diff --git a/flang/include/flang/Optimizer/Transforms/Passes.h b/flang/include/flang/Optimizer/Transforms/Passes.h
--- a/flang/include/flang/Optimizer/Transforms/Passes.h
+++ b/flang/include/flang/Optimizer/Transforms/Passes.h
@@ -31,6 +31,7 @@
 std::unique_ptr<mlir::Pass> createFirToCfgPass();
 std::unique_ptr<mlir::Pass> createCharacterConversionPass();
 std::unique_ptr<mlir::Pass> createExternalNameConversionPass();
+std::unique_ptr<mlir::Pass> createMemDataFlowOptPass();
 std::unique_ptr<mlir::Pass> createPromoteToAffinePass();
 
 /// Support for inlining on FIR.
diff --git a/flang/include/flang/Optimizer/Transforms/Passes.td b/flang/include/flang/Optimizer/Transforms/Passes.td
--- a/flang/include/flang/Optimizer/Transforms/Passes.td
+++ b/flang/include/flang/Optimizer/Transforms/Passes.td
@@ -120,4 +120,17 @@
   let constructor = "::fir::createExternalNameConversionPass()";
 }
 
+def MemRefDataFlowOpt : FunctionPass<"fir-memref-dataflow-opt"> {
+  let summary =
+    "Perform store/load forwarding and potentially removing dead stores.";
+  let description = [{
+    This pass performs store to load forwarding to eliminate memory accesses and
+    potentially the entire allocation if all the accesses are forwarded.
+  }];
+  let constructor = "::fir::createMemDataFlowOptPass()";
+  let dependentDialects = [
+    "fir::FIROpsDialect", "mlir::StandardOpsDialect"
+  ];
+}
+
 #endif // FLANG_OPTIMIZER_TRANSFORMS_PASSES
diff --git a/flang/lib/Optimizer/Transforms/CMakeLists.txt b/flang/lib/Optimizer/Transforms/CMakeLists.txt
--- a/flang/lib/Optimizer/Transforms/CMakeLists.txt
+++ b/flang/lib/Optimizer/Transforms/CMakeLists.txt
@@ -5,6 +5,7 @@
   CharacterConversion.cpp
   Inliner.cpp
   ExternalNameConversion.cpp
+  MemRefDataFlowOpt.cpp
   RewriteLoop.cpp
 
   DEPENDS
diff --git a/flang/lib/Optimizer/Transforms/MemRefDataFlowOpt.cpp b/flang/lib/Optimizer/Transforms/MemRefDataFlowOpt.cpp
new file mode 100644
--- /dev/null
+++ b/flang/lib/Optimizer/Transforms/MemRefDataFlowOpt.cpp
@@ -0,0 +1,130 @@
+//===- MemRefDataFlowOpt.cpp - Memory DataFlow Optimization pass ----------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "PassDetail.h"
+#include "flang/Optimizer/Dialect/FIRDialect.h"
+#include "flang/Optimizer/Dialect/FIROps.h"
+#include "flang/Optimizer/Dialect/FIRType.h"
+#include "flang/Optimizer/Transforms/Passes.h"
+#include "mlir/Dialect/StandardOps/IR/Ops.h"
+#include "mlir/IR/Dominance.h"
+#include "mlir/IR/Operation.h"
+#include "mlir/Transforms/Passes.h"
+#include "llvm/ADT/Optional.h"
+#include "llvm/ADT/STLExtras.h"
+#include "llvm/ADT/SmallVector.h"
+
+#define DEBUG_TYPE "fir-memref-dataflow-opt"
+
+namespace {
+
+template <typename OpT>
+static std::vector<OpT> getSpecificUsers(mlir::Value v) {
+  std::vector<OpT> ops;
+  for (auto *user : v.getUsers())
+    if (auto op = dyn_cast<OpT>(user))
+      ops.push_back(op);
+  return ops;
+}
+
+/// This is based on MLIR's MemRefDataFlowOpt which is specialized on AffineRead
+/// and AffineWrite interface
+template <typename ReadOp, typename WriteOp>
+class LoadStoreForwarding {
+public:
+  LoadStoreForwarding(mlir::DominanceInfo *di) : domInfo(di) {}
+
+  // FIXME: This algorithm has a bug. It ignores escaping references between a
+  // store and a load.
