update the interface of convertdatatype

source/tensor/XDataType.cpp

@@ -60,59 +60,4 @@ TENSOR_DATA_TYPE GetDataType(const char * typeName)
     }
 }
 
-/****************************************************
-Below is for calling CPU BLAS for fast matrix operations
-I'm not sure how fast it is. But it seems that other
-guys are crazy about this. So I decided to have a try.
-*/
-
-/* float -> float16 */
-_XINLINE_ unsigned short FloatToFloat16(float f)
-{
-    unsigned int x = *((unsigned int*)&f);
-    unsigned short h = ((x>>16)&0x8000)|((((x&0x7f800000)-0x38000000)>>13)&0x7c00)|((x>>13)&0x03ff);
-    return h;
-}
-
-/* float16 -> float */
-_XINLINE_ float Float16ToFloat(unsigned short h)
-{
-    float f = float(((h&0x8000)<<16) | (((h&0x7c00)+0x1C000)<<13) | ((h&0x03FF)<<13));
-    return f;
-}
-
-/* 
-data type conversion
->> devID - device id
->> s - source data array
->> typeS - source data type
->> t - target data array
->> typeT - target data type
->> size - number of the items in s (and t)
-*/
-void ConvertDataType(int devID, 
-                     void * s, TENSOR_DATA_TYPE typeS, 
-                     void * t, TENSOR_DATA_TYPE typeT, 
-                     int size)
-{
-    CheckNTErrors((devID < 0), "This code must be run on CPUs!");
-
-    if(typeS == typeT)
-        return;
-
-    if(typeS == X_FLOAT && typeT == X_FLOAT16){
-        for(int i = 0; i < size; i++){
-            ((unsigned short*)t)[i] = FloatToFloat16(((float*)s)[i]);
-        }
-    }
-    else if(typeS == X_FLOAT16 && typeT == X_FLOAT){
-        for(int i = 0; i < size; i++){
-            ((float*)t)[i] = Float16ToFloat(((unsigned short*)s)[i]);
-        }
-    }
-    else{
-        ShowNTErrors("Unsupported data types for conversion!");
-    }
-}
-
 } /* end of the nts (NiuTrans.Tensor) namespace */

source/tensor/XDataType.h

@@ -46,13 +46,6 @@ enum MATRIX_TRANS_TYPE{X_TRANS, X_NOTRANS};
 extern const char * GetDataTypeName(TENSOR_DATA_TYPE type);
 extern TENSOR_DATA_TYPE GetDataType(const char * typeName);
 
-/* data conversion (for lower precision computation) */
-unsigned short FloatToFloat16(float f);
-float Float16ToFloat(unsigned short h);
-void ConvertDataType(int devID, 
-                     void * s, TENSOR_DATA_TYPE typeS, 
-                     void * t, TENSOR_DATA_TYPE typeT, int size);
-
 } /* end of the nts (NiuTrans.Tensor) namespace */
 
 #endif
\ No newline at end of file

source/tensor/core/getandset/ConvertDataType.cpp

@@ -28,6 +28,61 @@
 namespace nts { // namespace nts(NiuTrans.Tensor)
 
 /*
+Below is for calling CPU BLAS for fast matrix operations
+I'm not sure how fast it is. But it seems that other
+guys are crazy about this. So I decided to have a try.
+*/
+
+/* float -> float16 */
+_XINLINE_ unsigned short FloatToFloat16(float f)
+{
+    unsigned int x = *((unsigned int*)&f);
+    unsigned short h = ((x>>16)&0x8000)|((((x&0x7f800000)-0x38000000)>>13)&0x7c00)|((x>>13)&0x03ff);
+    return h;
+}
+
+/* float16 -> float */
+_XINLINE_ float Float16ToFloat(unsigned short h)
+{
+    float f = float(((h&0x8000)<<16) | (((h&0x7c00)+0x1C000)<<13) | ((h&0x03FF)<<13));
+    return f;
+}
+
+/* 
+data type conversion
+>> devID - device id
+>> s - source data array
+>> typeS - source data type
+>> t - target data array
+>> typeT - target data type
+>> size - number of the items in s (and t)
+*/
+void ConvertDataType(int devID, 
+                     void * s, TENSOR_DATA_TYPE typeS, 
+                     void * t, TENSOR_DATA_TYPE typeT, 
+                     int size)
+{
+    CheckNTErrors((devID < 0), "This code must be run on CPUs!");
+
+    if(typeS == typeT)
+        return;
+
+    if(typeS == X_FLOAT && typeT == X_FLOAT16){
+        for(int i = 0; i < size; i++){
+            ((unsigned short*)t)[i] = FloatToFloat16(((float*)s)[i]);
+        }
+    }
+    else if(typeS == X_FLOAT16 && typeT == X_FLOAT){
+        for(int i = 0; i < size; i++){
+            ((float*)t)[i] = Float16ToFloat(((unsigned short*)s)[i]);
+        }
+    }
+    else{
+        ShowNTErrors("Unsupported data types for conversion!");
+    }
+}
+
+/*
 convert data type
 
 >> input - the input tensor

source/tensor/core/getandset/ConvertDataType.h

@@ -27,6 +27,13 @@
 
 namespace nts { // namespace nts(NiuTrans.Tensor)
 
+/* data conversion (for lower precision computation) */
+unsigned short FloatToFloat16(float f);
+float Float16ToFloat(unsigned short h);
+void ConvertDataType(int devID, 
+                     void * s, TENSOR_DATA_TYPE typeS, 
+                     void * t, TENSOR_DATA_TYPE typeT, int size);
+
 /* convert data type */
 void _ConvertDataType(const XTensor * input, XTensor * output);