Properly implemented beta == 0 semantics.

Details:
- Changed name of set0 and set0_mxn macros to set0s and set0s_mxn,
  respectively.
- Added code to the following operations that sets the output operand to
  zero if the corresponding scalar is zero (rather than performing the
  floating-point multiply, or in the case of setv, copying the value).
  This will prevent nan's and inf's from creeping into results from
  uninitialized memory.
  - axpy
  - dotxv
  - scalv
  - scal2v
  - setv
  - gemv
  - ger
  - hemv
  - her
  - her2
  - gemm reference ukernels

frame/include/level0/bl2_constants.h

@@ -130,22 +130,22 @@
 
 // set to constant
 
-// set0
+// set0s
 
-#define bl2_sset0( a ) \
+#define bl2_sset0s( a ) \
 { \
 	(a) = 0.0F; \
 }
-#define bl2_dset0( a ) \
+#define bl2_dset0s( a ) \
 { \
 	(a) = 0.0; \
 }
-#define bl2_cset0( a ) \
+#define bl2_cset0s( a ) \
 { \
 	(a).real = 0.0F; \
 	(a).imag = 0.0F; \
 }
-#define bl2_zset0( a ) \
+#define bl2_zset0s( a ) \
 { \
 	(a).real = 0.0; \
 	(a).imag = 0.0; \

frame/include/level0/bl2_set0s_mxn.h

@@ -32,49 +32,49 @@
 
 */
 
-#ifndef BLIS_SET0_MXN_H
-#define BLIS_SET0_MXN_H
+#ifndef BLIS_SET0S_MXN_H
+#define BLIS_SET0S_MXN_H
 
-// set0_mxn
+// set0s_mxn
 
 // Notes:
 // - The first char encodes the type of x.
 // - The second char encodes the type of y.
 
-#define bl2_sset0_mxn( m, n, y, rs_y, cs_y ) \
+#define bl2_sset0s_mxn( m, n, y, rs_y, cs_y ) \
 { \
 	dim_t i, j; \
 \
 	for ( j = 0; j < n; ++j ) \
 	for ( i = 0; i < m; ++i ) \
-	bl2_sset0( *(y + i*rs_y + j*cs_y) ); \
+	bl2_sset0s( *(y + i*rs_y + j*cs_y) ); \
 }
 
-#define bl2_dset0_mxn( m, n, y, rs_y, cs_y ) \
+#define bl2_dset0s_mxn( m, n, y, rs_y, cs_y ) \
 { \
 	dim_t i, j; \
 \
 	for ( j = 0; j < n; ++j ) \
 	for ( i = 0; i < m; ++i ) \
-	bl2_dset0( *(y + i*rs_y + j*cs_y) ); \
+	bl2_dset0s( *(y + i*rs_y + j*cs_y) ); \
 }
 
-#define bl2_cset0_mxn( m, n, y, rs_y, cs_y ) \
+#define bl2_cset0s_mxn( m, n, y, rs_y, cs_y ) \
 { \
 	dim_t i, j; \
 \
 	for ( j = 0; j < n; ++j ) \
 	for ( i = 0; i < m; ++i ) \
-	bl2_cset0( *(y + i*rs_y + j*cs_y) ); \
+	bl2_cset0s( *(y + i*rs_y + j*cs_y) ); \
 }
 
-#define bl2_zset0_mxn( m, n, y, rs_y, cs_y ) \
+#define bl2_zset0s_mxn( m, n, y, rs_y, cs_y ) \
 { \
 	dim_t i, j; \
 \
 	for ( j = 0; j < n; ++j ) \
 	for ( i = 0; i < m; ++i ) \
-	bl2_zset0( *(y + i*rs_y + j*cs_y) ); \
+	bl2_zset0s( *(y + i*rs_y + j*cs_y) ); \
 }