diff --git a/arch/sw_64/lib/deep-memset.S b/arch/sw_64/lib/deep-memset.S index ed2171c56d4dd554de7161a0fbd453df3d4800f2..7fbd529c72a84f842f59284399f3089e644b4c79 100644 --- a/arch/sw_64/lib/deep-memset.S +++ b/arch/sw_64/lib/deep-memset.S @@ -99,12 +99,11 @@ $mod32_aligned: .align 5 $mod32_loop_nc: subl $18, 64, $18 - blt $18, $mod32_tail + blt $18, $mod32_tail_memb vstd_nc $f10, 0($16) vstd_nc $f10, 32($16) addl $16, 64, $16 br $31, $mod32_loop_nc - memb # required for _nc store instructions .align 5 $mod32_loop: @@ -115,6 +114,8 @@ $mod32_loop: addl $16, 64, $16 br $31, $mod32_loop +$mod32_tail_memb: + memb # required for _nc store instructions $mod32_tail: vldd $f10, 0($4) addl $sp, 64, $sp