diff --git a/llvm/lib/CodeGen/MachinePipeliner.cpp b/llvm/lib/CodeGen/MachinePipeliner.cpp
--- a/llvm/lib/CodeGen/MachinePipeliner.cpp
+++ b/llvm/lib/CodeGen/MachinePipeliner.cpp
@@ -2277,20 +2277,28 @@
   assert(!OffsetSIsScalable && !OffsetDIsScalable &&
          "Expected offsets to be byte offsets");
 
-  if (!BaseOpS->isIdenticalTo(*BaseOpD))
+  MachineInstr *DefS = MRI.getVRegDef(BaseOpS->getReg());
+  MachineInstr *DefD = MRI.getVRegDef(BaseOpD->getReg());
+  if (!DefS || !DefD || !DefS->isPHI() || !DefD->isPHI())
+    return true;
+
+  unsigned InitValS = 0;
+  unsigned LoopValS = 0;
+  unsigned InitValD = 0;
+  unsigned LoopValD = 0;
+  getPhiRegs(*DefS, BB, InitValS, LoopValS);
+  getPhiRegs(*DefD, BB, InitValD, LoopValD);
+  MachineInstr *InitDefS = MRI.getVRegDef(InitValS);
+  MachineInstr *InitDefD = MRI.getVRegDef(InitValD);
+
+  if (!InitDefS->isIdenticalTo(*InitDefD))
     return true;
 
   // Check that the base register is incremented by a constant value for each
   // iteration.
-  MachineInstr *Def = MRI.getVRegDef(BaseOpS->getReg());
-  if (!Def || !Def->isPHI())
-    return true;
-  unsigned InitVal = 0;
-  unsigned LoopVal = 0;
-  getPhiRegs(*Def, BB, InitVal, LoopVal);
-  MachineInstr *LoopDef = MRI.getVRegDef(LoopVal);
+  MachineInstr *LoopDefS = MRI.getVRegDef(LoopValS);
   int D = 0;
-  if (!LoopDef || !TII->getIncrementValue(*LoopDef, D))
+  if (!LoopDefS || !TII->getIncrementValue(*LoopDefS, D))
     return true;
 
