dla

include/Network.h

@@ -59,7 +59,7 @@ public:
     dataDim_t input_dim;
     dataDim_t getOutputDim();
 
-    bool fp16;
+    bool fp16, dla;
 };
 
 }}

src/Network.cpp

@@ -24,12 +24,20 @@ Network::Network(dataDim_t input_dim) {
     num_layers = 0;
 
     fp16 = false;
-    if(const char* env_p = std::getenv("TKDNN_MODE"))
+    dla = false;
+    if(const char* env_p = std::getenv("TKDNN_MODE")) {
         if(strcmp(env_p, "FP16") == 0)
             fp16 = true;
+	else if(strcmp(env_p, "DLA") == 0) {
+    	    dla = true;
+	    fp16 = true;	
+	}
+    }
    
     if(fp16)
         std::cout<<COL_REDB<<"!! FP16 INERENCE ENABLED !!"<<COL_END<<"\n";
+    if(dla)
+        std::cout<<COL_GREENB<<"!! DLA INERENCE ENABLED !!"<<COL_END<<"\n";
 }
 
 Network::~Network() {

src/NetworkRT.cpp

@@ -51,6 +51,13 @@ NetworkRT::NetworkRT(Network *net, const char *name) {
             dtRT = DataType::kHALF;
             builderRT->setHalf2Mode(true);
         }
+	if(net->dla && builderRT->getNbDLACores() > 0) {
+            dtRT = DataType::kHALF;
+	    builderRT->setFp16Mode(true);
+	    builderRT->allowGPUFallback(true);
+            builderRT->setDefaultDeviceType(DeviceType::kDLA);
+	    builderRT->setDLACore(0);
+	}
 
         //add input layer
         ITensor *input = networkRT->addInput("data", DataType::kFLOAT,