summaryrefslogtreecommitdiffstats
path: root/llvm/lib
Commit message (Collapse)AuthorAgeFilesLines
* [InstCombine] Fix assertion when bitcast is converted to gepGerolf Hoflehner2016-05-231-0/+7
| | | | | | | | | | When an aggregate contains an opaque type its size cannot be determined. This triggers an "Invalid GetElementPtrInst indices for type" assert in function checkGEPType. The fix suppresses the conversion in this case. http://reviews.llvm.org/D20319 llvm-svn: 270479
* [LoopUnroll] Enable advanced unrolling analysis by default.Michael Zolotukhin2016-05-231-3/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Summary: This patch turns on LoopUnrollAnalyzer by default. To mitigate compile time regressions, I chose very conservative thresholds for now. Later we can make them more aggressive, but it might require being smarter in which loops we're optimizing. E.g. currently the biggest issue is that with more agressive thresholds we unroll many cold loops, which increases compile time for no performance benefit (performance of those loops is improved, but it doesn't matter since they are cold). Test results for compile time(using 4 samples to reduce noise): ``` MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes 5.19% SingleSource/Benchmarks/Polybench/medley/reg_detect/reg_detect 4.19% MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow 3.39% MultiSource/Applications/JM/lencod/lencod 1.47% MultiSource/Benchmarks/Fhourstones-3_1/fhourstones3_1 -6.06% ``` I didn't see any performance changes in the testsuite, but it improves some internal tests. Reviewers: hfinkel, chandlerc Subscribers: llvm-commits, mzolotukhin Differential Revision: http://reviews.llvm.org/D20482 llvm-svn: 270478
* Fix DEBUG logs in MachineLICM.Justin Lebar2016-05-231-7/+5
| | | | | | | | | | | | | | | Summary: MBBs don't necessarily have a name (in my experience, they almost never do), in which case this logging is quite unhelpful. The number seems to work well. Reviewers: iteratee Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D20533 llvm-svn: 270477
* [codeview] Refactor symbol records to use same pattern as types.Zachary Turner2016-05-231-11/+11
| | | | | | | | | | | This will pave the way to introduce a full fledged symbol visitor similar to how we have a type visitor, thus allowing the same dumping code to be used in llvm-readobj and llvm-pdbdump. Differential Revision: http://reviews.llvm.org/D20384 Reviewed By: rnk llvm-svn: 270475
* fix typo; NFCSanjay Patel2016-05-231-1/+1
| | | | llvm-svn: 270469
* use range-loop; NFCISanjay Patel2016-05-231-4/+2
| | | | llvm-svn: 270467
* fix formatting; NFCSanjay Patel2016-05-231-4/+2
| | | | llvm-svn: 270465
* [WebAssembly] Speed up LiveIntervals updating.Dan Gohman2016-05-231-6/+9
| | | | | | | | Use the more specific LiveInterval::removeSegment instead of LiveInterval::shrinkToUses when we know the specific range that's being removed. llvm-svn: 270463
* [Hexagon] Move some debug-only variable declarations into DEBUGKrzysztof Parzyszek2016-05-231-19/+21
| | | | llvm-svn: 270459
* Extract renaming from D19181Amaury Sechet2016-05-231-7/+2
| | | | | | | | | | | | Summary: This needs to get in before anything is released concerning attribute. If the old name gets in the wild, then we are stuck with it forever. Putting it in its own diff should getting that part at least in fast. Reviewers: Wallbraker, whitequark, joker.eph, echristo, rafael, jyknight Subscribers: llvm-commits, joker.eph Differential Revision: http://reviews.llvm.org/D20417 llvm-svn: 270452
* Removing a switch statement that contains only a default label; NFC.Aaron Ballman2016-05-231-3/+1
| | | | llvm-svn: 270444
* [BPF] Remove exit-on-error flag in test (PR27766)Diana Picus2016-05-232-4/+10
| | | | | | | | | | | | | | The exit-on-error flag on the many_args1.ll test is needed to avoid an unreachable in BPFTargetLowering::LowerCall. We can also avoid it by ignoring any superfluous arguments to the call (i.e. any arguments after the first 5). Fixes PR27766. Differential Revision: http://reviews.llvm.org/D20471 v2 of r270419 llvm-svn: 270440
* [InlineAsm] Avoid creating extra string instances in ConstraintInfo::Parse()Alexander Potapenko2016-05-231-4/+4
| | | | | | | Don't create unnecessary std::string objects when pushing back to |pCodes|. NFC. llvm-svn: 270436
* Reverts "[BPF] Remove exit-on-error flag in test (PR27766)"Renato Golin2016-05-232-8/+4
