From 735d721de451067c3a618b309703d0b8beb9cacc Mon Sep 17 00:00:00 2001
From: Wael Yehia <wmyehia2001@yahoo.com>
Date: Mon, 23 Jun 2025 13:22:33 -0400
Subject: [PATCH] [PowerPC] Fix handling of undefs in the
 PPC::isSplatShuffleMask query (#145149)

Currently, the query assumes that a single undef byte implies the rest of
the `EltSize - 1` bytes are undefs, but that's not always true.
e.g. isSplatShuffleMask(
<0,1,2,3,4,5,6,7,undef,undef,undef,undef,0,1,2,3>, 8) should return
false.

---------

Co-authored-by: Wael Yehia <wyehia@ca.ibm.com>
---
 llvm/lib/Target/PowerPC/PPCISelLowering.cpp | 13 +++++++++----
 llvm/test/CodeGen/PowerPC/pr141642.ll       | 13 +++++++++++++
 2 files changed, 22 insertions(+), 4 deletions(-)
 create mode 100644 llvm/test/CodeGen/PowerPC/pr141642.ll

diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
index 421a808de667..88c6fe632d26 100644
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -2242,10 +2242,15 @@ bool PPC::isSplatShuffleMask(ShuffleVectorSDNode *N, unsigned EltSize) {
       return false;
 
   for (unsigned i = EltSize, e = 16; i != e; i += EltSize) {
-    if (N->getMaskElt(i) < 0) continue;
-    for (unsigned j = 0; j != EltSize; ++j)
-      if (N->getMaskElt(i+j) != N->getMaskElt(j))
-        return false;
+    // An UNDEF element is a sequence of UNDEF bytes.
+    if (N->getMaskElt(i) < 0) {
+      for (unsigned j = 1; j != EltSize; ++j)
+        if (N->getMaskElt(i + j) >= 0)
+          return false;
+    } else
+      for (unsigned j = 0; j != EltSize; ++j)
+        if (N->getMaskElt(i + j) != N->getMaskElt(j))
+          return false;
   }
   return true;
 }
diff --git a/llvm/test/CodeGen/PowerPC/pr141642.ll b/llvm/test/CodeGen/PowerPC/pr141642.ll
new file mode 100644
index 000000000000..38a706574786
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/pr141642.ll
@@ -0,0 +1,13 @@
+; RUN: llc -mcpu=pwr8 -mtriple=powerpc64le-unknown-linux-gnu -O0 -debug-only=selectiondag -o - < %s 2>&1 | \
+; RUN:  FileCheck %s
+; CHECK-NOT: lxvdsx
+; CHECK-NOT: LD_SPLAT
+
+define weak_odr dso_local void @unpack(ptr noalias noundef %packed_in) local_unnamed_addr {
+entry:
+  %ld = load <2 x i32>, ptr %packed_in, align 2
+  %shuf = shufflevector <2 x i32> %ld, <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 0>
+  %ie = insertelement <4 x i32> %shuf, i32 7, i32 2
+  store <4 x i32> %shuf, ptr %packed_in, align 2
+  ret void
+}
-- 
2.49.0