+  llvm::Optional<WriteOp> findStoreToForward(ReadOp loadOp,
+                                             std::vector<WriteOp> &&storeOps) {
+    llvm::SmallVector<WriteOp> candidateSet;
+
+    for (auto storeOp : storeOps)
+      if (domInfo->dominates(storeOp, loadOp))
+        candidateSet.push_back(storeOp);
+
+    if (candidateSet.empty())
+      return {};
+
+    llvm::Optional<WriteOp> nearestStore;
+    for (auto candidate : candidateSet) {
+      auto nearerThan = [&](WriteOp otherStore) {
+        if (candidate == otherStore)
+          return false;
+        auto rv = domInfo->properlyDominates(candidate, otherStore);
+        if (rv) {
+          LLVM_DEBUG(llvm::dbgs()
+                     << "candidate " << candidate << " is not the nearest to "
+                     << loadOp << " because " << otherStore << " is closer\n");
+        }
+        return rv;
+      };
+      if (!llvm::any_of(candidateSet, nearerThan)) {
+        nearestStore = mlir::cast<WriteOp>(candidate);
+        break;
+      }
+    }
+    if (!nearestStore) {
+      LLVM_DEBUG(
+          llvm::dbgs()
+          << "load " << loadOp << " has " << candidateSet.size()
+          << " store candidates, but this algorithm can't find a best.\n");
+    }
+    return nearestStore;
+  }
+
+  llvm::Optional<ReadOp> findReadForWrite(WriteOp storeOp,
+                                          std::vector<ReadOp> &&loadOps) {
+    for (auto &loadOp : loadOps) {
+      if (domInfo->dominates(storeOp, loadOp))
+        return loadOp;
+    }
+    return {};
+  }
+
+private:
+  mlir::DominanceInfo *domInfo;
+};
+
+class MemDataFlowOpt : public fir::MemRefDataFlowOptBase<MemDataFlowOpt> {
+public:
+  void runOnFunction() override {
+    mlir::FuncOp f = getFunction();
+
+    auto *domInfo = &getAnalysis<mlir::DominanceInfo>();
+    LoadStoreForwarding<fir::LoadOp, fir::StoreOp> lsf(domInfo);
+    f.walk([&](fir::LoadOp loadOp) {
+      auto maybeStore = lsf.findStoreToForward(
+          loadOp, getSpecificUsers<fir::StoreOp>(loadOp.memref()));
+      if (maybeStore) {
+        auto storeOp = maybeStore.getValue();
+        LLVM_DEBUG(llvm::dbgs() << "FlangMemDataFlowOpt: In " << f.getName()
+                                << " erasing load " << loadOp
+                                << " with value from " << storeOp << '\n');
+        loadOp.getResult().replaceAllUsesWith(storeOp.value());
+        loadOp.erase();
+      }
+    });
+    f.walk([&](fir::AllocaOp alloca) {
+      for (auto &storeOp : getSpecificUsers<fir::StoreOp>(alloca.getResult())) {
+        if (!lsf.findReadForWrite(
+                storeOp, getSpecificUsers<fir::LoadOp>(storeOp.memref()))) {
+          LLVM_DEBUG(llvm::dbgs() << "FlangMemDataFlowOpt: In " << f.getName()
+                                  << " erasing store " << storeOp << '\n');
+          storeOp.erase();
+        }
+      }
+    });
+  }
+};
+} // namespace
+
+std::unique_ptr<mlir::Pass> fir::createMemDataFlowOptPass() {
+  return std::make_unique<MemDataFlowOpt>();
+}
