diff --git a/flang/lib/Lower/Bridge.cpp b/flang/lib/Lower/Bridge.cpp
--- a/flang/lib/Lower/Bridge.cpp
+++ b/flang/lib/Lower/Bridge.cpp
@@ -119,11 +119,6 @@
 
   // Data members for structured loops.
   fir::DoLoopOp doLoop = nullptr;
-  // Do loop block argument holding the current value
-  // of the do-variable. It has the same data type as the original
-  // do-variable. It is non-null after genFIRIncrementLoopBegin()
-  // iff doVarIsALoopArg() returns true.
-  mlir::Value doVarValue = nullptr;
 
   // Data members for unstructured loops.
   bool hasRealControl = false;
@@ -1275,7 +1270,6 @@
           // The loop variable value is the region's argument rather
           // than the DoLoop's index value.
           value = info.doLoop.getRegionIterArgs()[0];
-          info.doVarValue = value;
         }
         builder->create<fir::StoreOp>(loc, value, info.loopVariable);
         if (info.maskExpr) {
@@ -1377,8 +1371,10 @@
             // type, so we need to cast it, first.
             mlir::Value stepCast = builder->createConvert(
                 loc, info.getLoopVariableType(), info.doLoop.getStep());
+            mlir::Value doVarValue =
+                builder->create<fir::LoadOp>(loc, info.loopVariable);
             results.push_back(builder->create<mlir::arith::AddIOp>(
-                loc, info.doVarValue, stepCast));
+                loc, doVarValue, stepCast));
           }
           builder->create<fir::ResultOp>(loc, results);
         }
diff --git a/flang/test/Lower/OpenMP/omp-parallel-private-clause-fixes.f90 b/flang/test/Lower/OpenMP/omp-parallel-private-clause-fixes.f90
--- a/flang/test/Lower/OpenMP/omp-parallel-private-clause-fixes.f90
+++ b/flang/test/Lower/OpenMP/omp-parallel-private-clause-fixes.f90
@@ -31,7 +31,8 @@
 ! CHECK:               fir.store %[[VAL_16]] to %[[PRIV_X]] : !fir.ref<i32>
 ! CHECK:               %[[VAL_17:.*]] = arith.addi %[[VAL_13]], %[[VAL_11]] : index
 ! CHECK:               %[[STEPCAST:.*]] = fir.convert %[[VAL_11]] : (index) -> i32
-! CHECK:               %[[IVINC:.*]] = arith.addi %[[IV]], %[[STEPCAST]]
+! CHECK:               %[[IVLOAD:.*]] = fir.load %[[PRIV_J]] : !fir.ref<i32>
+! CHECK:               %[[IVINC:.*]] = arith.addi %[[IVLOAD]], %[[STEPCAST]]
 ! CHECK:               fir.result %[[VAL_17]], %[[IVINC]] : index, i32
 ! CHECK:             }
 ! CHECK:             fir.store %[[VAL_12]]#1 to %[[PRIV_J]] : !fir.ref<i32>
diff --git a/flang/test/Lower/OpenMP/omp-wsloop-variable.f90 b/flang/test/Lower/OpenMP/omp-wsloop-variable.f90
--- a/flang/test/Lower/OpenMP/omp-wsloop-variable.f90
+++ b/flang/test/Lower/OpenMP/omp-wsloop-variable.f90
@@ -112,7 +112,8 @@
 !CHECK:             fir.store %[[VAL_25]] to %[[VAL_6]] : !fir.ref<f32>
 !CHECK:             %[[VAL_26:.*]] = arith.addi %[[VAL_20]], %[[VAL_18]] : index
