[llvm] [PowerPC] Fix handling of undefs in the PPC::isSplatShuffleMask query (PR #145149)

[Wael Yehia via llvm-commits]

https://github.com/w2yehia created https://github.com/llvm/llvm-project/pull/145149

Currently, the query assumes that a single undef bit implies the rest of the `EltSize - 1` bits 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.

>From fd9c9caeaff72489ae2e708bacd7fd7e513a8345 Mon Sep 17 00:00:00 2001
From: Wael Yehia <wyehia at ca.ibm.com>
Date: Sat, 21 Jun 2025 01:31:53 +0000
Subject: [PATCH] fix

---
 llvm/lib/Target/PowerPC/PPCISelLowering.cpp |  9 +++++++--
 llvm/test/CodeGen/PowerPC/pr141642.ll       | 13 +++++++++++++
 2 files changed, 20 insertions(+), 2 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 f502d8570425a..d1b17f227a684 100644
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -2242,8 +2242,13 @@ 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)
+    // An UNDEF element is a sequence of UNDEF bits.
+    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;
   }
diff --git a/llvm/test/CodeGen/PowerPC/pr141642.ll b/llvm/test/CodeGen/PowerPC/pr141642.ll
new file mode 100644
index 0000000000000..38a7065747867
--- /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
+}