Craig Topper [Fri, 22 Sep 2017 19:54:15 +0000 (19:54 +0000)]
[InstCombine] Add constant splat handling to one of the ICMP_SLT/SGT cases in foldICmpUsingKnownBits.
llvm-svn: 314025
Sanjay Patel [Fri, 22 Sep 2017 19:49:37 +0000 (19:49 +0000)]
[x86] shiftRightAlgebraic -> shiftRightArithmetic; NFC
x86 re-education camp is in session. The LLVM LangRef agrees with x86 too.
The DAG nodes are undocumented and ambiguous as always. :)
llvm-svn: 314024
Sanjay Patel [Fri, 22 Sep 2017 19:37:21 +0000 (19:37 +0000)]
[x86] swap order of srl (and X, C1), C2 when it saves size
The (non-)obvious win comes from saving 3 bytes by using the 0x83 'and' opcode variant instead of 0x81.
There are also better improvements based on known-bits that allow us to eliminate the mask entirely.
As noted, this could be extended. There are potentially other wins from always shifting first, but doing
that reveals a tangle of problems in other pattern matching. We do this transform generically in
instcombine, but we often have icmp IR that doesn't match that pattern, so we must account for this
in the backend.
Differential Revision: https://reviews.llvm.org/D38181
llvm-svn: 314023
Alexander Shaposhnikov [Fri, 22 Sep 2017 19:29:38 +0000 (19:29 +0000)]
[clang] Fix isExternC matcher docs
The wording in the documentation for the matcher isExternC
appears to be misleading since this matcher
is applicable to functions and variables as well.
This diff changes the comment and regenerates the html file.
Differential revision: https://reviews.llvm.org/D38151
llvm-svn: 314022
Francis Ricci [Fri, 22 Sep 2017 19:22:08 +0000 (19:22 +0000)]
Fix fuchsia builds broken by r313999
llvm-svn: 314021
Ilya Biryukov [Fri, 22 Sep 2017 19:07:45 +0000 (19:07 +0000)]
[clangd] Updated gold for completion tests after cfe changes.
llvm-svn: 314020
Ilya Biryukov [Fri, 22 Sep 2017 19:07:37 +0000 (19:07 +0000)]
Set completion priority of destructors and operators to CCP_Unlikely.
Summary:
It will move destructors and operators to the end of completion list.
Destructors and operators are currently very high on the completion
list, as they have the same priority as member functions. However,
they are clearly not something users usually choose in completion
lists.
Reviewers: arphaman, erikjv, bkramer, krasimir
Reviewed By: arphaman
Subscribers: eraman, klimek, cfe-commits
Differential Revision: https://reviews.llvm.org/D38081
llvm-svn: 314019
Craig Topper [Fri, 22 Sep 2017 18:57:23 +0000 (18:57 +0000)]
[InstCombine] Move the call to isSignBitCheck into getDemandedBitsLHSMask instead of calling it outside and passing its result through a flag. NFCI
The result of the isSignBitCheck isn't used anywhere else and this allows us to share the m_APInt call in the likely case that it isn't a sign bit check.
llvm-svn: 314018
Craig Topper [Fri, 22 Sep 2017 18:57:22 +0000 (18:57 +0000)]
[InstCombine] Simplify check for RHS being a splat constant in foldICmpUsingKnownBits by just checking Op1Min==Op1Max rather than going through m_APInt.
llvm-svn: 314017
Craig Topper [Fri, 22 Sep 2017 18:57:20 +0000 (18:57 +0000)]
[InstCombine] Make cases for ICMP_UGT/ICMP_ULT use similar formatting since they use similar code. NFC
llvm-svn: 314016
Vitaly Buka [Fri, 22 Sep 2017 18:50:18 +0000 (18:50 +0000)]
[sanitizer] Replace AddressSanitizer with correct tool name
llvm-svn: 314015
Kuba Mracek [Fri, 22 Sep 2017 18:49:56 +0000 (18:49 +0000)]
Deflake the "xpc-race.mm" test.
llvm-svn: 314014
Vedant Kumar [Fri, 22 Sep 2017 18:42:28 +0000 (18:42 +0000)]
[lit.cfg] Avoid concatenating which(clang-func-mapping) if it's missing
This un-breaks a lit workflow where you run lit tests from a test
sub-directory within clang without first building clang-func-mapping.
llvm-svn: 314013
Rafael Espindola [Fri, 22 Sep 2017 18:40:14 +0000 (18:40 +0000)]
Move code to a helper function. NFC.