 !CHECK:             %[[STEPCAST:.*]] = fir.convert %[[VAL_18]] : (index) -> i64
-!CHECK:             %[[IVINC:.*]] = arith.addi %[[IV]], %[[STEPCAST]]
+!CHECK:             %[[IVLOAD:.*]] = fir.load %[[VAL_5]] : !fir.ref<i64>
+!CHECK:             %[[IVINC:.*]] = arith.addi %[[IVLOAD]], %[[STEPCAST]]
 !CHECK:             fir.result %[[VAL_26]], %[[IVINC]] : index, i64
 !CHECK:           }
 !CHECK:           fir.store %[[VAL_19]]#1 to %[[VAL_5]] : !fir.ref<i64>
diff --git a/flang/test/Lower/array-expression-slice-1.f90 b/flang/test/Lower/array-expression-slice-1.f90
--- a/flang/test/Lower/array-expression-slice-1.f90
+++ b/flang/test/Lower/array-expression-slice-1.f90
@@ -25,14 +25,14 @@
 ! CHECK-DAG:         %[[VAL_30:.*]] = fir.alloca i32 {bindc_name = "j", uniq_name = "_QFEj"}
 ! CHECK-DAG:         %[[VAL_31:.*]] = fir.alloca i32 {bindc_name = "k", uniq_name = "_QFEk"}
 ! CHECK:         fir.store %[[VAL_24]] to %[[VAL_31]] : !fir.ref<i32>
-! CHECK:         %[[LB:.*]] = fir.convert %[[VAL_5]] : (index) -> i32
-! CHECK:         br ^bb1(%[[LB]], %[[VAL_0]] : i32, index)
+! CHECK:         %[[STEP:.*]] = fir.convert %[[VAL_5]] : (index) -> i32
+! CHECK:         br ^bb1(%[[STEP]], %[[VAL_0]] : i32, index)
 ! CHECK:       ^bb1(%[[VAL_32:.*]]: i32, %[[VAL_33:.*]]: index):
 ! CHECK:         %[[VAL_34:.*]] = arith.cmpi sgt, %[[VAL_33]], %[[VAL_6]] : index
 ! CHECK:         cond_br %[[VAL_34]], ^bb2, ^bb6
 ! CHECK:       ^bb2:
 ! CHECK:         fir.store %[[VAL_32]] to %[[VAL_30]] : !fir.ref<i32>
-! CHECK:         br ^bb3(%[[LB]], %[[VAL_0]] : i32, index)
+! CHECK:         br ^bb3(%[[STEP]], %[[VAL_0]] : i32, index)
 ! CHECK:       ^bb3(%[[VAL_36:.*]]: i32, %[[VAL_37:.*]]: index):
 ! CHECK:         %[[VAL_38:.*]] = arith.cmpi sgt, %[[VAL_37]], %[[VAL_6]] : index
 ! CHECK:         cond_br %[[VAL_38]], ^bb4, ^bb5
@@ -52,7 +52,8 @@
 ! CHECK:         %[[VAL_50:.*]] = arith.subi %[[VAL_49]], %[[VAL_20]] : i64
 ! CHECK:         %[[VAL_51:.*]] = fir.coordinate_of %[[VAL_25]], %[[VAL_47]], %[[VAL_50]] : (!fir.ref<!fir.array<10x10xf32>>, i64, i64) -> !fir.ref<f32>
 ! CHECK:         fir.store %[[VAL_44]] to %[[VAL_51]] : !fir.ref<f32>
-! CHECK:         %[[VAL_52:.*]] = arith.addi %[[VAL_36]], %[[LB]] : i32
+! CHECK:         %[[LOADI:.*]] = fir.load %[[VAL_28]] : !fir.ref<i32>
+! CHECK:         %[[VAL_52:.*]] = arith.addi %[[LOADI]], %[[STEP]] : i32
 ! CHECK:         %[[VAL_53:.*]] = arith.subi %[[VAL_37]], %[[VAL_5]] : index
 ! CHECK:         br ^bb3(%[[VAL_52]], %[[VAL_53]] : i32, index)
 ! CHECK:       ^bb5:
@@ -65,7 +66,8 @@
 ! CHECK:         %[[VAL_60:.*]] = arith.subi %[[VAL_59]], %[[VAL_20]] : i64
 ! CHECK:         %[[VAL_61:.*]] = fir.coordinate_of %[[VAL_27]], %[[VAL_60]] : (!fir.ref<!fir.array<10xf32>>, i64) -> !fir.ref<f32>
 ! CHECK:         fir.store %[[VAL_57]] to %[[VAL_61]] : !fir.ref<f32>
-! CHECK:         %[[VAL_62:.*]] = arith.addi %[[VAL_32]], %[[LB]] : i32
