summaryrefslogtreecommitdiffstats
path: root/llvm/lib
Commit message (Collapse)AuthorAgeFilesLines
...
* [SimplifyCFG] Tweak heuristic for merging conditional storesJames Molloy2015-11-051-7/+13
| | | | | | We were correctly skipping dbginfo intrinsics and terminators, but the initial bailout wasn't, causing it to bail out on almost any block. llvm-svn: 252152
* [X86][AVX512] small bugfix in VPBROADCASTMAsaf Badouh2015-11-051-2/+2
| | | | | | | | VPBROADCASTMW2D and VPBROADCASTMB2Q Differential Revision: http://reviews.llvm.org/D14335 llvm-svn: 252151
* RuntimeDyld: fix -Wtype-limitsSaleem Abdulrasool2015-11-051-2/+2
| | | | | | | Adjust the casted type. By casting to the same size rather than just the signed-ness, we were asserting tautological statements. NFC. llvm-svn: 252150
* Fix LoopAccessAnalysis when potentially nullptr check are involvedMehdi Amini2015-11-051-1/+6
| | | | | | | | | | | | | | Summary: GetUnderlyingObjects() can return "null" among its list of objects, we don't want to deduce that two pointers can point to the same memory in this case, so filter it out. Reviewers: anemet Subscribers: dexonsmith, llvm-commits From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 252149
* AMDGPU: Also track whether SGPRs were spilledMatt Arsenault2015-11-053-2/+20
| | | | llvm-svn: 252145
* AMDGPU: Print number user SGPRsMatt Arsenault2015-11-051-0/+6
| | | | | | | This doesn't quite match how SC prints it, which doesn't put it in a comment. llvm-svn: 252144
* AMDGPU: Disallow s[102:103] on VI in assemblerMatt Arsenault2015-11-051-2/+28
| | | | llvm-svn: 252142
* [FunctionAttrs] Remove a loop, NFC refactorSanjoy Das2015-11-051-16/+14
| | | | | | | | | | | | | | | | | | | | | | Summary: Remove the loop over the uses of the CallSite in ArgumentUsesTracker. Since we have the `Use *` for actual argument operand, we can just use pointer subtraction. The time complexity remains the same though (except for a vararg argument) -- `std::advance` is O(UseIndex) for the ArgumentList iterator. The real motivation is to make a later change adding support for operand bundles simpler. Reviewers: reames, chandlerc, nlewycky Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D14363 llvm-svn: 252141
* AMDGPU: Fix assert when legalizing atomic operandsMatt Arsenault2015-11-053-15/+59
| | | | | | | | | | The operand layout is slightly different for the atomic opcodes from the usual MUBUF loads and stores. This should only fix it on SI/CI. VI is still broken because it still emits the addr64 replacement. llvm-svn: 252140
* AMDGPU: Make addr64 atomic operand order consistentMatt Arsenault2015-11-051-2/+2
| | | | | | | vaddr comes before srsrc in every other MUBUF instruction, and is the order it is printed. llvm-svn: 252139
* Fix OSX build after r252118 (missing parameter for findModulesAndOffsets())Mehdi Amini2015-11-051-1/+2
| | | | | From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 252137
* Remove empty linesMehdi Amini2015-11-051-2/+2
| | | | | From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 252136
* [WinEH] Fix establisher param reg in CLR funcletsJoseph Tremoulet2015-11-051-9/+20
| | | | | | | | | | | | | | Summary: The CLR's personality routine passes the pointer to the establisher frame in RCX, not RDX. Reviewers: pgavlin, majnemer, rnk Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D14343 llvm-svn: 252135
* [IR] Add bounds checking to dataOperandHasImpliedAttrSanjoy Das2015-11-051-0/+8
| | | | | | This is similar to the bounds check added to paramHasAttr in r252073. llvm-svn: 252130
* [libFuzzer] print a bit fewer linesKostya Serebryany2015-11-052-2/+3
| | | | llvm-svn: 252123
* Go back to producing relocations for out of range symbols.Rafael Espindola2015-11-051-6/+4
| | | | | | | | This brings back the behavior from before r252090 for out of range symbols. Should bring some arm bots back. llvm-svn: 252119
* [Windows] Symbolize with llvm-symbolizer instead of dbghelp in a self-hostReid Kleckner2015-11-053-97/+227