Part of a patch by Jake Ehrlich!
llvm-svn: 314012
Alexander Shaposhnikov [Fri, 22 Sep 2017 18:36:06 +0000 (18:36 +0000)]
[clang] Fix printf fixit for objc specific types
For the triple thumbv7-apple-ios8.0.0 ssize_t is long and size_t is unsigned long,
while NSInteger is int and NSUinteger is unsigned int. Following
https://developer.apple.com/library/content/documentation/Cocoa/Conceptual/Strings/Articles/formatSpecifiers.html
Clang catches it and insert a cast to long, for example
printf("%zd", getNSInteger())
will be replaced with
printf("%zd", (long)getNSInteger())
but since the underlying type of ssize_t is long the specifier "%zd" is not getting replaced.
This diff changes this behavior to enable replacing the specifier "%zd" with the correct one.
Differential revision: https://reviews.llvm.org/D38159
Test plan: make check-all
llvm-svn: 314011
Rafael Espindola [Fri, 22 Sep 2017 18:36:00 +0000 (18:36 +0000)]
llvm-ar: align the first archive member consistently.
Before we were aligning the member after the symbol table to 4 but
other members to 8.
llvm-svn: 314010
Saleem Abdulrasool [Fri, 22 Sep 2017 18:35:09 +0000 (18:35 +0000)]
bindings: expose Linkage to the python bindings
Add Python bindings for the 'clang_getCursorLinkage', and tests to
validate the functionality.
Patch by Masud Rahman!
llvm-svn: 314009
Vitaly Buka [Fri, 22 Sep 2017 18:32:05 +0000 (18:32 +0000)]
[sanitizer] Move report locking code from asan into common
llvm-svn: 314008
Vitaly Buka [Fri, 22 Sep 2017 18:31:51 +0000 (18:31 +0000)]
[asan] Fix unlocking order for CommonSanitizerReportMutex and reporting_thread_tid_
llvm-svn: 314007
Vitaly Buka [Fri, 22 Sep 2017 18:31:37 +0000 (18:31 +0000)]
[sanitizer] Move CommonSanitizerReportMutex from _print.cc to _common.cc
llvm-svn: 314006
Tim Shen [Fri, 22 Sep 2017 18:30:02 +0000 (18:30 +0000)]
[XRay] support conditional return on PPC.
Summary: Conditional returns were not taken into consideration at all. Implement them by turning them into jumps and normal returns. This means there is a slightly higher performance penalty for conditional returns, but this is the best we can do, and it still disturbs little of the rest.
Reviewers: dberris, echristo
Subscribers: sanjoy, nemanjai, hiraditya, kbarton, llvm-commits
Differential Revision: https://reviews.llvm.org/D38102
llvm-svn: 314005
Krzysztof Parzyszek [Fri, 22 Sep 2017 18:29:37 +0000 (18:29 +0000)]
[TableGen] Replace InfoByHwMode::getAsString with writeToStream
Also add operator<< for use with raw_ostream to InfoByHwMode and its
derived classes.
Recommitting r313989 with the fix for unresolved references: explicitly
define the operator<< in namespace llvm.
llvm-svn: 314004
Guozhi Wei [Fri, 22 Sep 2017 18:25:53 +0000 (18:25 +0000)]
[TargetTransformInfo] Handle intrinsic call in getInstructionLatency()
Usually an intrinsic is a simple target instruction, it should have a small latency. A real function call has much larger latency. So handle the intrinsic call in function getInstructionLatency().
Differential Revision: https://reviews.llvm.org/D38104
llvm-svn: 314003
Vedant Kumar [Fri, 22 Sep 2017 18:23:04 +0000 (18:23 +0000)]
[Coverage] Add an option to emit limited coverage info
Add an option to emit limited coverage info for unused decls. It's just a
cl::opt for now to allow us to experiment quickly.
When building llc, this results in an 84% size reduction in the llvm_covmap
section, and a similar size reduction in the llvm_prf_names section. In
practice I expect the size reduction to be roughly quadratic with the size of
the program.
The downside is that coverage for headers will no longer be complete. This will
make the line/function/region coverage metrics incorrect, since they will be
artificially high. One mitigation would be to somehow disable those metrics
when using limited-coverage=true.
This is related to: llvm.org/PR34533 (make SourceBasedCodeCoverage scale)
Differential Revision: https://reviews.llvm.org/D38107
llvm-svn: 314002
Francis Ricci [Fri, 22 Sep 2017 18:17:26 +0000 (18:17 +0000)]
Fix windows buildbot broken by r313999
llvm-svn: 314001
Rafael Espindola [Fri, 22 Sep 2017 18:16:13 +0000 (18:16 +0000)]
llvm-ar: Don't add an unnecessary alignment in gnu mode.
