[LAA] Improve non-wrapping pointer detection by handling loop-invariant case.

This fixes PR26314. This patch adds new helper “isNoWrap” with detection of
loop-invariant pointer case.

Patch by Roman Shirokiy.

Ref: https://llvm.org/bugs/show_bug.cgi?id=26314

Differential Revision: http://reviews.llvm.org/D17268

llvm-svn: 272014

llvm/lib/Analysis/LoopAccessAnalysis.cpp

@@ -467,7 +467,7 @@ public:
   /// (i.e. the pointers have computable bounds).
   bool canCheckPtrAtRT(RuntimePointerChecking &RtCheck, ScalarEvolution *SE,
                        Loop *TheLoop, const ValueToValueMap &Strides,
-                       bool ShouldCheckStride = false);
+                       bool ShouldCheckWrap = false);
 
   /// \brief Goes over all memory accesses, checks whether a RT check is needed
   /// and builds sets of dependent accesses.
@@ -551,10 +551,21 @@ static bool hasComputableBounds(PredicatedScalarEvolution &PSE,
   return AR->isAffine();
 }
 
+/// \brief Check whether a pointer address cannot wrap.
+static bool isNoWrap(PredicatedScalarEvolution &PSE,
+                     const ValueToValueMap &Strides, Value *Ptr, Loop *L) {
+  const SCEV *PtrScev = PSE.getSCEV(Ptr);
+  if (PSE.getSE()->isLoopInvariant(PtrScev, L))
+    return true;
+
+  int Stride = getPtrStride(PSE, Ptr, L, Strides);
+  return Stride == 1;
+}
+
 bool AccessAnalysis::canCheckPtrAtRT(RuntimePointerChecking &RtCheck,
                                      ScalarEvolution *SE, Loop *TheLoop,
                                      const ValueToValueMap &StridesMap,
-                                     bool ShouldCheckStride) {
+                                     bool ShouldCheckWrap) {
   // Find pointers with computable bounds. We are going to use this information
   // to place a runtime bound check.
   bool CanDoRT = true;
@@ -589,8 +600,7 @@ bool AccessAnalysis::canCheckPtrAtRT(RuntimePointerChecking &RtCheck,
       if (hasComputableBounds(PSE, StridesMap, Ptr, TheLoop) &&
           // When we run after a failing dependency check we have to make sure
           // we don't have wrapping pointers.
-          (!ShouldCheckStride ||
+          (!ShouldCheckWrap || isNoWrap(PSE, StridesMap, Ptr, TheLoop))) {
-           getPtrStride(PSE, Ptr, TheLoop, StridesMap) == 1)) {
         // The id of the dependence set.
         unsigned DepId;
 

