[llvm] LoopVectorize: update comment following 63d8058 (NFC) (PR #91120)

[Ramkumar Ramachandra via llvm-commits]

https://github.com/artagnon created https://github.com/llvm/llvm-project/pull/91120

Address a review comment post landing 63d8058 (LoopVectorize: guard appending InstsToScalarize; fix bug) to update a comment.

>From 3d65064a1ddd729272bb8e2d9cb602700fdee372 Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <r at artagnon.com>
Date: Sun, 5 May 2024 13:43:01 +0100
Subject: [PATCH] LoopVectorize: update comment following 63d8058 (NFC)

Address a review comment post landing 63d8058 (LoopVectorize: guard
appending InstsToScalarize; fix bug) to update a comment.
---
 llvm/lib/Transforms/Vectorize/LoopVectorize.cpp | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 3be0102bea3e34..0c2a87bde9d76a 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -5813,10 +5813,11 @@ void LoopVectorizationCostModel::collectInstsToScalarize(ElementCount VF) {
     for (Instruction &I : *BB)
       if (isScalarWithPredication(&I, VF)) {
         ScalarCostsTy ScalarCosts;
-        // Do not apply discount if scalable, because that would lead to
-        // invalid scalarization costs.
-        // Do not apply discount logic if hacked cost is needed
-        // for emulated masked memrefs.
+        // Do not apply discount logic for:
+        // 1. Scalars after vectorization, as there will only be a single copy
+        // of the instruction.
+        // 2. Scalable VF, as that would lead to invalid scalarization costs.
+        // 3. Emulated masked memrefs, if a hacked cost is needed.
         if (!isScalarAfterVectorization(&I, VF) && !VF.isScalable() &&
             !useEmulatedMaskMemRefHack(&I, VF) &&
             computePredInstDiscount(&I, ScalarCosts, VF) >= 0)