platform/upstream/llvm.git
4 years agoFix implicit conversion in the lldb Python plugin
Benjamin Kramer [Tue, 28 Jan 2020 23:06:33 +0000 (00:06 +0100)]
Fix implicit conversion in the lldb Python plugin

4 years ago[lldb/Reproducer] Include result in recording statements
Jonas Devlieghere [Tue, 28 Jan 2020 22:47:29 +0000 (14:47 -0800)]
[lldb/Reproducer] Include result in recording statements

Include the return value in the recording log statements. This helps
diagnose uninstrumented (copy assignment) constructors.

4 years ago[Support] Fix implicit std::string conversions on Win32.
Benjamin Kramer [Tue, 28 Jan 2020 23:02:26 +0000 (00:02 +0100)]
[Support] Fix implicit std::string conversions on Win32.

4 years ago[ADT] Make StringRef's std::string conversion operator explicit
Benjamin Kramer [Tue, 28 Jan 2020 22:30:02 +0000 (23:30 +0100)]
[ADT] Make StringRef's std::string conversion operator explicit

This has the same behavior as converting std::string_view to
std::string. This is an expensive conversion, so explicit conversions
are helpful for avoiding unneccessary string copies.

4 years ago[libcxx] Link against android_support when needed
Shoaib Meenai [Tue, 28 Jan 2020 01:29:41 +0000 (17:29 -0800)]
[libcxx] Link against android_support when needed

libc++ on Android needs to be linked against libandroid_support on API
levels less than 21 to provide needed functions that aren't in the libc
on those platforms (e.g. posix_memalign for libcxxabi). libc++ from the
NDK is a linker script that pulls in libandroid_support, but for
building libc++ itself, we need to explicitly add libandroid_support as
a dependency. Moreover, libc++ headers reference the functions provided
by libandroid_support, so it needs to be added as a public dependency.

Differential Revision: https://reviews.llvm.org/D73516

4 years ago[asan] Fix test compilation on Android API <= 17
Shoaib Meenai [Tue, 28 Jan 2020 01:25:38 +0000 (17:25 -0800)]
[asan] Fix test compilation on Android API <= 17

mlockall and munlockall were introduced in Android API 17, so avoid
referencing them on prior versions.

Differential Revision: https://reviews.llvm.org/D73515

4 years ago[runtimes] Fix passing lists to runtimes configures
Shoaib Meenai [Tue, 28 Jan 2020 01:04:21 +0000 (17:04 -0800)]
[runtimes] Fix passing lists to runtimes configures

We have to replace the ";" with "|" (since LLVMExternalProjectUtils uses
"|" as the `LIST_SEPARATOR` when invoking `ExternalProject_Add`) in
order for lists to be passed correctly to the runtimes CMake configures.
Remove the special case for `LLVM_ENABLE_RUNTIMES`, since it'll just get
handled by the general logic now.

Differential Revision: https://reviews.llvm.org/D73512

4 years agoMake llvm::StringRef to std::string conversions explicit.
Benjamin Kramer [Tue, 28 Jan 2020 19:23:46 +0000 (20:23 +0100)]
Make llvm::StringRef to std::string conversions explicit.

This is how it should've been and brings it more in line with
std::string_view. There should be no functional change here.

This is mostly mechanical from a custom clang-tidy check, with a lot of
manual fixups. It uncovers a lot of minor inefficiencies.

This doesn't actually modify StringRef yet, I'll do that in a follow-up.

4 years ago[lldb] Delete ValueObject::GetBaseClassPath
Alex Langford [Tue, 28 Jan 2020 01:59:12 +0000 (17:59 -0800)]
[lldb] Delete ValueObject::GetBaseClassPath

Summary:
This method has exactly one call site, which is only actually executed
if `ValueObject::IsBaseClass` returns false. However, the first thing
that `ValueObject::GetBaseClassPath` does is check if `ValueObject::IsBaseClass`
is true. Because this can never be the case, this method always returns false
and is therefore effectively dead.

Differential Revision: https://reviews.llvm.org/D73517

4 years ago[AArch64][SVE] Add SVE2 mla indexed intrinsics.
Danilo Carvalho Grael [Tue, 28 Jan 2020 21:09:51 +0000 (16:09 -0500)]
[AArch64][SVE] Add SVE2 mla indexed intrinsics.

Summary:
Add SVE2 mla indexed intrinsics:
- smlalb, smalalt, umlalb, umlalt, smlslb, smlslt, umlslb, umlslt.

Reviewers: efriedma, sdesmalen, dancgr, cameron.mcinally, c-rhodes, rengolin

Subscribers: tschuett, kristof.beyls, hiraditya, rkruppe, arphaman, psnobl, llvm-commits, amehsan

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D73576

4 years ago[AArch64][GlobalISel] Fold G_AND into G_BRCOND
Jessica Paquette [Tue, 28 Jan 2020 19:35:44 +0000 (11:35 -0800)]
[AArch64][GlobalISel] Fold G_AND into G_BRCOND

When the G_BRCOND is fed by a eq or ne G_ICMP, it may be possible to fold a
G_AND into the branch by producing a tbnz/tbz instead.

This happens when

  1. We have a ne/eq G_ICMP feeding into the G_BRCOND
  2. The G_ICMP is a comparison against 0
  3. One of the operands of the G_AND is a power of 2 constant

This is very similar to the code in AArch64TargetLowering::LowerBR_CC.

Add opt-and-tbnz-tbz to test this.

Differential Revision: https://reviews.llvm.org/D73573

4 years ago[CodeGen] Attach no-builtin attributes to function definitions with no Decl
Francis Visoiu Mistrih [Mon, 27 Jan 2020 18:40:14 +0000 (10:40 -0800)]
[CodeGen] Attach no-builtin attributes to function definitions with no Decl

When using -fno-builtin[-<name>], we don't attach the IR attributes to
function definitions with no Decl, like the ones created through
`CreateGlobalInitOrDestructFunction`.

This results in projects using -fno-builtin or -ffreestanding to start
seeing symbols like _memset_pattern16.

The fix changes the behavior to always add the attribute if LangOptions
requests it.

Differential Revision: https://reviews.llvm.org/D73495

4 years ago[lldb] Remove ClangASTImporter from Target
Alex Langford [Thu, 23 Jan 2020 21:49:54 +0000 (13:49 -0800)]
[lldb] Remove ClangASTImporter from Target

Target is one of the classes responsible for vending ClangASTImporter.
Target doesn't need to know anything about ClangASTImporter, so if we
instead have ClangPersistentVariables vend it, we can preserve
existing behavior while improving layering and removing dependencies
from non-plugins to plugins.

