[llvm] [AArch64] Support commuted operands in performFlagSettingCombine (PR #162496)

[Cullen Rhodes via llvm-commits]

https://github.com/c-rhodes created https://github.com/llvm/llvm-project/pull/162496

Fixes #122624.

Assisted-by: gpt-5-codex

>From 98cbbdfed66df01321056826d722a406874ca5ba Mon Sep 17 00:00:00 2001
From: Cullen Rhodes <cullen.rhodes at arm.com>
Date: Wed, 8 Oct 2025 11:56:38 +0000
Subject: [PATCH] [AArch64] Support commuted operands in
 performFlagSettingCombine

Fixes #122624.

Assisted-by: gpt-5-codex
---
 .../lib/Target/AArch64/AArch64ISelLowering.cpp | 18 +++++++++++++++---
 llvm/test/CodeGen/AArch64/adds_cmn.ll          |  6 ++----
 llvm/test/CodeGen/AArch64/sat-add.ll           |  6 ++----
 3 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index dc8e7c84f5e2c..b8d81291a85d8 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -26193,9 +26193,21 @@ static SDValue performFlagSettingCombine(SDNode *N,
   }
 
   // Combine identical generic nodes into this node, re-using the result.
-  if (SDNode *Generic = DCI.DAG.getNodeIfExists(
-          GenericOpcode, DCI.DAG.getVTList(VT), {LHS, RHS}))
-    DCI.CombineTo(Generic, SDValue(N, 0));
+  auto CombineWithExistingGeneric = [&](SDValue Op0, SDValue Op1) {
+    if (SDNode *Generic = DCI.DAG.getNodeIfExists(
+            GenericOpcode, DCI.DAG.getVTList(VT), {Op0, Op1})) {
+      DCI.CombineTo(Generic, SDValue(N, 0));
+      return true;
+    }
+    return false;
+  };
+
+  if (CombineWithExistingGeneric(LHS, RHS))
+    return SDValue();
+
+  if (DCI.DAG.getTargetLoweringInfo().isCommutativeBinOp(GenericOpcode) &&
+      CombineWithExistingGeneric(RHS, LHS))
+    return SDValue();
 
   return SDValue();
 }
diff --git a/llvm/test/CodeGen/AArch64/adds_cmn.ll b/llvm/test/CodeGen/AArch64/adds_cmn.ll
index aa070b7886ba5..9b456a5419d61 100644
--- a/llvm/test/CodeGen/AArch64/adds_cmn.ll
+++ b/llvm/test/CodeGen/AArch64/adds_cmn.ll
@@ -22,10 +22,8 @@ entry:
 define { i32, i32 } @adds_cmn_c(i32 noundef %x, i32 noundef %y) {
 ; CHECK-LABEL: adds_cmn_c:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    cmn w0, w1
-; CHECK-NEXT:    add w1, w1, w0
-; CHECK-NEXT:    cset w8, lo
-; CHECK-NEXT:    mov w0, w8
+; CHECK-NEXT:    adds w1, w0, w1
+; CHECK-NEXT:    cset w0, lo
 ; CHECK-NEXT:    ret
 entry:
   %0 = tail call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 %x, i32 %y)
diff --git a/llvm/test/CodeGen/AArch64/sat-add.ll b/llvm/test/CodeGen/AArch64/sat-add.ll
index ecd48d6b7c65b..149b4c4fd26c9 100644
--- a/llvm/test/CodeGen/AArch64/sat-add.ll
+++ b/llvm/test/CodeGen/AArch64/sat-add.ll
@@ -290,8 +290,7 @@ define i32 @unsigned_sat_variable_i32_using_cmp_sum(i32 %x, i32 %y) {
 define i32 @unsigned_sat_variable_i32_using_cmp_notval(i32 %x, i32 %y) {
 ; CHECK-LABEL: unsigned_sat_variable_i32_using_cmp_notval:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    add w8, w0, w1
-; CHECK-NEXT:    cmn w1, w0
+; CHECK-NEXT:    adds w8, w1, w0
 ; CHECK-NEXT:    csinv w0, w8, wzr, lo
 ; CHECK-NEXT:    ret
   %noty = xor i32 %y, -1
@@ -331,8 +330,7 @@ define i64 @unsigned_sat_variable_i64_using_cmp_sum(i64 %x, i64 %y) {
 define i64 @unsigned_sat_variable_i64_using_cmp_notval(i64 %x, i64 %y) {
 ; CHECK-LABEL: unsigned_sat_variable_i64_using_cmp_notval:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    add x8, x0, x1
-; CHECK-NEXT:    cmn x1, x0
+; CHECK-NEXT:    adds x8, x1, x0
 ; CHECK-NEXT:    csinv x0, x8, xzr, lo
 ; CHECK-NEXT:    ret
   %noty = xor i64 %y, -1