From 92f377bd74aa89dadfa51521f5065f9d9b931349 Mon Sep 17 00:00:00 2001
From: Keno Fischer <kfischer@college.harvard.edu>
Date: Mon, 5 Dec 2016 21:25:03 +0000
Subject: [PATCH] [LAA] Prevent invalid IR for loop-invariant bound in loop
 body

Summary:
If LAA expands a bound that is loop invariant, but not hoisted out
of the loop body, it used to use that value anyway, causing a
non-domination error, because the memcheck block is of course not
dominated by the scalar loop body. Detect this situation and expand
the SCEV expression instead.

Fixes PR31251

Reviewers: anemet
Subscribers: mzolotukhin, llvm-commits

Differential Revision: https://reviews.llvm.org/D27397

llvm-svn: 288705
---
 llvm/lib/Analysis/LoopAccessAnalysis.cpp           | 20 ++++++++----
 .../LoopVersioning/loop-invariant-bound.ll         | 37 ++++++++++++++++++++++
 2 files changed, 50 insertions(+), 7 deletions(-)
 create mode 100644 llvm/test/Transforms/LoopVersioning/loop-invariant-bound.ll

diff --git a/llvm/lib/Analysis/LoopAccessAnalysis.cpp b/llvm/lib/Analysis/LoopAccessAnalysis.cpp
index 01a2f46..2f3dca3 100644
--- a/llvm/lib/Analysis/LoopAccessAnalysis.cpp
+++ b/llvm/lib/Analysis/LoopAccessAnalysis.cpp
@@ -1870,18 +1870,24 @@ expandBounds(const RuntimePointerChecking::CheckingPtrGroup *CG, Loop *TheLoop,
   Value *Ptr = PtrRtChecking.Pointers[CG->Members[0]].PointerValue;
   const SCEV *Sc = SE->getSCEV(Ptr);
 
+  unsigned AS = Ptr->getType()->getPointerAddressSpace();
+  LLVMContext &Ctx = Loc->getContext();
+
+  // Use this type for pointer arithmetic.
+  Type *PtrArithTy = Type::getInt8PtrTy(Ctx, AS);
+
   if (SE->isLoopInvariant(Sc, TheLoop)) {
     DEBUG(dbgs() << "LAA: Adding RT check for a loop invariant ptr:" << *Ptr
                  << "\n");
-    return {Ptr, Ptr};
+    // Ptr could be in the loop body. If so, expand a new one at the correct
+    // location.
+    Instruction *Inst = dyn_cast<Instruction>(Ptr);
+    Value *NewPtr = (Inst && TheLoop->contains(Inst))
+                        ? Exp.expandCodeFor(Sc, PtrArithTy, Loc)
+                        : Ptr;
+    return {NewPtr, NewPtr};
   } else {
-    unsigned AS = Ptr->getType()->getPointerAddressSpace();
-    LLVMContext &Ctx = Loc->getContext();
-
-    // Use this type for pointer arithmetic.
-    Type *PtrArithTy = Type::getInt8PtrTy(Ctx, AS);
     Value *Start = nullptr, *End = nullptr;
-
     DEBUG(dbgs() << "LAA: Adding RT check for range:\n");
     Start = Exp.expandCodeFor(CG->Low, PtrArithTy, Loc);
     End = Exp.expandCodeFor(CG->High, PtrArithTy, Loc);
diff --git a/llvm/test/Transforms/LoopVersioning/loop-invariant-bound.ll b/llvm/test/Transforms/LoopVersioning/loop-invariant-bound.ll
new file mode 100644
index 0000000..3411adb
--- /dev/null
+++ b/llvm/test/Transforms/LoopVersioning/loop-invariant-bound.ll
@@ -0,0 +1,37 @@
+; RUN: opt -loop-versioning -S < %s | FileCheck %s
+; Checks that when introducing check, we don't accidentally introduce non-dominating instructions
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+
+%Dual.212 = type { %Dual.213, %Partials.215 }
+%Dual.213 = type { double, %Partials.214 }
+%Partials.214 = type { [2 x double] }
+%Partials.215 = type { [2 x %Dual.213] }
+
+; Function Attrs: sspreq
+define void @"julia_axpy!_65480"(%Dual.212*) {
+top:
+  br label %if24
+
+; CHECK-NOT: %bc = bitcast i64* %v2.sroa.0.0..sroa_cast
+; CHECK: %bound0
+
+if24:                                             ; preds = %if24, %top
+  %"#temp#1.sroa.3.02" = phi i64 [ undef, %top ], [ %2, %if24 ]
+  %"#temp#1.sroa.0.01" = phi i64 [ undef, %top ], [ %1, %if24 ]
+  %1 = add i64 %"#temp#1.sroa.0.01", 1
+  %2 = add i64 %"#temp#1.sroa.3.02", 1
+  ; This pointer is loop invariant. LAA used to re-use it from memcheck, even though it didn't dominate.
+  %v2.sroa.0.0..sroa_cast = bitcast %Dual.212* %0 to i64*
+  %v2.sroa.0.0.copyload = load i64, i64* %v2.sroa.0.0..sroa_cast, align 1
+  %3 = add i64 %"#temp#1.sroa.0.01", -1
+  %4 = getelementptr inbounds %Dual.212, %Dual.212* undef, i64 %3, i32 1, i32 0, i64 0, i32 1, i32 0, i64 0
+  %5 = bitcast double* %4 to i64*
+  store i64 undef, i64* %5, align 8
+  %notlhs27 = icmp eq i64 %2, undef
+  %notrhs28 = icmp eq i64 %1, undef
+  %6 = or i1 %notrhs28, %notlhs27
+  br i1 %6, label %L41.L335_crit_edge, label %if24
+
+L41.L335_crit_edge:                               ; preds = %if24
+  ret void
+}
-- 
2.7.4