fix typo and remove some unused code

paddle/gserver/layers/MKLDNNConvLayer.cpp

@@ -294,12 +294,9 @@ void MKLDNNConvLayer::resetOutValue(
     std::shared_ptr<conv_fwd::primitive_desc>& pd, MKLDNNMatrixPtr& out) {
   out = MKLDNNMatrix::create(output_.value, pd->dst_primitive_desc());
 
-  // change original output value from cpu matrix to mkldnn matrix
-  output_.value = std::dynamic_pointer_cast<Matrix>(out);
-
   // create reorder if output value has cpu device and pd do not match
   cpuOutVal_ = nullptr;
-  cpuOutVal_ = nullptr;
+  cvtOutVal_ = nullptr;
   if (!outputIsOnlyMKLDNN()) {
     const MatrixPtr& cpuOut = getOutput(CPU_DEVICE).value;
     memory::dims outDims = memory::dims{bs_, oc_, oh_, ow_};

paddle/gserver/layers/MKLDNNFcLayer.cpp

@@ -172,12 +172,10 @@ void MKLDNNFcLayer::resetWgtBiasValue(MKLDNNMatrixPtr& wgt,
 
 void MKLDNNFcLayer::resetOutValue(MKLDNNMatrixPtr& out) {
   out = MKLDNNMatrix::create(output_.value, {bs_, oc_}, format::nc, engine_);
-  // change original output value to mkldnn output value
-  output_.value = std::dynamic_pointer_cast<Matrix>(out);
   if (!outputIsOnlyMKLDNN()) {
     // fc cpu output value do not need create convert
     // just share point
-    getOutput(CPU_DEVICE).value->setData(output_.value->getData());
+    getOutput(CPU_DEVICE).value->setData(out->getData());
   }
 }
 

paddle/gserver/layers/MKLDNNLayer.h

@@ -119,6 +119,10 @@ public:
         inputElemenCnt_ = elemenCnt;
         reshape(bs_, ic_, ih_, iw_, oc_, oh_, ow_);
         resetFwd(pipelineFwd_, inVal_, wgtVal_, biasVal_, outVal_);
+        if (outVal_) {
+          // change original output value to mkldnn output value
+          output_.value = std::dynamic_pointer_cast<Matrix>(outVal_);
+        }
         convertWeightsFromPaddle();
         needResetBwd_ = true;
       }

paddle/gserver/layers/MKLDNNPoolLayer.cpp

@@ -134,7 +134,6 @@ void MKLDNNPoolLayer::resetOutValue(MKLDNNMatrixPtr& out) {
   memory::dims outDims = memory::dims{bs_, oc_, oh_, ow_};
   out = MKLDNNMatrix::create(
       output_.value, outDims, inVal_->getFormat(), engine_);
-  output_.value = std::dynamic_pointer_cast<Matrix>(out);
 
   // create reorder if output value has cpu device and pd do not match
   cpuOutVal_ = nullptr;

paddle/gserver/tests/test_MKLDNN.cpp

@@ -162,7 +162,6 @@ void testPoolLayer(const testPoolDesc& pm) {
        0});
   LayerInputConfig* input = cfg.layerConfig.add_inputs();
   PoolConfig* pool = input->mutable_pool_conf();
-  // pool->set_pool_type(poolType);
   pool->set_channels(pm.ch);
   pool->set_img_size(pm.iw);
   pool->set_img_size_y(pm.ih);