Bug fixed

1. Enable the isGradEfficient;
2. Adjust global memory size.

source/network/XNet.cpp

@@ -55,7 +55,7 @@ void XNetClearAll()
 XNet::XNet()
 {
     nodes.Clear();
-    isGradEfficient = false;
+    isGradEfficient = true;
 }
 
 /* de-constructor */

source/tensor/XMem.cpp

@@ -1562,9 +1562,9 @@ void XMemManager::GetBufferSize(MTYPE freeMem, MTYPE * myBufSize)
             if (freeMem >= MILLION * 512){
                 *myBufSize = MILLION * 128;
                 if (freeMem >= MILLION * 1024) {
-                    *myBufSize = MILLION * 256;
+                    *myBufSize = MILLION * 128;
                     if (freeMem >= MILLION * 2048)
-                        *myBufSize = MILLION * 512;
+                        *myBufSize = MILLION * 128;
                 }
             }
         }
@@ -1596,9 +1596,9 @@ void XMemManager::Initialize()
 /* free it */
 void XMemManager::Free()
 {
-    for (int i = 0; i < MAX_CPU_NUM; i++)
+    for (int i = 0; i < MAX_CPU_MEM_NUM; i++)
         CPUMems[i].Free();
-    for (int i = 0; i < MAX_GPU_NUM; i++)
+    for (int i = 0; i < MAX_GPU_MEM_NUM; i++)
         GPUMems[i].Free();
 }
 

source/tensor/XMem.h

@@ -60,10 +60,10 @@ typedef long long          INT_64;
 #define CUDA_HOST_MALLOC 1
 #define MY_PITCH CUDA_PITCH
 #define BUF_PITCH 256
-#define MIN_BLOCK_SIZE_FOR_MEMPOOL 128 * 1024 * 1024
+#define MIN_BLOCK_SIZE_FOR_MEMPOOL 256 * 1024 * 1024
 #define MIN_BLOCK_NUM_FOR_MEMPOOL 1024
-#define MAX_CPU_NUM 1
-#define MAX_GPU_NUM 1 
+#define MAX_CPU_MEM_NUM 16
+#define MAX_GPU_MEM_NUM 16
 
 /* 
 mode of runnig a memory pool 
@@ -434,13 +434,13 @@ class XMemManager
 {
 private:
     /* cpu memory pool information */
-    XMem CPUMems[MAX_CPU_NUM];
+    XMem CPUMems[MAX_CPU_MEM_NUM];
 
     /* number of cpu memory pools */
     int nCPUMem;
 
     /* gpu memory pool information */
-    XMem GPUMems[MAX_GPU_NUM];
+    XMem GPUMems[MAX_GPU_MEM_NUM];
 
     /* number of gpu memory pools */
     int nGPUMem;