| | | | | | | | | | | | | | | | Summary: llvm-symbolizer understands both PDBs and DWARF, so it is more likely to succeed at symbolization. If llvm-symbolizer is unavailable, we will fall back to dbghelp. This also makes our crash traces more similar between Windows and Linux. Reviewers: Bigcheese, zturner, chapuni Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D12884 llvm-svn: 252118
* AMDGPU: Fix typoMatt Arsenault2015-11-051-2/+2
| | | | llvm-svn: 252116
* [PGO] Use template file to define runtime structuresXinliang David Li2015-11-052-32/+33
| | | | | | | | | | | With this change, instrumentation code and reader/write code related to profile data structs are kept strictly in-sync. THis will be extended to cfe and compile-rt references as well. Differential Revision: http://reviews.llvm.org/D13843 llvm-svn: 252113
* Fix Abbrev emission in WriteIdentificationBlockMehdi Amini2015-11-051-1/+2
| | | | | | | This Abbrev was not emitted and basically unused, just leacking there. From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 252110
* Fix pr24832.Rafael Espindola2015-11-051-9/+1
| | | | | | It is pretty simple now that the yak is shaved. llvm-svn: 252105
* Simplify now that emitValueToOffset always returns false.Rafael Espindola2015-11-044-21/+6
| | | | llvm-svn: 252102
* Simplify .org processing and make it a bit more powerful.Rafael Espindola2015-11-042-19/+10
| | | | | | | We now always create the fragment, which lets us handle things like .org after a .align. llvm-svn: 252101
* [SimplifyLibCalls] New transformation: tan(atan(x)) -> xDavide Italiano2015-11-041-1/+38
| | | | | | | | | | | | | | | | | | | | This is enabled only under -ffast-math. So, instead of emitting: 4007b0: 50 push %rax 4007b1: e8 8a fd ff ff callq 400540 <atanf@plt> 4007b6: 58 pop %rax 4007b7: e9 94 fd ff ff jmpq 400550 <tanf@plt> 4007bc: 0f 1f 40 00 nopl 0x0(%rax) for: float mytan(float x) { return tanf(atanf(x)); } we emit a single retq. Differential Revision: http://reviews.llvm.org/D14302 llvm-svn: 252098
* [libFuzzer] when choosing the next unit to mutate, give some preference to ↵Kostya Serebryany2015-11-042-26/+46
| | | | | | the most recent units (they are more likely to be interesting) llvm-svn: 252097
* [CaptureTracking] Support operand bundles conservativelySanjoy Das2015-11-041-2/+3
| | | | | | | | | | | | | | | | | | | | | Summary: Earlier CaptureTracking would assume all "interesting" operands to a call or invoke were its arguments. With operand bundles this is no longer true. Note: an earlier change got `doesNotCapture` working correctly with operand bundles. This change uses DSE to test the changes to CaptureTracking. DSE is a vehicle for testing only, and is not directly involved in this change. Reviewers: reames, majnemer Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D14306 llvm-svn: 252095
* Slightly saner handling of thumb branches.Rafael Espindola2015-11-041-9/+15
| | | | | | | | The generic infrastructure already did a lot of work to decide if the fixup value is know or not. It doesn't make sense to reimplement a very basic case: same fragment. llvm-svn: 252090
* [x86] Teach the shrink-wrapping hooks to do the proper thing with Win64.Quentin Colombet2015-11-041-0/+8
| | | | | | | | | | Win64 has some strict requirements for the epilogue. As a result, we disable shrink-wrapping for Win64 unless the block that gets the epilogue is already an exit block. Fixes PR24193. llvm-svn: 252088
* Fix some Clang-tidy modernize warnings, other minor fixes.Eugene Zelenko2015-11-046-26/+22
| | | | | | | | Fixed warnings are: modernize-use-override, modernize-use-nullptr and modernize-redundant-void-arg. Differential revision: http://reviews.llvm.org/D14312 llvm-svn: 252087
* PM: Rephrase PrintLoopPass as a wrapper around a new-style pass. NFCJustin Bogner2015-11-042-17/+23
| | | | | | | Splits PrintLoopPass into a new-style pass and a PrintLoopPassWrapper, much like we already do for PrintFunctionPass and PrintModulePass. llvm-svn: 252085
* Add new interfaces to MBB for manipulating successors with probabilities ↵Cong Hou2015-11-041-0/+82
| | | | | | | | | | | instead of weights. NFC. This is part-1 of the patch that replaces all edge weights in MBB by probabilities, which only adds new interfaces. No functional changes. Differential revision: http://reviews.llvm.org/D13908 llvm-svn: 252083