diff --git a/flang/test/Fir/memref-data-flow.fir b/flang/test/Fir/memref-data-flow.fir
new file mode 100644
--- /dev/null
+++ b/flang/test/Fir/memref-data-flow.fir
@@ -0,0 +1,427 @@
+// RUN: fir-opt --split-input-file --fir-memref-dataflow-opt %s | FileCheck %s
+
+// All store-load chains are removed
+
+func @forward_store0(%arg0: !fir.ref<!fir.array<60xi32>>, %arg1: !fir.ref<!fir.array<60xi32>>, %arg2: !fir.ref<!fir.array<60xi32>>) {
+  %c1_i64 = arith.constant 1 : i64
+  %c60 = arith.constant 60 : index
+  %c0 = arith.constant 0 : index
+  %c1 = arith.constant 1 : index
+  %0 = fir.alloca i32 {bindc_name = "i", uniq_name = "_QFf1dcEi"}
+  %1 = fir.alloca !fir.array<60xi32> {bindc_name = "t1", uniq_name = "_QFf1dcEt1"}
+  br ^bb1(%c1, %c60 : index, index)
+^bb1(%2: index, %3: index):  // 2 preds: ^bb0, ^bb2
+  %4 = arith.cmpi sgt, %3, %c0 : index
+  cond_br %4, ^bb2, ^bb3
+^bb2:  // pred: ^bb1
+  %5 = fir.convert %2 : (index) -> i32
+  fir.store %5 to %0 : !fir.ref<i32>
+  %6 = fir.load %0 : !fir.ref<i32>
+  %7 = fir.convert %6 : (i32) -> i64
+  %8 = arith.subi %7, %c1_i64 : i64
+  %9 = fir.coordinate_of %arg0, %8 : (!fir.ref<!fir.array<60xi32>>, i64) -> !fir.ref<i32>
+  %10 = fir.load %9 : !fir.ref<i32>
+  %11 = arith.addi %10, %10 : i32
+  %12 = fir.coordinate_of %1, %8 : (!fir.ref<!fir.array<60xi32>>, i64) -> !fir.ref<i32>
+  fir.store %11 to %12 : !fir.ref<i32>
+  %13 = arith.addi %2, %c1 : index
+  %14 = arith.subi %3, %c1 : index
+  br ^bb1(%13, %14 : index, index)
+^bb3:  // pred: ^bb1
+  %15 = fir.convert %2 : (index) -> i32
+  fir.store %15 to %0 : !fir.ref<i32>
+  br ^bb4(%c1, %c60 : index, index)
+^bb4(%16: index, %17: index):  // 2 preds: ^bb3, ^bb5
+  %18 = arith.cmpi sgt, %17, %c0 : index
+  cond_br %18, ^bb5, ^bb6
+^bb5:  // pred: ^bb4
+  %19 = fir.convert %16 : (index) -> i32
+  fir.store %19 to %0 : !fir.ref<i32>
+  %20 = fir.load %0 : !fir.ref<i32>
+  %21 = fir.convert %20 : (i32) -> i64
+  %22 = arith.subi %21, %c1_i64 : i64
+  %23 = fir.coordinate_of %1, %22 : (!fir.ref<!fir.array<60xi32>>, i64) -> !fir.ref<i32>
+  %24 = fir.load %23 : !fir.ref<i32>
+  %25 = fir.coordinate_of %arg1, %22 : (!fir.ref<!fir.array<60xi32>>, i64) -> !fir.ref<i32>
+  %26 = fir.load %25 : !fir.ref<i32>
+  %27 = arith.muli %24, %26 : i32
+  %28 = fir.coordinate_of %arg2, %22 : (!fir.ref<!fir.array<60xi32>>, i64) -> !fir.ref<i32>
+  fir.store %27 to %28 : !fir.ref<i32>
+  %29 = arith.addi %16, %c1 : index
+  %30 = arith.subi %17, %c1 : index
+  br ^bb4(%29, %30 : index, index)
+^bb6:  // pred: ^bb4
+  %31 = fir.convert %16 : (index) -> i32
+  fir.store %31 to %0 : !fir.ref<i32>
+  return
+}
+
+// CHECK-LABEL: func @forward_store0
+// CHECK-LABEL: ^bb1
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-NOT:     %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb2:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-NOT:     %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK:         %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK:         fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb3:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb5:
+// CHECK:         %{{.*}} = fir.convert %{{.*}} : (index) -> i32
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-NOT:     %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK:         %{{.*}} = fir.convert %{{.*}} : (i32) -> i64
+// CHECK:         %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK:         %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK:         fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb6:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+
+// -----
+
+func @forward_store1(%arg0: !fir.ref<!fir.array<?xi32>>, %arg1: !fir.ref<!fir.array<?xi32>>, %arg2: !fir.ref<!fir.array<?xi32>>, %arg3: !fir.ref<i32>) {
+  %c1_i64 = arith.constant 1 : i64
+  %c0 = arith.constant 0 : index
+  %c1 = arith.constant 1 : index
+  %0 = fir.alloca i32 {bindc_name = "i", uniq_name = "_QFf1dvEi"}
+  %1 = fir.load %arg3 : !fir.ref<i32>
+  %2 = fir.convert %1 : (i32) -> index
+  %3 = fir.alloca !fir.array<?xi32>, %2 {bindc_name = "t1", uniq_name = "_QFf1dvEt1"}
+  br ^bb1(%c1, %2 : index, index)
+^bb1(%4: index, %5: index):  // 2 preds: ^bb0, ^bb2
+  %6 = arith.cmpi sgt, %5, %c0 : index
+  cond_br %6, ^bb2, ^bb3
+^bb2:  // pred: ^bb1
+  %7 = fir.convert %4 : (index) -> i32
+  fir.store %7 to %0 : !fir.ref<i32>
+  %8 = fir.load %0 : !fir.ref<i32>
+  %9 = fir.convert %8 : (i32) -> i64
+  %10 = arith.subi %9, %c1_i64 : i64
+  %11 = fir.coordinate_of %arg0, %10 : (!fir.ref<!fir.array<?xi32>>, i64) -> !fir.ref<i32>
+  %12 = fir.load %11 : !fir.ref<i32>
+  %13 = arith.addi %12, %12 : i32
+  %14 = fir.coordinate_of %3, %10 : (!fir.ref<!fir.array<?xi32>>, i64) -> !fir.ref<i32>
+  fir.store %13 to %14 : !fir.ref<i32>
+  %15 = arith.addi %4, %c1 : index
+  %16 = arith.subi %5, %c1 : index
+  br ^bb1(%15, %16 : index, index)
+^bb3:  // pred: ^bb1
+  %17 = fir.convert %4 : (index) -> i32
+  fir.store %17 to %0 : !fir.ref<i32>
+  %18 = fir.load %arg3 : !fir.ref<i32>
+  %19 = fir.convert %18 : (i32) -> index
+  br ^bb4(%c1, %19 : index, index)
+^bb4(%20: index, %21: index):  // 2 preds: ^bb3, ^bb5
+  %22 = arith.cmpi sgt, %21, %c0 : index
+  cond_br %22, ^bb5, ^bb6
+^bb5:  // pred: ^bb4
+  %23 = fir.convert %20 : (index) -> i32
+  fir.store %23 to %0 : !fir.ref<i32>
+  %24 = fir.load %0 : !fir.ref<i32>
+  %25 = fir.convert %24 : (i32) -> i64
+  %26 = arith.subi %25, %c1_i64 : i64
+  %27 = fir.coordinate_of %3, %26 : (!fir.ref<!fir.array<?xi32>>, i64) -> !fir.ref<i32>
+  %28 = fir.load %27 : !fir.ref<i32>
+  %29 = fir.coordinate_of %arg1, %26 : (!fir.ref<!fir.array<?xi32>>, i64) -> !fir.ref<i32>
+  %30 = fir.load %29 : !fir.ref<i32>
+  %31 = arith.muli %28, %30 : i32
+  %32 = fir.coordinate_of %arg2, %26 : (!fir.ref<!fir.array<?xi32>>, i64) -> !fir.ref<i32>
+  fir.store %31 to %32 : !fir.ref<i32>
+  %33 = arith.addi %20, %c1 : index
+  %34 = arith.subi %21, %c1 : index
+  br ^bb4(%33, %34 : index, index)
+^bb6:  // pred: ^bb4
+  %35 = fir.convert %20 : (index) -> i32
+  fir.store %35 to %0 : !fir.ref<i32>
+  return
+}
+
+// CHECK-LABEL: func @forward_store1