4 years ago[llvm] Ensure InlineCost-related fields are initialized
Mircea Trofin [Tue, 28 Jan 2020 21:36:46 +0000 (13:36 -0800)]
[llvm] Ensure InlineCost-related fields are initialized

Summary: Small fix - never hurts to have things initialized.

Reviewers: davidxl, eraman

Reviewed By: davidxl

Subscribers: haicheng, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D73420

4 years ago[GlobalMerge] Preserve symbol visibility when merging globals
Michael Spang [Tue, 28 Jan 2020 20:43:07 +0000 (12:43 -0800)]
[GlobalMerge] Preserve symbol visibility when merging globals

Symbols created for merged external global variables have default
visibility. This can break programs when compiling with -Oz
-fvisibility=hidden as symbols that should be hidden will be exported at
link time.

Differential Revision: https://reviews.llvm.org/D73235

4 years agoRevert "[MS] Overhaul how clang passes overaligned args on x86_32"
Hans Wennborg [Tue, 28 Jan 2020 21:17:31 +0000 (22:17 +0100)]
Revert "[MS] Overhaul how clang passes overaligned args on x86_32"

It broke some Chromium tests, so let's revert until it can be fixed; see
https://crbug.com/1046362

This reverts commit 2af74e27ed7d0832cbdde9cb969aaca7a42e99f9.

4 years ago[lldb/Reproducer] Include deserialized value in log statement
Jonas Devlieghere [Tue, 28 Jan 2020 21:23:36 +0000 (13:23 -0800)]
[lldb/Reproducer] Include deserialized value in log statement

Extend the replay log statement to include the deserialized value.

4 years ago[lldb] [test] Restrict x86-64-write register test to x86-64
Michał Górny [Tue, 28 Jan 2020 21:14:33 +0000 (22:14 +0100)]
[lldb] [test] Restrict x86-64-write register test to x86-64

4 years ago[gn build] (manually) port 90a10f00ff8
Nico Weber [Tue, 28 Jan 2020 21:00:54 +0000 (16:00 -0500)]
[gn build] (manually) port 90a10f00ff8

4 years ago[mlir][Linalg][doc] Add Design Document for the Linalg Dialect
Nicolas Vasilache [Tue, 28 Jan 2020 20:47:18 +0000 (15:47 -0500)]
[mlir][Linalg][doc] Add Design Document for the Linalg Dialect

4 years ago[LoopUnrollAndJamPass] Clean unnecessary includes. [NFCI]
Alina Sbirlea [Tue, 28 Jan 2020 19:34:13 +0000 (11:34 -0800)]
[LoopUnrollAndJamPass] Clean unnecessary includes. [NFCI]

4 years ago[NFCI][LoopUnrollAndJam] Minor changes.
Whitney Tsang [Tue, 28 Jan 2020 20:21:48 +0000 (20:21 +0000)]
[NFCI][LoopUnrollAndJam] Minor changes.

Summary:
1. Add assertions.
2. Verify more analyses.
These changes are moved out of https://reviews.llvm.org/D73129 to
simplify that review.

Reviewer: dmgreen, jdoerfert, Meinersbur, kbarton, bmahjour, etiotto
Reviewed By: dmgreen
Subscribers: fhahn, hiraditya, zzheng, llvm-commits, prithayan, anhtuyen
Tag: LLVM
Differential Revision: https://reviews.llvm.org/D73204

4 years ago[Instrumentation] Set hidden visibility for the bias variable
Petr Hosek [Tue, 28 Jan 2020 07:28:03 +0000 (23:28 -0800)]
[Instrumentation] Set hidden visibility for the bias variable

We have to avoid using a GOT relocation to access the bias variable,
setting the hidden visibility achieves that.

Differential Revision: https://reviews.llvm.org/D73529

4 years agoFix compiling with clang-cl inside a Visual Studio 2019 16.4 command prompt.
Alexandre Ganea [Tue, 28 Jan 2020 19:48:12 +0000 (14:48 -0500)]
Fix compiling with clang-cl inside a Visual Studio 2019 16.4 command prompt.

This was introduced by 0d17410e919124b3a9194b9bdbe2ce39dd779941 and was preventing from compiling with clang-cl on Windows.
The problem was that clang-cl detects the triple from the current env vars (was x86_64-pc-windows-msvc19.24.28315 for me, as I happen to always run inside a VS2019 cmd prompt).

4 years ago[InstCombine] refactor foldVectorCmp(); NFC
Sanjay Patel [Tue, 28 Jan 2020 19:39:42 +0000 (14:39 -0500)]
[InstCombine] refactor foldVectorCmp(); NFC

We can handle other patterns here as shown in PR44588.

4 years ago[CMake] Set ASM compiler for external projects
Petr Hosek [Tue, 28 Jan 2020 03:14:32 +0000 (19:14 -0800)]
[CMake] Set ASM compiler for external projects

This is necessary on Windows, otherwise CMake fails. It's not
conventional on Windows to use cl for assembly (you'd use ml or ml64
instead), but CMake has a separate ASM_MASM mode for that, and clang-cl
works fine for assembly so we'll use that on Windows for consistency.

Differential Revision: https://reviews.llvm.org/D73522

4 years agoDon't fail step out if remote server doesn't implement qMemoryRegionInfo
Ted Woodward [Tue, 28 Jan 2020 19:31:40 +0000 (13:31 -0600)]
Don't fail step out if remote server doesn't implement qMemoryRegionInfo

Summary:
The return address validation in D71372 will fail if the memory permissions can't be determined. Many embedded stubs either don't implement the qMemoryRegionInfo packet, or don't have memory permissions at all.

Remove the return from the if clause that calls GetLoadAddressPermissions, so this call failing doesn't cause the step out to abort. Instead, assume that the memory permission check doesn't apply to this type of target.

Reviewers: labath, jingham, clayborg, mossberg

Reviewed By: labath

Subscribers: lldb-commits

Tags: #lldb

Differential Revision: https://reviews.llvm.org/D72513

4 years ago[lsan] Support LeakSanitizer runtime on Fuchsia
Roland McGrath [Tue, 28 Jan 2020 19:34:53 +0000 (11:34 -0800)]
[lsan] Support LeakSanitizer runtime on Fuchsia

Support LeakSanitizer runtime on Fuchsia.

