diff --git a/paddle/math/tests/test_matrixCompare.cpp b/paddle/math/tests/test_matrixCompare.cpp
index ae5bc5a86a1790ce30a8d7f83c9564f52d7cf7ea..de540dad4c8eefe5084c7089d7960d8ca8cf9875 100644
--- a/paddle/math/tests/test_matrixCompare.cpp
+++ b/paddle/math/tests/test_matrixCompare.cpp
@@ -448,6 +448,24 @@ void testMatrixZeroAtOffset(int height, int width) {
   MatrixCheckEqual(*cpuA, *cpuTest);
 }
 
+void testMatrixDeepSwap(int height, int width) {
+  MatrixPtr cpuA = std::make_shared<CpuMatrix>(height, width);
+  MatrixPtr cpuB = std::make_shared<CpuMatrix>(height, width);
+  MatrixPtr cpuCopyA = std::make_shared<CpuMatrix>(height, width);
+  MatrixPtr cpuCopyB = std::make_shared<CpuMatrix>(height, width);
+
+  cpuA->randomizeUniform();
+  cpuB->randomizeUniform();
+  cpuCopyA->copyFrom(*cpuA);
+  cpuCopyB->copyFrom(*cpuB);
+
+  // swap matrix cpuA and cpuB
+  cpuA->deepSwap(*cpuB);
+
+  MatrixCheckEqual(*cpuA, *cpuCopyB);
+  MatrixCheckEqual(*cpuB, *cpuCopyA);
+}
+
 void testMatrixBinaryAdd(int height, int width) {
   MatrixPtr cpuA = std::make_shared<CpuMatrix>(height, width);
   MatrixPtr cpuB = std::make_shared<CpuMatrix>(height, width);
@@ -480,6 +498,7 @@ void testMatrixAssign(int height, int width) {
   MatrixCheckEqual(*cpuA, *outputCheck);
 }
 
+
 void testMatrixAdd(int height, int width) {
   MatrixPtr cpuA = std::make_shared<CpuMatrix>(height, width);
   MatrixPtr gpuA = std::make_shared<GpuMatrix>(height, width);
@@ -798,6 +817,7 @@ TEST(Matrix, unary) {
       testMatrixBinaryAdd(height, width);
       testMatrixTanh(height, width);
       testMatrixTanhDerivative(height, width);
+      testMatrixDeepSwap(height, width);
 
       // applyTernary
       testMatrixTernarySub(height, width);