TODO evaluate strncpy and strlen
https://groups.google.com/forum/m/#!msg/comp.arch/bGBeaNjAKvc/_vbqyxTUAQAJ
+
+strncpy:
+ mv a3, a0 # Copy dst
+loop:
+ setvli x0, a2, vint8 # Vectors of bytes.
+ vlbff.v v1, (a1) # Get src bytes
+ vseq.vi v0, v1, 0 # Flag zero bytes
+ vmfirst a4, v0 # Zero found?
+ vmsif.v v0, v0 # Set mask up to and including zero byte.
+ vsb.v v1, (a3), v0.t # Write out bytes
+ bgez a4, exit # Done
+ csrr t1, vl # Get number of bytes fetched
+ add a1, a1, t1 # Bump src pointer
+ sub a2, a2, t1 # Decrement count.
+ add a3, a3, t1 # Bump dst pointer
+ bnez a2, loop # Anymore?
+
+exit:
+ ret
+
+
+
+ mv a3, a0 # Save start
+loop:
+ setvli a1, x0, vint8 # byte vec, x0 (Zero reg) => use max hardware len
+ vldbff.v v1, (a3) # Get bytes
+ csrr a1, vl # Get bytes actually read e.g. if fault
+ vseq.vi v0, v1, 0 # Set v0[i] where v1[i] = 0
+ add a3, a3, a1 # Bump pointer
+ vmfirst a2, v0 # Find first set bit in mask, returns -1 if none
+ bltz a2, loop # Not found?
+
+ add a0, a0, a1 # Sum start + bump
+ add a3, a3, a2 # Add index of zero byte
+ sub a0, a3, a0 # Subtract start address+bump
+ ret