Reland "[RISCV][TTI] Enable masked interleave access for scalable vector (llvm#149981)"

The patch "[LV] Fix gap mask requirement for interleaved access
(llvm#151105)" fixed the an assertion for the RISC-V arch string zvl1024b.

Author: Mel-Chen

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

@@ -979,10 +979,12 @@ InstructionCost RISCVTTIImpl::getInterleavedMemoryOpCost(
     Align Alignment, unsigned AddressSpace, TTI::TargetCostKind CostKind,
     bool UseMaskForCond, bool UseMaskForGaps) const {
 
-  // The interleaved memory access pass will lower interleaved memory ops (i.e
-  // a load and store followed by a specific shuffle) to vlseg/vsseg
-  // intrinsics.
-  if (!UseMaskForCond && !UseMaskForGaps &&
+  // The interleaved memory access pass will lower (de)interleave ops combined
+  // with an adjacent appropriate memory to vlseg/vsseg intrinsics. vlseg/vsseg
+  // only support masking per-iteration (i.e. condition), not per-segment (i.e.
+  // gap).
+  // TODO: Support masked interleaved access for fixed length vector.
+  if ((isa<ScalableVectorType>(VecTy) || !UseMaskForCond) && !UseMaskForGaps &&
       Factor <= TLI->getMaxSupportedInterleaveFactor()) {
     auto *VTy = cast<VectorType>(VecTy);
     std::pair<InstructionCost, MVT> LT = getTypeLegalizationCost(VTy);

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h

@@ -398,6 +398,10 @@ class RISCVTTIImpl final : public BasicTTIImplBase<RISCVTTIImpl> {
 
   bool enableInterleavedAccessVectorization() const override { return true; }
 
+  bool enableMaskedInterleavedAccessVectorization() const override {
+    return ST->hasVInstructions();
+  }
+
   unsigned getMinTripCountTailFoldingThreshold() const override;
 
   enum RISCVRegisterClass { GPRRC, FPRRC, VRRC };

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -1378,7 +1378,9 @@ class LoopVectorizationCostModel {
       return;
     // Override EVL styles if needed.
     // FIXME: Investigate opportunity for fixed vector factor.
+    // FIXME: Support interleave accesses.
     bool EVLIsLegal = UserIC <= 1 && IsScalableVF &&
+                      !InterleaveInfo.hasGroups() &&
                       TTI.hasActiveVectorLength() && !EnableVPlanNativePath;
     if (EVLIsLegal)
       return;