diff options
| -rw-r--r-- | ChangeLog | 4 | ||||
| -rw-r--r-- | sysdeps/aarch64/memset.S | 7 |
2 files changed, 8 insertions, 3 deletions
diff --git a/ChangeLog b/ChangeLog index d340866c43..be2344248f 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,7 @@ +2018-11-20 Wilco Dijkstra <wdijkstr@arm.com> + + * sysdeps/aarch64/memset.S (MEMSET): Improve non-zero memset loop. + 2018-11-20 Joseph Myers <joseph@codesourcery.com> * conform/conformtest.py (ElementTest.run): Use unique identifiers diff --git a/sysdeps/aarch64/memset.S b/sysdeps/aarch64/memset.S index 4a45459361..9738cf5fd5 100644 --- a/sysdeps/aarch64/memset.S +++ b/sysdeps/aarch64/memset.S @@ -89,10 +89,10 @@ L(set_long): b.eq L(try_zva) L(no_zva): sub count, dstend, dst /* Count is 16 too large. */ - add dst, dst, 16 + sub dst, dst, 16 /* Dst is biased by -32. */ sub count, count, 64 + 16 /* Adjust count and bias for loop. */ -1: stp q0, q0, [dst], 64 - stp q0, q0, [dst, -32] +1: stp q0, q0, [dst, 32] + stp q0, q0, [dst, 64]! L(tail64): subs count, count, 64 b.hi 1b @@ -183,6 +183,7 @@ L(zva_other): subs count, count, zva_len b.hs 3b 4: add count, count, zva_len + sub dst, dst, 32 /* Bias dst for tail loop. */ b L(tail64) #endif |