This is mostly for getting stricter testing in preparation for future
changes.
llvm-svn: 314000
Francis Ricci [Fri, 22 Sep 2017 17:48:24 +0000 (17:48 +0000)]
Removed platform-specific ifdefs from sanitizer_procmaps.h
Summary: Removed platform-specific ifdefs for linux, mac, freebsd and netbsd from sanitizer_procmaps.h
Patch by Yicheng Wang <yichengfb@fb.com>
Reviewers: kcc, kubamracek, alekseyshl, fjricci, vitalybuka
Reviewed By: fjricci, vitalybuka
Subscribers: vitalybuka, emaste, krytarowski, llvm-commits
Differential Revision: https://reviews.llvm.org/D38098
llvm-svn: 313999
Balaram Makam [Fri, 22 Sep 2017 17:46:36 +0000 (17:46 +0000)]
[Falkor] Add falkor CPU to host detection
This returns "falkor" for Falkor CPU.
llvm-svn: 313998
Dave Lee [Fri, 22 Sep 2017 16:58:57 +0000 (16:58 +0000)]
[index] Generate class & metaclass manglings for objc
Summary:
ObjC classes have two associated symbols, one for the class and one for the
metaclass.
This change overloads `CodegenNameGenerator::getAllManglings` to produce both
class and metaclass symbols.
While this function is called by `clang_Cursor_getCXXManglings`, it's only
called for CXXRecordDecl and CXXMethodDecl, and so libclang's behavior is
unchanged.
Reviewers: arphaman, abdulras, alexshap, compnerd
Reviewed By: compnerd
Subscribers: compnerd
Differential Revision: https://reviews.llvm.org/D37671
llvm-svn: 313997
Simon Pilgrim [Fri, 22 Sep 2017 16:57:28 +0000 (16:57 +0000)]
Remove trailing whitespace. NFCI.
llvm-svn: 313996
Alexey Bataev [Fri, 22 Sep 2017 16:56:13 +0000 (16:56 +0000)]
[OPENMP] Handle re-declaration of captured variables in CodeGen.
If the captured variable has re-declaration we may end up with the
situation where the captured variable is the re-declaration while the
referenced variable is the canonical declaration (or vice versa). In
this case we may generate wrong code. Patch fixes this situation.
llvm-svn: 313995
Pranav Bhandarkar [Fri, 22 Sep 2017 16:43:31 +0000 (16:43 +0000)]
Check vector elements for equivalence in the HexagonVectorLoopCarriedReuse pass
If the two instructions being compared for equivalence have corresponding operands
that are integer constants, then check their values to determine equivalence.
Patch by Suyog Sarda!
llvm-svn: 313993
Wei Mi [Fri, 22 Sep 2017 16:30:00 +0000 (16:30 +0000)]
[Atomic][X8664] set max atomic inline width according to the target
This is to fix PR31620. MaxAtomicInlineWidth is set to 128 for x86_64. However
for target without cx16 support, 128 atomic operation will generate __sync_*
libcalls. The patch set MaxAtomicInlineWidth to 64 if the target doesn't support
cx16.
Differential Revision: https://reviews.llvm.org/D38046
llvm-svn: 313992
Simon Pilgrim [Fri, 22 Sep 2017 16:26:17 +0000 (16:26 +0000)]
Fix unused variable warning. NFCI.
llvm-svn: 313991
Krzysztof Parzyszek [Fri, 22 Sep 2017 16:18:35 +0000 (16:18 +0000)]
Revert "[TableGen] Replace InfoByHwMode::getAsString with writeToStream"
This reverts commit r313989: it breaks Windows bots.
llvm-svn: 313990
Krzysztof Parzyszek [Fri, 22 Sep 2017 16:06:35 +0000 (16:06 +0000)]
[TableGen] Replace InfoByHwMode::getAsString with writeToStream
Also add operator<< for use with raw_ostream to InfoByHwMode and its
derived classes.
llvm-svn: 313989
Daniel Neilson [Fri, 22 Sep 2017 15:47:57 +0000 (15:47 +0000)]
[SCEV] Generalize folding of trunc(x)+n*trunc(y) into folding m*trunc(x)+n*trunc(y)
Summary:
A SCEV such as:
{%v2,+,((-1 * (trunc i64 (-1 * %v1) to i32)) + (-1 * (trunc i64 %v1 to i32)))}<%loop>
can be folded into, simply, {%v2,+,0}. However, the current code in ::getAddExpr()
will not try to apply the simplification m*trunc(x)+n*trunc(y) -> trunc(trunc(m)*x+trunc(n)*y)
because it only keys off having a non-multiplied trunc as the first term in the simplification.