+// CHECK:         %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb2:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK:         %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK:         fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>  
+// CHECK-LABEL: ^bb3:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK:         %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb5:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK:         %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK:         %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK:         fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL:  ^bb6:
+// CHECK-NOT       fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+
+// -----
+
+func @forward_store2(%arg0: !fir.ref<!fir.array<3x3xi32>>, %arg1: !fir.ref<!fir.array<3x3xi32>>, %arg2: !fir.ref<!fir.array<3x3xi32>>) {
+  %c100_i32 = arith.constant 100 : i32
+  %c10000_i32 = arith.constant 10000 : i32
+  %c1_i64 = arith.constant 1 : i64
+  %c3 = arith.constant 3 : index
+  %c0 = arith.constant 0 : index
+  %c1 = arith.constant 1 : index
+  %0 = fir.alloca i32 {bindc_name = "i", uniq_name = "_QFf2dcEi"}
+  %1 = fir.alloca i32 {bindc_name = "j", uniq_name = "_QFf2dcEj"}
+  %2 = fir.alloca !fir.array<3x3xi32> {bindc_name = "t1", uniq_name = "_QFf2dcEt1"}
+  br ^bb1(%c1, %c3 : index, index)
+^bb1(%3: index, %4: index):  // 2 preds: ^bb0, ^bb5
+  %5 = arith.cmpi sgt, %4, %c0 : index
+  cond_br %5, ^bb2, ^bb6
+^bb2:  // pred: ^bb1
+  %6 = fir.convert %3 : (index) -> i32
+  fir.store %6 to %0 : !fir.ref<i32>
+  br ^bb3(%c1, %c3 : index, index)
+^bb3(%7: index, %8: index):  // 2 preds: ^bb2, ^bb4
+  %9 = arith.cmpi sgt, %8, %c0 : index
+  cond_br %9, ^bb4, ^bb5
+^bb4:  // pred: ^bb3
+  %10 = fir.convert %7 : (index) -> i32
+  fir.store %10 to %1 : !fir.ref<i32>
+  %11 = fir.load %0 : !fir.ref<i32>
+  %12 = fir.convert %11 : (i32) -> i64
+  %13 = arith.subi %12, %c1_i64 : i64
+  %14 = fir.load %1 : !fir.ref<i32>
+  %15 = fir.convert %14 : (i32) -> i64
+  %16 = arith.subi %15, %c1_i64 : i64
+  %17 = fir.coordinate_of %arg0, %13, %16 : (!fir.ref<!fir.array<3x3xi32>>, i64, i64) -> !fir.ref<i32>
+  %18 = fir.load %17 : !fir.ref<i32>
+  %19 = fir.coordinate_of %arg0, %16, %13 : (!fir.ref<!fir.array<3x3xi32>>, i64, i64) -> !fir.ref<i32>
+  %20 = fir.load %19 : !fir.ref<i32>
+  %21 = arith.muli %20, %c100_i32 : i32
+  %22 = arith.addi %18, %21 : i32
+  %23 = fir.coordinate_of %2, %13, %16 : (!fir.ref<!fir.array<3x3xi32>>, i64, i64) -> !fir.ref<i32>
+  fir.store %22 to %23 : !fir.ref<i32>
+  %24 = arith.addi %7, %c1 : index
+  %25 = arith.subi %8, %c1 : index
+  br ^bb3(%24, %25 : index, index)
+^bb5:  // pred: ^bb3
+  %26 = fir.convert %7 : (index) -> i32
+  fir.store %26 to %1 : !fir.ref<i32>
+  %27 = arith.addi %3, %c1 : index
+  %28 = arith.subi %4, %c1 : index
+  br ^bb1(%27, %28 : index, index)
+^bb6:  // pred: ^bb1
+  %29 = fir.convert %3 : (index) -> i32
+  fir.store %29 to %0 : !fir.ref<i32>
+  br ^bb7(%c1, %c3 : index, index)