+! CHECK:         %[[LOADJ:.*]] = fir.load %[[VAL_30]] : !fir.ref<i32>
+! CHECK:         %[[VAL_62:.*]] = arith.addi %[[LOADJ]], %[[STEP]] : i32
 ! CHECK:         %[[VAL_63:.*]] = arith.subi %[[VAL_33]], %[[VAL_5]] : index
 ! CHECK:         br ^bb1(%[[VAL_62]], %[[VAL_63]] : i32, index)
 ! CHECK:       ^bb6:
diff --git a/flang/test/Lower/do_loop.f90 b/flang/test/Lower/do_loop.f90
--- a/flang/test/Lower/do_loop.f90
+++ b/flang/test/Lower/do_loop.f90
@@ -24,7 +24,8 @@
   ! CHECK:   fir.store %[[IV]] to %[[I_REF]] : !fir.ref<i32>
   ! CHECK:   %[[LI_NEXT:.*]] = arith.addi %[[LI]], %[[C1]] : index
   ! CHECK:   %[[STEPCAST:.*]] = fir.convert %[[C1]] : (index) -> i32
-  ! CHECK:   %[[IVINC:.*]] = arith.addi %[[IV]], %[[STEPCAST]] : i32
+  ! CHECK:   %[[IVLOAD:.*]] = fir.load %[[I_REF]] : !fir.ref<i32>
+  ! CHECK:   %[[IVINC:.*]] = arith.addi %[[IVLOAD]], %[[STEPCAST]] : i32
   ! CHECK:  fir.result %[[LI_NEXT]], %[[IVINC]] : index, i32
   ! CHECK: }
   end do
@@ -82,14 +83,16 @@
       asum = asum + arr(i,j)
       ! CHECK: %[[LJ_NEXT:.*]] = arith.addi %[[LJ]], %[[ST_J]] : index
       ! CHECK: %[[J_STEPCAST:.*]] = fir.convert %[[ST_J]] : (index) -> i32
-      ! CHECK: %[[J_IVINC:.*]] = arith.addi %[[J_IV]], %[[J_STEPCAST]] : i32
+      ! CHECK: %[[J_IVLOAD:.*]] = fir.load %[[J_REF]] : !fir.ref<i32>
+      ! CHECK: %[[J_IVINC:.*]] = arith.addi %[[J_IVLOAD]], %[[J_STEPCAST]] : i32
       ! CHECK: fir.result %[[LJ_NEXT]], %[[J_IVINC]] : index, i32
     ! CHECK: }
     end do
     ! CHECK: fir.store %[[J_RES]]#1 to %[[J_REF]] : !fir.ref<i32>
     ! CHECK: %[[LI_NEXT:.*]] = arith.addi %[[LI]], %[[ST_I]] : index
     ! CHECK: %[[I_STEPCAST:.*]] = fir.convert %[[ST_I]] : (index) -> i32
-    ! CHECK: %[[I_IVINC:.*]] = arith.addi %[[I_IV]], %[[I_STEPCAST]] : i32
+    ! CHECK: %[[I_IVLOAD:.*]] = fir.load %[[I_REF]] : !fir.ref<i32>
+    ! CHECK: %[[I_IVINC:.*]] = arith.addi %[[I_IVLOAD]], %[[I_STEPCAST]] : i32
     ! CHECK: fir.result %[[LI_NEXT]], %[[I_IVINC]] : index, i32
   ! CHECK: }
   end do
@@ -116,7 +119,8 @@
   ! CHECK: fir.store %[[I_IV]] to %[[I_REF]] : !fir.ref<i32>
   ! CHECK: %[[LI_NEXT:.*]] = arith.addi %[[LI]], %[[CMINUS1_STEP_CVT]] : index
   ! CHECK: %[[I_STEPCAST:.*]] = fir.convert %[[CMINUS1_STEP_CVT]] : (index) -> i32
-  ! CHECK: %[[I_IVINC:.*]] = arith.addi %[[I_IV]], %[[I_STEPCAST]] : i32
+  ! CHECK: %[[I_IVLOAD:.*]] = fir.load %[[I_REF]] : !fir.ref<i32>
+  ! CHECK: %[[I_IVINC:.*]] = arith.addi %[[I_IVLOAD]], %[[I_STEPCAST]] : i32
   ! CHECK: fir.result %[[LI_NEXT]], %[[I_IVINC]] : index, i32
   ! CHECK: }
   end do
@@ -142,7 +146,8 @@
   ! CHECK:  fir.store %[[I_IV]] to %[[I_REF]] : !fir.ref<i32>
   ! CHECK:  %[[LI_NEXT:.*]] = arith.addi %[[LI]], %[[ST_CVT]] : index
   ! CHECK: %[[I_STEPCAST:.*]] = fir.convert %[[ST_CVT]] : (index) -> i32
