From ac6bde281d97d9ebbd04f28e31a36bd3743f3ed3 Mon Sep 17 00:00:00 2001
From: Jonas Paulsson <paulsson@linux.vnet.ibm.com>
Date: Wed, 11 Jan 2017 14:40:39 +0000
Subject: [PATCH] [SystemZ]  Improve isFoldableMemAccessOffset().

A store of an extracted element or a load which gets inserted into a vector,
will be combined into a vector load/store element instruction.

Therefore, isFoldableMemAccessOffset(), which is called by LSR, should
return false in these cases.

Reviewer: Ulrich Weigand

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@291673 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Target/SystemZ/SystemZISelLowering.cpp | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/lib/Target/SystemZ/SystemZISelLowering.cpp b/lib/Target/SystemZ/SystemZISelLowering.cpp
index 2081809def7..2d0a06af18a 100644
--- a/lib/Target/SystemZ/SystemZISelLowering.cpp
+++ b/lib/Target/SystemZ/SystemZISelLowering.cpp
@@ -547,8 +547,26 @@ bool SystemZTargetLowering::isFoldableMemAccessOffset(Instruction *I,
   assert (isa<LoadInst>(I) || isa<StoreInst>(I));
   Type *MemAccessTy = (isa<LoadInst>(I) ? I->getType() :
                        I->getOperand(0)->getType());
-  if (!isUInt<12>(Offset) &&
-      (MemAccessTy->isFloatingPointTy() || MemAccessTy->isVectorTy()))
+  bool IsFPAccess = MemAccessTy->isFloatingPointTy();
+  bool IsVectorAccess = MemAccessTy->isVectorTy();
+
+  // A store of an extracted vector element will be combined into a VSTE type
+  // instruction.
+  if (!IsVectorAccess && isa<StoreInst>(I)) {
+    Value *DataOp = I->getOperand(0);
+    if (isa<ExtractElementInst>(DataOp))
+      IsVectorAccess = true;
+  }
+
+  // A load which gets inserted into a vector element will be combined into a
+  // VLE type instruction.
+  if (!IsVectorAccess && isa<LoadInst>(I) && I->hasOneUse()) {
+    User *LoadUser = *I->user_begin();
+    if (isa<InsertElementInst>(LoadUser))
+      IsVectorAccess = true;
+  }
+
+  if (!isUInt<12>(Offset) && (IsFPAccess || IsVectorAccess))
     return false;
 
   return true;
-- 
2.40.0