summaryrefslogtreecommitdiffstats
path: root/llvm/test/Transforms
Commit message (Collapse)AuthorAgeFilesLines
...
* [InstCombine] remove stale comments for tests; NFCSanjay Patel2018-03-011-3/+0
| | | | llvm-svn: 326448
* [InstCombine] move/add tests for fmul reassociation; NFCSanjay Patel2018-03-012-12/+72
| | | | | | | This transform may be out-of-scope for instcombine, but this is only documenting the current behavior. llvm-svn: 326442
* [InstCombine] auto-generate full checks; NFCSanjay Patel2018-03-011-51/+49
| | | | llvm-svn: 326440
* [SCEV] Smart range calculation for SCEVUnknown PhisMax Kazantsev2018-03-012-3/+109
| | | | | | | | | | The range of SCEVUnknown Phi which merges values `X1, X2, ..., XN` can be evaluated as `U(Range(X1), Range(X2), ..., Range(XN))`. Reviewed By: sanjoy Differential Revision: https://reviews.llvm.org/D43810 llvm-svn: 326418
* [IPSCCP] do not break musttail invariant (PR36485)Reid Kleckner2018-03-011-0/+58
| | | | | | | | | | | | | | | | | Do not replace results of `musttail` calls with a constant if the call itself can't be removed. Do not zap returns of `musttail` callees, if the call site can't be removed and replaced with a constant. Do not zap returns of `musttail`-calling blocks, this breaks invariant too. Patch by Fedor Indutny Differential Revision: https://reviews.llvm.org/D43695 llvm-svn: 326404
* [DAE] don't remove args of musttail target/callerReid Kleckner2018-03-011-0/+16
| | | | | | | | | | | | | `musttail` requires identical signatures of caller and callee. Removing arguments breaks `musttail` semantics. PR36441 Patch by Fedor Indutny Differential Revision: https://reviews.llvm.org/D43708 llvm-svn: 326394
* [InstCombine] simplify code for X * -1.0 --> -X; NFCSanjay Patel2018-02-281-2/+2
| | | | | | I've added random FMF to one of the tests to show those are propagated. llvm-svn: 326377
* [GlobalOpt] don't change CC of musttail calle(e|r)Jonas Devlieghere2018-02-281-0/+34
| | | | | | | | | | | | | | | When the function has musttail call - its cc is fixed to be equal to the cc of the musttail callee. In such case (and in the case of the musttail callee), GlobalOpt should not change the cc to fastcc as it will break the invariant. This fixes PR36546 Patch by: Fedor Indutny (indutny) Differential revision: https://reviews.llvm.org/D43859 llvm-svn: 326376
* [InstCombine] auto-generate complete checks; NFCSanjay Patel2018-02-281-26/+36
| | | | llvm-svn: 326331
* [MergeICmp] Fix a bug in MergeICmp that can lead to a block being processed ↵Xin Tong2018-02-281-0/+57
| | | | | | | | | | | | | | | | | | | | | more than once. Summary: Fix a bug in MergeICmp that can lead to a BCECmp block being processed more than once and eventually lead to a broken LLVM module. The problem is that if the non-constant value is not produced by the last block, the producer will be processed once when the its parent block is processed and second time when the last block is processed. We end up having 2 same BCECmpBlock in the merge queue. And eventually lead to a broken LLVM module. Reviewers: courbet, davide Reviewed By: courbet Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D43825 llvm-svn: 326318
* [SLP] Added new tests and updated existing for jumbled load, NFC.Mohammad Shahid2018-02-284-6/+468
| | | | llvm-svn: 326303
* [InstSimplify] add tests for FP with undef operand; NFCSanjay Patel2018-02-272-18/+89
| | | | | | Are any of these correct? llvm-svn: 326241
* [ValueTracking] Teach cannotBeOrderedLessThanZeroImpl to look through ↵Craig Topper2018-02-271-0/+14
| | | | | | | | | | ExtractElement. This is similar to what's done in computeKnownBits and computeSignBits. Don't do anything fancy just collect information valid for any element. Differential Revision: https://reviews.llvm.org/D43789 llvm-svn: 326237
* [ARM] add loop vectorizer test based on 482.sphinx3 from SPEC2006; NFCSanjay Patel2018-02-271-0/+165
| | | | | | | | This is a slight reduction of one of the benchmarks that suffered with D43079. Cost model changes should not cause this test to remain scalarized. llvm-svn: 326221
* [AArch64] add SLP test based on TSVC; NFCSanjay Patel2018-02-271-0/+127
