[LV] Suppress vectorization in some nontemporal cases

When considering a loop containing nontemporal stores or loads for
vectorization, suppress the vectorization if the corresponding
vectorized store or load with the aligment of the original scaler
memory op is not supported with the nontemporal hint on the target.

This adds two new functions:
  bool isLegalNTStore(Type *DataType, unsigned Alignment) const;
  bool isLegalNTLoad(Type *DataType, unsigned Alignment) const;

to TTI, leaving the target independent default implementation as
returning true, but with overriding implementations for X86 that
check the legality based on available Subtarget features.

This fixes https://llvm.org/PR40759

Differential Revision: https://reviews.llvm.org/D61764

llvm-svn: 363581

1 files changed, 32 insertions, 0 deletions

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
index e5713c4355f..6ef8dc2d3cd 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
@@ -767,6 +767,38 @@ bool LoopVectorizationLegality::canVectorizeInstrs() {
           return false;
         }
 
+        // For nontemporal stores, check that a nontemporal vector version is
+        // supported on the target.
+        if (ST->getMetadata(LLVMContext::MD_nontemporal)) {
+          // Arbitrarily try a vector of 2 elements.
+          Type *VecTy = VectorType::get(T, /*NumElements=*/2);
+          assert(VecTy && "did not find vectorized version of stored type");
+          unsigned Alignment = getLoadStoreAlignment(ST);
+          if (!TTI->isLegalNTStore(VecTy, Alignment)) {
+            reportVectorizationFailure(
+                "nontemporal store instruction cannot be vectorized",
+                "nontemporal store instruction cannot be vectorized",
+                "CantVectorizeNontemporalStore", ST);
+            return false;
+          }
+        }
+
+      } else if (auto *LD = dyn_cast<LoadInst>(&I)) {
+        if (LD->getMetadata(LLVMContext::MD_nontemporal)) {
+          // For nontemporal loads, check that a nontemporal vector version is
+          // supported on the target (arbitrarily try a vector of 2 elements).
+          Type *VecTy = VectorType::get(I.getType(), /*NumElements=*/2);
+          assert(VecTy && "did not find vectorized version of load type");
+          unsigned Alignment = getLoadStoreAlignment(LD);
+          if (!TTI->isLegalNTLoad(VecTy, Alignment)) {
+            reportVectorizationFailure(
+                "nontemporal load instruction cannot be vectorized",
+                "nontemporal load instruction cannot be vectorized",
+                "CantVectorizeNontemporalLoad", LD);
+            return false;
+          }
+        }
+
         // FP instructions can allow unsafe algebra, thus vectorizable by
         // non-IEEE-754 compliant SIMD units.
         // This applies to floating-point math operations and calls, not memory