Fix declaration of input arguments in the x86_64 microkernels for DOT and AXPY (#1965)

* Tag operands 0 and 1 as both input and output

For #1964 (basically a continuation of coding problems first seen in #1292)

kernel/x86_64/cdot_microk_steamroller-2.c

@@ -97,9 +97,9 @@ static void cdot_kernel_16( BLASLONG n, FLOAT *x, FLOAT *y, FLOAT *dot)
 	"vzeroupper		        	\n\t"
 
 	:
-        : 
-          "r" (i),	// 0	
-	  "r" (n),  	// 1
+          "+r" (i),	// 0	
+	  "+r" (n)  	// 1
+        :
           "r" (x),      // 2
           "r" (y),      // 3
           "r" (dot)     // 4
@@ -175,10 +175,10 @@ static void cdot_kernel_16( BLASLONG n, FLOAT *x, FLOAT *y, FLOAT *dot)
 	"vmovups        %%xmm4,  16(%4)		\n\t"
 	"vzeroupper		        	\n\t"
 
-	:
-        : 
-          "r" (i),	// 0	
-	  "r" (n),  	// 1
+	: 
+          "+r" (i),	// 0	
+	  "+r" (n)  	// 1
+        :
           "r" (x),      // 2
           "r" (y),      // 3
           "r" (dot)     // 4