[llvm] 5748ddb - [SLP] NFC. Add a comment to introduce the alternate instruction. (#134572)

[via llvm-commits]

Author: Han-Kuan Chen
Date: 2025-04-07T18:03:26+08:00
New Revision: 5748ddbab4883420ea23d2319006d814c4bfbda4

URL: https://github.com/llvm/llvm-project/commit/5748ddbab4883420ea23d2319006d814c4bfbda4
DIFF: https://github.com/llvm/llvm-project/commit/5748ddbab4883420ea23d2319006d814c4bfbda4.diff

LOG: [SLP] NFC. Add a comment to introduce the alternate instruction. (#134572)

Added: 
    

Modified: 
    llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 94c0289807245..e2031df810573 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -817,7 +817,28 @@ namespace {
 
 /// Main data required for vectorization of instructions.
 class InstructionsState {
-  /// The main/alternate instruction. MainOp is also VL0.
+  /// MainOp and AltOp are primarily determined by getSameOpcode. Currently,
+  /// only BinaryOperator, CastInst, and CmpInst support alternate instructions
+  /// (i.e., AltOp is not equal to MainOp; this can be checked using
+  /// isAltShuffle).
+  /// A rare exception is TrySplitNode, where the InstructionsState is derived
+  /// from getMainAltOpsNoStateVL.
+  /// For those InstructionsState that use alternate instructions, the resulting
+  /// vectorized output ultimately comes from a shufflevector. For example,
+  /// given a vector list (VL):
+  /// VL[0] = add i32 a, e
+  /// VL[1] = sub i32 b, f
+  /// VL[2] = add i32 c, g
+  /// VL[3] = sub i32 d, h
+  /// The vectorized result would be:
+  /// intermediated_0 = add <4 x i32> <a, b, c, d>, <e, f, g, h>
+  /// intermediated_1 = sub <4 x i32> <a, b, c, d>, <e, f, g, h>
+  /// result = shufflevector <4 x i32> intermediated_0,
+  ///                        <4 x i32> intermediated_1,
+  ///                        <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+  /// Since shufflevector is used in the final result, when calculating the cost
+  /// (getEntryCost), we must account for the usage of shufflevector in
+  /// GetVectorCost.
   Instruction *MainOp = nullptr;
   Instruction *AltOp = nullptr;