[TTI][RISCV] Deduplicate type-based VP costing

We have a lot of code in RISCVTTIImpl::getIntrinsicInstrCost for vp intrinsics, which just forward the cost to the underlying non-vp cost function.

However I just also noticed that there is generic code in BasicTTIImpl's getIntrinsicInstrCost that does the same thing, added in llvm#67178. The only difference is that BasicTTIImpl doesn't yet handle it for type-based costing. There doesn't seem to be any reason that it can't since it's just inspecting the argument types.

This shuffles the VP costing up to handle both regular and type-based costing, and begins to deduplicate the VP specific costing in RISCVTTIImpl by moving them into BasicTTIImpl.h.

It's not NFC since it picks up a couple of VP nodes that had slipped through the cracks. Future PRs can begin to move more of the code from RISCVTTIImpl to BasicTTIImpl.

Author: lukel97

llvm/include/llvm/CodeGen/BasicTTIImpl.h

@@ -1574,6 +1574,67 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
     if (Intrinsic::isTargetIntrinsic(IID))
       return TargetTransformInfo::TCC_Basic;
 
+    // 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.
+    // TODO: Support other kinds of VPIntrinsics
+    if (VPIntrinsic::isVPIntrinsic(ICA.getID())) {
+      std::optional<unsigned> FOp =
+          VPIntrinsic::getFunctionalOpcodeForVP(ICA.getID());
+      if (FOp) {
+        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.getArgTypes().size() > 1)
+            if (auto *PtrTy = dyn_cast<PointerType>(ICA.getArgTypes()[0]))
+              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.getArgTypes().size() >= 2)
+            if (auto *PtrTy = dyn_cast<PointerType>(ICA.getArgTypes()[1]))
+              AS = PtrTy->getAddressSpace();
+          return thisT()->getMemoryOpCost(*FOp, ICA.getArgTypes()[0], 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 arg types except mask and vector
+        // length.
+        assert(ICA.getArgTypes().size() >= 2 &&
+               "Expected VPIntrinsic to have Mask and Vector Length args and "
+               "types");
+        ArrayRef<Type *> NewTys = ArrayRef(ICA.getArgTypes()).drop_back(2);
+
+        // VPReduction intrinsics have a start value argument that their non-vp
+        // counterparts do not have, except for the fadd and fmul non-vp
+        // counterpart.
+        if (VPReductionIntrinsic::isVPReduction(ICA.getID()) &&
+            *FID != Intrinsic::vector_reduce_fadd &&
+            *FID != Intrinsic::vector_reduce_fmul)
+          NewTys = NewTys.drop_front();
+
+        IntrinsicCostAttributes NewICA(*FID, ICA.getReturnType(), NewTys,
+                                       ICA.getFlags());
+        return thisT()->getIntrinsicInstrCost(NewICA, CostKind);
+      }
+    }
+
     if (ICA.isTypeBasedOnly())
       return getTypeBasedIntrinsicInstrCost(ICA, CostKind);
 
@@ -1834,68 +1895,6 @@ 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.
-    // TODO: Support other kinds of VPIntrinsics
-    if (VPIntrinsic::isVPIntrinsic(ICA.getID())) {
-      std::optional<unsigned> FOp =
-          VPIntrinsic::getFunctionalOpcodeForVP(ICA.getID());
-      if (FOp) {
-        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<Type *> NewTys = ArrayRef(ICA.getArgTypes()).drop_back(2);
-
-        // VPReduction intrinsics have a start value argument that their non-vp
-        // counterparts do not have, except for the fadd and fmul non-vp
-        // counterpart.
-        if (VPReductionIntrinsic::isVPReduction(ICA.getID()) &&
-            *FID != Intrinsic::vector_reduce_fadd &&
-            *FID != Intrinsic::vector_reduce_fmul)
-          NewTys = NewTys.drop_front();
-
-        IntrinsicCostAttributes NewICA(*FID, ICA.getReturnType(), NewTys,
-                                       ICA.getFlags());
-        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/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