Patch By: mcgrathr

Differential Revision: https://reviews.llvm.org/D72887

4 years ago[Fuchsia] Remove aarch64-fuchsia target-specific -mcmodel=kernel
Roland McGrath [Tue, 28 Jan 2020 19:32:08 +0000 (11:32 -0800)]
[Fuchsia] Remove aarch64-fuchsia target-specific -mcmodel=kernel

Under --target=aarch64-fuchsia, -mcmodel=kernel has the effect of
(the default) -mcmodel=small plus -mtp=el1 (which did not exist when
this behavior was added). Fuchsia's kernel now uses -mtp=el1
directly instead of -mcmodel=kernel, so remove this special support.

Patch By: mcgrathr

Differential Revision: https://reviews.llvm.org/D73409

4 years ago[mlir] Add primitive transform pattern to rewrite linalg.fill into vector.broadcast...
Ahmed Taei [Sat, 25 Jan 2020 00:23:16 +0000 (16:23 -0800)]
[mlir] Add primitive transform pattern to rewrite linalg.fill into vector.broadcast form.

Summary:
This diff adds a transformation patter to rewrite linalg.fill as broadcasting a scaler into a vector.
It uses the same preconditioning as matmul (memory is contiguous).

Reviewers: nicolasvasilache

Subscribers: mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, arpith-jacob, mgester, lucyrfox, aartbik, liufengdb, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D73391

4 years ago[mlir] Optimize OpResult use case for single result operations.
River Riddle [Tue, 28 Jan 2020 19:19:20 +0000 (11:19 -0800)]
[mlir] Optimize OpResult use case for single result operations.

Summary:
Operation represents all of the uses of each result with one use list, so manipulating the use list of a specific result requires filtering the main use list. This revision adds an optimization for the case of single result operations to avoid this filtering.

Differential Revision: https://reviews.llvm.org/D73430

4 years agollvm-symbolizer test: Add a bit of extra detail on how to compile/reproduce this
David Blaikie [Tue, 28 Jan 2020 19:02:16 +0000 (11:02 -0800)]
llvm-symbolizer test: Add a bit of extra detail on how to compile/reproduce this

The details are also in the .test file, but doesn't hurt to make it a
bit clearer.

4 years ago[ELF][PPC32] Support --emit-relocs link of R_PPC_PLTREL24
Fangrui Song [Tue, 28 Jan 2020 08:01:20 +0000 (00:01 -0800)]
[ELF][PPC32] Support --emit-relocs link of R_PPC_PLTREL24

Similar to R_MIPS_GPREL16 and R_MIPS_GPREL32 (D45972).

If the addend of an R_PPC_PLTREL24 is >= 0x8000, it indicates that r30
is relative to the input section .got2.

```
addis 30, 30, .got2+0x8000-.L1$pb@ha
addi 30, 30, .got2+0x8000-.L1$pb@l
...
bl foo+0x8000@PLT
```

After linking, the relocation will be relative to the output section .got2.
To compensate for the shift `address(input section .got2) - address(output section .got2) = ppc32Got2OutSecOff`, adjust by `ppc32Got2OutSecOff`:

```
addis 30, 30, .got2+0x8000-.L1+ppc32Got2OutSecOff$pb@ha
addi 30, 30, .got2+0x8000-.L1+ppc32Got2OutSecOff$pb@ha$pb@l
...
bl foo+0x8000+ppc32Got2OutSecOff@PLT
```

This rule applys to a relocatable link or a non-relocatable link with --emit-relocs.

Reviewed By: Bdragon28

Differential Revision: https://reviews.llvm.org/D73532

4 years ago[scudo][standalone] Fix Android logging
Kostya Kortchinsky [Tue, 28 Jan 2020 17:38:59 +0000 (09:38 -0800)]
[scudo][standalone] Fix Android logging

Summary:
Zygote & children's stderr is lost, so use Bionic's provided allocation
free syslog function for `outputRaw`. Get rid of the mutex as it's not
vital and could cause issues with `fork`.

Reviewers: cferris, pcc, eugenis, hctim, morehouse

Subscribers: #sanitizers, llvm-commits

Tags: #sanitizers, #llvm

Differential Revision: https://reviews.llvm.org/D73561

4 years ago[gn build] Port 2c03c899d50
LLVM GN Syncbot [Tue, 28 Jan 2020 18:59:31 +0000 (18:59 +0000)]
[gn build] Port 2c03c899d50

4 years ago[MBFI] Move BranchFolding::MBFIWrapper to its own files. NFC.
Hiroshi Yamauchi [Mon, 27 Jan 2020 18:05:54 +0000 (10:05 -0800)]
[MBFI] Move BranchFolding::MBFIWrapper to its own files. NFC.

Summary:
To avoid header file circular dependency issues in passing updated MBFI (in
MBFIWrapper) to the interface of profile guided size optimizations.

A prep step for (and split off of) D73381.

Reviewers: davidxl

Subscribers: mgorny, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D73494

4 years agoFix test hip-device-libs.hip
Yaxun (Sam) Liu [Tue, 28 Jan 2020 18:57:35 +0000 (13:57 -0500)]
Fix test hip-device-libs.hip

4 years ago[lldb/Bindings] Sort headers in headers.swig
Jonas Devlieghere [Tue, 28 Jan 2020 18:57:34 +0000 (10:57 -0800)]
[lldb/Bindings] Sort headers in headers.swig

4 years ago[llvm-dwarfdump][Statistics] Make calculations of vars in global scope more accurate
Kristina Bessonova [Tue, 14 Jan 2020 18:39:04 +0000 (20:39 +0200)]
[llvm-dwarfdump][Statistics] Make calculations of vars in global scope more accurate

It isn't known how many times we've seen the same variable or member in
the global scope (unlike in functions), but there still can be some duplicates
among different CUs.
So, this patch proposes to count variables in the global scope just as a sum of
the number of vars, constant members and artificial entities.

Reviewed by: aprantl

Differential Revision: https://reviews.llvm.org/D73004

4 years ago[llvm-dwarfdump][Statistics] Distinguish parameters with same name or w/o a name
Kristina Bessonova [Tue, 14 Jan 2020 18:37:47 +0000 (20:37 +0200)]
[llvm-dwarfdump][Statistics] Distinguish parameters with same name or w/o a name

A few DW_TAG_formal_parameter's of the same function may have the same
name (e.g. variadic (template) functions) or don't have a name at all
(if the parameter isn't used inside the function body), but we still
need to be able to distinguish between them to get correct number of 'total vars'
and 'availability' metric.

