[flang-commits] [libcxx] [lldb] [clang] [lld] [libc] [llvm] [mlir] [flang] [openmp] [clang-tools-extra] [SLP]Add support for strided loads. (PR #80310)

[Philip Reames via flang-commits]

================
@@ -3878,6 +3883,130 @@ static Align computeCommonAlignment(ArrayRef<Value *> VL) {
   return CommonAlignment;
 }
 
+/// Check if \p Order represents reverse order.
+static bool isReverseOrder(ArrayRef<unsigned> Order) {
+  unsigned Sz = Order.size();
+  return !Order.empty() && all_of(enumerate(Order), [&](const auto &Pair) {
+    return Pair.value() == Sz || Sz - Pair.index() - 1 == Pair.value();
+  });
+}
+
+/// Checks if the provided list of pointers \p Pointers represents the strided
+/// pointers for type ElemTy. If they are not, std::nullopt is returned.
+/// Otherwise, if \p Inst is not specified, just initialized optional value is
+/// returned to show that the pointers represent strided pointers. If \p Inst
+/// specified, the runtime stride is materialized before the given \p Inst.
+/// \returns std::nullopt if the pointers are not pointers with the runtime
+/// stride, nullptr or actual stride value, otherwise.
+static std::optional<Value *>
+calculateRtStride(ArrayRef<Value *> PointerOps, Type *ElemTy,
+                  const DataLayout &DL, ScalarEvolution &SE,
+                  SmallVectorImpl<unsigned> &SortedIndices,
+                  Instruction *Inst = nullptr) {
+  SmallVector<const SCEV *> SCEVs;
----------------
preames wrote:

An alternate approach which might be simpler and yet cover many of the interesting test cases might be:
* Loop over the pointers, check that getPointerBase matches.
* Loop again doing removePointerBase
* This gives a list of offsets from base, bail if any non-constant
* Sort the list of constant offsets
* Check if strided w/shuffle?

If you don't want a shuffle afterwards, you can check the delta without sorting.

This won't cover non-constant strides, but I'm not sure we really care about those in practice.

https://github.com/llvm/llvm-project/pull/80310