Bug fixes in ZSCALV

Fixes for a couple of issues:
- Modify alpha argument in kernel call in zscal_blis_impl to
  avoid compiler warning message about discarding 'const'
  qualifier from pointer target type.
- When BLIS_ARCH_TYPE=generic, call to bli_cntx_get_l1v_ker_dt
  in ref_kernels/1/bli_scalv_ref.c for ZSCAL was causing a
  segmentation fault. This was because the cntx was NULL on
  entry to this function. Correct by getting zscal_blis_impl
  to pass the cntx it has initialized for non-Zen codepaths.
  This changes has been copied to idamax_blis_impl for
  consistency.

AMD-Internal: [CPUPL-2773]
Change-Id: Ib02e4c1a2a7bf30c208732241d4959f7a2696179

frame/compat/bla_amax_amd.c

@@ -291,7 +291,7 @@ f77_int idamax_blis_impl
         incx0 = ( inc_t )(*incx);
     }
 
-    cntx_t* cntx;
+    cntx_t* cntx = NULL;
 
     // Query the architecture ID
     arch_t id = bli_arch_query_id();
@@ -325,7 +325,7 @@ f77_int idamax_blis_impl
       n0,
       x0, incx0,
       &bli_index,
-      NULL
+      cntx
     );
 
     /*

frame/compat/bla_scal_amd.c

@@ -666,7 +666,7 @@ void zscal_blis_impl
   // Definition of function pointer
   zscalv_ker_ft scalv_fun_ptr;
 
-  cntx_t* cntx;
+  cntx_t* cntx = NULL;
 
   // Query the architecture ID
   arch_t id = bli_arch_query_id();
@@ -700,9 +700,9 @@ void zscal_blis_impl
   (
     BLIS_NO_CONJUGATE,
     n0,
-    alpha,
+    (dcomplex*) alpha,
     x0, incx0,
-    NULL
+    cntx
   );
 
   AOCL_DTL_TRACE_EXIT(AOCL_DTL_LEVEL_TRACE_1)