mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-26 04:32:44 +01:00
d39edfda46
Interleaved memory accesses are grouped and vectorized into vector load/store and shufflevector.
E.g. for (i = 0; i < N; i+=2) {
a = A[i]; // load of even element
b = A[i+1]; // load of odd element
... // operations on a, b, c, d
A[i] = c; // store of even element
A[i+1] = d; // store of odd element
}
The loads of even and odd elements are identified as an interleave load group, which will be transfered into vectorized IRs like:
%wide.vec = load <8 x i32>, <8 x i32>* %ptr
%vec.even = shufflevector <8 x i32> %wide.vec, <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
%vec.odd = shufflevector <8 x i32> %wide.vec, <8 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
The stores of even and odd elements are identified as an interleave store group, which will be transfered into vectorized IRs like:
%interleaved.vec = shufflevector <4 x i32> %vec.even, %vec.odd, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
store <8 x i32> %interleaved.vec, <8 x i32>* %ptr
This optimization is currently disabled by defaut. To try it by adding '-enable-interleaved-mem-accesses=true'.
llvm-svn: 239291
|
||
|---|---|---|
| .. | ||
| AliasAnalysis.h | ||
| AliasSetTracker.h | ||
| AssumptionCache.h | ||
| BlockFrequencyInfo.h | ||
| BlockFrequencyInfoImpl.h | ||
| BranchProbabilityInfo.h | ||
| CallGraph.h | ||
| CallGraphSCCPass.h | ||
| CallPrinter.h | ||
| CaptureTracking.h | ||
| CFG.h | ||
| CFGPrinter.h | ||
| CGSCCPassManager.h | ||
| CodeMetrics.h | ||
| ConstantFolding.h | ||
| DependenceAnalysis.h | ||
| DominanceFrontier.h | ||
| DominanceFrontierImpl.h | ||
| DomPrinter.h | ||
| DOTGraphTraitsPass.h | ||
| InlineCost.h | ||
| InstructionSimplify.h | ||
| Interval.h | ||
| IntervalIterator.h | ||
| IntervalPartition.h | ||
| IteratedDominanceFrontier.h | ||
| IVUsers.h | ||
| JumpInstrTableInfo.h | ||
| LazyCallGraph.h | ||
| LazyValueInfo.h | ||
| LibCallAliasAnalysis.h | ||
| LibCallSemantics.h | ||
| Lint.h | ||
| Loads.h | ||
| LoopAccessAnalysis.h | ||
| LoopInfo.h | ||
| LoopInfoImpl.h | ||
| LoopIterator.h | ||
| LoopPass.h | ||
| MemoryBuiltins.h | ||
| MemoryDependenceAnalysis.h | ||
| MemoryLocation.h | ||
| Passes.h | ||
| PHITransAddr.h | ||
| PostDominators.h | ||
| PtrUseVisitor.h | ||
| RegionInfo.h | ||
| RegionInfoImpl.h | ||
| RegionIterator.h | ||
| RegionPass.h | ||
| RegionPrinter.h | ||
| ScalarEvolution.h | ||
| ScalarEvolutionExpander.h | ||
| ScalarEvolutionExpressions.h | ||
| ScalarEvolutionNormalization.h | ||
| SparsePropagation.h | ||
| TargetFolder.h | ||
| TargetLibraryInfo.def | ||
| TargetLibraryInfo.h | ||
| TargetTransformInfo.h | ||
| TargetTransformInfoImpl.h | ||
| Trace.h | ||
| ValueTracking.h | ||