Load/Store instructions should use getMemoryOpCost

Author: michaelmaitland

llvm/include/llvm/CodeGen/BasicTTIImpl.h

@@ -1692,11 +1692,40 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
     // counterpart when the vector length argument is smaller than the maximum
     // vector length.
     if (VPIntrinsic::isVPIntrinsic(ICA.getID())) {
-      std::optional<Intrinsic::ID> FOp =
+      std::optional<unsigned> FOp =
           VPIntrinsic::getFunctionalOpcodeForVP(ICA.getID());
-      if (FOp)
+      if (FOp) {
+        if (ICA.getID() == Intrinsic::vp_load) {
+          Align Alignment = isa_and_nonnull<VPIntrinsic>(ICA.getInst())
+                                ? cast<VPIntrinsic>(ICA.getInst())
+                                      ->getPointerAlignment()
+                                      .valueOrOne()
+                                : Align(1);
+          unsigned AS = ICA.getArgs().size() >= 1 &&
+                                isa<PointerType>(ICA.getArgs()[0]->getType())
+                            ? cast<PointerType>(ICA.getArgs()[0]->getType())
+                                  ->getAddressSpace()
+                            : 0;
+          return thisT()->getMemoryOpCost(*FOp, ICA.getReturnType(), Alignment,
+                                          AS, CostKind);
+        } else if (ICA.getID() == Intrinsic::vp_store) {
+          Align Alignment = isa_and_nonnull<VPIntrinsic>(ICA.getInst())
+                                ? cast<VPIntrinsic>(ICA.getInst())
+                                      ->getPointerAlignment()
+                                      .valueOrOne()
+                                : Align(1);
+          unsigned AS = ICA.getArgs().size() >= 2 &&
+                                isa<PointerType>(ICA.getArgs()[1]->getType())
+                            ? cast<PointerType>(ICA.getArgs()[1]->getType())
+                                  ->getAddressSpace()
+                            : 0;
+          return thisT()->getMemoryOpCost(*FOp, Args[0]->getType(), Alignment,
+                                          AS, CostKind);
+        }
+        // TODO: Support other kinds of Intrinsics (i.e. reductions)
         return thisT()->getArithmeticInstrCost(*FOp, ICA.getReturnType(),
                                                CostKind);
+      }
 
       std::optional<Intrinsic::ID> FID =
           VPIntrinsic::getFunctionalIntrinsicIDForVP(ICA.getID());

llvm/test/Analysis/CostModel/RISCV/gep.ll

@@ -270,7 +270,7 @@ define void @non_foldable_vector_uses(ptr %base, <2 x ptr> %base.vec) {
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = getelementptr i8, ptr %base, i32 42
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %x4 = call <2 x i8> @llvm.masked.expandload.v2i8(ptr %4, <2 x i1> undef, <2 x i8> undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = getelementptr i8, ptr %base, i32 42
-; RVI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x5 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr %5, <2 x i1> undef, i32 undef)
+; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %x5 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr %5, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = getelementptr i8, ptr %base, i32 42
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %x6 = call <2 x i8> @llvm.experimental.vp.strided.load.v2i8.p0.i64(ptr %6, i64 undef, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = getelementptr i8, ptr %base, i32 42
@@ -340,7 +340,7 @@ define void @foldable_vector_uses(ptr %base, <2 x ptr> %base.vec) {
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %4 = getelementptr i8, ptr %base, i32 0
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %x4 = call <2 x i8> @llvm.masked.expandload.v2i8(ptr %4, <2 x i1> undef, <2 x i8> undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %5 = getelementptr i8, ptr %base, i32 0
-; RVI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x5 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr %5, <2 x i1> undef, i32 undef)
+; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %x5 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr %5, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %6 = getelementptr i8, ptr %base, i32 0
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %x6 = call <2 x i8> @llvm.experimental.vp.strided.load.v2i8.p0.i64(ptr %6, i64 undef, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %7 = getelementptr i8, ptr %base, i32 0