| | | | | | | | This is a slight reduction of one of the benchmarks that suffered with D43079. Cost model changes should not cause this test to remain scalarized. llvm-svn: 326217
* [NewGVN] Update phi-of-ops def block when updating existing ValuePHI.Florian Hahn2018-02-271-0/+56
| | | | | | | | | | | | | | | | | | | | | | | | | In case we update a ValuePHI node created earlier, we could update it based on a different OpPHI which could be in a different block. We need to update the TempToBlock mapping reflecting the new block, otherwise we would end up placing the new phi node in a wrong block. This problem is exposed by the test case in https://bugs.llvm.org/show_bug.cgi?id=36504. This patch fixes a slightly simpler problem than in the bug report. In the bug's re-producer, the additional problem is that we are re-using a ValuePHI node with to few incoming values for the new OpPHI. If this patch makes sense, I will follow it up with a patch that creates a new PHI node if the existing PHI node has a different number of incoming values. Reviewers: davide, dberlin Reviewed By: dberlin Differential Revision: https://reviews.llvm.org/D43770 llvm-svn: 326181
* Make test agnostic to cost modelAdam Nemet2018-02-271-1/+1
| | | | | | This was causing bot failures on greendragon llvm-svn: 326169
* Fix r326154 buildbots test failEvgeny Stupachenko2018-02-272-3/+2
| | | | | | | | | | Summary: Add specific mtriples to tests added in r326154. From: Evgeny Stupachenko <evstupac@gmail.com> <evgeny.v.stupachenko@intel.com> llvm-svn: 326158
* Fix PR36032, PR35432Evgeny Stupachenko2018-02-272-0/+367
| | | | | | | | | | | | | | | Summary: The change fix an assert fail at ScalarEvolutionExpander.cpp: assert(ExitCount != SE.getCouldNotCompute() && "Invalid loop count"); Reviewers: sbaranga Differential Revision: http://reviews.llvm.org/D42604 From: Evgeny Stupachenko <evstupac@gmail.com> <evgeny.v.stupachenko@intel.com> llvm-svn: 326154
* [InstCombine, InstSimplify] add tests with undef elements in constant FP ↵Sanjay Patel2018-02-262-0/+62
| | | | | | vectors; NFC llvm-svn: 326148
* [ValueTracking] Teach cannotBeOrderedLessThanZeroImpl to handle vector ↵Craig Topper2018-02-261-4/+2
| | | | | | | | | | | | | | | | constants. Summary: This allows vector fabs to be removed in more cases. Reviewers: spatel, arsenm, RKSimon Reviewed By: spatel Subscribers: wdng, llvm-commits Differential Revision: https://reviews.llvm.org/D43739 llvm-svn: 326138
* [X86][SSE] Reduce FADD/FSUB/FMUL costs on later targets (PR36280)Simon Pilgrim2018-02-265-146/+109
| | | | | | | | | | Agner's tables indicate that for SSE42+ targets (Core2 and later) we can reduce the FADD/FSUB/FMUL costs down to 1, which should fix the Himeno benchmark. Note: the AVX512 FDIV costs look rather dodgy, but this isn't part of this patch. Differential Revision: https://reviews.llvm.org/D43733 llvm-svn: 326133
* [SLP] Added new test + fixed some checks, NFC.Alexey Bataev2018-02-262-13/+175
| | | | llvm-svn: 326117
* [InstCombine] Add test cases with vector constants to fpextend.llCraig Topper2018-02-261-0/+41
| | | | llvm-svn: 326115
* [InstCombine] Switch to using FileCheck instead of grep. Auto-generate ↵Craig Topper2018-02-261-30/+61
| | | | | | checks. NFC llvm-svn: 326114
* [InstCombine] allow fdiv folds with less than fully 'fast' opsSanjay Patel2018-02-261-8/+8
| | | | | | | | | | | | | | | | | | Note: gcc appears to allow this fold with -freciprocal-math alone, but clang/llvm require more than that with this patch. The wording in the definitions seems fuzzy enough that it could go either way, but we'll err on the conservative side of FMF interpretation. This patch also changes the newly created fmul to have FMF propagated by the last fdiv rather than intersecting the FMF of the fdivs. This matches the behavior of other folds near here. The new fmul is only used to produce an intermediate op for the final fdiv result, so it shouldn't be any stricter than that result. The previous behavior could result in dropping FMF via other folds in instcombine or CSE. Differential Revision: https://reviews.llvm.org/D43398 llvm-svn: 326098
* [LV] Move isLegalMasked* functions from Legality to CostModelRenato Golin2018-02-262-2/+3
