diff --git a/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp b/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
--- a/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
+++ b/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
@@ -2494,6 +2494,10 @@
                                      InsertPointTy AllocaIP, unsigned NumLoops,
                                      ArrayRef<llvm::Value *> StoreValues,
                                      const Twine &Name, bool IsDependSource) {
+  for (size_t I = 0; I < StoreValues.size(); I++)
+    assert(StoreValues[I]->getType()->isIntegerTy(64) &&
+           "OpenMP runtime requires depend vec with i64 type");
+
   if (!updateToLocation(Loc))
     return Loc.IP;
 
@@ -2508,7 +2512,8 @@
   for (unsigned I = 0; I < NumLoops; ++I) {
     Value *DependAddrGEPIter = Builder.CreateInBoundsGEP(
         ArrI64Ty, ArgsBase, {Builder.getInt64(0), Builder.getInt64(I)});
-    Builder.CreateStore(StoreValues[I], DependAddrGEPIter);
+    StoreInst *STInst = Builder.CreateStore(StoreValues[I], DependAddrGEPIter);
+    STInst->setAlignment(Align(8));
   }
 
   Value *DependBaseAddrGEP = Builder.CreateInBoundsGEP(
diff --git a/llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp b/llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp
--- a/llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp
+++ b/llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp
@@ -2267,6 +2267,7 @@
     ASSERT_NE(StoreValue, nullptr);
     EXPECT_EQ(StoreValue->getValueOperand(), StoreValues[Iter]);
     EXPECT_EQ(StoreValue->getPointerOperand(), DependAddrGEPIter);
+    EXPECT_EQ(StoreValue->getAlignment(), 8);
     IterInst = dyn_cast<Instruction>(StoreValue);
   }
 
@@ -2351,6 +2352,7 @@
     ASSERT_NE(StoreValue, nullptr);
     EXPECT_EQ(StoreValue->getValueOperand(), StoreValues[Iter]);
     EXPECT_EQ(StoreValue->getPointerOperand(), DependAddrGEPIter);
+    EXPECT_EQ(StoreValue->getAlignment(), 8);
     IterInst = dyn_cast<Instruction>(StoreValue);
   }
 
diff --git a/mlir/test/Target/LLVMIR/openmp-llvm.mlir b/mlir/test/Target/LLVMIR/openmp-llvm.mlir
--- a/mlir/test/Target/LLVMIR/openmp-llvm.mlir
+++ b/mlir/test/Target/LLVMIR/openmp-llvm.mlir
@@ -659,14 +659,14 @@
 
   omp.wsloop (%arg7) : i32 = (%arg0) to (%arg1) step (%arg2) ordered(1) {
     // CHECK: [[TMP:%.*]] = getelementptr inbounds [1 x i64], [1 x i64]* [[ADDR]], i64 0, i64 0
-    // CHECK: store i64 [[ARG0:%.*]], i64* [[TMP]], align 4
+    // CHECK: store i64 [[ARG0:%.*]], i64* [[TMP]], align 8
     // CHECK: [[TMP2:%.*]] = getelementptr inbounds [1 x i64], [1 x i64]* [[ADDR]], i64 0, i64 0
     // CHECK: [[OMP_THREAD2:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB3:[0-9]+]])
     // CHECK: call void @__kmpc_doacross_wait(%struct.ident_t* @[[GLOB3]], i32 [[OMP_THREAD2]], i64* [[TMP2]])
     omp.ordered depend_type("dependsink") depend_vec(%arg3 : i64) {num_loops_val = 1 : i64}
 