This patch generalizes this code to try to do a more generic fold of these trunc
expressions.
Reviewers: sanjoy
Reviewed By: sanjoy
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D37888
llvm-svn: 313988
Kostya Kortchinsky [Fri, 22 Sep 2017 15:35:37 +0000 (15:35 +0000)]
[scudo] Scudo thread specific data refactor, part 1
Summary:
We are going through an overhaul of Scudo's TSD, to allow for new platforms
to be integrated more easily, and make the code more sound.
This first part is mostly renaming, preferring some shorter names, correcting
some comments. I removed `getPrng` and `getAllocatorCache` to directly access
the members, there was not really any benefit to them (and it was suggested by
Dmitry in D37590).
The only functional change is in `scudo_tls_android.cpp`: we enforce bounds to
the `NumberOfTSDs` and most of the logic in `getTSDAndLockSlow` is skipped if we
only have 1 TSD.
Reviewers: alekseyshl, dvyukov, kcc
Reviewed By: dvyukov
Subscribers: llvm-commits, srhines
Differential Revision: https://reviews.llvm.org/D38139
llvm-svn: 313987
Sanjay Patel [Fri, 22 Sep 2017 14:38:57 +0000 (14:38 +0000)]
[x86] remove unnecessary OS specifier from test
llvm-svn: 313986
Sanjay Patel [Fri, 22 Sep 2017 14:30:52 +0000 (14:30 +0000)]
[x86] auto-generate complete checks; NFC
llvm-svn: 313985
Sanjay Patel [Fri, 22 Sep 2017 14:29:47 +0000 (14:29 +0000)]
[x86] update test to use FileCheck; NFC
llvm-svn: 313984
Simon Pilgrim [Fri, 22 Sep 2017 13:32:26 +0000 (13:32 +0000)]
[TableGen] Return StringRef from ValueTypeByHwMode::getMVTName
Avoid unnecessary std::string creations during TypeSetByHwMode::writeToStream.
Found during investigations into PR28222
Differential Revision: https://reviews.llvm.org/D38174
llvm-svn: 313983
Alexander Ivchenko [Fri, 22 Sep 2017 13:21:39 +0000 (13:21 +0000)]
[X86] Combining CMOVs with [ANY,SIGN,ZERO]_EXTEND for cases where CMOV has constant arguments
Combine CMOV[i16]<-[SIGN,ZERO,ANY]_EXTEND to [i32,i64] into CMOV[i32,i64].
One example of where it is useful is:
before (20 bytes)
<foo>:
test $0x1,%dil
mov $0x307e,%ax
mov $0xffff,%cx
cmovne %ax,%cx
movzwl %cx,%eax
retq
after (18 bytes)
<foo>:
test $0x1,%dil
mov $0x307e,%ecx
mov $0xffff,%eax
cmovne %ecx,%eax
retq
Reviewers: craig.topper, aaboud, spatel, RKSimon, zvi
Reviewed By: spatel
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D36711
llvm-svn: 313982
Artur Pilipenko [Fri, 22 Sep 2017 13:13:57 +0000 (13:13 +0000)]
Rework loop predication pass
We've found a serious issue with the current implementation of loop predication.
The current implementation relies on SCEV and this turned out to be problematic.
To fix the problem we had to rework the pass substantially. We have had the
reworked implementation in our downstream tree for a while. This is the initial
patch of the series of changes to upstream the new implementation.
For now the transformation is limited to the following case:
* The loop has a single latch with either ult or slt icmp condition.
* The step of the IV used in the latch condition is 1.
* The IV of the latch condition is the same as the post increment IV of the guard condition.
* The guard condition is ult.
See the review or the LoopPredication.cpp header for the details about the
problem and the new implementation.
Reviewed By: sanjoy, mkazantsev
Differential Revision: https://reviews.llvm.org/D37569
llvm-svn: 313981
Nemanja Ivanovic [Fri, 22 Sep 2017 12:26:00 +0000 (12:26 +0000)]
Remove the default clause from a fully-covering switch
to appease bots that use a compiler that warns about this
and use -Werror.
llvm-svn: 313980
Andre Vieira [Fri, 22 Sep 2017 12:17:42 +0000 (12:17 +0000)]
[ARM] Fix assembly and disassembly for VMRS/VMSR
Reviewed by: t.p.northover
Differential Revision: https://reviews.llvm.org/D36306
llvm-svn: 313979
Nemanja Ivanovic [Fri, 22 Sep 2017 11:50:25 +0000 (11:50 +0000)]
Recommit r310809 with a fix for the spill problem
This patch re-commits the patch that was pulled out due to a
problem it caused, but with a fix for the problem. The fix
was reviewed separately by Eric Christopher and Hal Finkel.
