summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
...
* Fix cppcheck + MSVC analyzer uninitialized member variable warning. NFCI.Simon Pilgrim2019-08-141-1/+1
| | | | llvm-svn: 368865
* [X86] Use PSADBW for v8i8 addition reductions.Craig Topper2019-08-142-104/+40
| | | | | | | | Improves the 8 byte case from PR42674. Differential Revision: https://reviews.llvm.org/D66069 llvm-svn: 368864
* [NFC] Fix testcase for ARMsDavid Bolvansky2019-08-141-3/+3
| | | | llvm-svn: 368863
* [libTooling] Fix code to avoid unused-function warning after r368681.Yitzhak Mandelbaum2019-08-141-0/+2
| | | | llvm-svn: 368862
* [LangRef] Remove opening [ that was missing a closing ] from ↵Craig Topper2019-08-141-3/+3
| | | | | | | | | call/callbr/invoke syntax. It looks like this bracket was added when the addrspace was added. before it. So I think it can jut be removed. llvm-svn: 368861
* [NFC][AIX] Change assertionXiangling Liao2019-08-141-1/+1
| | | | | | | | | Address one left comment on https://reviews.llvm.org/D63547. A minor change for assertion. Differential Revision: https://reviews.llvm.org/D63547 llvm-svn: 368860
* [PowerPC][NFC] Add test for build all one vector with different types.Jinsong Ji2019-08-141-0/+109
| | | | | | | build-vector-tests.ll is far too big, split such type tests for single buildvector into new file. llvm-svn: 368859
* [X86][CostModel] Adjust the costs of ZERO_EXTEND/SIGN_EXTEND with less than ↵Craig Topper2019-08-147-276/+332
| | | | | | | | | | | | 128-bit inputs Now that we legalize by widening, the element types here won't change. Previously these were modeled as the elements being widened and then the instruction might become an AND or SHL/ASHR pair. But now they'll become something like a ZERO_EXTEND_VECTOR_INREG/SIGN_EXTEND_VECTOR_INREG. For AVX2, when the destination type is legal its clear the cost should be 1 since we have extend instructions that can produce 256 bit vectors from less than 128 bit vectors. I'm a little less sure about AVX1 costs, but I think the ones I changed were definitely too high, but they might still be too high. Differential Revision: https://reviews.llvm.org/D66169 llvm-svn: 368858
* [X86] Add llvm_unreachable to a switch that covers all expected values.Craig Topper2019-08-141-0/+1
| | | | llvm-svn: 368857
* [PowerPC][NFC] Consolidate duplicate XX3Form_SetZero and XX3Form_Zero.Jinsong Ji2019-08-142-11/+4
| | | | | | Rename one to XX3Form_SameOp, remove the other one. llvm-svn: 368856
* [AIX] Add call lowering for parameters that could pass onto FPRsJason Liu2019-08-143-4/+176
| | | | | | | | | | Summary: This patch adds call lowering functionality to enable passing parameters onto floating point registers when needed. Differential Revision: https://reviews.llvm.org/D63654 llvm-svn: 368855
* Revert "raw_ostream: add operator<< overload for std::error_code"Pavel Labath2019-08-1410-25/+78
| | | | | | | | | | | This reverts commit r368849, because it breaks some bots (e.g. llvm-clang-x86_64-win-fast). It turns out this is not as NFC as we had hoped, because operator== will consider two std::error_codes to be distinct even though they both hold "success" values if they have different categories. llvm-svn: 368854
* [analyzer][NFC] Prove that we only track the evaluated part of the conditionKristof Umann2019-08-141-0/+35
| | | | | | | | | ...because we're working with a BugReporterVisitor, and the non-evaluated part of the condition isn't in the bugpath. Differential Revision: https://reviews.llvm.org/D65290 llvm-svn: 368853
* Add missing SetID method to fix Windows buildAaron Smith2019-08-141-0/+2
| | | | llvm-svn: 368852
* [clangd][vscode] Surface the error when applying tweaks failsHaojian Wu2019-08-141-2/+19
| | | | | | | | | | | | | | | | | | | Summary: The current behavior for a failed request is just to log it in the output panel. When applyTweak fails for whatever reason, users usually don't get informed (unless they open the output panel and dig the log). this patch is to surface these errors by prompting up a message diag. Reviewers: ilya-biryukov Subscribers: MaskRay, jkorous, arphaman, kadircet, cfe-commits Tags: #clang Differential Revision: https://reviews.llvm.org/D66211 llvm-svn: 368851
