mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-20 03:23:01 +02:00
384913118b
This was originally planned as the fix for: https://bugs.llvm.org/show_bug.cgi?id=35834 ...but simpler transforms handled that case, so I implemented a lesser solution. It turns out we need to handle the case with 'not' ops too because the real code example that we are trying to solve: https://bugs.llvm.org/show_bug.cgi?id=35875 ...has extra uses of the intermediate values, so we can't rely on smaller canonicalizations to get us to the goal. As with rL321672, I've tried to show every possibility in the codegen tests because that's the simplest way to prove we're doing the right thing in the wide variety of permutations of this pattern. We can also show an InstCombine win because we added a fold for this case in: rL321998 / D41603 An Alive proof for one variant of the pattern to show that the InstCombine and codegen results are correct: https://rise4fun.com/Alive/vd1 Name: min3_nots %nx = xor i8 %x, -1 %ny = xor i8 %y, -1 %nz = xor i8 %z, -1 %cmpxz = icmp slt i8 %nx, %nz %minxz = select i1 %cmpxz, i8 %nx, i8 %nz %cmpyz = icmp slt i8 %ny, %nz %minyz = select i1 %cmpyz, i8 %ny, i8 %nz %cmpyx = icmp slt i8 %y, %x %r = select i1 %cmpyx, i8 %minxz, i8 %minyz => %cmpxyz = icmp slt i8 %minxz, %ny %r = select i1 %cmpxyz, i8 %minxz, i8 %ny Name: min3_nots_alt %nx = xor i8 %x, -1 %ny = xor i8 %y, -1 %nz = xor i8 %z, -1 %cmpxz = icmp slt i8 %nx, %nz %minxz = select i1 %cmpxz, i8 %nx, i8 %nz %cmpyz = icmp slt i8 %ny, %nz %minyz = select i1 %cmpyz, i8 %ny, i8 %nz %cmpyx = icmp slt i8 %y, %x %r = select i1 %cmpyx, i8 %minxz, i8 %minyz => %xz = icmp sgt i8 %x, %z %maxxz = select i1 %xz, i8 %x, i8 %z %xyz = icmp sgt i8 %maxxz, %y %maxxyz = select i1 %xyz, i8 %maxxz, i8 %y %r = xor i8 %maxxyz, -1 llvm-svn: 322283 |
||
|---|---|---|
| .. | ||
| AliasAnalysis.cpp | ||
| AliasAnalysisEvaluator.cpp | ||
| AliasAnalysisSummary.cpp | ||
| AliasAnalysisSummary.h | ||
| AliasSetTracker.cpp | ||
| Analysis.cpp | ||
| AssumptionCache.cpp | ||
| BasicAliasAnalysis.cpp | ||
| BlockFrequencyInfo.cpp | ||
| BlockFrequencyInfoImpl.cpp | ||
| BranchProbabilityInfo.cpp | ||
| CallGraph.cpp | ||
| CallGraphSCCPass.cpp | ||
| CallPrinter.cpp | ||
| CaptureTracking.cpp | ||
| CFG.cpp | ||
| CFGPrinter.cpp | ||
| CFLAndersAliasAnalysis.cpp | ||
| CFLGraph.h | ||
| CFLSteensAliasAnalysis.cpp | ||
| CGSCCPassManager.cpp | ||
| CMakeLists.txt | ||
| CmpInstAnalysis.cpp | ||
| CodeMetrics.cpp | ||
| ConstantFolding.cpp | ||
| CostModel.cpp | ||
| Delinearization.cpp | ||
| DemandedBits.cpp | ||
| DependenceAnalysis.cpp | ||
| DivergenceAnalysis.cpp | ||
| DominanceFrontier.cpp | ||
| DomPrinter.cpp | ||
| EHPersonalities.cpp | ||
| GlobalsModRef.cpp | ||
| IndirectCallPromotionAnalysis.cpp | ||
| InlineCost.cpp | ||
| InstCount.cpp | ||
| InstructionSimplify.cpp | ||
| Interval.cpp | ||
| IntervalPartition.cpp | ||
| IteratedDominanceFrontier.cpp | ||
| IVUsers.cpp | ||
| LazyBlockFrequencyInfo.cpp | ||
| LazyBranchProbabilityInfo.cpp | ||
| LazyCallGraph.cpp | ||
| LazyValueInfo.cpp | ||
| Lint.cpp | ||
| LLVMBuild.txt | ||
| Loads.cpp | ||
| LoopAccessAnalysis.cpp | ||
| LoopAnalysisManager.cpp | ||
| LoopInfo.cpp | ||
| LoopPass.cpp | ||
| LoopUnrollAnalyzer.cpp | ||
| MemDepPrinter.cpp | ||
| MemDerefPrinter.cpp | ||
| MemoryBuiltins.cpp | ||
| MemoryDependenceAnalysis.cpp | ||
| MemoryLocation.cpp | ||
| MemorySSA.cpp | ||
| MemorySSAUpdater.cpp | ||
| ModuleDebugInfoPrinter.cpp | ||
| ModuleSummaryAnalysis.cpp | ||
| ObjCARCAliasAnalysis.cpp | ||
| ObjCARCAnalysisUtils.cpp | ||
| ObjCARCInstKind.cpp | ||
| OptimizationRemarkEmitter.cpp | ||
| OrderedBasicBlock.cpp | ||
| PHITransAddr.cpp | ||
| PostDominators.cpp | ||
| ProfileSummaryInfo.cpp | ||
| PtrUseVisitor.cpp | ||
| README.txt | ||
| RegionInfo.cpp | ||
| RegionPass.cpp | ||
| RegionPrinter.cpp | ||
| ScalarEvolution.cpp | ||
| ScalarEvolutionAliasAnalysis.cpp | ||
| ScalarEvolutionExpander.cpp | ||
| ScalarEvolutionNormalization.cpp | ||
| ScopedNoAliasAA.cpp | ||
| StratifiedSets.h | ||
| SyntheticCountsUtils.cpp | ||
| TargetLibraryInfo.cpp | ||
| TargetTransformInfo.cpp | ||
| Trace.cpp | ||
| TypeBasedAliasAnalysis.cpp | ||
| TypeMetadataUtils.cpp | ||
| ValueLattice.cpp | ||
| ValueLatticeUtils.cpp | ||
| ValueTracking.cpp | ||
| VectorUtils.cpp | ||
Analysis Opportunities:
//===---------------------------------------------------------------------===//
In test/Transforms/LoopStrengthReduce/quadradic-exit-value.ll, the
ScalarEvolution expression for %r is this:
{1,+,3,+,2}<loop>
Outside the loop, this could be evaluated simply as (%n * %n), however
ScalarEvolution currently evaluates it as
(-2 + (2 * (trunc i65 (((zext i64 (-2 + %n) to i65) * (zext i64 (-1 + %n) to i65)) /u 2) to i64)) + (3 * %n))
In addition to being much more complicated, it involves i65 arithmetic,
which is very inefficient when expanded into code.
//===---------------------------------------------------------------------===//
In formatValue in test/CodeGen/X86/lsr-delayed-fold.ll,
ScalarEvolution is forming this expression:
((trunc i64 (-1 * %arg5) to i32) + (trunc i64 %arg5 to i32) + (-1 * (trunc i64 undef to i32)))
This could be folded to
(-1 * (trunc i64 undef to i32))
//===---------------------------------------------------------------------===//