| | | | | | | | | | | | | | | | | | | | | | | All SIMD architectures can emulate masked load/store/gather/scatter through element-wise condition check, scalar load/store, and insert/extract. Therefore, bailing out of vectorization as legality failure, when they return false, is incorrect. We should proceed to cost model and determine profitability. This patch is to address the vectorizer's architectural limitation described above. As such, I tried to keep the cost model and vectorize/don't-vectorize behavior nearly unchanged. Cost model tuning should be done separately. Please see http://lists.llvm.org/pipermail/llvm-dev/2018-January/120164.html for RFC and the discussions. Closes D43208. Patch by: Hideki Saito <hideki.saito@intel.com> llvm-svn: 326079
* [LoopInterchange] Add test case for D43236.Florian Hahn2018-02-261-0/+44
| | | | llvm-svn: 326078
* [InstSimplify] Add test cases for removal of vector fabs on known positive.Craig Topper2018-02-251-0/+118
| | | | llvm-svn: 326050
* [InstSimplify] Remove unused parameter from test cases.Craig Topper2018-02-251-7/+7
| | | | llvm-svn: 326049
* Revert "StructurizeCFG: Test for branch divergence correctly"Adam Nemet2018-02-241-82/+0
| | | | | | | | This reverts commit r325881. Breaks many bots llvm-svn: 326037
* [InstSimplify] sqrt(X) * sqrt(X) --> XSanjay Patel2018-02-232-11/+15
| | | | | | This was misplaced in InstCombine. We can loosen the FMF as a follow-up step. llvm-svn: 325965
* [InstCombine] allow fmul-sqrt folds with less than full -ffast-mathSanjay Patel2018-02-231-21/+27
| | | | | | Also, add a Builder method for intrinsics to reduce code duplication for clients. llvm-svn: 325960
* [Test] Fix the test to output to /dev/null instead of redirecting.Matt Davis2018-02-231-1/+1
| | | | | | The redirection was confusing the windows build machine. llvm-svn: 325937
* [Debug] Add dbg.value intrinsics for PHIs created during LCSSA.Matt Davis2018-02-232-4/+135
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Summary: This patch is an enhancement to propagate dbg.value information when Phis are created on behalf of LCSSA. I noticed a case where a value carried across a loop was reported as <optimized out>. Specifically this case: ``` int bar(int x, int y) { return x + y; } int foo(int size) { int val = 0; for (int i = 0; i < size; ++i) { val = bar(val, i); // Both val and i are correct } return val; // <optimized out> } ``` In the above case, after all of the interesting computation completes our value is reported as "optimized out." This change will add a dbg.value to correct this. This patch also moves the dbg.value insertion routine from LoopRotation.cpp into Local.cpp, so that we can share it in both places (LoopRotation and LCSSA). Reviewers: mzolotukhin, aprantl, vsk, davide Reviewed By: aprantl, vsk Subscribers: dberlin, llvm-commits Differential Revision: https://reviews.llvm.org/D42551 llvm-svn: 325926
* StructurizeCFG: Test for branch divergence correctlyNicolai Haehnle2018-02-231-0/+82
| | | | | | | | | | | | | | | | | | | | | | Summary: This fixes cases like the new test @nonuniform. In that test, %cc itself is a uniform value; however, when reading it after the end of the loop in basic block %if, its value is effectively non-uniform. This problem was encountered in https://bugs.freedesktop.org/show_bug.cgi?id=103743; however, this change in itself is not sufficient to fix that bug, as there is another issue in the AMDGPU backend. Change-Id: I32bbffece4a32f686fab54964dae1a5dd72949d4 Reviewers: arsenm, rampitec, jlebar Subscribers: wdng, tpr, llvm-commits Differential Revision: https://reviews.llvm.org/D40546 llvm-svn: 325881
* Mark MergedLoadStoreMotion as not preserving MemDep resultsBjorn Steinbrink2018-02-231-0/+22
| | | | | | | | | | | | | | | | | | Summary: MemDep caches results that signify that a dependence is non-local, and there is currently no way to invalidate such cache entries. Unfortunately, when MLSM sinks a store that can result in a non-local dependence becoming a local one, and then MemDep gives wrong answers. The easiest way out here is to just say that MLSM does indeed not preserve MemDep results. Reviewers: davide, Gerolf Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D43177 llvm-svn: 325880