   uint64_t AccessSizeS = (*SI->memoperands_begin())->getSize();
diff --git a/llvm/test/CodeGen/Hexagon/swp-carried-dep3.mir b/llvm/test/CodeGen/Hexagon/swp-carried-dep3.mir
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/Hexagon/swp-carried-dep3.mir
@@ -0,0 +1,107 @@
+# RUN: llc -mtriple=hexagon -run-pass pipeliner -debug-only=pipeliner %s -o /dev/null 2>&1 -pipeliner-experimental-cg=true | FileCheck %s
+# REQUIRES: asserts
+
+# Test that the loop carried dependence check correctly identifies a recurrence
+# when load and store use distinct increment for their pointer.
+
+# CHECK: Rec NodeSet
+# CHECK: Rec NodeSet
+# CHECK: Rec NodeSet
+# CHECK: Rec NodeSet
+# CHECK: Rec NodeSet
+# CHECK-NEXT: SU(5)
+# CHECK-NEXT: SU(7)
+
+--- |
+
+  %struct.A = type { i16, i16 }
+
+  define i32 @test(%struct.A* noalias nocapture %s, i16* noalias nocapture readonly %r, i32 %n) {
+  entry:
+    %cmp19 = icmp eq i32 %n, 2
+    br i1 %cmp19, label %for.end, label %for.body.preheader
+
+  for.body.preheader:
+    %0 = add i32 %n, -2
+    %cgep = getelementptr %struct.A, %struct.A* %s, i32 2, i32 1
+    %scevgep1 = bitcast i16* %cgep to %struct.A*
+    %cgep9 = getelementptr i16, i16* %r, i32 2
+    br label %for.body
+
+  for.body:
+    %lsr.iv7 = phi i16* [ %cgep9, %for.body.preheader ], [ %cgep12, %for.body ]
+    %lsr.iv2 = phi %struct.A* [ %scevgep1, %for.body.preheader ], [ %cgep11, %for.body ]
+    %lsr.iv = phi i32 [ %0, %for.body.preheader ], [ %lsr.iv.next, %for.body ]
+    %sum.020 = phi i32 [ %add7, %for.body ], [ 0, %for.body.preheader ]
+    %lsr.iv24 = bitcast %struct.A* %lsr.iv2 to i16*
+    %1 = load i16, i16* %lsr.iv7, align 2
+    %conv = sext i16 %1 to i32
+    %cgep10 = getelementptr i16, i16* %lsr.iv24, i32 -4
+    %2 = load i16, i16* %cgep10, align 2
+    %conv2 = sext i16 %2 to i32
+    %add = add i16 %1, 10
+    store i16 %add, i16* %lsr.iv24, align 2
+    %add6 = add i32 %sum.020, %conv
+    %add7 = add i32 %add6, %conv2
+    %lsr.iv.next = add i32 %lsr.iv, -1
+    %cmp = icmp eq i32 %lsr.iv.next, 0
+    %cgep11 = getelementptr %struct.A, %struct.A* %lsr.iv2, i32 1
+    %cgep12 = getelementptr i16, i16* %lsr.iv7, i32 1
+    br i1 %cmp, label %for.end, label %for.body
+
+  for.end:
+    %sum.0.lcssa = phi i32 [ 0, %entry ], [ %add7, %for.body ]
+    ret i32 %sum.0.lcssa
+  }
+
+...
+---
+name:            test
+tracksRegLiveness: true
+
+body:             |
+  bb.0:
+    successors: %bb.3, %bb.1
+    liveins: $r0, $r1, $r2
+
+    %14:intregs = COPY $r2
+    %13:intregs = COPY $r1
+    %12:intregs = COPY $r0
+    %16:predregs = C2_cmpeqi %14, 2
+    %15:intregs = A2_tfrsi 0
+    J2_jumpt killed %16, %bb.3, implicit-def dead $pc
+    J2_jump %bb.1, implicit-def dead $pc
+
+  bb.1:
+    successors: %bb.2
+
+    %0:intregs = A2_addi %14, -2
+    %1:intregs = A2_addi %12, 10
+    %2:intregs = A2_addi %13, 4
+    %17:intregs = A2_tfrsi 0
+    %23:intregs = COPY %0
+    J2_loop0r %bb.2, %23, implicit-def $lc0, implicit-def $sa0, implicit-def $usr
+
+  bb.2 (machine-block-address-taken):
+    successors: %bb.3, %bb.2
+
+    %3:intregs = PHI %2, %bb.1, %10, %bb.2
+    %4:intregs = PHI %1, %bb.1, %9, %bb.2
+    %21:intregs = PHI %1, %bb.1, %22, %bb.2
+    %6:intregs = PHI %17, %bb.1, %7, %bb.2
+    %18:intregs, %10:intregs = L2_loadrh_pi %3, 2 :: (load (s16) from %ir.lsr.iv7)
+    %19:intregs = L2_loadrh_io %21, -8 :: (load (s16) from %ir.cgep10)
+    %20:intregs = A2_addi %18, 10
+    S2_storerh_io %4, 0, killed %20 :: (store (s16) into %ir.lsr.iv24)
+    %7:intregs = M2_acci %19, %6, %18
+    %9:intregs = A2_addi %4, 4
+    %22:intregs = A2_addi %21, 4
+    ENDLOOP0 %bb.2, implicit-def $pc, implicit-def $lc0, implicit $sa0, implicit $lc0
+    J2_jump %bb.3, implicit-def dead $pc
+
+  bb.3:
+    %11:intregs = PHI %15, %bb.0, %7, %bb.2
+    $r0 = COPY %11
+    PS_jmpret $r31, implicit-def dead $pc, implicit $r0
+
+...