* [Tooling] Added DeclStmtClass to ExtractionSemicolonPolicyShaurya Gupta2019-08-142-1/+13
| | | | | | | Since the DeclStmt range includes the semicolon, it doesn't need a semicolon at the end during extraction llvm-svn: 368850
* raw_ostream: add operator<< overload for std::error_codePavel Labath2019-08-1410-78/+25
| | | | | | | | | | | | | | | | | | | | | | | Summary: The main motivation for this is unit tests, which contain a large macro for pretty-printing std::error_code, and this macro is duplicated in every file that needs to do this. However, the functionality may be useful elsewhere too. In this patch I have reimplemented the existing ASSERT_NO_ERROR macros to reuse the new functionality, but I have kept the macro (as a one-liner) as it is slightly more readable than ASSERT_EQ(..., std::error_code()). Reviewers: sammccall, ilya-biryukov Subscribers: zturner, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D65643 llvm-svn: 368849
* [SimplifyCFG] Add "safe abs" test from CMSIS DSP 'abs_with_clamp()'Roman Lebedev2019-08-141-0/+34
| | | | | | | | | With -phi-node-folding-threshold=3 this branch would get flattened into select. See https://reviews.llvm.org/D65148#1629010 llvm-svn: 368847
* [ELF] --gdb-index: fix odd variable name cUs after r365730 and replace ↵Fangrui Song2019-08-141-7/+6
| | | | | | lower_bound with partition_point. NFC llvm-svn: 368845
* [clangd] Print qualifiers of out-of-line definitions in document outlineIlya Biryukov2019-08-142-35/+128
| | | | | | | | | | | | | | | | Summary: To improve the UX around navigating and searching through the results. Reviewers: hokein Reviewed By: hokein Subscribers: MaskRay, jkorous, arphaman, kadircet, cfe-commits Tags: #clang Differential Revision: https://reviews.llvm.org/D66215 llvm-svn: 368842
* [Clangd] NFC: Fixed comment typoShaurya Gupta2019-08-141-1/+1
| | | | llvm-svn: 368841
* gn build: Pre-merge https://reviews.llvm.org/D66195Nico Weber2019-08-141-1/+1
| | | | llvm-svn: 368840
* [X86] Add missing regular 512-bit vXi8 extract subvector cost model testsSimon Pilgrim2019-08-141-73/+421
| | | | | | These tests don't cover many cases where the subvectors don't start on aligned indices, but that can be added later. llvm-svn: 368839
* Revert "Minidump/Windows: Fix module lookup"Pavel Labath2019-08-144-69/+0
| | | | | | | | | | | Although there is nothing wrong with this patch, the test added here uncovers a problem in other parts of the code which cause the test to fail when running under asan. Reverting the patch until I can fix the underlying issue(s). This reverts commit r368416. llvm-svn: 368838
* [ELF][test] Update silent-ignore.testFangrui Song2019-08-141-3/+5
| | | | | | | | | | | Some options are implemented now: --no-warn-common : r263413 --allow-shlib-undefined : r352826 Some are ignored but were not reflected in this test. llvm-svn: 368837
* [analyzer][CFG] Don't track the condition of assertsKristof Umann2019-08-146-100/+365
| | | | | | | | | | | | | | Well, what is says on the tin I guess! Some more changes: * Move isInevitablySinking() from BugReporter.cpp to CFGBlock's interface * Rename and move findBlockForNode() from BugReporter.cpp to ExplodedNode::getCFGBlock() Differential Revision: https://reviews.llvm.org/D65287 llvm-svn: 368836
* [DebugInfo] MCP: collect and update DBG_VALUEs encountered in local blockJeremy Morse2019-08-143-12/+44
| | | | | | | | | | | | | | | | | | | | MCP currently uses changeDebugValuesDefReg / collectDebugValues to find debug users of a register, however those functions assume that all DBG_VALUEs immediately follow the specified instruction, which isn't necessarily true. This is going to become very often untrue when we turn off CodeGenPrepare::placeDbgValues. Instead of calling changeDebugValuesDefReg on an instruction to change its debug users, in this patch we instead collect DBG_VALUEs of copies as we iterate over insns, and update the debug users of copies that are made dead. This isn't a non-functional change, because MCP will now update DBG_VALUEs that aren't immediately after a copy, but refer to the same register. I've hijacked the regression test for PR38773 to test for this new behaviour, an entirely new test seemed overkill. Differential Revision: https://reviews.llvm.org/D56265 llvm-svn: 368835