* Warning fix.Simon Pilgrim2015-11-041-2/+2
| | | | llvm-svn: 252078
* [IR] Add a `data_operand` abstractionSanjoy Das2015-11-041-0/+29
| | | | | | | | | | | | | | | | | | | | | Summary: Data operands of a call or invoke consist of the call arguments, and the bundle operands associated with the `call` (or `invoke`) instruction. The motivation for this change is that we'd like to be able to query "argument attributes" like `readonly` and `nocapture` for bundle operands naturally. This change also provides a conservative "implementation" for these attributes for any bundle operand, and an extension point for future work. Reviewers: chandlerc, majnemer, reames Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D14305 llvm-svn: 252077
* [X86][SSE] Add general memory folding for (V)INSERTPS instructionSimon Pilgrim2015-11-043-58/+79
| | | | | | | | | | | | | | | | This patch improves the memory folding of the inserted float element for the (V)INSERTPS instruction. The existing implementation occurs in the DAGCombiner and relies on the narrowing of a whole vector load into a scalar load (and then converted into a vector) to (hopefully) allow folding to occur later on. Not only has this proven problematic for debug builds, it also prevents other memory folds (notably stack reloads) from happening. This patch removes the old implementation and moves the folding code to the X86 foldMemoryOperand handler. A new private 'special case' function - foldMemoryOperandCustom - has been added to deal with memory folding of instructions that can't just use the lookup tables - (V)INSERTPS is the first of several that could be done. It also tweaks the memory operand folding code with an additional pointer offset that allows existing memory addresses to be modified, in this case to convert the vector address to the explicit address of the scalar element that will be inserted. Unlike the previous implementation we now set the insertion source index to zero, although this is ignored for the (V)INSERTPSrm version, anything that relied on shuffle decodes (such as unfolding of insertps loads) was incorrectly calculating the source address - I've added a test for this at insertps-unfold-load-bug.ll Differential Revision: http://reviews.llvm.org/D13988 llvm-svn: 252074
* [IR] Add bounds checking to paramHasAttrSanjoy Das2015-11-042-4/+10
| | | | | | | | | | | | | | | | | Summary: This is intended to make a later change simpler. Note: adding this bounds checking required fixing `X86FastISel`. As far I can tell I've preserved original behavior but a careful review will be appreciated. Reviewers: reames Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D14304 llvm-svn: 252073
* Created new X86 FMA3 opcodes (FMA*_Int) that are used now for lowering of ↵Andrew Kaylor2015-11-042-38/+118
| | | | | | | | | | | | | | scalar FMA intrinsics. Patch by Slava Klochkov The key difference between FMA* and FMA*_Int opcodes is that FMA*_Int opcodes are handled more conservatively. It is illegal to commute the 1st operand of FMA*_Int instructions as the upper bits of scalar FMA intrinsic result must be taken from the 1st operand, but such commute transformation would change those upper bits and invalidate the intrinsic's result. Reviewers: Quentin Colombet, Elena Demikhovsky Differential Revision: http://reviews.llvm.org/D13710 llvm-svn: 252060
* [ARM] Combine CMOV into BFI where possibleJames Molloy2015-11-042-0/+106
| | | | | | | | | | | | | | If we have a CMOV, OR and AND combination such as: if (x & CN) y |= CM; And: * CN is a single bit; * All bits covered by CM are known zero in y; Then we can convert this to a sequence of BFI instructions. This will always be a win if CM is a single bit, will always be no worse than the TST & OR sequence if CM is two bits, and for thumb will be no worse if CM is three bits (due to the extra IT instruction). llvm-svn: 252057
* [ThinLTO] Always set linkage type to external when converting aliasTeresa Johnson2015-11-041-2/+4
