From 42ddd71120e445748a8d992e12297560590b3ca4 Mon Sep 17 00:00:00 2001
From: Bill Schmidt <wschmidt@linux.vnet.ibm.com>
Date: Wed, 29 Jul 2015 14:31:57 +0000
Subject: [PATCH] [PPC] Fix PR24216: Don't generate splat for misaligned
 shuffle mask

Given certain shuffle-vector masks, LLVM emits splat instructions
which splat the wrong bytes from the source register.  The issue is
that the function PPC::isSplatShuffleMask() in PPCISelLowering.cpp
does not ensure that the splat pattern found is requesting bytes that
are aligned on an EltSize boundary.  This patch detects this situation
as not a valid splat mask, resulting in a permute being generated
instead of a splat.

Patch and test case by Tyler Kenney, cleaned up a bit by me.

This is a simple bug fix that would be good to incorporate into 3.7.

llvm-svn: 243519
---
 llvm/lib/Target/PowerPC/PPCISelLowering.cpp |  5 +++++
 llvm/test/CodeGen/PowerPC/pr24216.ll        | 14 ++++++++++++++
 2 files changed, 19 insertions(+)
 create mode 100644 llvm/test/CodeGen/PowerPC/pr24216.ll

diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
index e7bc903..94171a6 100644
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -1430,6 +1430,11 @@ bool PPC::isSplatShuffleMask(ShuffleVectorSDNode *N, unsigned EltSize) {
   assert(N->getValueType(0) == MVT::v16i8 &&
          (EltSize == 1 || EltSize == 2 || EltSize == 4));
 
+  // The consecutive indices need to specify an element, not part of two
+  // different elements.  So abandon ship early if this isn't the case.
+  if (N->getMaskElt(0) % EltSize != 0)
+    return false;
+
   // This is a splat operation if each element of the permute is the same, and
   // if the value doesn't reference the second vector.
   unsigned ElementBase = N->getMaskElt(0);
diff --git a/llvm/test/CodeGen/PowerPC/pr24216.ll b/llvm/test/CodeGen/PowerPC/pr24216.ll
new file mode 100644
index 0000000..4ab4198
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/pr24216.ll
@@ -0,0 +1,14 @@
+; RUN: llc -mcpu=pwr8 -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s
+
+; Test case adapted from PR24216.
+
+define void @foo(<16 x i8>* nocapture readonly %in, <16 x i8>* nocapture %out) {
+entry:
+  %0 = load <16 x i8>, <16 x i8>* %in, align 16
+  %1 = shufflevector <16 x i8> %0, <16 x i8> undef, <16 x i32> <i32 2, i32 3, i32 4, i32 5, i32 2, i32 3, i32 4, i32 5, i32 2, i32 3, i32 4, i32 5, i32 2, i32 3, i32 4, i32 5>
+  store <16 x i8> %1, <16 x i8>* %out, align 16
+  ret void
+}
+
+; CHECK: vperm
+; CHECK-NOT: vspltw
-- 
2.7.4