diff --git a/flang/lib/Optimizer/Transforms/LoopVersioning.cpp b/flang/lib/Optimizer/Transforms/LoopVersioning.cpp
--- a/flang/lib/Optimizer/Transforms/LoopVersioning.cpp
+++ b/flang/lib/Optimizer/Transforms/LoopVersioning.cpp
@@ -262,15 +262,19 @@
                                             loc, curIndex, totalIndex)
                                       : curIndex;
           }
-          mlir::Value elemSize =
-              builder.createIntegerConstant(loc, idxTy, arg.size);
           // This is the lowest dimension - which doesn't need scaling
           mlir::Value finalIndex =
               builder.createConvert(loc, idxTy, coop->getOperand(1));
           if (totalIndex) {
+            assert(llvm::isPowerOf2_32(arg.size) &&
+                   "Expected power of two here");
+            unsigned bits = llvm::Log2_32(arg.size);
+            mlir::Value elemShift =
+                builder.createIntegerConstant(loc, idxTy, bits);
             totalIndex = builder.create<mlir::arith::AddIOp>(
                 loc,
-                builder.create<mlir::arith::DivSIOp>(loc, totalIndex, elemSize),
+                builder.create<mlir::arith::ShRSIOp>(loc, totalIndex,
+                                                     elemShift),
                 finalIndex);
           } else {
             totalIndex = finalIndex;
diff --git a/flang/test/Transforms/loop-versioning.fir b/flang/test/Transforms/loop-versioning.fir
--- a/flang/test/Transforms/loop-versioning.fir
+++ b/flang/test/Transforms/loop-versioning.fir
@@ -366,9 +366,9 @@
 // Check the 2D -> 1D coordinate conversion, should have a multiply and a final add.
 // Some other operations are checked to synch the different parts.
 // CHECK: %[[OUTER_IDX:.*]] = arith.muli %[[DIMS1]]#2, {{.*}}
-// CHECK: %[[ITEMSIZE:.*]] = arith.constant 8 : index
 // CHECK: %[[INNER_IDX:.*]] = fir.convert {{.*}}
-// CHECK: %[[OUTER_DIV:.*]] = arith.divsi %[[OUTER_IDX]], %[[ITEMSIZE]]
+// CHECK: %[[ITEMSHIFT:.*]] = arith.constant 3 : index
+// CHECK: %[[OUTER_DIV:.*]] = arith.shrsi %[[OUTER_IDX]], %[[ITEMSHIFT]]
 // CHECK: %[[C2D:.*]] = arith.addi %[[OUTER_DIV]], %[[INNER_IDX]]
 // CHECK: %[[COORD:.*]] = fir.coordinate_of %[[BOXADDR]], %[[C2D]] : (!fir.ref<!fir.array<?xf64>>, index) -> !fir.ref<f64>
 // CHECK: %{{.*}} = fir.load %[[COORD]] : !fir.ref<f64>
@@ -498,9 +498,9 @@
 // CHECK: %[[OUTER_IDX:.*]] = arith.muli %[[DIMS2]]#2, {{.*}}
 // CHECK: %[[MIDDLE_IDX:.*]] = arith.muli %[[DIMS1]]#2, {{.*}}
 // CHECK: %[[MIDDLE_SUM:.*]] = arith.addi %[[MIDDLE_IDX]], %[[OUTER_IDX]]
-// CHECK: %[[ITEMSIZE:.*]] = arith.constant 8 : index
 // CHECK: %[[INNER_IDX:.*]] = fir.convert {{.*}}
-// CHECK: %[[MIDDLE_DIV:.*]] = arith.divsi %[[MIDDLE_SUM]], %[[ITEMSIZE]]
+// CHECK: %[[ITEMSHIFT:.*]] = arith.constant 3 : index
+// CHECK: %[[MIDDLE_DIV:.*]] = arith.shrsi %[[MIDDLE_SUM]], %[[ITEMSHIFT]]
 // CHECK: %[[C3D:.*]] = arith.addi %[[MIDDLE_DIV]], %[[INNER_IDX]]
 // CHECK: %[[COORD:.*]] = fir.coordinate_of %[[BOXADDR]], %[[C3D]] : (!fir.ref<!fir.array<?xf64>>, index) -> !fir.ref<f64>
 // CHECK: %{{.*}} = fir.load %[[COORD]] : !fir.ref<f64>