Reviewed by: aprantl

Differential Revision: https://reviews.llvm.org/D73003

4 years ago[llvm-dwarfdump][Statistics] Count more than one conrete out-of-line instances of...
Kristina Bessonova [Wed, 8 Jan 2020 15:33:51 +0000 (17:33 +0200)]
[llvm-dwarfdump][Statistics] Count more than one conrete out-of-line instances of a function

Here may be more than one out-of-line instance of the same function
among different CUs. All of them should be accounted for to get an accurate
total number of variables/parameters.

Reviewed by: aprantl

Differential Revision: https://reviews.llvm.org/D73002

4 years ago[InstCombine] add tests for cmp with splat operand and splat constant; NFC
Sanjay Patel [Tue, 28 Jan 2020 18:21:36 +0000 (13:21 -0500)]
[InstCombine] add tests for cmp with splat operand and splat constant; NFC

See PR44588:
https://bugs.llvm.org/show_bug.cgi?id=44588

4 years ago[gn build] Port a928d127a52
LLVM GN Syncbot [Tue, 28 Jan 2020 18:39:09 +0000 (18:39 +0000)]
[gn build] Port a928d127a52

4 years agoCorrected clang amdgpu-features.cl test for 6d614a82a4230ea69e322f56dc18dcbd815ed37b...
Konstantin Pyzhov [Tue, 28 Jan 2020 10:41:42 +0000 (05:41 -0500)]
Corrected clang amdgpu-features.cl test for 6d614a82a4230ea69e322f56dc18dcbd815ed37b (AMDGPU MFMA built-ins)

Differential Revision: https://reviews.llvm.org/D72723

4 years ago[CUDA] Assume the latest known CUDA version if we've found an unknown one.
Artem Belevich [Wed, 22 Jan 2020 20:44:22 +0000 (12:44 -0800)]
[CUDA] Assume the latest known CUDA version if we've found an unknown one.

This makes clang somewhat forward-compatible with new CUDA releases
without having to patch it for every minor release without adding
any new function.

If an unknown version is found, clang issues a warning (can be disabled
with -Wno-cuda-unknown-version) and assumes that it has detected
the latest known version. CUDA releases are usually supersets
of older ones feature-wise, so it should be sufficient to keep
released clang versions working with minor CUDA updates without
having to upgrade clang, too.

Differential Revision: https://reviews.llvm.org/D73231

4 years ago[clang-tidy] adjust scripts to subsubsections in Release Notes
Nathan James [Tue, 28 Jan 2020 18:09:53 +0000 (18:09 +0000)]
[clang-tidy] adjust scripts to subsubsections in Release Notes

Summary:
I added subsubsections for typical Clang-tidy entries in Release Notes, so now scripts are aware of this changes.

I don't have GitHub commit access, so please commit changes.

Reviewers: aaron.ballman, alexfh, hokein

Reviewed By: alexfh

Subscribers: njames93, xazax.hun, cfe-commits

Tags: #clang-tools-extra, #clang

Differential Revision: https://reviews.llvm.org/D72527

4 years ago[AArch64][GlobalISel] Don't bail out of the select(cmp(a, b)) -> csel optimization...
Amara Emerson [Mon, 27 Jan 2020 23:57:16 +0000 (15:57 -0800)]
[AArch64][GlobalISel] Don't bail out of the select(cmp(a, b)) -> csel optimization with multiple users.

It can still be beneficial to do the optimization if the result of the compare
is used by *another* select.

Differential Revision: https://reviews.llvm.org/D73511

4 years agoFix a crash when casting _Complex and ignoring the results.
Aaron Ballman [Tue, 28 Jan 2020 18:04:32 +0000 (13:04 -0500)]
Fix a crash when casting _Complex and ignoring the results.

Performing a cast where the result is ignored caused Clang to crash when
performing codegen for the conversion:

  _Complex int a;
  void fn1() { (_Complex double) a; }

This patch addresses the crash by not trying to emit the scalar conversions,
causing it to be a noop. Fixes PR44624.

4 years ago[WebAssembly] Add WebAssembly support to llvm-symbolizer
Derek Schuff [Thu, 23 Jan 2020 01:40:11 +0000 (17:40 -0800)]
[WebAssembly] Add WebAssembly support to llvm-symbolizer

The only thing missing for basic llvm-symbolizer support is the ability on
lib/Object to get a wasm symbol's section ID, which allows sorting and
computation of the symbols' sizes.

Also, when the WasmAsmParser switches sections on new functions, also add the
section to the list of Dwarf sections if Dwarf is being generated for assembly;
this allows writing of simple tests.

Reviewers: sbc100, jhenderson, aardappel

Differential Revision: https://reviews.llvm.org/D73246

4 years ago[llvm-dwarfdump][Statistics] Ignore declarations of global variables
Kristina Bessonova [Sun, 19 Jan 2020 14:28:35 +0000 (16:28 +0200)]
[llvm-dwarfdump][Statistics] Ignore declarations of global variables

Reviewed by: djtodoro

Differential Revision: https://reviews.llvm.org/D73001

4 years ago[llvm-dwarfdump][Statistics] Ignore DW_TAG_subroutine_type in statistics
Kristina Bessonova [Thu, 9 Jan 2020 20:21:17 +0000 (22:21 +0200)]
[llvm-dwarfdump][Statistics] Ignore DW_TAG_subroutine_type in statistics

DW_TAG_subroutine_type is not really useful for statistics purposes, as it never
has location information. But it may contain DW_TAG_formal_parameter
children that generate number of parameters w/o location and decrease
'availability' metric significantly.

Reviewed by: djtodoro

Differential Revision: https://reviews.llvm.org/D72983

4 years ago[llvm-dwarfdump][Statistics] Distinguish functions/variables with same name across...
Kristina Bessonova [Tue, 14 Jan 2020 18:36:30 +0000 (20:36 +0200)]
[llvm-dwarfdump][Statistics] Distinguish functions/variables with same name across different CUs

Different variables and functions might have the same name in different CU.
To calculate 'Availability' metric more accurate (i.e. to avoid getting
availability above 100%), we need to have some additional logic to
distinguish between them.

The patch introduces a DIE identifier that consists of a function/variable name
and declaration information: a filename and a line number. This allows
distinguishing different functions/variables (different means declared in
different files/lines) with the same name, keeping duplicates counted
as duplicates.