Differential Revision: https://reviews.llvm.org/D38054
llvm-svn: 313978
Michael Kruse [Fri, 22 Sep 2017 11:30:26 +0000 (11:30 +0000)]
polly-update-format after change in clang-format. NFC.
r313963 changed the sorting of using-declarations.
llvm-svn: 313976
Gabor Horvath [Fri, 22 Sep 2017 11:11:01 +0000 (11:11 +0000)]
Add Cross Translation Unit support library
This patch introduces a class that can help to build tools that require cross
translation unit facilities. This class allows function definitions to be loaded
from external AST files based on an index. In order to use this functionality an
index is required. The index format is a flat text file but it might be
replaced with a different solution in the near future. USRs are used as names to
look up the functions definitions. This class also does caching to avoid
redundant loading of AST files.
Right now only function defnitions can be loaded using this API because this is
what the in progress cross translation unit feature of the Static Analyzer
requires. In to future this might be extended to classes, types etc.
Differential Revision: https://reviews.llvm.org/D34512
llvm-svn: 313975
Maxim Ostapenko [Fri, 22 Sep 2017 10:44:28 +0000 (10:44 +0000)]
[asan/lsan] Trying to fix PPC64 and x380x buildbots after r313966
llvm-svn: 313974
Gabor Horvath [Fri, 22 Sep 2017 10:16:33 +0000 (10:16 +0000)]
[analyzer] Add new delete with non-virtual destructor check
Patch by: Reka Nikolett Kovacs
Differential Revision: https://reviews.llvm.org/D35796
llvm-svn: 313973
Simon Pilgrim [Fri, 22 Sep 2017 09:50:52 +0000 (09:50 +0000)]
[ARM] Add missing selection patterns for vnmla
For the following function:
double fn1(double d0, double d1, double d2) {
double a = -d0 - d1 * d2;
return a;
}
on ARM, LLVM generates code along the lines of
vneg.f64 d0, d0
vmls.f64 d0, d1, d2
i.e., a negate and a multiply-subtract.
The attached patch adds instruction selection patterns to allow it to generate the single instruction
vnmla.f64 d0, d1, d2
(multiply-add with negation) instead, like GCC does.
Committed on behalf of @gergo- (Gergö Barany)
Differential Revision: https://reviews.llvm.org/D35911
llvm-svn: 313972
Jonas Devlieghere [Fri, 22 Sep 2017 09:38:52 +0000 (09:38 +0000)]
[dwarfdump] Fix ambiguous call to make_unique
Fix buildbot failures:
- http://lab.llvm.org:8011/builders/lldb-x86-windows-msvc2015/builds/13153
- http://lab.llvm.org:8011/builders/lld-x86_64-win7/builds/13566
llvm-svn: 313971
Alexander Richardson [Fri, 22 Sep 2017 09:30:40 +0000 (09:30 +0000)]
[obj2yaml] Don't crash for input files without symbol table
Summary: Previously we would dereference Symtab without checking for null.
Reviewers: davide, atanasyan, rafael
Reviewed By: davide, atanasyan
Differential Revision: https://reviews.llvm.org/D38080
llvm-svn: 313970
Jonas Devlieghere [Fri, 22 Sep 2017 09:20:57 +0000 (09:20 +0000)]
[dwarfdump] Add support for redirecting output to a file
This patch adds the -o and --out-file options for compatibility with
Darwin's dwarfdump.
Differential revision: https://reviews.llvm.org/D38125
llvm-svn: 313969
Alexander Richardson [Fri, 22 Sep 2017 08:52:03 +0000 (08:52 +0000)]
[mips] clang-format MipsTargetMachine.cpp
This is my test commit as it only changes two lines
llvm-svn: 313968
Maxim Ostapenko [Fri, 22 Sep 2017 08:23:16 +0000 (08:23 +0000)]
[asan/lsan] Trying to fix buildbots after r313966
llvm-svn: 313967
Maxim Ostapenko [Fri, 22 Sep 2017 07:11:43 +0000 (07:11 +0000)]
[asan/lsan] Make LSan compliant with recovery mode when running on top of ASan
Don't overwrite exit code in LSan when running on top of ASan in recovery mode
to avoid breakage of users code due to found leaks.
Patch by Slava Barinov.
Differential Revision: https://reviews.llvm.org/D38026
llvm-svn: 313966
Dylan McKay [Fri, 22 Sep 2017 06:32:23 +0000 (06:32 +0000)]
[AVR] Remove the 'IsN64' argument to 'MCELFObjectWriter'
This has since been removed.
llvm-svn: 313965
Jatin Bhateja [Fri, 22 Sep 2017 05:48:20 +0000 (05:48 +0000)]
[X86] Updating the test case for FMF propagation.