+^bb7(%30: index, %31: index):  // 2 preds: ^bb6, ^bb11
+  %32 = arith.cmpi sgt, %31, %c0 : index
+  cond_br %32, ^bb8, ^bb12
+^bb8:  // pred: ^bb7
+  %33 = fir.convert %30 : (index) -> i32
+  fir.store %33 to %0 : !fir.ref<i32>
+  br ^bb9(%c1, %c3 : index, index)
+^bb9(%34: index, %35: index):  // 2 preds: ^bb8, ^bb10
+  %36 = arith.cmpi sgt, %35, %c0 : index
+  cond_br %36, ^bb10, ^bb11
+^bb10:  // pred: ^bb9
+  %37 = fir.convert %34 : (index) -> i32
+  fir.store %37 to %1 : !fir.ref<i32>
+  %38 = fir.load %0 : !fir.ref<i32>
+  %39 = fir.convert %38 : (i32) -> i64
+  %40 = arith.subi %39, %c1_i64 : i64
+  %41 = fir.load %1 : !fir.ref<i32>
+  %42 = fir.convert %41 : (i32) -> i64
+  %43 = arith.subi %42, %c1_i64 : i64
+  %44 = fir.coordinate_of %2, %40, %43 : (!fir.ref<!fir.array<3x3xi32>>, i64, i64) -> !fir.ref<i32>
+  %45 = fir.load %44 : !fir.ref<i32>
+  %46 = fir.coordinate_of %arg1, %40, %43 : (!fir.ref<!fir.array<3x3xi32>>, i64, i64) -> !fir.ref<i32>
+  %47 = fir.load %46 : !fir.ref<i32>
+  %48 = arith.muli %47, %c10000_i32 : i32
+  %49 = arith.addi %45, %48 : i32
+  %50 = fir.coordinate_of %arg2, %40, %43 : (!fir.ref<!fir.array<3x3xi32>>, i64, i64) -> !fir.ref<i32>
+  fir.store %49 to %50 : !fir.ref<i32>
+  %51 = arith.addi %34, %c1 : index
+  %52 = arith.subi %35, %c1 : index
+  br ^bb9(%51, %52 : index, index)
+^bb11:  // pred: ^bb9
+  %53 = fir.convert %34 : (index) -> i32
+  fir.store %53 to %1 : !fir.ref<i32>
+  %54 = arith.addi %30, %c1 : index
+  %55 = arith.subi %31, %c1 : index
+  br ^bb7(%54, %55 : index, index)
+^bb12:  // pred: ^bb7
+  %56 = fir.convert %30 : (index) -> i32
+  fir.store %56 to %0 : !fir.ref<i32>
+  return
+}
+
+// CHECK-LABEL:  func @forward_store2
+// CHECK-LABEL: ^bb2:
+// CHECK-NOT:    fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb4:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-COUNT-2: %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK:         fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb5:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb6:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb10:
+// CHECK:         %{{.*}} = fir.convert %{{.*}} : (index) -> i32
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-COUNT-2: %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK:         fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb11:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb12:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+
+// -----
+
+func @forward_store3(%arg0: !fir.ref<!fir.array<?x?xi32>>, %arg1: !fir.ref<!fir.array<?x?xi32>>, %arg2: !fir.ref<!fir.array<?x?xi32>>, %arg3: !fir.ref<i32>, %arg4: !fir.ref<i32>) {
+  %c100_i32 = arith.constant 100 : i32
+  %c10000_i32 = arith.constant 10000 : i32
+  %c0 = arith.constant 0 : index
+  %c1 = arith.constant 1 : index
+  %0 = fir.alloca i32 {bindc_name = "i", uniq_name = "_QFf2dvEi"}
+  %1 = fir.alloca i32 {bindc_name = "j", uniq_name = "_QFf2dvEj"}
+  %2 = fir.alloca i32 {bindc_name = "s1e", uniq_name = "_QFf2dvEs1e"}
+  %3 = fir.alloca i32 {bindc_name = "s2e", uniq_name = "_QFf2dvEs2e"}
