[RISCV][CostModel] Recommit VPIntrinsics have same cost as their non-vp counterparts

This was reverted in commit 0abaf3c (llvm#67178).
This version of the patch includes a fix which was caused by
vp-reductions having an extra start value argument which the non-vp
counterparts did not have.

Author: michaelmaitland

llvm/include/llvm/CodeGen/BasicTTIImpl.h

@@ -1691,6 +1691,62 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
     }
     }
 
+    // VP Intrinsics should have the same cost as their non-vp counterpart.
+    // TODO: Adjust the cost to make the vp intrinsic cheaper than its non-vp
+    // counterpart when the vector length argument is smaller than the maximum
+    // vector length.
+    if (VPIntrinsic::isVPIntrinsic(ICA.getID())) {
+      std::optional<unsigned> FOp =
+          VPIntrinsic::getFunctionalOpcodeForVP(ICA.getID());
+      if (FOp) {
+        // TODO: Support other kinds of Intrinsics (i.e. reductions)
+        if (ICA.getID() == Intrinsic::vp_load) {
+          Align Alignment;
+          if (auto *VPI = dyn_cast_or_null<VPIntrinsic>(ICA.getInst()))
+            Alignment = VPI->getPointerAlignment().valueOrOne();
+          unsigned AS = 0;
+          if (ICA.getArgs().size() > 1)
+            if (auto *PtrTy =
+                    dyn_cast<PointerType>(ICA.getArgs()[0]->getType()))
+              AS = PtrTy->getAddressSpace();
+          return thisT()->getMemoryOpCost(*FOp, ICA.getReturnType(), Alignment,
+                                          AS, CostKind);
+        }
+        if (ICA.getID() == Intrinsic::vp_store) {
+          Align Alignment;
+          if (auto *VPI = dyn_cast_or_null<VPIntrinsic>(ICA.getInst()))
+            Alignment = VPI->getPointerAlignment().valueOrOne();
+          unsigned AS = 0;
+          if (ICA.getArgs().size() >= 2)
+            if (auto *PtrTy =
+                    dyn_cast<PointerType>(ICA.getArgs()[1]->getType()))
+              AS = PtrTy->getAddressSpace();
+          return thisT()->getMemoryOpCost(*FOp, Args[0]->getType(), Alignment,
+                                          AS, CostKind);
+        }
+        if (VPBinOpIntrinsic::isVPBinOp(ICA.getID())) {
+          return thisT()->getArithmeticInstrCost(*FOp, ICA.getReturnType(),
+                                                 CostKind);
+        }
+      }
+
+      std::optional<Intrinsic::ID> FID =
+          VPIntrinsic::getFunctionalIntrinsicIDForVP(ICA.getID());
+      if (FID) {
+        // Non-vp version will have same Args/Tys except mask and vector length.
+        assert(ICA.getArgs().size() >= 2 && ICA.getArgTypes().size() >= 2 &&
+               "Expected VPIntrinsic to have Mask and Vector Length args and "
+               "types");
+        ArrayRef<const Value *> NewArgs = ArrayRef(ICA.getArgs()).drop_back(2);
+        ArrayRef<Type *> NewTys = ArrayRef(ICA.getArgTypes()).drop_back(2);
+
+        IntrinsicCostAttributes NewICA(*FID, ICA.getReturnType(), NewArgs,
+                                       NewTys, ICA.getFlags(), ICA.getInst(),
+                                       ICA.getScalarizationCost());
+        return thisT()->getIntrinsicInstrCost(NewICA, CostKind);
+      }
+    }
+
     // Assume that we need to scalarize this intrinsic.
     // Compute the scalarization overhead based on Args for a vector
     // intrinsic.

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 5 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
@@ -282,7 +282,7 @@ 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: %10 = getelementptr i8, ptr %base, i32 42
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.compressstore.v2i8(<2 x i8> undef, ptr %10, <2 x i1> undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = getelementptr i8, ptr %base, i32 42
-; RVI-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.vp.store.v2i8.p0(<2 x i8> undef, ptr %11, <2 x i1> undef, i32 undef)
+; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.v2i8.p0(<2 x i8> undef, ptr %11, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = getelementptr i8, ptr %base, i32 42
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.experimental.vp.strided.store.v2i8.p0.i64(<2 x i8> undef, ptr %12, i64 undef, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
@@ -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 5 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
@@ -352,7 +352,7 @@ define void @foldable_vector_uses(ptr %base, <2 x ptr> %base.vec) {
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %10 = getelementptr i8, ptr %base, i32 0
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.compressstore.v2i8(<2 x i8> undef, ptr %10, <2 x i1> undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %11 = getelementptr i8, ptr %base, i32 0
-; RVI-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.vp.store.v2i8.p0(<2 x i8> undef, ptr %11, <2 x i1> undef, i32 undef)
+; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.v2i8.p0(<2 x i8> undef, ptr %11, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %12 = getelementptr i8, ptr %base, i32 0
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.experimental.vp.strided.store.v2i8.p0.i64(<2 x i8> undef, ptr %12, i64 undef, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void