| | | | | | | | When converting an alias to a non-alias when the aliasee is not imported, ensure that the linkage type is set to external so that it is a valid linkage type. Added a test case that exposed this issue. llvm-svn: 252054
* [SimplifyCFG] Merge conditional storesJames Molloy2015-11-041-3/+312
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We can often end up with conditional stores that cannot be speculated. They can come from fairly simple, idiomatic code: if (c & flag1) *a = x; if (c & flag2) *a = y; ... There is no dominating or post-dominating store to a, so it is not legal to move the store unconditionally to the end of the sequence and cache the intermediate result in a register, as we would like to. It is, however, legal to merge the stores together and do the store once: tmp = undef; if (c & flag1) tmp = x; if (c & flag2) tmp = y; if (c & flag1 || c & flag2) *a = tmp; The real power in this optimization is that it allows arbitrary length ladders such as these to be completely and trivially if-converted. The typical code I'd expect this to trigger on often uses binary-AND with constants as the condition (as in the above example), which means the ending condition can simply be truncated into a single binary-AND too: 'if (c & (flag1|flag2))'. As in the general case there are bitwise operators here, the ladder can often be optimized further too. This optimization involves potentially increasing register pressure. Even in the simplest case, the lifetime of the first predicate is extended. This can be elided in some cases such as using binary-AND on constants, but not in the general case. Threading 'tmp' through all branches can also increase register pressure. The optimization as in this patch is enabled by default but kept in a very conservative mode. It will only optimize if it thinks the resultant code should be if-convertable, and additionally if it can thread 'tmp' through at least one existing PHI, so it will only ever in the worst case create one more PHI and extend the lifetime of a predicate. This doesn't trigger much in LNT, unfortunately, but it does trigger in a big way in a third party test suite. llvm-svn: 252051
* Error out when faced with value names containing '\0'Filipe Cabecinhas2015-11-041-1/+4
| | | | | | Bug found with afl-fuzz. llvm-svn: 252048
* [ELF] elfiamcu triple should imply e_machine == EM_IAMCUMichael Kuperstein2015-11-044-4/+24
| | | | | | Differential Revision: http://reviews.llvm.org/D14109 llvm-svn: 252043
* [X86] DAGCombine should not introduce FILD in soft-float modeMichael Kuperstein2015-11-041-2/+2
| | | | | | | The x86 "sitofp i64 to double" dag combine, in 32-bit mode, lowers sitofp directly to X86ISD::FILD (or FILD_FLAG). This should not be done in soft-float mode. llvm-svn: 252042
* [LVI] Update a comment to clarify what's actually happening and whyPhilip Reames2015-11-041-3/+22
| | | | llvm-svn: 252033
* [CVP] Fold return values if possiblePhilip Reames2015-11-041-0/+51
| | | | | | | | | | | | In my previous change to CVP (251606), I made CVP much more aggressive about trying to constant fold comparisons. This patch is a reversal in direction. Rather than being agressive about every compare, we restore the non-block local restriction for most, and then try hard for compares feeding returns. The motivation for this is two fold: * The more I thought about it, the less comfortable I got with the possible compile time impact of the other approach. There have been no reported issues, but after talking to a couple of folks, I've come to the conclusion the time probably isn't justified. * It turns out we need to know the context to leverage the full power of LVI. In particular, asking about something at the end of it's block (the use of a compare in a return) will frequently get more precise results than something in the middle of a block. This is an implementation detail, but it's also hard to get around since mid-block queries have to reason about possible throwing instructions and don't get to use most of LVI's block focused infrastructure. This will become particular important when combined with http://reviews.llvm.org/D14263. Differential Revision: http://reviews.llvm.org/D14271 llvm-svn: 252032