-  ! CHECK: %[[I_IVINC:.*]] = arith.addi %[[I_IV]], %[[I_STEPCAST]] : i32
+  ! CHECK: %[[I_IVLOAD:.*]] = fir.load %[[I_REF]] : !fir.ref<i32>
+  ! CHECK: %[[I_IVINC:.*]] = arith.addi %[[I_IVLOAD]], %[[I_STEPCAST]] : i32
   ! CHECK:  fir.result %[[LI_NEXT]], %[[I_IVINC]] : index, i32
   ! CHECK: }
   end do
@@ -193,7 +198,8 @@
 ! CHECK:    fir.store %[[I_IV]] to %[[I_PTR]] : !fir.ptr<i32>
 ! CHECK:    %[[LI_NEXT:.*]] = arith.addi %[[LI]], %[[ST_CVT]] : index
 ! CHECK:    %[[I_STEPCAST:.*]] = fir.convert %[[ST_CVT]] : (index) -> i32
-! CHECK:    %[[I_IVINC:.*]] = arith.addi %[[I_IV]], %[[I_STEPCAST]] : i32
+! CHECK:    %[[I_IVLOAD:.*]] = fir.load %[[I_PTR]] : !fir.ptr<i32>
+! CHECK:    %[[I_IVINC:.*]] = arith.addi %[[I_IVLOAD]], %[[I_STEPCAST]] : i32
 ! CHECK:    fir.result %[[LI_NEXT]], %[[I_IVINC]] : index, i32
   end do
 ! CHECK:  }
@@ -222,7 +228,8 @@
     ! CHECK: fir.store %[[I_IV]] to %[[I_REF]] : !fir.ref<i64>
     ! CHECK: %[[LI_NEXT:.*]] = arith.addi %[[LI]], %[[ST_CVT]] : index
     ! CHECK: %[[I_STEPCAST:.*]] = fir.convert %[[ST_CVT]] : (index) -> i64
-    ! CHECK: %[[I_IVINC:.*]] = arith.addi %[[I_IV]], %[[I_STEPCAST]] : i64
+    ! CHECK: %[[I_IVLOAD:.*]] = fir.load %[[I_REF]] : !fir.ref<i64>
+    ! CHECK: %[[I_IVINC:.*]] = arith.addi %[[I_IVLOAD]], %[[I_STEPCAST]] : i64
     ! CHECK: fir.result %[[LI_NEXT]], %[[I_IVINC]] : index, i64
   end do
   ! CHECK: }
diff --git a/flang/test/Lower/infinite_loop.f90 b/flang/test/Lower/infinite_loop.f90
--- a/flang/test/Lower/infinite_loop.f90
+++ b/flang/test/Lower/infinite_loop.f90
@@ -97,7 +97,8 @@
 ! CHECK:    fir.store %[[J_IV]] to %[[J_REF]] : !fir.ref<i32>
 ! CHECK:    %[[J_NEXT:.*]] = arith.addi %[[J]], %[[C1_1]] : index
 ! CHECK:    %[[J_STEPCAST:.*]] = fir.convert %[[C1_1]] : (index) -> i32
-! CHECK:    %[[J_IVINC:.*]] = arith.addi %[[J_IV]], %[[J_STEPCAST]] : i32
+! CHECK:    %[[J_IVLOAD:.*]] = fir.load %[[J_REF]] : !fir.ref<i32>
+! CHECK:    %[[J_IVINC:.*]] = arith.addi %[[J_IVLOAD]], %[[J_STEPCAST]] : i32
 ! CHECK:    fir.result %[[J_NEXT]], %[[J_IVINC]] : index, i32
 ! CHECK:  }
 ! CHECK:  fir.store %[[J_FINAL]]#1 to %[[J_REF]] : !fir.ref<i32>
diff --git a/flang/test/Lower/mixed_loops.f90 b/flang/test/Lower/mixed_loops.f90
--- a/flang/test/Lower/mixed_loops.f90
+++ b/flang/test/Lower/mixed_loops.f90
@@ -101,7 +101,8 @@
         ! CHECK: fir.store %[[JINC]] to %[[J_REF]] : !fir.ref<i32>
         ! CHECK: %[[IINC:.*]] = arith.addi %[[IDX]], %[[C1]] : index
         ! CHECK: %[[I_STEPCAST:.*]] = fir.convert %[[C1]] : (index) -> i32
-        ! CHECK: %[[I_IVINC:.*]] = arith.addi %[[I_IV]], %[[I_STEPCAST]] : i32
+        ! CHECK: %[[I_IVLOAD:.*]] = fir.load %[[I_REF]] : !fir.ref<i32>
+        ! CHECK: %[[I_IVINC:.*]] = arith.addi %[[I_IVLOAD]], %[[I_STEPCAST]] : i32
         ! CHECK: fir.result %[[IINC]], %[[I_IVINC]] : index, i32
       do i=8,13
         j=j*2