Reviewed by: aprantl, djtodoro

Differential Revision: https://reviews.llvm.org/D72797

4 years ago[llvm-objcopy] Initial support for wasm in llvm-objcopy
Derek Schuff [Sat, 23 Nov 2019 02:02:10 +0000 (18:02 -0800)]
[llvm-objcopy] Initial support for wasm in llvm-objcopy

Currently only supports simple copying, other operations to follow.

Reviewers: sbc100, alexshap, jhenderson

Differential Revision: https://reviews.llvm.org/D70930

4 years agoRevert "[lldb/Target] Add Assert StackFrame Recognizer"
Med Ismail Bennani [Tue, 28 Jan 2020 17:40:08 +0000 (18:40 +0100)]
Revert "[lldb/Target] Add Assert StackFrame Recognizer"

This reverts commit 03a6b858fde5c644ec16b1fddd8e10aa9ef3f0ad.

The test doesn't pass on Debian.

4 years agoAdd missing clang tests for 6d614a82a4230ea69e322f56dc18dcbd815ed37b (AMDGPU MFMA...
Konstantin Pyzhov [Tue, 28 Jan 2020 09:41:21 +0000 (04:41 -0500)]
Add missing clang tests for 6d614a82a4230ea69e322f56dc18dcbd815ed37b (AMDGPU MFMA built-ins)

Differential Revision: https://reviews.llvm.org/D72723

4 years ago[Matrix] Mark expressions shared between multiple remarks.
Florian Hahn [Tue, 28 Jan 2020 17:01:00 +0000 (09:01 -0800)]
[Matrix] Mark expressions shared between multiple remarks.

This patch adds support for explicitly highlighting sub-expressions
shared by multiple leaf nodes. For example consider the following
code

  %shared.load = tail call <8 x double> @llvm.matrix.columnwise.load.v8f64.p0f64(double* %arg1, i32 %stride, i32 2, i32 4), !dbg !10, !noalias !10
  %trans = tail call <8 x double> @llvm.matrix.transpose.v8f64(<8 x double> %shared.load, i32 2, i32 4), !dbg !10
  tail call void @llvm.matrix.columnwise.store.v8f64.p0f64(<8 x double> %trans, double* %arg3, i32 10, i32 4, i32 2), !dbg !10
  %load.2 = tail call <30 x double> @llvm.matrix.columnwise.load.v30f64.p0f64(double* %arg3, i32 %stride, i32 2, i32 15), !dbg !10, !noalias !10
  %mult = tail call <60 x double> @llvm.matrix.multiply.v60f64.v8f64.v30f64(<8 x double> %trans, <30 x double> %load.2, i32 4, i32 2, i32 15), !dbg !11
  tail call void @llvm.matrix.columnwise.store.v60f64.p0f64(<60 x double> %mult, double* %arg2, i32 10, i32 4, i32 15), !dbg !11

We have two leaf nodes (the 2 stores) and the first store stores %trans
which is also used by the matrix multiply %mult. We generate separate
remarks for each leaf (stores). To denote that parts are shared, the
shared expressions are marked as shared (), with a reference to the
other remark that shares it. The operation summary also denotes the
shared operations separately.

Reviewers: anemet, Gerolf, thegameg, hfinkel, andrew.w.kaylor, LuoYuanke

Reviewed By: anemet

Differential Revision: https://reviews.llvm.org/D72526

4 years ago[lldb/Target] Add Assert StackFrame Recognizer
Med Ismail Bennani [Thu, 23 Jan 2020 14:11:53 +0000 (15:11 +0100)]
[lldb/Target] Add Assert StackFrame Recognizer

When a thread stops, this checks depending on the platform if the top frame is
an abort stack frame. If so, it looks for an assert stack frame in the upper
frames and set it as the most relavant frame when found.

To do so, the StackFrameRecognizer class holds a "Most Relevant Frame" and a
"cooked" stop reason description. When the thread is about to stop, it checks
if the current frame is recognized, and if so, it fetches the recognized frame's
attributes and applies them.

rdar://58528686

Differential Revision: https://reviews.llvm.org/D73303

Signed-off-by: Med Ismail Bennani <medismail.bennani@gmail.com>
4 years ago[llvm] Fix broken cases of 'CHECK[^:]*$' in tests
Jonathan Roelofs [Mon, 27 Jan 2020 01:16:57 +0000 (18:16 -0700)]
[llvm] Fix broken cases of 'CHECK[^:]*$' in tests

4 years ago[LV] Hoist code to mark conditional assumes as dead to caller (NFC).
Florian Hahn [Tue, 28 Jan 2020 16:46:27 +0000 (08:46 -0800)]
[LV] Hoist code to mark conditional assumes as dead to caller (NFC).

This is a follow-up suggested in D73423. It is sufficient to just add
the conditional assumes to DeadInstructions once.

4 years agoSummary:
Konstantin Pyzhov [Tue, 28 Jan 2020 08:51:27 +0000 (03:51 -0500)]
Summary:
This CL adds clang declarations of built-in functions for AMDGPU MFMA intrinsics and instructions.
OpenCL tests for new built-ins are included.

Differential Revision: https://reviews.llvm.org/D72723

4 years ago[LLD] Avoid exiting with a locked mutex NFC
Andrew Ng [Wed, 22 Jan 2020 17:08:09 +0000 (17:08 +0000)]
[LLD] Avoid exiting with a locked mutex NFC

In ErrorHandler::error(), rearrange code to avoid calling exitLld with
the mutex locked. Acquire mutex lock when flushing the output streams in
exitLld.

Differential Revision: https://reviews.llvm.org/D73281

4 years ago[OPENMP50]Check for lastprivate conditional updates in atomic
Alexey Bataev [Tue, 28 Jan 2020 16:19:45 +0000 (11:19 -0500)]
[OPENMP50]Check for lastprivate conditional updates in atomic
constructs.

Added analysis in atomic constrcuts to support checks for updates of
conditional lastprivate variables.

4 years agoFix warning of `-Wcast-qual`. NFC.
Michael Liao [Tue, 28 Jan 2020 16:35:52 +0000 (11:35 -0500)]
Fix warning of `-Wcast-qual`. NFC.

4 years ago[LV] Do not try to sink dead instructions.
Florian Hahn [Tue, 28 Jan 2020 16:20:40 +0000 (08:20 -0800)]
[LV] Do not try to sink dead instructions.

Dead instructions do not need to be sunk. Currently we try and record
the recipies for them, but there are no recipes emitted for them and
there's nothing to sink. They can be removed from SinkAfter while
marking them for recording.

Fixes PR44634.