Differential Revision: https://reviews.llvm.org/D38163
llvm-svn: 313964
Krasimir Georgiev [Fri, 22 Sep 2017 04:48:17 +0000 (04:48 +0000)]
[clang-format] Ignore case and stable sort using-declarations
Summary:
This ignores case while sorting using-declarations, fixing a case where `_` would appear between lowercase and uppercase characters.
It also applies stable sort, so that replacements for the exact same using declarations are not generated.
Reviewers: klimek, alexfh
Reviewed By: alexfh
Subscribers: cfe-commits
Differential Revision: https://reviews.llvm.org/D37263
llvm-svn: 313963
Krasimir Georgiev [Fri, 22 Sep 2017 04:37:56 +0000 (04:37 +0000)]
[clang-tidy] Fix example in documentation, NFC
Summary: A fix in documentation.
Reviewers: bkramer
Reviewed By: bkramer
Subscribers: JDevlieghere, xazax.hun
Differential Revision: https://reviews.llvm.org/D38087
llvm-svn: 313962
Yonghong Song [Fri, 22 Sep 2017 04:36:36 +0000 (04:36 +0000)]
bpf: initial 32-bit ALU encoding support in assembler
This patch adds instruction patterns for operations in BPF_ALU. After this,
assembler could recognize some 32-bit ALU statement. For example, those listed
int the unit test file.
Separate MOV patterns are unnecessary as MOV is ALU operation that could reuse
ALU encoding infrastructure, this patch removed those redundant patterns.
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Reviewed-by: Yonghong Song <yhs@fb.com>
llvm-svn: 313961
Yonghong Song [Fri, 22 Sep 2017 04:36:35 +0000 (04:36 +0000)]
bpf: add 32bit register set
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Reviewed-by: Yonghong Song <yhs@fb.com>
llvm-svn: 313960
Yonghong Song [Fri, 22 Sep 2017 04:36:34 +0000 (04:36 +0000)]
bpf: refactor inst patterns with better inheritance
Arithmetic and jump instructions, load and store instructions are sharing
the same 8-bit code field encoding,
A better instruction pattern implemention could be the following inheritance
relationships, and each layer only encoding those fields which start to
diverse from that layer. This avoids some redundant code.
InstBPF -> TYPE_ALU_JMP -> ALU/JMP
InstBPF -> TYPE_LD_ST -> Load/Store
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Reviewed-by: Yonghong Song <yhs@fb.com>
llvm-svn: 313959
Yonghong Song [Fri, 22 Sep 2017 04:36:32 +0000 (04:36 +0000)]
bpf: refactor inst patterns with more mnemonics
Currently, eBPF backend is using some constant directly in instruction patterns,
This patch replace them with mnemonics and removed some unnecessary temparary
variables.
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Reviewed-by: Yonghong Song <yhs@fb.com>
llvm-svn: 313958
Richard Smith [Fri, 22 Sep 2017 04:33:20 +0000 (04:33 +0000)]
Closure types have no name (and can't have a typedef name for linkage
purposes), so they never formally have linkage.
llvm-svn: 313957
Saleem Abdulrasool [Fri, 22 Sep 2017 04:31:44 +0000 (04:31 +0000)]
AArch64: support SwiftCC properly on AAPCS64
The previous SwiftCC support for AAPCS64 was partially correct. It
setup swiftself parameters in the proper register but failed to setup
swifterror in the correct register. This would break compilation of
swift code for non-Darwin AAPCS64 conforming environments.
llvm-svn: 313956
Richard Smith [Fri, 22 Sep 2017 04:25:05 +0000 (04:25 +0000)]
Give external linkage and mangling to lambdas inside inline variables and variable templates.
This implements the proposed approach in https://github.com/itanium-cxx-abi/cxx-abi/issues/33
This reinstates r313827, reverted in r313856, with a fix for the 'out-of-bounds
enumeration value' ubsan error in that change.
llvm-svn: 313955
Saleem Abdulrasool [Fri, 22 Sep 2017 04:01:12 +0000 (04:01 +0000)]
Driver: remove support for libstdc++ from CrossWindows
This code path is entirely untested and not really maintained. The
expected use here is with libc++ only.
llvm-svn: 313954
Richard Smith [Fri, 22 Sep 2017 02:22:32 +0000 (02:22 +0000)]
Clean up some mistreatment of enumerations.
llvm-svn: 313953
Akira Hatanaka [Fri, 22 Sep 2017 01:54:36 +0000 (01:54 +0000)]
Add test cases that weren't committed in r313945.
llvm-svn: 313952
Sanjoy Das [Fri, 22 Sep 2017 01:47:41 +0000 (01:47 +0000)]
Rename markAsErased to erase, as pointed out in a previous review; NFC
llvm-svn: 313951
George Karpenkov [Fri, 22 Sep 2017 01:43:12 +0000 (01:43 +0000)]
[Analyzer] Static analyzer script for updating reference results
The script updates reference results from the previous run, and stages them.
