diff --git a/llvm/lib/Analysis/DependenceAnalysis.cpp b/llvm/lib/Analysis/DependenceAnalysis.cpp
--- a/llvm/lib/Analysis/DependenceAnalysis.cpp
+++ b/llvm/lib/Analysis/DependenceAnalysis.cpp
@@ -3349,12 +3349,8 @@
     return false;
   }
 
-  Value *SrcBasePtr = SrcGEP->getOperand(0);
-  Value *DstBasePtr = DstGEP->getOperand(0);
-  while (auto *PCast = dyn_cast<BitCastInst>(SrcBasePtr))
-    SrcBasePtr = PCast->getOperand(0);
-  while (auto *PCast = dyn_cast<BitCastInst>(DstBasePtr))
-    DstBasePtr = PCast->getOperand(0);
+  Value *SrcBasePtr = SrcGEP->getOperand(0)->stripPointerCasts();
+  Value *DstBasePtr = DstGEP->getOperand(0)->stripPointerCasts();
 
   // Check that for identical base pointers we do not miss index offsets
   // that have been added before this GEP is applied.
diff --git a/llvm/test/Analysis/DependenceAnalysis/SimpleSIVNoValidityCheckFixedSize.ll b/llvm/test/Analysis/DependenceAnalysis/SimpleSIVNoValidityCheckFixedSize.ll
--- a/llvm/test/Analysis/DependenceAnalysis/SimpleSIVNoValidityCheckFixedSize.ll
+++ b/llvm/test/Analysis/DependenceAnalysis/SimpleSIVNoValidityCheckFixedSize.ll
@@ -15,7 +15,8 @@
 ;;     for (int j = 2; j < M; ++j)
 ;;       a[i][j] = a[i+1][j-2];
 ;; }
-
+;;
+;; Note that there is a getelementptr with index 0, make sure we can analyze this case.
 define void @t1([2048 x i32]* %a) {
 entry:
   br label %for.body
@@ -30,7 +31,8 @@
   %1 = add nsw i64 %indvars.iv, -2
   %arrayidx6 = getelementptr inbounds [2048 x i32], [2048 x i32]* %a, i64 %0, i64 %1
   %2 = load i32, i32* %arrayidx6, align 4
-  %arrayidx10 = getelementptr inbounds [2048 x i32], [2048 x i32]* %a, i64 %indvars.iv4, i64 %indvars.iv
+  %a_gep = getelementptr inbounds [2048 x i32], [2048 x i32]* %a, i64 0
+  %arrayidx10 = getelementptr inbounds [2048 x i32], [2048 x i32]* %a_gep, i64 %indvars.iv4, i64 %indvars.iv
   store i32 %2, i32* %arrayidx10, align 4
   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
   %exitcond = icmp ne i64 %indvars.iv.next, 2048
@@ -45,8 +47,45 @@
   ret void
 }
 
-
 ; CHECK-LABEL: t2
+; CHECK: da analyze - consistent anti [1 -2]!
+
+;; Similar to @t1 but includes a call with a "returned" arg, make sure we can analyze
+;; this case.
+
+define void @t2([2048 x i32]* %a) {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.inc11
+  %indvars.iv4 = phi i64 [ 0, %entry ], [ %indvars.iv.next5, %for.inc11 ]
+  br label %for.body4
+
+for.body4:                                        ; preds = %for.body, %for.body4
+  %indvars.iv = phi i64 [ 2, %for.body ], [ %indvars.iv.next, %for.body4 ]
+  %0 = add nuw nsw i64 %indvars.iv4, 1
+  %1 = add nsw i64 %indvars.iv, -2
+  %arrayidx6 = getelementptr inbounds [2048 x i32], [2048 x i32]* %a, i64 %0, i64 %1
+  %2 = load i32, i32* %arrayidx6, align 4
+  %call = call [2048 x i32]* @func_with_returned_arg([2048 x i32]* returned %a)
+  %arrayidx10 = getelementptr inbounds [2048 x i32], [2048 x i32]* %call, i64 %indvars.iv4, i64 %indvars.iv
+  store i32 %2, i32* %arrayidx10, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp ne i64 %indvars.iv.next, 2048
+  br i1 %exitcond, label %for.body4, label %for.inc11
+
+for.inc11:                                        ; preds = %for.body4
+  %indvars.iv.next5 = add nuw nsw i64 %indvars.iv4, 1
+  %exitcond7 = icmp ne i64 %indvars.iv.next5, 1023
+  br i1 %exitcond7, label %for.body, label %for.end13
+
+for.end13:                                        ; preds = %for.inc11
+  ret void
+}
+
+declare [2048 x i32]* @func_with_returned_arg([2048 x i32]* returned %arg)
+
+; CHECK-LABEL: t3
 ; CHECK: da analyze - none!
 ; CHECK: da analyze - consistent anti [1 -2 0 -3 2]!
 ; CHECK: da analyze - none!
@@ -62,7 +101,7 @@
 ;;             a[i1][i2][i3][i4][i5] = a[i1+1][i2-2][i3][i4-3][i5+2];
 ;; }
 
-define void @t2([1024 x [1024 x [1024 x [2048 x i32]]]]* %a) {
+define void @t3([1024 x [1024 x [1024 x [2048 x i32]]]]* %a) {
 entry:
   br label %for.body