| | | | | | | | This patch reverts r270419 because it broke a lot of buildbots, mostly Windows. We'd like help in investigating the issues, but for now, it should stay out. llvm-svn: 270433
* [BPF] Remove exit-on-error flag in test (PR27766)Diana Picus2016-05-232-4/+8
| | | | | | | | | | The exit-on-error flag on the many_args1.ll test is needed to avoid an unreachable in BPFTargetLowering::LowerCall. We can also avoid it by ignoring any superfluous arguments to the call (i.e. any arguments after the first 5). Fixes PR27766 llvm-svn: 270419
* [Sparc] LEON erratum fix - Delay Slot Filler modification.Chris Dewhurst2016-05-231-0/+9
| | | | | | This code should have been with the previous check-in (r270417) and prevents the DelaySlotFiller pass being utilized in functions where the erratum fix has been applied as this will break the run-time code. llvm-svn: 270418
* [Sparc][LEON] LEON Erratum fix. Insert NOP after LD or LDF instruction.Chris Dewhurst2016-05-2310-9/+152
| | | | | | | | | | Due to an erratum in some versions of LEON, we must insert a NOP after any LD or LDF instruction to ensure the processor has time to load the value correctly before using it. This pass will implement that erratum fix. The code will have no effect for other Sparc, but non-LEON processors. Differential Review: http://reviews.llvm.org/D20353 llvm-svn: 270417
* [AMDGPU] Assembler: refactor parsing of modifiers and immediates. Allow ↵Sam Kolton2016-05-232-175/+245
| | | | | | | | | | | | modifiers for imms. Reviewers: nhaustov, tstellarAMD Subscribers: kzhuravl, arsenm Differential Revision: http://reviews.llvm.org/D20166 llvm-svn: 270415
* Test commitJacob Baungard Hansen2016-05-231-1/+0
| | | | llvm-svn: 270414
* Enable use of sigaltstack for signal handlers when available. With this,Richard Smith2016-05-231-1/+1
| | | | | | | backtraces from the signal handler on stack overflow now work reliably (on my system at least...). llvm-svn: 270395
* [X86] Use instruction aliases to replace custom asm parser code for ↵Craig Topper2016-05-233-51/+53
| | | | | | optimizing moves to use 2 byte VEX prefix. llvm-svn: 270394
* Revert "Modify emitTypeInformation to use MemoryTypeTableBuilder"David Majnemer2016-05-232-19/+42
| | | | | | | This reverts commit r270106. It results in certain function types omitted in the output. llvm-svn: 270389
* [AVX512] Add patterns to implement stores of extracts of least signficant ↵Craig Topper2016-05-221-0/+123
| | | | | | | | subvectors using XMM or YMM stores instead of the vector extract instructions. Similar is already done for AVX and we had lost it going to AVX512VL. llvm-svn: 270383
* [x86, AVX] don't add a vzeroupper if that's what the code is already doing ↵Sanjay Patel2016-05-221-0/+6
| | | | | | | | | | | | | | | (PR27823) This isn't the complete fix, but it handles the trivial examples of duplicate vzero* ops in PR27823: https://llvm.org/bugs/show_bug.cgi?id=27823 ...and amusingly, the bogus cases already exist as regression tests, so let's take this baby step. We'll need to do more in the general case where there's legitimate AVX usage in the function + there's already a vzero in the code. Differential Revision: http://reviews.llvm.org/D20477 llvm-svn: 270378
* reduce indent; NFCSanjay Patel2016-05-221-19/+19
| | | | llvm-svn: 270372
* use 'auto' with 'dyn_cast'; fix formatting; NFCSanjay Patel2016-05-221-10/+8
| | | | llvm-svn: 270370
* [ValueTracking, InstCombine] extend isKnownToBeAPowerOfTwo() to handle ↵Sanjay Patel2016-05-221-3/+4
| | | | | | | | | | | | | | vector splat constants We could try harder to handle non-splat vector constants too, but that seems much rarer to me. Note that the div test isn't resolved because there's a check for isIntegerTy() guarding that transform. Differential Revision: http://reviews.llvm.org/D20497 llvm-svn: 270369
* [AVX512] Implement missing patterns for any_extend load lowering.Igor Breger2016-05-222-55/+88
| | | | | | Differential Revision: http://reviews.llvm.org/D20513 llvm-svn: 270357
* [AVX512] The AVX512 file only need subtract_subvector index 0 patterns where ↵Craig Topper2016-05-221-15/+35
| | | | | | the source is 512-bits. The 256-bit source patterns were redundant with AVX. llvm-svn: 270356
* [AVX512] Add an AddedComplexity line to the 512-bit insert_subvector undef ↵Craig Topper2016-05-221-0/+2
| | | | | | index 0 patterns. This gives them higher priority than the memory patterns. This matches AVX1/2. llvm-svn: 270355
* [AVX512] Change the AddedComplexity on some patterns to match their AVX/SSE ↵Craig Topper2016-05-221-9/+13