* [AlignmentFromAssumptions] Set source and dest alignments of memory ↵Daniel Neilson2018-02-222-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | intrinsiscs separately Summary: This change is part of step five in the series of changes to remove alignment argument from memcpy/memmove/memset in favour of alignment attributes. In particular, this changes the AlignmentFromAssumptions pass to cease using the old getAlignment()/setAlignment API of MemoryIntrinsic in favour of getting/setting source & dest specific alignments through the new API. This allows us to simplify some of the code in this pass and also be more aggressive about setting the source and destination alignments separately. Steps: Step 1) Remove alignment parameter and create alignment parameter attributes for memcpy/memmove/memset. ( rL322965, rC322964, rL322963 ) Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. ( rL323597 ) Step 3) Update Clang to use the new IRBuilder API. ( rC323617 ) Step 4) Update Polly to use the new IRBuilder API. ( rL323618 ) Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use [get|set]DestAlignment() and [get|set]SourceAlignment() instead. ( rL323886, rL323891, rL324148, rL324273, rL324278, rL324384, rL324395, rL324402, rL324626, rL324642, rL324653, rL324654, rL324773, rL324774, rL324781, rL324784, rL324955, rL324960 ) Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reference http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html Reviewers: hfinkel, bollu, reames Reviewed By: reames Subscribers: reames, llvm-commits Differential Revision: https://reviews.llvm.org/D43081 llvm-svn: 325816
* [FunctionAttrs][ArgumentPromotion][GlobalOpt] Disable some optimisations ↵Luke Cheeseman2018-02-223-0/+71
| | | | | | | | | | | | | | passes for naked functions - Fix for bug 36078. - Prevent the functionattrs, function-attrs, globalopt and argpromotion passes from changing naked functions. - These passes can perform some alterations to the functions that should not be applied. An example is removing parameters that are seemingly not used because they are only referenced in the inline assembly. Another example is marking the function as fastcc. llvm-svn: 325788
* [InstCombine] add fmul multi-use test; NFCSanjay Patel2018-02-221-14/+33
| | | | | | Also, rename tests to make their intent clearer. llvm-svn: 325785
* [SLPVectorizer][X86] Add load extend tests (PR36091)Simon Pilgrim2018-02-222-0/+1696
| | | | llvm-svn: 325772
* [InstCombine] add some random FMF to tests so we know it's not dropped; NFCSanjay Patel2018-02-211-8/+8
| | | | llvm-svn: 325734
* [AArch64] fix IR names to not be 'tmp' because that gives the CHECK script ↵Sanjay Patel2018-02-211-40/+40
| | | | | | problems llvm-svn: 325718
* [AArch64] add SLP test for matmul (PR36280); NFCSanjay Patel2018-02-211-0/+139
| | | | | | | | This is a slight reduction of one of the benchmarks that suffered with D43079. Cost model changes should not cause this test to remain scalarized. llvm-svn: 325717
* [LV] Fix test checks, NFCAlexey Bataev2018-02-211-76/+2363
| | | | llvm-svn: 325699
* [SLP] Fix test checks, NFC.Alexey Bataev2018-02-211-15/+30
| | | | llvm-svn: 325689
* [SCEV] Temporarily disable loop versioning for the purposeSilviu Baranga2018-02-213-4/+4
| | | | | | | | | | of turning SCEVUnknowns of PHIs into AddRecExprs. This feature is now hidden behind the -scev-version-unknown flag. Fixes PR36032 and PR35432. llvm-svn: 325687
* [BDCE] Salvage debug info from dying instsVedant Kumar2018-02-211-0/+11
| | | | | | | | This results in 15 additional unique source variables in a stage2 build of FileCheck (at '-Os -g'), with a negligible increase in the size of the .debug_loc section. llvm-svn: 325660
* revert r325515: [TTI CostModel] change default cost of FP ops to 1 (PR36280)Sanjay Patel2018-02-217-123/+183
| | | | | | | | There are too many perf regressions resulting from this, so we need to investigate (and add tests for) targets like ARM and AArch64 before trying to reinstate. llvm-svn: 325658
* [InstCombine] C / -X --> -C / XSanjay Patel2018-02-211-4/+2
| | | | | | | | | We already do this in DAGCombiner, but it should also be good to eliminate the fsub use in IR. This is similar to rL325648. llvm-svn: 325649
OpenPOWER on IntegriCloud