+  %4 = fir.load %arg3 : !fir.ref<i32>
+  %5 = fir.convert %4 : (i32) -> index
+  %6 = fir.load %arg4 : !fir.ref<i32>
+  %7 = fir.convert %6 : (i32) -> index
+  %8 = fir.alloca !fir.array<?x?xi32>, %5, %7 {bindc_name = "t", uniq_name = "_QFf2dvEt"}
+  fir.store %4 to %2 : !fir.ref<i32>
+  %9 = fir.load %arg4 : !fir.ref<i32>
+  fir.store %9 to %3 : !fir.ref<i32>
+  %10 = fir.load %2 : !fir.ref<i32>
+  %11 = fir.convert %10 : (i32) -> index
+  br ^bb1(%c1, %11 : index, index)
+^bb1(%12: index, %13: index):  // 2 preds: ^bb0, ^bb5
+  %14 = arith.cmpi sgt, %13, %c0 : index
+  cond_br %14, ^bb2, ^bb6
+^bb2:  // pred: ^bb1
+  %15 = fir.convert %12 : (index) -> i32
+  fir.store %15 to %0 : !fir.ref<i32>
+  %16 = fir.load %3 : !fir.ref<i32>
+  %17 = fir.convert %16 : (i32) -> index
+  br ^bb3(%c1, %17 : index, index)
+^bb3(%18: index, %19: index):  // 2 preds: ^bb2, ^bb4
+  %20 = arith.cmpi sgt, %19, %c0 : index
+  cond_br %20, ^bb4, ^bb5
+^bb4:  // pred: ^bb3
+  %21 = fir.convert %18 : (index) -> i32
+  fir.store %21 to %1 : !fir.ref<i32>
+  %22 = fir.convert %arg0 : (!fir.ref<!fir.array<?x?xi32>>) -> !fir.ref<!fir.array<?xi32>>
+  %23 = fir.load %0 : !fir.ref<i32>
+  %24 = fir.convert %23 : (i32) -> index
+  %25 = arith.subi %24, %c1 : index
+  %26 = fir.load %1 : !fir.ref<i32>
+  %27 = fir.convert %26 : (i32) -> index
+  %28 = arith.subi %27, %c1 : index
+  %29 = arith.muli %5, %28 : index
+  %30 = arith.addi %29, %25 : index
+  %31 = fir.coordinate_of %22, %30 : (!fir.ref<!fir.array<?xi32>>, index) -> !fir.ref<i32>
+  %32 = fir.load %31 : !fir.ref<i32>
+  %33 = arith.muli %5, %25 : index
+  %34 = arith.addi %33, %28 : index
+  %35 = fir.coordinate_of %22, %34 : (!fir.ref<!fir.array<?xi32>>, index) -> !fir.ref<i32>
+  %36 = fir.load %35 : !fir.ref<i32>
+  %37 = arith.muli %36, %c100_i32 : i32
+  %38 = arith.addi %32, %37 : i32
+  %39 = fir.convert %8 : (!fir.ref<!fir.array<?x?xi32>>) -> !fir.ref<!fir.array<?xi32>>
+  %40 = fir.coordinate_of %39, %30 : (!fir.ref<!fir.array<?xi32>>, index) -> !fir.ref<i32>
+  fir.store %38 to %40 : !fir.ref<i32>
+  %41 = arith.addi %18, %c1 : index
+  %42 = arith.subi %19, %c1 : index
+  br ^bb3(%41, %42 : index, index)
+^bb5:  // pred: ^bb3
+  %43 = fir.convert %18 : (index) -> i32
+  fir.store %43 to %1 : !fir.ref<i32>
+  %44 = arith.addi %12, %c1 : index
+  %45 = arith.subi %13, %c1 : index
+  br ^bb1(%44, %45 : index, index)
+^bb6:  // pred: ^bb1
+  %46 = fir.convert %12 : (index) -> i32
+  fir.store %46 to %0 : !fir.ref<i32>
+  %47 = fir.load %2 : !fir.ref<i32>
+  %48 = fir.convert %47 : (i32) -> index
+  br ^bb7(%c1, %48 : index, index)
+^bb7(%49: index, %50: index):  // 2 preds: ^bb6, ^bb11
+  %51 = arith.cmpi sgt, %50, %c0 : index
+  cond_br %51, ^bb8, ^bb12
+^bb8:  // pred: ^bb7
+  %52 = fir.convert %49 : (index) -> i32
+  fir.store %52 to %0 : !fir.ref<i32>
+  %53 = fir.load %3 : !fir.ref<i32>
+  %54 = fir.convert %53 : (i32) -> index
+  br ^bb9(%c1, %54 : index, index)
+^bb9(%55: index, %56: index):  // 2 preds: ^bb8, ^bb10
+  %57 = arith.cmpi sgt, %56, %c0 : index