Reviewers: rengolin, hsaito, fhahn, Ayal, gilr

Reviewed By: gilr

Differential Revision: https://reviews.llvm.org/D73423

4 years ago[HIP] Fix environment variable HIP_DEVICE_LIB_PATH
Yaxun (Sam) Liu [Thu, 23 Jan 2020 22:30:07 +0000 (17:30 -0500)]
[HIP] Fix environment variable HIP_DEVICE_LIB_PATH

Currently device lib path set by environment variable HIP_DEVICE_LIB_PATH
does not work due to extra "-L" added to each entry.

This patch fixes that by allowing argument name to be empty in addDirectoryList.

Differential Revision: https://reviews.llvm.org/D73299

4 years agoRevert "[lldb/PDB] Use the new line table constructor"
Pavel Labath [Tue, 28 Jan 2020 16:15:26 +0000 (17:15 +0100)]
Revert "[lldb/PDB] Use the new line table constructor"

This reverts commit bb73210ba9f16c1516f564235c86cbddccd1bd6d due to
failures on the windows bot.

4 years ago[gn build] Port a32f894f17b
LLVM GN Syncbot [Tue, 28 Jan 2020 15:50:50 +0000 (15:50 +0000)]
[gn build] Port a32f894f17b

4 years ago[ADT] Remove more llvm::make_unique
Jonathan Roelofs [Fri, 24 Jan 2020 00:54:15 +0000 (17:54 -0700)]
[ADT] Remove more llvm::make_unique

https://reviews.llvm.org/D73316

4 years ago[clang] Fix EOL whitespace. NFC
Jonathan Roelofs [Sun, 26 Jan 2020 19:05:46 +0000 (12:05 -0700)]
[clang] Fix EOL whitespace. NFC

4 years ago[clang][CodeComplete] Support for designated initializers
Kadir Cetinkaya [Thu, 23 Jan 2020 12:28:16 +0000 (13:28 +0100)]
[clang][CodeComplete] Support for designated initializers

Reviewers: sammccall

Subscribers: cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D73271

4 years ago[scudo][standalone] Secondary & general other improvements
Kostya Kortchinsky [Mon, 27 Jan 2020 22:03:21 +0000 (14:03 -0800)]
[scudo][standalone] Secondary & general other improvements

Summary:
This CL changes multiple things to improve performance (notably on
Android).We introduce a cache class for the Secondary that is taking
care of this mechanism now.

The changes:
- change the Secondary "freelist" to an array. By keeping free secondary
  blocks linked together through their headers, we were keeping a page
  per block, which isn't great. Also we know touch less pages when
  walking the new "freelist".
- fix an issue with the freelist getting full: if the pattern is an ever
  increasing size malloc then free, the freelist would fill up and
  entries would not be used. So now we empty the list if we get to many
  "full" events;
- use the global release to os interval option for the secondary: it
  was too costly to release all the time, particularly for pattern that
  are malloc(X)/free(X)/malloc(X). Now the release will only occur
  after the selected interval, when going through the deallocate path;
- allow release of the `BatchClassId` class: it is releasable, we just
  have to make sure we don't mark the batches containing batches
  pointers as free.
- change the default release interval to 1s for Android to match the
  current Bionic allocator configuration. A patch is coming up to allow
  changing it through `mallopt`.
- lower the smallest class that can be released to `PageSize/64`.

Reviewers: cferris, pcc, eugenis, morehouse, hctim

Subscribers: phosek, #sanitizers, llvm-commits

Tags: #sanitizers, #llvm

Differential Revision: https://reviews.llvm.org/D73507

4 years ago[mlir][spirv] Add GroupNonUniform arithmetic operations.
Denis Khalikov [Tue, 28 Jan 2020 14:36:01 +0000 (09:36 -0500)]
[mlir][spirv] Add GroupNonUniform arithmetic operations.

Add GroupNonUniform arithmetic operations: FAdd, FMul, IMul.
Unify parser, printer, verifier for GroupNonUniform arithmetic
operations.

Differential Revision: https://reviews.llvm.org/D73491

4 years ago[clangd] Make bin/llvm-lit run standalone clangd tests
Kadir Cetinkaya [Tue, 28 Jan 2020 11:24:45 +0000 (12:24 +0100)]
[clangd] Make bin/llvm-lit run standalone clangd tests

Summary:
Currently clangd lit tests can't be run in isolation because we don't
set some of the config parameters. This enables running

./bin/llvm-lit ../clang-tools-extra/clangd/test/

or any other test in that subdirectory.

Reviewers: sammccall

Subscribers: mgorny, ilya-biryukov, MaskRay, jkorous, arphaman, usaxena95, cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D73538

4 years agoPrevent building with MSVC 14.24
Nico Weber [Tue, 28 Jan 2020 15:09:52 +0000 (10:09 -0500)]
Prevent building with MSVC 14.24

MSVC 14.24 miscompiles some of LLVM's code, which makes at least these tests fail:

    LLVM :: MC/MachO/gen-dwarf-cpp.s
    LLVM :: MC/MachO/gen-dwarf-macro-cpp.s
    LLVM :: MC/MachO/gen-dwarf-producer.s
    LLVM :: MC/MachO/gen-dwarf.s

It seems better to diagnose that at build time. Since both the previous
and the next version have a fix, this might be good enough and we might
not need a real workaround. (We ran into this at
https://crbug.com/1045948)

If you hit this, use either a newer or an older version of MSVC,
or use clang-cl as host compiler.

Differential Revision: https://reviews.llvm.org/D73550

4 years ago[clang-format] Handle quotes and escaped braces in C# interpolated strings
Jonathan Coe [Tue, 28 Jan 2020 14:46:27 +0000 (14:46 +0000)]
[clang-format] Handle quotes and escaped braces in C# interpolated strings

Summary:
This addresses issues raised in https://bugs.llvm.org/show_bug.cgi?id=44454.

There are outstanding issues with multi-line verbatim strings in C# that will be addressed in a follow-up PR.

Reviewers: krasimir, MyDeveloperDay

Reviewed By: krasimir, MyDeveloperDay

Subscribers: MyDeveloperDay

Tags: #clang-format

Differential Revision: https://reviews.llvm.org/D73492

4 years agoRevert "[Clang] Warn about 'z' printf modifier in old MSVC."
Nico Weber [Tue, 28 Jan 2020 14:27:54 +0000 (09:27 -0500)]
Revert "[Clang] Warn about 'z' printf modifier in old MSVC."