* [clangd] Loading TokenColorRules as a class mapping the rules to their ↵Johan Vikstrom2019-08-142-3/+67
| | | | | | | | | | | | | | | | associated clangd TextMate scope index. Summary: Loads a mapping of the clangd scope lookup table scopes to the most specific rule with the highest "precedence" on initialize. Preprocesses into a class so it's simple/fast to access when doing the actual coloring later. Reviewers: hokein, ilya-biryukov Subscribers: MaskRay, jkorous, arphaman, kadircet, cfe-commits Tags: #clang Differential Revision: https://reviews.llvm.org/D65856 llvm-svn: 368834
* [IR] Simplify removeDeadConstantUsers. NFCFangrui Song2019-08-141-6/+3
| | | | llvm-svn: 368833
* Removed ToolExecutor::isSingleProcess, it is not used by anythingDmitri Gribenko2019-08-144-13/+0
| | | | | | | | | | Subscribers: cfe-commits Tags: #clang Differential Revision: https://reviews.llvm.org/D66212 llvm-svn: 368832
* Fix "not all control paths return a value" MSVC warnings. NFCI.Simon Pilgrim2019-08-141-1/+4
| | | | llvm-svn: 368831
* Fix "not all control paths return a value" MSVC warning. NFCI.Simon Pilgrim2019-08-141-0/+1
| | | | llvm-svn: 368830
* Fix "not all control paths return a value" MSVC warnings. NFCI.Simon Pilgrim2019-08-141-0/+2
| | | | llvm-svn: 368829
* [NFC] Make test more robustDavid Bolvansky2019-08-141-27/+5
| | | | | | Currently fails on ARMs llvm-svn: 368828
* Improved the doc comment for getCommentsInFileDmitri Gribenko2019-08-141-1/+2
| | | | | | | | | | Subscribers: cfe-commits Tags: #clang Differential Revision: https://reviews.llvm.org/D66209 llvm-svn: 368827
* Recommit r368812 "[llvm/Object] - Convert SectionRef::getName() to return ↵George Rimar2019-08-1440-240/+423
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | Expected<>" Changes: no changes. A fix for the clang code will be landed right on top. Original commit message: SectionRef::getName() returns std::error_code now. Returning Expected<> instead has multiple benefits. For example, it forces user to check the error returned. Also Expected<> may keep a valuable string error message, what is more useful than having a error code. (Object\invalid.test was updated to show the new messages printed.) This patch makes a change for all users to switch to Expected<> version. Note: in a few places the error returned was ignored before my changes. In such places I left them ignored. My intention was to convert the interface used, and not to improve and/or the existent users in this patch. (Though I think this is good idea for a follow-ups to revisit such places and either remove consumeError calls or comment each of them to clarify why it is OK to have them). Differential revision: https://reviews.llvm.org/D66089 llvm-svn: 368826
* [clang] - An update after LLVM change.George Rimar2019-08-142-2/+9
| | | | | | SectionRef::getName() was changed to return Expected<> (D66089) llvm-svn: 368825
* [clangd] Fix typos and grammar in a comment. NFCIlya Biryukov2019-08-141-4/+4
| | | | llvm-svn: 368824
* [AsmPrinter] Delete redundant .type foo, @function when emitting an ifuncFangrui Song2019-08-142-7/+5
| | | | | | | | | | | In MCAsmStreamer: .type foo,@function # <--- this is redundant .type foo,@gnu_indirect_function In MCELFStreamer, the latter STT_GNU_IFUNC overrides STT_FUNC. llvm-svn: 368823
* Fix _WIN32 / _WIN64 Wundef warningsSven van Haastregt2019-08-141-1/+1
| | | | | | | | For these macros it is the definedness that matters rather than the value. Make new uses of these macros consistent with existing uses. llvm-svn: 368822
* [llvm-size][test] Improve llvm-size testingJames Henderson2019-08-1427-143/+1088
| | | | | | | | | | | | | | | | | | | | | This patch significantly improves the llvm-size testing. The changes made are: 1) Change all tests to use yaml2obj instead of assembly or pre-canned inputs. 2) Move the tests out of the X86 directory, since they don't need to be there after 1). 3) Increased test coverage. 4) Added comments to explain purpose of tests. I haven't attempted to add test coverage for all Mach-O related code, as I am not familiar enough with that file format to be able to. Reviewers: grimar, MaskRay Differential Revision: https://reviews.llvm.org/D66134 llvm-svn: 368821