+  cond_br %57, ^bb10, ^bb11
+^bb10:  // pred: ^bb9
+  %58 = fir.convert %55 : (index) -> i32
+  fir.store %58 to %1 : !fir.ref<i32>
+  %59 = fir.convert %8 : (!fir.ref<!fir.array<?x?xi32>>) -> !fir.ref<!fir.array<?xi32>>
+  %60 = fir.load %0 : !fir.ref<i32>
+  %61 = fir.convert %60 : (i32) -> index
+  %62 = arith.subi %61, %c1 : index
+  %63 = fir.load %1 : !fir.ref<i32>
+  %64 = fir.convert %63 : (i32) -> index
+  %65 = arith.subi %64, %c1 : index
+  %66 = arith.muli %5, %65 : index
+  %67 = arith.addi %66, %62 : index
+  %68 = fir.coordinate_of %59, %67 : (!fir.ref<!fir.array<?xi32>>, index) -> !fir.ref<i32>
+  %69 = fir.load %68 : !fir.ref<i32>
+  %70 = fir.convert %arg1 : (!fir.ref<!fir.array<?x?xi32>>) -> !fir.ref<!fir.array<?xi32>>
+  %71 = fir.coordinate_of %70, %67 : (!fir.ref<!fir.array<?xi32>>, index) -> !fir.ref<i32>
+  %72 = fir.load %71 : !fir.ref<i32>
+  %73 = arith.muli %72, %c10000_i32 : i32
+  %74 = arith.addi %69, %73 : i32
+  %75 = fir.convert %arg2 : (!fir.ref<!fir.array<?x?xi32>>) -> !fir.ref<!fir.array<?xi32>>
+  %76 = fir.coordinate_of %75, %67 : (!fir.ref<!fir.array<?xi32>>, index) -> !fir.ref<i32>
+  fir.store %74 to %76 : !fir.ref<i32>
+  %77 = arith.addi %55, %c1 : index
+  %78 = arith.subi %56, %c1 : index
+  br ^bb9(%77, %78 : index, index)
+^bb11:  // pred: ^bb9
+  %79 = fir.convert %55 : (index) -> i32
+  fir.store %79 to %1 : !fir.ref<i32>
+  %80 = arith.addi %49, %c1 : index
+  %81 = arith.subi %50, %c1 : index
+  br ^bb7(%80, %81 : index, index)
+^bb12:  // pred: ^bb7
+  %82 = fir.convert %49 : (index) -> i32
+  fir.store %82 to %0 : !fir.ref<i32>
+  return
+}
+
+// CHECK-LABEL: func @forward_store3
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK:         %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK:         %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK:         %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-NOT:     %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb2:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb4:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-NOT:     %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK:         %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK-NOT:     %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK:         %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK:         fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb5:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb6:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-NOT      %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb8:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-NOT:     %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK:       ^bb10:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-COUNT-2: %{{.*}} = fir.load %{{.*}} : !fir.ref<i32>
+// CHECK:         fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb11:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>
+// CHECK-LABEL: ^bb12:
+// CHECK-NOT:     fir.store %{{.*}} to %{{.*}} : !fir.ref<i32>