llvm/test/Analysis/LoopAccessAnalysis/multiple-strides-rt-memory-checks.ll

@@ -0,0 +1,67 @@
+; RUN: opt -loop-accesses -analyze -S < %s | FileCheck %s
+
+; This is the test case from PR26314.
+; When we were retrying dependence checking with memchecks only, 
+; the loop-invariant access in the inner loop was incorrectly determined to be wrapping 
+; because it was not strided in the inner loop.
+ 
+; #define Z 32
+; typedef struct s {
+;	int v1[Z];
+;	int v2[Z];
+;	int v3[Z][Z];
+; } s;
+;
+; void slow_function (s* const obj) {
+;    for (int j=0; j<Z; j++) {
+;        for (int k=0; k<Z; k++) {
+;            int x = obj->v1[k] + obj->v2[j];
+;            obj->v3[j][k] += x;
+;        }
+;    }
+; }
+
+; CHECK: function 'Test':
+; CHECK:   .inner:
+; CHECK-NEXT:     Memory dependences are safe
+; CHECK-NEXT:     Dependences:
+; CHECK-NEXT:     Run-time memory checks:
+; CHECK:          Check 0:
+; CHECK:          Check 1:
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+%struct.s = type { [32 x i32], [32 x i32], [32 x [32 x i32]] }
+
+define void @Test(%struct.s* nocapture %obj) #0 {
+  br label %.outer.preheader
+
+
+.outer.preheader:
+  %i = phi i64 [ 0, %0 ], [ %i.next, %.outer ]
+  %1 = getelementptr inbounds %struct.s, %struct.s* %obj, i64 0, i32 1, i64 %i
+  br label %.inner
+
+.exit:
+  ret void
+ 
+.outer:
+  %i.next = add nuw nsw i64 %i, 1
+  %exitcond.outer = icmp eq i64 %i.next, 32
+  br i1 %exitcond.outer, label %.exit, label %.outer.preheader
+
+.inner:
+  %j = phi i64 [ 0, %.outer.preheader ], [ %j.next, %.inner ]
+  %2 = getelementptr inbounds %struct.s, %struct.s* %obj, i64 0, i32 0, i64 %j
+  %3 = load i32, i32* %2
+  %4 = load i32, i32* %1
+  %5 = add nsw i32 %4, %3
+  %6 = getelementptr inbounds %struct.s, %struct.s* %obj, i64 0, i32 2, i64 %i, i64 %j
+  %7 = load i32, i32* %6
+  %8 = add nsw i32 %5, %7
+  store i32 %8, i32* %6  
+  %j.next = add nuw nsw i64 %j, 1
+  %exitcond.inner = icmp eq i64 %j.next, 32
+  br i1 %exitcond.inner, label %.outer, label %.inner
+}

llvm/test/Transforms/LoopVectorize/multiple-strides-vectorization.ll

@@ -0,0 +1,65 @@
+; RUN: opt -loop-vectorize -S < %s | FileCheck %s
+
+; This is the test case from PR26314.
+; When we were retrying dependence checking with memchecks only,
+; the loop-invariant access in the inner loop was incorrectly determined to be wrapping
+; because it was not strided in the inner loop.
+; Improved wrapping detection allows vectorization in the following case.
+
+; #define Z 32
+; typedef struct s {
+;       int v1[Z];
+;       int v2[Z];
+;       int v3[Z][Z];
+; } s;
+;
+; void slow_function (s* const obj) {
+;    for (int j=0; j<Z; j++) {
+;        for (int k=0; k<Z; k++) {
+;            int x = obj->v1[k] + obj->v2[j];
+;            obj->v3[j][k] += x;
+;        }
+;    }
+; }
+
+; CHECK-LABEL: Test
+; CHECK: <4 x i64>
+; CHECK: <4 x i32>, <4 x i32>
+; CHECK: llvm.loop.vectorize.width
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+%struct.s = type { [32 x i32], [32 x i32], [32 x [32 x i32]] }
+
+define void @Test(%struct.s* nocapture %obj) #0 {
+  br label %.outer.preheader
+
+
+.outer.preheader:
+  %i = phi i64 [ 0, %0 ], [ %i.next, %.outer ]
+  %1 = getelementptr inbounds %struct.s, %struct.s* %obj, i64 0, i32 1, i64 %i
+  br label %.inner
+
+.exit:
+  ret void
+ 
+.outer:
+  %i.next = add nuw nsw i64 %i, 1
+  %exitcond.outer = icmp eq i64 %i.next, 32
+  br i1 %exitcond.outer, label %.exit, label %.outer.preheader
+
+.inner:
+  %j = phi i64 [ 0, %.outer.preheader ], [ %j.next, %.inner ]
+  %2 = getelementptr inbounds %struct.s, %struct.s* %obj, i64 0, i32 0, i64 %j
+  %3 = load i32, i32* %2
+  %4 = load i32, i32* %1
+  %5 = add nsw i32 %4, %3
+  %6 = getelementptr inbounds %struct.s, %struct.s* %obj, i64 0, i32 2, i64 %i, i64 %j
+  %7 = load i32, i32* %6
+  %8 = add nsw i32 %5, %7
+  store i32 %8, i32* %6  
+  %j.next = add nuw nsw i64 %j, 1
+  %exitcond.inner = icmp eq i64 %j.next, 32
+  br i1 %exitcond.inner, label %.outer, label %.inner
+}