     // CHECK: [[TMP3:%.*]] = getelementptr inbounds [1 x i64], [1 x i64]* [[ADDR3]], i64 0, i64 0
-    // CHECK: store i64 [[ARG0]], i64* [[TMP3]], align 4
+    // CHECK: store i64 [[ARG0]], i64* [[TMP3]], align 8
     // CHECK: [[TMP4:%.*]] = getelementptr inbounds [1 x i64], [1 x i64]* [[ADDR3]], i64 0, i64 0
     // CHECK: [[OMP_THREAD4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB5:[0-9]+]])
     // CHECK: call void @__kmpc_doacross_post(%struct.ident_t* @[[GLOB5]], i32 [[OMP_THREAD4]], i64* [[TMP4]])
@@ -677,25 +677,25 @@
 
   omp.wsloop (%arg7) : i32 = (%arg0) to (%arg1) step (%arg2) ordered(2) {
     // CHECK: [[TMP5:%.*]] = getelementptr inbounds [2 x i64], [2 x i64]* [[ADDR5]], i64 0, i64 0
-    // CHECK: store i64 [[ARG0]], i64* [[TMP5]], align 4
+    // CHECK: store i64 [[ARG0]], i64* [[TMP5]], align 8
     // CHECK: [[TMP6:%.*]] = getelementptr inbounds [2 x i64], [2 x i64]* [[ADDR5]], i64 0, i64 1
-    // CHECK: store i64 [[ARG1:%.*]], i64* [[TMP6]], align 4
+    // CHECK: store i64 [[ARG1:%.*]], i64* [[TMP6]], align 8
     // CHECK: [[TMP7:%.*]] = getelementptr inbounds [2 x i64], [2 x i64]* [[ADDR5]], i64 0, i64 0
     // CHECK: [[OMP_THREAD6:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB7:[0-9]+]])
     // CHECK: call void @__kmpc_doacross_wait(%struct.ident_t* @[[GLOB7]], i32 [[OMP_THREAD6]], i64* [[TMP7]])
     // CHECK: [[TMP8:%.*]] = getelementptr inbounds [2 x i64], [2 x i64]* [[ADDR7]], i64 0, i64 0
-    // CHECK: store i64 [[ARG2:%.*]], i64* [[TMP8]], align 4
+    // CHECK: store i64 [[ARG2:%.*]], i64* [[TMP8]], align 8
     // CHECK: [[TMP9:%.*]] = getelementptr inbounds [2 x i64], [2 x i64]* [[ADDR7]], i64 0, i64 1
-    // CHECK: store i64 [[ARG3:%.*]], i64* [[TMP9]], align 4
+    // CHECK: store i64 [[ARG3:%.*]], i64* [[TMP9]], align 8
     // CHECK: [[TMP10:%.*]] = getelementptr inbounds [2 x i64], [2 x i64]* [[ADDR7]], i64 0, i64 0
     // CHECK: [[OMP_THREAD8:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB7]])
     // CHECK: call void @__kmpc_doacross_wait(%struct.ident_t* @[[GLOB7]], i32 [[OMP_THREAD8]], i64* [[TMP10]])
     omp.ordered depend_type("dependsink") depend_vec(%arg3, %arg4, %arg5, %arg6 : i64, i64, i64, i64) {num_loops_val = 2 : i64}
 
     // CHECK: [[TMP11:%.*]] = getelementptr inbounds [2 x i64], [2 x i64]* [[ADDR9]], i64 0, i64 0
-    // CHECK: store i64 [[ARG0]], i64* [[TMP11]], align 4
+    // CHECK: store i64 [[ARG0]], i64* [[TMP11]], align 8
     // CHECK: [[TMP12:%.*]] = getelementptr inbounds [2 x i64], [2 x i64]* [[ADDR9]], i64 0, i64 1
-    // CHECK: store i64 [[ARG1]], i64* [[TMP12]], align 4
+    // CHECK: store i64 [[ARG1]], i64* [[TMP12]], align 8
     // CHECK: [[TMP13:%.*]] = getelementptr inbounds [2 x i64], [2 x i64]* [[ADDR9]], i64 0, i64 0
     // CHECK: [[OMP_THREAD10:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB9:[0-9]+]])
     // CHECK: call void @__kmpc_doacross_post(%struct.ident_t* @[[GLOB9]], i32 [[OMP_THREAD10]], i64* [[TMP13]])