diff options
| author | Sunil K Pandey <skpgkp1@gmail.com> | 2020-06-12 08:57:16 -0700 |
|---|---|---|
| committer | H.J. Lu <hjl.tools@gmail.com> | 2020-06-17 07:07:38 -0700 |
| commit | 75870237ff3bb363447b03f4b0af100227570910 (patch) | |
| tree | eed2d178cbae830002110df6152d1471acc73745 /sysdeps/x86_64/multiarch/strcmp-avx2.S | |
| parent | 7a508406dfbf9121daeef2a32a3a41c7be7e5add (diff) | |
| download | glibc-75870237ff3bb363447b03f4b0af100227570910.zip glibc-75870237ff3bb363447b03f4b0af100227570910.tar.gz glibc-75870237ff3bb363447b03f4b0af100227570910.tar.bz2 | |
Fix avx2 strncmp offset compare condition check [BZ #25933]
strcmp-avx2.S: In avx2 strncmp function, strings are compared in
chunks of 4 vector size(i.e. 32x4=128 byte for avx2). After first 4
vector size comparison, code must check whether it already passed
the given offset. This patch implement avx2 offset check condition
for strncmp function, if both string compare same for first 4 vector
size.
Diffstat (limited to 'sysdeps/x86_64/multiarch/strcmp-avx2.S')
| -rw-r--r-- | sysdeps/x86_64/multiarch/strcmp-avx2.S | 15 |
1 files changed, 15 insertions, 0 deletions
diff --git a/sysdeps/x86_64/multiarch/strcmp-avx2.S b/sysdeps/x86_64/multiarch/strcmp-avx2.S index 5f88a68..d42b04b 100644 --- a/sysdeps/x86_64/multiarch/strcmp-avx2.S +++ b/sysdeps/x86_64/multiarch/strcmp-avx2.S @@ -591,7 +591,14 @@ L(loop_cross_page_2_vec): movl $(PAGE_SIZE / (VEC_SIZE * 4) - 1), %esi testq %rdi, %rdi +# ifdef USE_AS_STRNCMP + /* At this point, if %rdi value is 0, it already tested + VEC_SIZE*4+%r10 byte starting from %rax. This label + checks whether strncmp maximum offset reached or not. */ + je L(string_nbyte_offset_check) +# else je L(back_to_loop) +# endif tzcntq %rdi, %rcx addq %r10, %rcx /* Adjust for number of bytes skipped. */ @@ -627,6 +634,14 @@ L(loop_cross_page_2_vec): VZEROUPPER ret +# ifdef USE_AS_STRNCMP +L(string_nbyte_offset_check): + leaq (VEC_SIZE * 4)(%r10), %r10 + cmpq %r10, %r11 + jbe L(zero) + jmp L(back_to_loop) +# endif + .p2align 4 L(cross_page_loop): /* Check one byte/dword at a time. */ |