This reverts commit fe0d1b6a8ac5048b8007e5e7cc2aeb4e3291bda0.
Makes Analysis/taint-generic.c fail on some Windows systems.

4 years ago[PowerPC][Future] Add pld and pstd to future CPU
Victor Huang [Tue, 28 Jan 2020 14:22:53 +0000 (08:22 -0600)]
[PowerPC][Future] Add pld and pstd to future CPU
Add the prefixed instructions pld and pstd to future CPU. These are load and
store instructions that require new operand types that are 34 bits. This patch
adds the two instructions as well as the operand types required.

Note that this patch also makes a minor change to tablegen to account for the
fact that some instructions are going to require shifts greater than 31 bits
for the new 34 bit instructions.

Differential Revision: https://reviews.llvm.org/D72574

4 years ago[CodeMoverUtils] Improve IsControlFlowEquivalent.
Whitney Tsang [Tue, 28 Jan 2020 03:50:33 +0000 (03:50 +0000)]
[CodeMoverUtils] Improve IsControlFlowEquivalent.

Summary:
Currently IsControlFlowEquivalent determine if two blocks are control
flow equivalent by checking if A dominates B and B post dominates A.
There exists blocks that are control flow equivalent even if they don't
satisfy the A dominates B and B post dominates A condition.
For example,

if (cond)
  A
if (cond)
  B
In the PR, we determine if two blocks are control flow equivalent by
also checking if the two sets of conditions A and B depends on are
equivalent.
Reviewer: jdoerfert, Meinersbur, dmgreen, etiotto, bmahjour, fhahn,
hfinkel, kbarton
Reviewed By: fhahn
Subscribers: hiraditya, llvm-commits
Tag: LLVM
Differential Revision: https://reviews.llvm.org/D71578

4 years ago[lldb/PDB] Use the new line table constructor
Pavel Labath [Tue, 28 Jan 2020 14:03:09 +0000 (15:03 +0100)]
[lldb/PDB] Use the new line table constructor

The old method of adding line sequences one by one can easily go
quadratic if the sequences are not perfectly sorted. The equivalent
change in DWARF brought a considerable improvement in line table
parsing. It is not clear if the same will be the case for PDB, but this
does bring us a step closer towards removing the dangerous API.

4 years agoFix sphinx build bot failure. NFCI.
Wang, Pengfei [Tue, 28 Jan 2020 14:05:15 +0000 (22:05 +0800)]
Fix sphinx build bot failure. NFCI.

4 years agoRevert "PR44684: Look through parens and similar constructs when determining"
Nico Weber [Tue, 28 Jan 2020 14:03:27 +0000 (09:03 -0500)]
Revert "PR44684: Look through parens and similar constructs when determining"

This reverts commit af80b8ccc5772c14920d4554b7ca7e15f2fad1c4.
It broke clang-tidy/checkers/modernize-use-uncaught-exceptions.cpp in
check-clang-tools on macOS and Windows, see e.g.
http://lab.llvm.org:8011/builders/clang-x64-windows-msvc/builds/13976/steps/stage%201%20check/logs/stdio

4 years ago[NFC][RDA] typedef SmallPtrSetImpl<MachineInstr*>
Sam Parker [Tue, 28 Jan 2020 13:06:07 +0000 (13:06 +0000)]
[NFC][RDA] typedef SmallPtrSetImpl<MachineInstr*>

4 years ago[ASTMatchers] Add cxxNoexceptExpr AST matcher
Nathan [Tue, 28 Jan 2020 13:12:08 +0000 (13:12 +0000)]
[ASTMatchers] Add cxxNoexceptExpr AST matcher

Summary: Adds a cxxNoexceptExpr matcher that matches the [[ https://en.cppreference.com/w/cpp/language/noexcept |  noexcept operator ]].

Reviewers: aaron.ballman

Reviewed By: aaron.ballman

Subscribers: merge_guards_bot, cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D73439

4 years ago[ADT] Implicitly convert between StringRef and std::string_view when we have C++17
Benjamin Kramer [Tue, 28 Jan 2020 12:51:38 +0000 (13:51 +0100)]
[ADT] Implicitly convert between StringRef and std::string_view when we have C++17

This makes the types almost seamlessly interchangeable in C++17
codebases. Eventually we want to replace StringRef with the standard
type, but that requires C++17 being the default and a huge refactoring
job as StringRef has a lot more functionality.

4 years agoRevert "[lldb/DWARF] Only match mangled name in full-name function lookup (with accel...
Pavel Labath [Tue, 28 Jan 2020 12:42:34 +0000 (13:42 +0100)]
Revert "[lldb/DWARF] Only match mangled name in full-name function lookup (with accelerators)"

This reverts commit 1b12766883006b8aa9d1ff744e57317647aa052a because of
breaking the mac test suite.

I'm not certain this is the cause because of a concurrent build breakage
which masked this problem, but the failure messages are related to
symbol lookup, which makes this very likely.

4 years ago[FPEnv] Add pragma FP_CONTRACT support under strict FP.
Wang, Pengfei [Wed, 15 Jan 2020 11:08:38 +0000 (19:08 +0800)]
[FPEnv] Add pragma FP_CONTRACT support under strict FP.

Summary: Support pragma FP_CONTRACT under strict FP.

Reviewers: craig.topper, andrew.w.kaylor, uweigand, RKSimon, LiuChen3

Subscribers: hiraditya, jdoerfert, cfe-commits, llvm-commits, LuoYuanke

Tags: #clang, #llvm

Differential Revision: https://reviews.llvm.org/D72820

4 years ago[mips][NFC] Remove unused instruction formats
Miloš Stojanović [Mon, 27 Jan 2020 15:29:26 +0000 (16:29 +0100)]
[mips][NFC] Remove unused instruction formats

`BranchBase` unused sice: rL170663
`FI` unsused since: rL170954
`FFI` unused since: rL190221

Differential revision: https://reviews.llvm.org/D73489

4 years ago[X86] Add combination for fma and fneg on X86 under strict FP.
Wang, Pengfei [Wed, 15 Jan 2020 11:08:38 +0000 (19:08 +0800)]
[X86] Add combination for fma and fneg on X86 under strict FP.

Summary: X86 has instructions to calculate fma and fneg at the same time. But we combine the fneg and fma only when fneg is the source operand under strict FP.