Differential Revision: https://reviews.llvm.org/D38157
llvm-svn: 313950
George Karpenkov [Fri, 22 Sep 2017 01:41:16 +0000 (01:41 +0000)]
[Analyzer] Refactor analyzer testing scripts.
- Exporting needed function for future reuse.
- Idiomatic python: using with `file as f` instead of `try/finally`.
- Fixing some indentation issues.
- No need to reinvent python `multiprocessing.getCPUCount()`
- Removing a function parameter which is always the same under all invocations.
- Adding some docstrings.
Differential Revision: https://reviews.llvm.org/D38156
llvm-svn: 313949
Richard Smith [Fri, 22 Sep 2017 01:04:22 +0000 (01:04 +0000)]
Fix tracking of whether a destructor would be deleted.
I've been unable to find any cases whose behavior is actually changed by this,
but only because an implicitly deleted destructor also results in it being
impossible to have a trivial (non-deleted) copy constructor, which the place
where this really matters (choosing whether to pass a class in registers)
happens to also check.
llvm-svn: 313948
NAKAMURA Takumi [Fri, 22 Sep 2017 01:01:33 +0000 (01:01 +0000)]
HexagonVectorLoopCarriedReuse.cpp: Apply LLVM_ATTRIBUTE_UNUSED. [-Wunused-function]
llvm-svn: 313947
NAKAMURA Takumi [Fri, 22 Sep 2017 01:01:31 +0000 (01:01 +0000)]
Reformat.
llvm-svn: 313946
Akira Hatanaka [Fri, 22 Sep 2017 00:41:05 +0000 (00:41 +0000)]
Add support for attribute 'noescape'.
The attribute informs the compiler that the annotated pointer parameter
of a function cannot escape and enables IRGen to attach attribute
'nocapture' to parameters that are annotated with the attribute. That is
the only optimization that currently takes advantage of 'noescape', but
there are other optimizations that will be added later that improves
IRGen for ObjC blocks.
This recommits r313722, which was reverted in r313725 because clang
couldn't build compiler-rt. It failed to build because there were
function declarations that were missing 'noescape'. That has been fixed
in r313929.
rdar://problem/
19886775
Differential Revision: https://reviews.llvm.org/D32210
llvm-svn: 313945
George Karpenkov [Fri, 22 Sep 2017 00:37:12 +0000 (00:37 +0000)]
[Analyzer] Log when auto-synthesized body is used.
Differential Revision: https://reviews.llvm.org/D37910
llvm-svn: 313944
Richard Smith [Fri, 22 Sep 2017 00:11:15 +0000 (00:11 +0000)]
Extend -ast-dump for CXXRecordDecl to dump the flags from the DefinitionData.
llvm-svn: 313943
Richard Trieu [Thu, 21 Sep 2017 23:48:01 +0000 (23:48 +0000)]
Fix unused variable warning.
Move function call into debug macro to suppress unused variable warning
in non-debug builds.
llvm-svn: 313942
Eugene Zelenko [Thu, 21 Sep 2017 23:20:16 +0000 (23:20 +0000)]
[CodeGen] Fix some Clang-tidy modernize-use-bool-literals and Include What You Use warnings; other minor fixes (NFC).
llvm-svn: 313941
Adrian Prantl [Thu, 21 Sep 2017 23:14:55 +0000 (23:14 +0000)]
Fix a bug in a historic bitcode testcase.
llvm-svn: 313940
Adrian Prantl [Thu, 21 Sep 2017 23:14:52 +0000 (23:14 +0000)]
Fix a bug in a historic bitcode testcase. NFC.
llvm-svn: 313939
Rafael Espindola [Thu, 21 Sep 2017 23:13:40 +0000 (23:13 +0000)]
Update for llvm change.
llvm-svn: 313938
Rafael Espindola [Thu, 21 Sep 2017 23:13:36 +0000 (23:13 +0000)]
Convert the archive writer to use Error.
