[llvm] [VPlan] Pass the mask's compare predicate when costing a blend. (PR #218422)

[via llvm-commits]

llvmorg-github-actions[bot] wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-llvm-transforms

Author: Florian Hahn (fhahn)

<details>
<summary>Changes</summary>

Pass the predicate to getCmpSelInstrCost in VPBlendRecipe if the mask is a compare. This improves cost estimates on targets like AArch64 where selects on compares can be lowered more efficiently.

---
Full diff: https://github.com/llvm/llvm-project/pull/218422.diff


2 Files Affected:

- (modified) llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp (+10-3) 
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/cmp_cost.ll (+4-4) 


``````````diff
diff --git a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
index 306a4a259affe..8c0fb36684320 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
@@ -3334,9 +3334,16 @@ InstructionCost VPBlendRecipe::computeCost(ElementCount VF,
 
   Type *ResultTy = toVectorTy(this->getScalarType(), VF);
   Type *CmpTy = toVectorTy(Type::getInt1Ty(Ctx.LLVMCtx), VF);
-  return (getNumIncomingValues() - 1) *
-         Ctx.TTI.getCmpSelInstrCost(Instruction::Select, ResultTy, CmpTy,
-                                    CmpInst::BAD_ICMP_PREDICATE, Ctx.CostKind);
+
+  InstructionCost Cost = 0;
+  for (unsigned I = 1, E = getNumIncomingValues(); I != E; ++I) {
+    CmpPredicate Pred;
+    if (!match(getMask(I), m_Cmp(Pred, m_VPValue(), m_VPValue())))
+      Pred = CmpInst::BAD_ICMP_PREDICATE;
+    Cost += Ctx.TTI.getCmpSelInstrCost(Instruction::Select, ResultTy, CmpTy,
+                                       Pred, Ctx.CostKind);
+  }
+  return Cost;
 }
 
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/cmp_cost.ll b/llvm/test/Transforms/LoopVectorize/AArch64/cmp_cost.ll
index 5bc97910eb2f0..e33ab81d36fa6 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/cmp_cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/cmp_cost.ll
@@ -183,7 +183,7 @@ define i32 @switch_to_cmp(ptr %s, ptr %dst, i64 %n) {
 ; CHECK:  Cost of 0 for VF 2: EMIT vp<[[VP36:%[0-9]+]]> = or vp<[[VP35]]>, vp<[[VP21]]>
 ; CHECK:  Cost of 1 for VF 2: WIDEN ir<%c.4> = add ir<%c>, ir<4>
 ; CHECK:  Cost of 1 for VF 2: WIDEN ir<%c.1> = add ir<%c>, ir<1>
-; CHECK:  Cost of 12 for VF 2: BLEND ir<%c.next> = ir<%c> ir<%c.4>/vp<[[VP22]]> ir<%c.1>/vp<[[VP36]]>
+; CHECK:  Cost of 7 for VF 2: BLEND ir<%c.next> = ir<%c> ir<%c.4>/vp<[[VP22]]> ir<%c.1>/vp<[[VP36]]>
 ; CHECK:  Cost of 0 for VF 2: CLONE ir<%dst.gep> = getelementptr ir<%dst>, vp<[[VP5]]>
 ; CHECK:  Cost of 0 for VF 2: vp<[[VP37:%[0-9]+]]> = vector-pointer i8, ir<%dst.gep>, ir<1>
 ; CHECK:  Cost of 4 for VF 2: WIDEN store vp<[[VP37]]>, ir<%l>
@@ -242,7 +242,7 @@ define i32 @switch_to_cmp(ptr %s, ptr %dst, i64 %n) {
 ; CHECK:  Cost of 0 for VF 4: EMIT vp<[[VP36]]> = or vp<[[VP35]]>, vp<[[VP21]]>
 ; CHECK:  Cost of 1 for VF 4: WIDEN ir<%c.4> = add ir<%c>, ir<4>
 ; CHECK:  Cost of 1 for VF 4: WIDEN ir<%c.1> = add ir<%c>, ir<1>
-; CHECK:  Cost of 24 for VF 4: BLEND ir<%c.next> = ir<%c> ir<%c.4>/vp<[[VP22]]> ir<%c.1>/vp<[[VP36]]>
+; CHECK:  Cost of 13 for VF 4: BLEND ir<%c.next> = ir<%c> ir<%c.4>/vp<[[VP22]]> ir<%c.1>/vp<[[VP36]]>
 ; CHECK:  Cost of 0 for VF 4: CLONE ir<%dst.gep> = getelementptr ir<%dst>, vp<[[VP5]]>
 ; CHECK:  Cost of 0 for VF 4: vp<[[VP37]]> = vector-pointer i8, ir<%dst.gep>, ir<1>
 ; CHECK:  Cost of 2 for VF 4: WIDEN store vp<[[VP37]]>, ir<%l>
@@ -301,7 +301,7 @@ define i32 @switch_to_cmp(ptr %s, ptr %dst, i64 %n) {
 ; CHECK:  Cost of 0 for VF 8: EMIT vp<[[VP36]]> = or vp<[[VP35]]>, vp<[[VP21]]>
 ; CHECK:  Cost of 2 for VF 8: WIDEN ir<%c.4> = add ir<%c>, ir<4>
 ; CHECK:  Cost of 2 for VF 8: WIDEN ir<%c.1> = add ir<%c>, ir<1>
-; CHECK:  Cost of 16 for VF 8: BLEND ir<%c.next> = ir<%c> ir<%c.4>/vp<[[VP22]]> ir<%c.1>/vp<[[VP36]]>
+; CHECK:  Cost of 10 for VF 8: BLEND ir<%c.next> = ir<%c> ir<%c.4>/vp<[[VP22]]> ir<%c.1>/vp<[[VP36]]>
 ; CHECK:  Cost of 0 for VF 8: CLONE ir<%dst.gep> = getelementptr ir<%dst>, vp<[[VP5]]>
 ; CHECK:  Cost of 0 for VF 8: vp<[[VP37]]> = vector-pointer i8, ir<%dst.gep>, ir<1>
 ; CHECK:  Cost of 1 for VF 8: WIDEN store vp<[[VP37]]>, ir<%l>
@@ -360,7 +360,7 @@ define i32 @switch_to_cmp(ptr %s, ptr %dst, i64 %n) {
 ; CHECK:  Cost of 0 for VF 16: EMIT vp<[[VP36]]> = or vp<[[VP35]]>, vp<[[VP21]]>
 ; CHECK:  Cost of 4 for VF 16: WIDEN ir<%c.4> = add ir<%c>, ir<4>
 ; CHECK:  Cost of 4 for VF 16: WIDEN ir<%c.1> = add ir<%c>, ir<1>
-; CHECK:  Cost of 32 for VF 16: BLEND ir<%c.next> = ir<%c> ir<%c.4>/vp<[[VP22]]> ir<%c.1>/vp<[[VP36]]>
+; CHECK:  Cost of 20 for VF 16: BLEND ir<%c.next> = ir<%c> ir<%c.4>/vp<[[VP22]]> ir<%c.1>/vp<[[VP36]]>
 ; CHECK:  Cost of 0 for VF 16: CLONE ir<%dst.gep> = getelementptr ir<%dst>, vp<[[VP5]]>
 ; CHECK:  Cost of 0 for VF 16: vp<[[VP37]]> = vector-pointer i8, ir<%dst.gep>, ir<1>
 ; CHECK:  Cost of 1 for VF 16: WIDEN store vp<[[VP37]]>, ir<%l>

``````````

</details>


https://github.com/llvm/llvm-project/pull/218422