[VPlan] Compute cost for binary op VPInstruction with underlying values.

Author: fhahn

llvm/lib/Transforms/Vectorize/VPlan.h

@@ -972,10 +972,7 @@ class VPInstruction : public VPRecipeWithIRFlags,
 
   /// Return the cost of this VPInstruction.
   InstructionCost computeCost(ElementCount VF,
-                              VPCostContext &Ctx) const override {
-    // TODO: Compute accurate cost after retiring the legacy cost model.
-    return 0;
-  }
+                              VPCostContext &Ctx) const override;
 
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
   /// Print the VPInstruction to \p O.

llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp

@@ -768,6 +768,27 @@ void VPInstruction::execute(VPTransformState &State) {
             /*IsScalar*/ GeneratesPerFirstLaneOnly);
 }
 
+InstructionCost VPInstruction::computeCost(ElementCount VF,
+                                           VPCostContext &Ctx) const {
+  if (Instruction::isBinaryOp(getOpcode())) {
+    if (!getUnderlyingValue())
+      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);
+  }
+
+  assert(!getUnderlyingValue() &&
+         "unexpected VPInstruction without underlying value");
+  return 0;
+}
+
 bool VPInstruction::opcodeMayReadOrWriteFromMemory() const {
   if (Instruction::isBinaryOp(getOpcode()))
     return false;

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

@@ -18,7 +18,7 @@ define void @wide_or_replaced_with_add_vpinstruction(ptr %src, ptr noalias %dst)
 ; 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 0 for VF 2: EMIT ir<%or> = add ir<%iv.4>, ir<1>
+; 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>
@@ -36,7 +36,7 @@ define void @wide_or_replaced_with_add_vpinstruction(ptr %src, ptr noalias %dst)
 ; 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 0 for VF 4: EMIT ir<%or> = add ir<%iv.4>, ir<1>
+; 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>