@@ -1104,26 +1104,6 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
       return Cost * LT.first;
     break;
   }
-  // vp integer arithmetic ops.
-  case Intrinsic::vp_add:
-  case Intrinsic::vp_and:
-  case Intrinsic::vp_ashr:
-  case Intrinsic::vp_lshr:
-  case Intrinsic::vp_mul:
-  case Intrinsic::vp_or:
-  case Intrinsic::vp_sdiv:
-  case Intrinsic::vp_shl:
-  case Intrinsic::vp_srem:
-  case Intrinsic::vp_sub:
-  case Intrinsic::vp_udiv:
-  case Intrinsic::vp_urem:
-  case Intrinsic::vp_xor:
-  // vp float arithmetic ops.
-  case Intrinsic::vp_fadd:
-  case Intrinsic::vp_fsub:
-  case Intrinsic::vp_fmul:
-  case Intrinsic::vp_fdiv:
-  case Intrinsic::vp_frem:
   case Intrinsic::vp_fneg: {
     std::optional<unsigned> FOp =
         VPIntrinsic::getFunctionalOpcodeForVP(ICA.getID());
@@ -1164,23 +1144,6 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
     return getCmpSelInstrCost(*FOp, ICA.getArgTypes()[0], ICA.getReturnType(),
                               UI->getPredicate(), CostKind);
   }
-  // vp load/store
-  case Intrinsic::vp_load:
-  case Intrinsic::vp_store: {
-    if (!ICA.getInst())
-      break;
-    Intrinsic::ID IID = ICA.getID();
-    std::optional<unsigned> FOp = VPIntrinsic::getFunctionalOpcodeForVP(IID);
-    assert(FOp.has_value());
-    auto *UI = cast<VPIntrinsic>(ICA.getInst());
-    if (ICA.getID() == Intrinsic::vp_load)
-      return getMemoryOpCost(
-          *FOp, ICA.getReturnType(), UI->getPointerAlignment(),
-          UI->getOperand(0)->getType()->getPointerAddressSpace(), CostKind);
-    return getMemoryOpCost(
-        *FOp, ICA.getArgTypes()[0], UI->getPointerAlignment(),
-        UI->getOperand(1)->getType()->getPointerAddressSpace(), CostKind);
-  }
   case Intrinsic::vp_select: {
     Intrinsic::ID IID = ICA.getID();
     std::optional<unsigned> FOp = VPIntrinsic::getFunctionalOpcodeForVP(IID);

llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll

@@ -1172,37 +1172,37 @@ define void @abs() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; TYPEBASED-LABEL: 'abs'
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %1 = call <2 x i8> @llvm.vp.abs.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x i8> @llvm.vp.abs.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %2 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %3 = call <4 x i8> @llvm.vp.abs.v4i8(<4 x i8> undef, i1 false, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x i8> @llvm.vp.abs.v4i8(<4 x i8> undef, i1 false, <4 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %4 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %5 = call <8 x i8> @llvm.vp.abs.v8i8(<8 x i8> undef, i1 false, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <8 x i8> @llvm.vp.abs.v8i8(<8 x i8> undef, i1 false, <8 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %6 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 126 for instruction: %7 = call <16 x i8> @llvm.vp.abs.v16i8(<16 x i8> undef, i1 false, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %7 = call <16 x i8> @llvm.vp.abs.v16i8(<16 x i8> undef, i1 false, <16 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %9 = call <2 x i64> @llvm.vp.abs.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %9 = call <2 x i64> @llvm.vp.abs.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %10 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %11 = call <4 x i64> @llvm.vp.abs.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %11 = call <4 x i64> @llvm.vp.abs.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %13 = call <8 x i64> @llvm.vp.abs.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x i64> @llvm.vp.abs.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 141 for instruction: %15 = call <16 x i64> @llvm.vp.abs.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x i64> @llvm.vp.abs.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %16 = call <16 x i64> @llvm.abs.v16i64(<16 x i64> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x i8> @llvm.vp.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 2 x i8> @llvm.vp.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %18 = call <vscale x 2 x i8> @llvm.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 4 x i8> @llvm.vp.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = call <vscale x 4 x i8> @llvm.vp.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %20 = call <vscale x 4 x i8> @llvm.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %21 = call <vscale x 8 x i8> @llvm.vp.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %21 = call <vscale x 8 x i8> @llvm.vp.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %22 = call <vscale x 8 x i8> @llvm.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %23 = call <vscale x 16 x i8> @llvm.vp.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %23 = call <vscale x 16 x i8> @llvm.vp.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %24 = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %25 = call <vscale x 2 x i64> @llvm.vp.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %25 = call <vscale x 2 x i64> @llvm.vp.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %26 = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %27 = call <vscale x 4 x i64> @llvm.vp.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %27 = call <vscale x 4 x i64> @llvm.vp.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %28 = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %29 = call <vscale x 8 x i64> @llvm.vp.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %29 = call <vscale x 8 x i64> @llvm.vp.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %30 = call <vscale x 8 x i64> @llvm.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %31 = call <vscale x 16 x i64> @llvm.vp.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %31 = call <vscale x 16 x i64> @llvm.vp.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %32 = call <vscale x 16 x i64> @llvm.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;