diff options
Diffstat (limited to 'sysdeps/aarch64/strcmp.S')
| -rw-r--r-- | sysdeps/aarch64/strcmp.S | 31 |
1 files changed, 29 insertions, 2 deletions
diff --git a/sysdeps/aarch64/strcmp.S b/sysdeps/aarch64/strcmp.S index e99d6625b7..7eed82cee7 100644 --- a/sysdeps/aarch64/strcmp.S +++ b/sysdeps/aarch64/strcmp.S @@ -72,6 +72,7 @@ L(start_realigned): cbz syndrome, L(loop_aligned) /* End of performance-critical section -- one 64B cache line. */ +L(end): #ifndef __AARCH64EB__ rev syndrome, syndrome rev data1, data1 @@ -145,12 +146,38 @@ L(mutual_align): b L(start_realigned) L(misaligned8): - /* We can do better than this. */ + /* Align SRC1 to 8 bytes and then compare 8 bytes at a time, always + checking to make sure that we don't access beyond page boundary in + SRC2. */ + tst src1, #7 + b.eq L(loop_misaligned) +L(do_misaligned): ldrb data1w, [src1], #1 ldrb data2w, [src2], #1 cmp data1w, #1 ccmp data1w, data2w, #0, cs /* NZCV = 0b0000. */ - b.eq L(misaligned8) + b.ne L(done) + tst src1, #7 + b.ne L(do_misaligned) + +L(loop_misaligned): + /* Test if we are within the last dword of the end of a 4K page. If + yes then jump back to the misaligned loop to copy a byte at a time. */ + and tmp1, src2, #0xff8 + eor tmp1, tmp1, #0xff8 + cbz tmp1, L(do_misaligned) + ldr data1, [src1], #8 + ldr data2, [src2], #8 + + sub tmp1, data1, zeroones + orr tmp2, data1, #REP8_7f + eor diff, data1, data2 /* Non-zero if differences found. */ + bic has_nul, tmp1, tmp2 /* Non-zero if NUL terminator. */ + orr syndrome, diff, has_nul + cbz syndrome, L(loop_misaligned) + b L(end) + +L(done): sub result, data1, data2 RET END(strcmp) |