Reviewers: craig.topper, andrew.w.kaylor, uweigand, RKSimon, LiuChen3

Subscribers: LuoYuanke, llvm-commits, cfe-commits, jdoerfert, hiraditya

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D72824

4 years ago[LLD][ELF][ARM] Do not insert interworking thunks for non STT_FUNC symbols
Peter Smith [Thu, 23 Jan 2020 19:03:25 +0000 (19:03 +0000)]
[LLD][ELF][ARM] Do not insert interworking thunks for non STT_FUNC symbols

ELF for the ARM architecture requires linkers to provide
interworking for symbols that are of type STT_FUNC. Interworking for
other symbols must be encoded directly in the object file. LLD was always
providing interworking, regardless of the symbol type, this breaks some
programs that have branches from Thumb state targeting STT_NOTYPE symbols
that have bit 0 clear, but they are in fact internal labels in a Thumb
function. LLD treats these symbols as ARM and inserts a transition to Arm.

This fixes the problem for in range branches, R_ARM_JUMP24,
R_ARM_THM_JUMP24 and R_ARM_THM_JUMP19. This is expected to be the vast
majority of problem cases as branching to an internal label close to the
function.

There is at least one follow up patch required.
- R_ARM_CALL and R_ARM_THM_CALL may do interworking via BL/BLX
  substitution.

In theory range-extension thunks can be altered to not change state when
the symbol type is not STT_FUNC. I will need to check with ld.bfd to see if
this is the case in practice.

Fixes (part of) https://github.com/ClangBuiltLinux/linux/issues/773

Differential Revision: https://reviews.llvm.org/D73474

4 years ago[LLD][ELF][ARM] clang-format function signature [NFC]
Peter Smith [Tue, 28 Jan 2020 11:22:48 +0000 (11:22 +0000)]
[LLD][ELF][ARM] clang-format function signature [NFC]

ARM::needsThunk had gone over 80 characters, run clang-format over it to
prevent it wrapping.

4 years agoRevert "[DebugInfo] Make most debug line prologue errors non-fatal to parsing"
James Henderson [Tue, 28 Jan 2020 11:49:30 +0000 (11:49 +0000)]
Revert "[DebugInfo] Make most debug line prologue errors non-fatal to parsing"

This reverts commit b94191fecdbadc18b342a27df1109754edcb8c4b.

The change broke both an LLD test and the LLDB build.

4 years ago[DebugInfo] Make most debug line prologue errors non-fatal to parsing
James Henderson [Fri, 3 Jan 2020 15:19:27 +0000 (15:19 +0000)]
[DebugInfo] Make most debug line prologue errors non-fatal to parsing

Many of the debug line prologue errors are not inherently fatal. In most
cases, we can make reasonable assumptions and carry on. This patch does
exactly that. In the case of length problems, the approach of "the
claimed length is correct" is taken to be consistent with other
instances such as the SectionParser, which ignores the read length.

Reviewed by: dblaikie

Differential Revision: https://reviews.llvm.org/D72158

4 years ago[clangd] use SCOPED_TRACE to better trace the testcase in test failure, NFC
Haojian Wu [Mon, 27 Jan 2020 13:09:27 +0000 (14:09 +0100)]
[clangd] use SCOPED_TRACE to better trace the testcase in test failure, NFC

Reviewers: kadircet

Subscribers: ilya-biryukov, MaskRay, jkorous, arphaman, usaxena95, cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D73463

4 years ago[lldb/DWARF] Only match mangled name in full-name function lookup (with accelerators)
Jaroslav Sevcik [Tue, 28 Jan 2020 10:37:44 +0000 (11:37 +0100)]
[lldb/DWARF] Only match mangled name in full-name function lookup (with accelerators)

Summary:
In the spirit of https://reviews.llvm.org/D70846, we only return functions with matching mangled name from Apple/DebugNamesDWARFIndex::GetFunction if eFunctionNameTypeFull is requested.

This speeds up lookup in the presence of large amount of class methods of the same name (a typical examples would be constructors of templates with many instantiations or overloaded operators).

Reviewers: labath

Reviewed By: labath

Subscribers: aprantl, arphaman, lldb-commits

Tags: #lldb

Differential Revision: https://reviews.llvm.org/D73191

4 years ago[docs] Clarify llvm.used semantics with less awkward wording
Benjamin Kramer [Tue, 28 Jan 2020 11:13:57 +0000 (12:13 +0100)]
[docs] Clarify llvm.used semantics with less awkward wording

4 years agoAdd lowering for loop.parallel to cfg.
Stephan Herhut [Fri, 24 Jan 2020 14:17:04 +0000 (15:17 +0100)]
Add lowering for loop.parallel to cfg.

Summary:
This also removes the explicit pattern for loop.terminator to ensure
that the terminator is only erased if the parent op is rewritten.

Reductions are not yet supported.

Reviewers: nicolasvasilache

Subscribers: mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, arpith-jacob, mgester, lucyrfox, aartbik, liufengdb, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D73348

4 years ago[mlir] NFC: use ValueRange in AffineToStandard conversion
Alex Zinenko [Tue, 28 Jan 2020 10:53:00 +0000 (11:53 +0100)]
[mlir] NFC: use ValueRange in AffineToStandard conversion

ValueRange is a more flexible way of passing around ranges of Values
that avoids Value vector materialization in affine expression expansion.

4 years ago[AMDGPU] Fix vccz after v_readlane/v_readfirstlane to vcc_lo/hi
Jay Foad [Wed, 30 Oct 2019 12:18:51 +0000 (12:18 +0000)]
[AMDGPU] Fix vccz after v_readlane/v_readfirstlane to vcc_lo/hi

Summary:
Up to gfx9, writes to vcc_lo and vcc_hi by instructions like
v_readlane and v_readfirstlane do not update vccz to reflect the new
value of vcc. Fix it by reusing part of the existing vccz bug handling
code, which inserts an "s_mov_b64 vcc, vcc" instruction to restore vccz
just before an instruction that needs the correct value.

Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D69661

4 years ago[lldb][NFC] Simplify Materializer/Dematerializer constructors
Raphael Isemann [Tue, 28 Jan 2020 10:31:02 +0000 (11:31 +0100)]
[lldb][NFC] Simplify Materializer/Dematerializer constructors

4 years ago[clangd][Hover] Handle uninstantiated templates
Kadir Cetinkaya [Fri, 24 Jan 2020 12:04:00 +0000 (13:04 +0100)]
[clangd][Hover] Handle uninstantiated templates

Summary: Fixes https://github.com/clangd/clangd/issues/263

Reviewers: hokein, sammccall

Subscribers: ilya-biryukov, MaskRay, jkorous, arphaman, usaxena95, cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D73344