diff options
Diffstat (limited to 'sysdeps/powerpc/powerpc64/power8/strcmp.S')
| -rw-r--r-- | sysdeps/powerpc/powerpc64/power8/strcmp.S | 40 |
1 files changed, 15 insertions, 25 deletions
diff --git a/sysdeps/powerpc/powerpc64/power8/strcmp.S b/sysdeps/powerpc/powerpc64/power8/strcmp.S index 4d6c477194..15e7351d1b 100644 --- a/sysdeps/powerpc/powerpc64/power8/strcmp.S +++ b/sysdeps/powerpc/powerpc64/power8/strcmp.S @@ -1,5 +1,5 @@ /* Optimized strcmp implementation for PowerPC64/POWER8. - Copyright (C) 2015-2016 Free Software Foundation, Inc. + Copyright (C) 2015-2018 Free Software Foundation, Inc. This file is part of the GNU C Library. The GNU C Library is free software; you can redistribute it and/or @@ -18,6 +18,10 @@ #include <sysdep.h> +#ifndef STRCMP +# define STRCMP strcmp +#endif + /* Implements the function size_t [r3] strcmp (const char *s1 [r3], const char *s2 [r4]) @@ -27,24 +31,24 @@ 64K as default, the page cross handling assumes minimum page size of 4k. */ -EALIGN (strcmp, 4, 0) +ENTRY_TOCLESS (STRCMP, 4) li r0,0 - /* Check if [s1]+32 or [s2]+32 will cross a 4K page boundary using + /* Check if [s1]+16 or [s2]+16 will cross a 4K page boundary using the code: (((size_t) s1) % PAGE_SIZE > (PAGE_SIZE - ITER_SIZE)) - with PAGE_SIZE being 4096 and ITER_SIZE begin 32. */ + with PAGE_SIZE being 4096 and ITER_SIZE begin 16. */ rldicl r7,r3,0,52 rldicl r9,r4,0,52 - cmpldi cr7,r7,4096-32 + cmpldi cr7,r7,4096-16 bgt cr7,L(pagecross_check) - cmpldi cr5,r9,4096-32 + cmpldi cr5,r9,4096-16 bgt cr5,L(pagecross_check) - /* For short string up to 32 bytes, load both s1 and s2 using + /* For short string up to 16 bytes, load both s1 and s2 using unaligned dwords and compare. */ ld r8,0(r3) ld r10,0(r4) @@ -60,25 +64,11 @@ EALIGN (strcmp, 4, 0) orc. r9,r12,r11 bne cr0,L(different_nocmpb) - ld r8,16(r3) - ld r10,16(r4) - cmpb r12,r8,r0 - cmpb r11,r8,r10 - orc. r9,r12,r11 - bne cr0,L(different_nocmpb) - - ld r8,24(r3) - ld r10,24(r4) - cmpb r12,r8,r0 - cmpb r11,r8,r10 - orc. r9,r12,r11 - bne cr0,L(different_nocmpb) - - addi r7,r3,32 - addi r4,r4,32 + addi r7,r3,16 + addi r4,r4,16 L(align_8b): - /* Now it has checked for first 32 bytes, align source1 to doubleword + /* Now it has checked for first 16 bytes, align source1 to doubleword and adjust source2 address. */ rldicl r9,r7,0,61 /* source1 alignment to doubleword */ subf r4,r9,r4 /* Adjust source2 address based on source1 @@ -253,5 +243,5 @@ L(pagecross_retdiff): L(pagecross_nullfound): li r3,0 b L(pagecross_retdiff) -END (strcmp) +END (STRCMP) libc_hidden_builtin_def (strcmp) |