This found one place in lld that was not checking the error.
llvm-svn: 313937
Pranav Bhandarkar [Thu, 21 Sep 2017 23:11:28 +0000 (23:11 +0000)]
[Hexagon] - Fix testcase for the HexagonVectorLoopCarriedReuse pass.
llvm-svn: 313936
Rafael Espindola [Thu, 21 Sep 2017 23:06:23 +0000 (23:06 +0000)]
Use raw_ostream in functions that don't need to seek. NFC.
llvm-svn: 313935
Jason Molenda [Thu, 21 Sep 2017 23:02:56 +0000 (23:02 +0000)]
Revert this patch; I was emailing with Eugene and they have some other changes going
in today and don't want the two changes to confuse the situation with the build bots.
I'll commit tomorrow once they're known good.
llvm-svn: 313934
Rafael Espindola [Thu, 21 Sep 2017 23:00:55 +0000 (23:00 +0000)]
Simplify the logic for truncating UID and GID. NFC.
llvm-svn: 313933
Jason Molenda [Thu, 21 Sep 2017 23:00:19 +0000 (23:00 +0000)]
Initial patchset to get the testsuite running against armv7 and arm64 iOS devices.
Normal customer devices won't be able to run these devices, we're hoping to get
a public facing bot set up at some point.
There will be some smaller follow-on patches. The changes to tools/lldb-server are
verbose and I'm not thrilled with having to skip all of these tests manually.
There are a few places where I'm making the assumption that "armv7", "armv7k", "arm64"
means it's an ios device, and I need to review & clean these up with an OS check
as well. (Android will show up as "arm" and "aarch64" so by pure luck they shouldn't
cause problems, but it's not an assumption I want to rely on).
I'll be watching the bots for the rest of today; if any problems are introduced by
this patch I'll revert it - if anyone sees a problem with their bot that I don't
see, please do the same. I know it's a rather large patch.
One change I had to make specifically for iOS devices was that debugserver can't
create files. There were several tests that launch the inferior process redirecting
its output to a file, then they retrieve the file. They were not trying to test
file redirection in these tests, so I rewrote those to write their output to a file
directly.
llvm-svn: 313932
Rafael Espindola [Thu, 21 Sep 2017 22:57:43 +0000 (22:57 +0000)]
Revert "Add a testfile that I missed in a previous commit that added HexagonVectorLoopCarriedReuse pass"
This reverts commit r313926.
It was failing in some bots.
llvm-svn: 313931
Rafael Espindola [Thu, 21 Sep 2017 22:50:52 +0000 (22:50 +0000)]
Simplify error handling. NFC.
llvm-svn: 313930
Akira Hatanaka [Thu, 21 Sep 2017 22:16:50 +0000 (22:16 +0000)]
[tsan] Annotate function parameters with attribute 'noescape'.
This commit annotates the block parameters of the following functions
declared in compiler-rt with 'noescape':
- dispatch_sync
- dispatch_barrier_sync
- dispatch_once
- dispatch_apply
This is needed to commit the patch that adds support for 'noescape' in
clang (see https://reviews.llvm.org/D32210) since these functions are
annotated with 'noescape' in the SDK header files.
Differential Revision: https://reviews.llvm.org/D32210
llvm-svn: 313929
Zachary Turner [Thu, 21 Sep 2017 22:16:40 +0000 (22:16 +0000)]
Resubmit "[lit] Refactor out some more common lit configuration code."
There were two issues, one Python 3 specific related to Unicode,
and another which is that the tool substitution for lld no longer
rejected matches where a / preceded the tool name.
llvm-svn: 313928
George Karpenkov [Thu, 21 Sep 2017 22:12:49 +0000 (22:12 +0000)]
[Analyzer] Use CC environment variable to select analyzer path in SATestBuild.
This change is required to easily test the given checkout of the analyzer,
rather than the one bundled with a system compiler.
Differential Revision: https://reviews.llvm.org/D38155
llvm-svn: 313927
Pranav Bhandarkar [Thu, 21 Sep 2017 21:52:24 +0000 (21:52 +0000)]
Add a testfile that I missed in a previous commit that
added HexagonVectorLoopCarriedReuse pass
llvm-svn: 313926
Pranav Bhandarkar [Thu, 21 Sep 2017 21:48:23 +0000 (21:48 +0000)]
Enable the reuse of values computed in a previous loop iteration.
This patch adds a pass that removes the computation of provably redundant
expressions that have been computed earlier in a previous iteration. It
relies on the use of PHIs to identify loop carried dependences.
This is scalar replacement for vector types.
llvm-svn: 313925
George Karpenkov [Thu, 21 Sep 2017 21:47:33 +0000 (21:47 +0000)]
[Analyzer] Add simple help to SATestAdd.py
Differential Revision: https://reviews.llvm.org/D38003
llvm-svn: 313924