[llvm] [LV] Convert gather loads with constant stride into strided loads (PR #147297)

[Luke Lau via llvm-commits]

================
@@ -6364,3 +6385,111 @@ void VPlanTransforms::createPartialReductions(VPlan &Plan,
     for (const VPPartialReductionChain &Chain : Chains)
       transformToPartialReduction(Chain, CostCtx.Types, Plan, Phi);
 }
+
+void VPlanTransforms::convertToStridedAccesses(VPlan &Plan,
+                                               PredicatedScalarEvolution &PSE,
+                                               Loop &L, VPCostContext &Ctx,
+                                               VFRange &Range) {
+  if (Plan.hasScalarVFOnly())
+    return;
+
+  VPTypeAnalysis TypeInfo(Plan);
+  VPRegionBlock *VectorLoop = Plan.getVectorLoopRegion();
+  SmallVector<VPWidenMemoryRecipe *> ToErase;
+  VPValue *I32VF = nullptr;
+  for (VPBasicBlock *VPBB : VPBlockUtils::blocksOnly<VPBasicBlock>(
+           vp_depth_first_shallow(VectorLoop->getEntry()))) {
+    for (VPRecipeBase &R : make_early_inc_range(*VPBB)) {
+      auto *LoadR = dyn_cast<VPWidenLoadRecipe>(&R);
+      // TODO: Support strided store.
+      // TODO: Transform reverse access into strided access with -1 stride.
+      // TODO: Transform gather/scatter with uniform address into strided access
+      // with 0 stride.
+      // TODO: Transform interleave access into multiple strided accesses.
+      if (!LoadR || LoadR->isConsecutive())
+        continue;
+
+      auto *Ptr = dyn_cast<VPWidenGEPRecipe>(LoadR->getAddr());
+      if (!Ptr)
+        continue;
+
+      Type *LoadTy = TypeInfo.inferScalarType(LoadR);
+      Align Alignment = LoadR->getAlign();
+      auto IsProfitable = [&](ElementCount VF) -> bool {
----------------
lukel97 wrote:

Nit is the compiler able to deduce the return type automatically?

```suggestion
      auto IsProfitable = [&](ElementCount VF) {
```

https://github.com/llvm/llvm-project/pull/147297