diff options
| -rw-r--r-- | sysdeps/x86_64/multiarch/strcmp-evex.S | 26 |
1 files changed, 13 insertions, 13 deletions
diff --git a/sysdeps/x86_64/multiarch/strcmp-evex.S b/sysdeps/x86_64/multiarch/strcmp-evex.S index 06730ab2a1..cea034f394 100644 --- a/sysdeps/x86_64/multiarch/strcmp-evex.S +++ b/sysdeps/x86_64/multiarch/strcmp-evex.S @@ -209,7 +209,9 @@ returned. */ .section SECTION(.text), "ax", @progbits - .align 16 + /* Align 64 bytes here. This is to get the L(loop) block ideally + aligned for the DSB. */ + .align 64 .type STRCMP, @function .globl STRCMP # ifdef USE_AS_STRCASECMP_L @@ -509,9 +511,7 @@ L(ret4): ret # endif - /* 32 byte align here ensures the main loop is ideally aligned - for DSB. */ - .p2align 5 + .p2align 4,, 4 L(more_3x_vec): /* Safe to compare 4x vectors. */ VMOVU (VEC_SIZE)(%rdi), %VMM(0) @@ -1426,10 +1426,9 @@ L(less_32_till_page): L(ret_zero_page_cross_slow_case0): xorl %eax, %eax ret -# endif - - +# else .p2align 4,, 10 +# endif L(less_16_till_page): cmpl $((VEC_SIZE - 8) / SIZE_OF_CHAR), %eax ja L(less_8_till_page) @@ -1482,8 +1481,12 @@ L(less_16_till_page): # endif jmp L(prepare_loop_aligned) - - +# ifndef USE_AS_STRNCMP + /* Fits in aligning bytes. */ +L(ret_zero_4_loop): + xorl %eax, %eax + ret +# endif .p2align 4,, 10 L(less_8_till_page): @@ -1554,6 +1557,7 @@ L(ret_less_8_wcs): # ifdef USE_AS_STRNCMP .p2align 4,, 2 +L(ret_zero_4_loop): L(ret_zero_page_cross_slow_case1): xorl %eax, %eax ret @@ -1586,10 +1590,6 @@ L(less_4_loop): subq $-(CHAR_PER_VEC * 4), %rdx # endif jmp L(prepare_loop_aligned) - -L(ret_zero_4_loop): - xorl %eax, %eax - ret L(ret_less_4_loop): xorl %r8d, %eax subl %r8d, %eax |