Adapt ARM architect

Author: Qiyu8

kernel/arm64/KERNEL.ARMV8

@@ -97,7 +97,7 @@ CNRM2KERNEL    = znrm2.S
 ZNRM2KERNEL    = znrm2.S
 
 DDOTKERNEL     = dot.S
-SDOTKERNEL     = dot.S
+SDOTKERNEL     = ../generic/dot.c
 CDOTKERNEL     = zdot.S
 ZDOTKERNEL     = zdot.S
 DSDOTKERNEL    = dot.S

kernel/arm64/KERNEL.CORTEXA53

@@ -97,7 +97,7 @@ CNRM2KERNEL    = znrm2.S
 ZNRM2KERNEL    = znrm2.S
 
 DDOTKERNEL     = dot.S
-SDOTKERNEL     = dot.S
+SDOTKERNEL     = ../generic/dot.c
 CDOTKERNEL     = zdot.S
 ZDOTKERNEL     = zdot.S
 DSDOTKERNEL    = dot.S

kernel/arm64/KERNEL.CORTEXA57

@@ -70,7 +70,7 @@ DCOPYKERNEL  = copy.S
 CCOPYKERNEL  = copy.S
 ZCOPYKERNEL  = copy.S
 
-SDOTKERNEL   = dot.S
+SDOTKERNEL   = ../generic/dot.c
 DDOTKERNEL   = dot.S
 CDOTKERNEL   = zdot.S
 ZDOTKERNEL   = zdot.S

kernel/generic/dot.c

@@ -27,7 +27,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 
 #include "common.h"
-
+#include "../simd/intrin.h"
 #if defined(DSDOT)
 double CNAME(BLASLONG n, FLOAT *x, BLASLONG inc_x, FLOAT *y, BLASLONG inc_y)
 #else
@@ -47,9 +47,9 @@ FLOAT CNAME(BLASLONG n, FLOAT *x, BLASLONG inc_x, FLOAT *y, BLASLONG inc_y)
 
 	if ( (inc_x == 1) && (inc_y == 1) )
 	{
-		int n1 = n & -4;
+        int n1 = n & -4;
 #if V_SIMD && !defined(DSDOT)
-		const int vstep = v_nlanes_f32;
+        const int vstep = v_nlanes_f32;
         const int unrollx4 = n & (-vstep * 4);
         const int unrollx  = n &  -vstep;
 		v_f32 vsum0 = v_zero_f32();