* [InstCombine] Refactor getFlippedStrictnessPredicateAndConstant() out of ↵Roman Lebedev2019-08-142-32/+50
| | | | | | | | | canonicalizeCmpWithConstant(), NFCI I'd like to use it elsewhere, hopefully without reinventing the wheel. No functional change intended so far. llvm-svn: 368820
* [ASTImporter] Import default expression of param before creating the param.Balazs Keri2019-08-145-19/+86
| | | | | | | | | | | | | | | | | | | | | Summary: The default expression of a parameter variable should be imported before the parameter variable object is created. Otherwise the function is created with an incomplete parameter variable (default argument is nullptr) and in this intermediary state the expression is imported. This import can have a reference to the incomplete parameter variable that causes crash. Reviewers: martong, a.sidorin, shafik Reviewed By: martong Subscribers: rnkovacs, dkrupp, Szelethus, gamesh411, cfe-commits Tags: #clang Differential Revision: https://reviews.llvm.org/D65577 llvm-svn: 368818
* [analyzer] Note last writes to a condition only in a nested stackframeKristof Umann2019-08-143-31/+61
| | | | | | | | | Exactly what it says on the tin! The comments in the code detail this a little more too. Differential Revision: https://reviews.llvm.org/D64272 llvm-svn: 368817
* [MinGW] Correct handling different forms of a few optionsMartin Storsjo2019-08-142-10/+16
| | | | | | | | | | | | | | | | | | | | Support the equals form of the long --entry=<symbol> option, add a test for the -e<symbol> form. Add tests for single dash forms of -exclude-all-symbols and -export-all-symbols. Support single-dash forms of -out-implib and -output-def, support the equals form of --output-def=<file>. (We previously had a test to explicitly disallow -out-implib, but it turns out that GNU ld actually does support it just fine, despite also matching the -o<file> option.) Disallow the double-dashed --u form, add a test for -u<symbol>. Differential Revision: https://reviews.llvm.org/D66066 llvm-svn: 368816
* [MinGW] Restructure Options.td to use multiclass where sensible. NFC.Martin Storsjo2019-08-141-33/+29
| | | | | | Differential Revision: https://reviews.llvm.org/D66065 llvm-svn: 368815
* [MinGW] Remove stray/inconsistent comment chars in test file. NFC.Martin Storsjo2019-08-141-8/+8
| | | | | | Test directives don't need to be in comments in this file. llvm-svn: 368814
* Revert r368812 "[llvm/Object] - Convert SectionRef::getName() to return ↵George Rimar2019-08-1440-423/+240
| | | | | | | | Expected<>" It broke clang BB: http://lab.llvm.org:8011/builders/clang-x86_64-debian-fast/builds/16455 llvm-svn: 368813
* [llvm/Object] - Convert SectionRef::getName() to return Expected<>George Rimar2019-08-1440-240/+423
| | | | | | | | | | | | | | | | | | | | | | | SectionRef::getName() returns std::error_code now. Returning Expected<> instead has multiple benefits. For example, it forces user to check the error returned. Also Expected<> may keep a valuable string error message, what is more useful than having a error code. (Object\invalid.test was updated to show the new messages printed.) This patch makes a change for all users to switch to Expected<> version. Note: in a few places the error returned was ignored before my changes. In such places I left them ignored. My intention was to convert the interface used, and not to improve and/or the existent users in this patch. (Though I think this is good idea for a follow-ups to revisit such places and either remove consumeError calls or comment each of them to clarify why it is OK to have them). Differential revision: https://reviews.llvm.org/D66089 llvm-svn: 368812
* [llvm-objdump] - Add a relocation-xindex-symbol.test test case.George Rimar2019-08-143-8/+36
| | | | | | | | | This rewrites the exitent test case to use YAML instead of the precompiled object and moves it from test/Object to an appropriate llvm-objdump tests folder. Differential revision: https://reviews.llvm.org/D66140 llvm-svn: 368811
OpenPOWER on IntegriCloud