[VPlan] Compute cost for binary op VPInstruction with underlying values. (#125434)

As exposed by #125094, we are
missing cost computation for some binary VPInstructions we created based
on original IR instructions. Their cost should be considered.

PR: #125434

Author: fhahn

llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp

@@ -720,14 +720,34 @@ Value *VPInstruction::generate(VPTransformState &State) {
 
 InstructionCost VPInstruction::computeCost(ElementCount VF,
                                            VPCostContext &Ctx) const {
+  if (Instruction::isBinaryOp(getOpcode())) {
+    if (!getUnderlyingValue()) {
+      // TODO: Compute cost for VPInstructions without underlying values once
+      // the legacy cost model has been retired.
+      return 0;
+    }
+
+    assert(!doesGeneratePerAllLanes() &&
+           "Should only generate a vector value or single scalar, not scalars "
+           "for all lanes.");
+    Type *ResTy = Ctx.Types.inferScalarType(this);
+    if (!vputils::onlyFirstLaneUsed(this))
+      ResTy = toVectorTy(ResTy, VF);
+
+    return Ctx.TTI.getArithmeticInstrCost(getOpcode(), ResTy, Ctx.CostKind);
+  }
+
   switch (getOpcode()) {
   case VPInstruction::AnyOf: {
     auto *VecTy = toVectorTy(Ctx.Types.inferScalarType(this), VF);
     return Ctx.TTI.getArithmeticReductionCost(
         Instruction::Or, cast<VectorType>(VecTy), std::nullopt, Ctx.CostKind);
   }
   default:
-    // TODO: Fill out other opcodes!
+    // TODO: Compute cost other VPInstructions once the legacy cost model has
+    // been retired.
+    assert(!getUnderlyingValue() &&
+           "unexpected VPInstruction witht underlying value");
     return 0;
   }
 }

