* The algorithm for the leading and trailing quadwords remains the same,
* however the loop has been unrolled to enable better memory throughput,
* and the code has been replicated for each of the entry points: __memset
- * and __memsetw to permit better scheduling to eliminate the stalling
+ * and __memset16 to permit better scheduling to eliminate the stalling
* encountered during the mask replication.
* A future enhancement might be to put in a byte store loop for really
* small (say < 32 bytes) memset()s. Whether or not that change would be
.globl memset
.globl __memset
.globl ___memset
- .globl __memsetw
+ .globl __memset16
.globl __constant_c_memset
.ent ___memset
* to mask stalls. Note that entry point names also had to change
*/
.align 5
- .ent __memsetw
+ .ent __memset16
-__memsetw:
+__memset16:
.frame $30,0,$26,0
.prologue 0
nop
ret $31,($26),1 # L0 :
- .end __memsetw
- EXPORT_SYMBOL(__memsetw)
+ .end __memset16
+ EXPORT_SYMBOL(__memset16)
memset = ___memset
__memset = ___memset