningless.
2020-05-10 11:25:37 -04:00