| | | | | | equivalents. This helps group them close together in the isel tables and enable table compression. llvm-svn: 270354
* [AVX512] Add a couple patterns to fix some cases where two vector mask ↵Craig Topper2016-05-221-0/+11
| | | | | | inversions could appear in a row. llvm-svn: 270344
* [AVX512] Remove seemingly unnecessary AddedComplexity adjustment.Craig Topper2016-05-221-2/+0
| | | | llvm-svn: 270343
* [profile] Static counter allocation for value profiling (part-1)Xinliang David Li2016-05-211-12/+96
| | | | | | Differential Revision: http://reviews.llvm.org/D20459 llvm-svn: 270336
* [X86] Remove unnecessary alignment check on patterns that use VEXTRACTF128 ↵Craig Topper2016-05-211-8/+8
| | | | | | for integer types when only AVX1 is supported. llvm-svn: 270335
* [AVX512] Add patterns for extracting subvectors and storing to memory.Craig Topper2016-05-212-10/+15
| | | | llvm-svn: 270334
* [AVX512] Capitalize the Z in VEXTRACTPSzmr. Lowercase z has been primarily ↵Craig Topper2016-05-211-2/+2
| | | | | | used to indicating the zero masking behavior which is not the case here. NFC llvm-svn: 270333
* [AVX512] Rename vector extract instructions so 'mr' intead of 'rm' to ↵Craig Topper2016-05-211-2/+2
| | | | | | reflect the fact that memory is the destination. llvm-svn: 270332
* [AVX512] Fix copy/paste mistake a I made in a comment.Craig Topper2016-05-211-1/+1
| | | | llvm-svn: 270331
* Fix 80-column violation.Chad Rosier2016-05-211-1/+2
| | | | llvm-svn: 270329
* [LiveIntervalAnalysis] Don't dereference an end iterator in ↵Hal Finkel2016-05-211-1/+1
| | | | | | | | | | | | | | | | repairIntervalsInRange This fixes a bug introduced in: r262115 - CodeGen: Take MachineInstr& in SlotIndexes and LiveIntervals, NFC The iterator End here might == MBB->end(), and so we can't unconditionally dereference it. This often goes unnoticed (I don't have a test case that always crashes, and ASAN does not catch it either) because the function call arguments are turned right back into iterators. MachineInstrBundleIterator's constructor, however, does have an assert which might randomly fire. llvm-svn: 270323
* [Clang][AVX512][intrinsics] Fix rcp and sqrt intrinsics.Michael Zuckerman2016-05-214-7/+10
| | | | | | Differential Revision: http://reviews.llvm.org/D20438 llvm-svn: 270322
* [Clang][AVX512][intrinsics] Fix vscalef intrinsics.Michael Zuckerman2016-05-215-8/+11
| | | | | | Differential Revision: http://reviews.llvm.org/D20324 llvm-svn: 270321
* [AVX512] Add patterns for VEXTRACT v16i16->v8i16 and v32i8->v16i8. Disable ↵Craig Topper2016-05-212-1/+9
| | | | | | AVX2 versions of vector extract when AVX512VL is enabled. llvm-svn: 270318
* [AVX512] Disable AVX2 VPERMD, VPERMQ, VPERMPS, and VPERMPD patterns when ↵Craig Topper2016-05-212-30/+38
| | | | | | AVX512VL is enabled. Also add shuffle comment printing for AVX512VL VPERMPD/VPERMQ to keep some tests that now use these instructions instead of the AVX2 ones. llvm-svn: 270317
* [AVX512] Disable AVX/AVX2 VBROADCASTSS/VBROADCASTSD patterns when AVX512VL ↵Craig Topper2016-05-211-4/+4
| | | | | | is enabled. llvm-svn: 270316
* [SimplifyCFG] Remove cleanuppads which are empty except for calls to ↵David Majnemer2016-05-211-5/+17
| | | | | | | | | | | | | lifetime.end A cleanuppad is not cheap, they turn into many instructions and result in additional spills and fills. It is not worth keeping a cleanuppad around if all it does is hold a lifetime.end instruction. N.B. We first try to merge the cleanuppad with another cleanuppad to avoid dropping the lifetime and debug info markers. llvm-svn: 270314
* AMDGPU: Define priorities for register classesMatt Arsenault2016-05-211-11/+31
| | | | | | | | | | Allocating larger register classes first should give better allocation results (and more importantly for myself, make the lit tests more stable with respect to scheduler changes). Patch by Matthias Braun llvm-svn: 270312
* [AVX512] Disable AVX/AVX2 patterns for VPSADBW and VPMULUDQ when the ↵Craig Topper2016-05-211-4/+4
| | | | | | AVX512VL/AVX512BWI equivalents are available. llvm-svn: 270311
* [X86] Convert some SSE2/AVX2 intrinsics to ISD opcodes during lowering ↵Craig Topper2016-05-212-12/+24
| | | | | | instead of pattern matching the intrinsics. This unifies handling with AVX512 and allows these intrinsics to select EVEX encoded instructions to increase available registers. llvm-svn: 270310
OpenPOWER on IntegriCloud