* [StatepointLowering] Remove distinction between call and invoke safepointsIgor Laevsky2015-11-042-24/+31
| | | | | | | | | | | | There is no point in having invoke safepoints handled differently than the call safepoints. All relevant decisions could be made by looking at whether or not gc.result and gc.relocate lay in a same basic block. This change will allow to lower call safepoints with relocates and results in a different basic blocks. See test case for example. Differential Revision: http://reviews.llvm.org/D14158 llvm-svn: 252028
* [LLVMSymbolize] Reduce indentation by using helper function. NFC.Alexey Samsonov2015-11-041-21/+24
| | | | llvm-svn: 252022
* [LLVMSymbolize] Properly propagate object parsing errors from the library.Alexey Samsonov2015-11-041-90/+107
| | | | llvm-svn: 252021
* Fix unused variable warning from r252017Adam Nemet2015-11-041-3/+2
| | | | llvm-svn: 252019
* LLE 6/6: Add LoopLoadElimination passAdam Nemet2015-11-034-0/+566
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Summary: The goal of this pass is to perform store-to-load forwarding across the backedge of a loop. E.g.: for (i) A[i + 1] = A[i] + B[i] => T = A[0] for (i) T = T + B[i] A[i + 1] = T The pass relies on loop dependence analysis via LoopAccessAnalisys to find opportunities of loop-carried dependences with a distance of one between a store and a load. Since it's using LoopAccessAnalysis, it was easy to also add support for versioning away may-aliasing intervening stores that would otherwise prevent this transformation. This optimization is also performed by Load-PRE in GVN without the option of multi-versioning. As was discussed with Daniel Berlin in http://reviews.llvm.org/D9548, this is inferior to a more loop-aware solution applied here. Hopefully, we will be able to remove some complexity from GVN/MemorySSA as a consequence. In the long run, we may want to extend this pass (or create a new one if there is little overlap) to also eliminate loop-indepedent redundant loads and store that *require* versioning due to may-aliasing intervening stores/loads. I have some motivating cases for store elimination. My plan right now is to wait for MemorySSA to come online first rather than using memdep for this. The main motiviation for this pass is the 456.hmmer loop in SPECint2006 where after distributing the original loop and vectorizing the top part, we are left with the critical path exposed in the bottom loop. Being able to promote the memory dependence into a register depedence (even though the HW does perform store-to-load fowarding as well) results in a major gain (~20%). This gain also transfers over to x86: it's around 8-10%. Right now the pass is off by default and can be enabled with -enable-loop-load-elim. On the LNT testsuite, there are two performance changes (negative number -> improvement): 1. -28% in Polybench/linear-algebra/solvers/dynprog: the length of the critical paths is reduced 2. +2% in Polybench/stencils/adi: Unfortunately, I couldn't reproduce this outside of LNT The pass is scheduled after the loop vectorizer (which is after loop distribution). The rational is to try to reuse LAA state, rather than recomputing it. The order between LV and LLE is not critical because normally LV does not touch scalar st->ld forwarding cases where vectorizing would inhibit the CPU's st->ld forwarding to kick in. LoopLoadElimination requires LAA to provide the full set of dependences (including forward dependences). LAA is known to omit loop-independent dependences in certain situations. The big comment before removeDependencesFromMultipleStores explains why this should not occur for the cases that we're interested in. Reviewers: dberlin, hfinkel Subscribers: junbuml, dberlin, mssimpso, rengolin, sanjoy, llvm-commits Differential Revision: http://reviews.llvm.org/D13259 llvm-svn: 252017
* [LAA] LLE 5/6: Add predicate functions Dependence::isForward/isBackward, NFCAdam Nemet2015-11-031-2/+22
| | | | | | | | | | | | Summary: Will be used by the LoopLoadElimination pass. Reviewers: hfinkel Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D13258 llvm-svn: 252016
OpenPOWER on IntegriCloud