[LoopVectorize] Teach Loop Vectorizor about interleaved memory accesses.

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

1 files changed, 7 insertions, 0 deletions

diff --git a/llvm/lib/Analysis/TargetTransformInfo.cpp b/llvm/lib/Analysis/TargetTransformInfo.cpp
index d813cab..24cada3 100644
--- a/llvm/lib/Analysis/TargetTransformInfo.cpp
+++ b/llvm/lib/Analysis/TargetTransformInfo.cpp
@@ -237,6 +237,13 @@ TargetTransformInfo::getMaskedMemoryOpCost(unsigned Opcode, Type *Src,
   return TTIImpl->getMaskedMemoryOpCost(Opcode, Src, Alignment, AddressSpace);
 }
 
+unsigned TargetTransformInfo::getInterleavedMemoryOpCost(
+    unsigned Opcode, Type *VecTy, unsigned Factor, ArrayRef<unsigned> Indices,
+    unsigned Alignment, unsigned AddressSpace) const {
+  return TTIImpl->getInterleavedMemoryOpCost(Opcode, VecTy, Factor, Indices,
+                                             Alignment, AddressSpace);
+}
+
 unsigned
 TargetTransformInfo::getIntrinsicInstrCost(Intrinsic::ID ID, Type *RetTy,
                                            ArrayRef<Type *> Tys) const {