llvm/test/Transforms/LoopVectorize/X86/CostModel/vpinstruction-cost.ll

@@ -0,0 +1,74 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of"
+; RUN: opt -S -passes=loop-vectorize -mcpu=skylake-avx512 -mtriple=x86_64-apple-macosx -debug -disable-output -S %s 2>&1 | FileCheck %s
+
+; REQUIRES: asserts
+
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128"
+
+define void @wide_or_replaced_with_add_vpinstruction(ptr %src, ptr noalias %dst) {
+; CHECK-LABEL: 'wide_or_replaced_with_add_vpinstruction'
+; CHECK:  Cost of 1 for VF 2: induction instruction %iv.next = add nuw nsw i64 %iv, 1
+; CHECK:  Cost of 0 for VF 2: induction instruction %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop.latch ]
+; CHECK:  Cost of 1 for VF 2: exit condition instruction %exitcond = icmp eq i64 %iv.next, 32
+; CHECK:  Cost of 0 for VF 2: EMIT vp<%3> = CANONICAL-INDUCTION ir<0>, vp<%index.next>
+; CHECK:  Cost of 0 for VF 2: ir<%iv> = WIDEN-INDUCTION ir<0>, ir<1>, vp<%0>
+; CHECK:  Cost of 0 for VF 2: vp<%4> = SCALAR-STEPS vp<%3>, ir<1>
+; CHECK:  Cost of 0 for VF 2: CLONE ir<%g.src> = getelementptr inbounds ir<%src>, vp<%4>
+; CHECK:  Cost of 0 for VF 2: vp<%5> = vector-pointer ir<%g.src>
+; CHECK:  Cost of 1 for VF 2: WIDEN ir<%l> = load vp<%5>
+; CHECK:  Cost of 1 for VF 2: WIDEN ir<%iv.4> = add ir<%iv>, ir<4>
+; CHECK:  Cost of 1 for VF 2: WIDEN ir<%c> = icmp ule ir<%l>, ir<128>
+; CHECK:  Cost of 1 for VF 2: EMIT ir<%or> = add ir<%iv.4>, ir<1>
+; CHECK:  Cost of 0 for VF 2: CLONE ir<%g.dst> = getelementptr ir<%dst>, ir<%or>
+; CHECK:  Cost of 0 for VF 2: vp<%6> = vector-pointer ir<%g.dst>
+; CHECK:  Cost of 1 for VF 2: WIDEN store vp<%6>, ir<%iv.4>, ir<%c>
+; CHECK:  Cost of 0 for VF 2: EMIT vp<%index.next> = add nuw vp<%3>, vp<%1>
+; CHECK:  Cost of 0 for VF 2: EMIT branch-on-count vp<%index.next>, vp<%2>
+; CHECK:  Cost of 0 for VF 2: vector loop backedge
+; CHECK:  Cost of 1 for VF 4: induction instruction %iv.next = add nuw nsw i64 %iv, 1
+; CHECK:  Cost of 0 for VF 4: induction instruction %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop.latch ]
+; CHECK:  Cost of 1 for VF 4: exit condition instruction %exitcond = icmp eq i64 %iv.next, 32
+; CHECK:  Cost of 0 for VF 4: EMIT vp<%3> = CANONICAL-INDUCTION ir<0>, vp<%index.next>
+; CHECK:  Cost of 0 for VF 4: ir<%iv> = WIDEN-INDUCTION ir<0>, ir<1>, vp<%0>
+; CHECK:  Cost of 0 for VF 4: vp<%4> = SCALAR-STEPS vp<%3>, ir<1>
+; CHECK:  Cost of 0 for VF 4: CLONE ir<%g.src> = getelementptr inbounds ir<%src>, vp<%4>
+; CHECK:  Cost of 0 for VF 4: vp<%5> = vector-pointer ir<%g.src>
+; CHECK:  Cost of 1 for VF 4: WIDEN ir<%l> = load vp<%5>
+; CHECK:  Cost of 1 for VF 4: WIDEN ir<%iv.4> = add ir<%iv>, ir<4>
+; CHECK:  Cost of 1 for VF 4: WIDEN ir<%c> = icmp ule ir<%l>, ir<128>
+; CHECK:  Cost of 1 for VF 4: EMIT ir<%or> = add ir<%iv.4>, ir<1>
+; CHECK:  Cost of 0 for VF 4: CLONE ir<%g.dst> = getelementptr ir<%dst>, ir<%or>
+; CHECK:  Cost of 0 for VF 4: vp<%6> = vector-pointer ir<%g.dst>
+; CHECK:  Cost of 1 for VF 4: WIDEN store vp<%6>, ir<%iv.4>, ir<%c>
+; CHECK:  Cost of 0 for VF 4: EMIT vp<%index.next> = add nuw vp<%3>, vp<%1>
+; CHECK:  Cost of 0 for VF 4: EMIT branch-on-count vp<%index.next>, vp<%2>
+; CHECK:  Cost of 0 for VF 4: vector loop backedge
+; CHECK:  Cost of 1 for VF 4: induction instruction %iv.next = add nuw nsw i64 %iv, 1
+; CHECK:  Cost of 0 for VF 4: induction instruction %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop.latch ]
+; CHECK:  Cost of 1 for VF 4: exit condition instruction %exitcond = icmp eq i64 %iv.next, 32
+;
+entry:
+  br label %loop.header
+
+loop.header:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop.latch ]
+  %g.src = getelementptr inbounds i64, ptr %src, i64 %iv
+  %l = load i64, ptr %g.src
+  %iv.4 = add nuw nsw i64 %iv, 4
+  %c = icmp ule i64 %l, 128
+  br i1 %c, label %loop.then, label %loop.latch
+
+loop.then:
+  %or = or disjoint i64 %iv.4, 1
+  %g.dst = getelementptr inbounds i64, ptr %dst, i64 %or
+  store i64 %iv.4, ptr %g.dst, align 4
+  br label %loop.latch
+
+loop.latch:
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 32
+  br i1 %exitcond, label %exit, label %loop.header
+
+exit:
+  ret void
+}