diff options
Diffstat (limited to 'libc/string/arc/strcmp.S')
| -rw-r--r-- | libc/string/arc/strcmp.S | 29 |
1 files changed, 13 insertions, 16 deletions
diff --git a/libc/string/arc/strcmp.S b/libc/string/arc/strcmp.S index ad38d9e00..48d2d7ec1 100644 --- a/libc/string/arc/strcmp.S +++ b/libc/string/arc/strcmp.S @@ -1,5 +1,5 @@ /* - * Copyright (C) 2013, 2014-2015, 2017 Synopsys, Inc. (www.synopsys.com) + * Copyright (C) 2013, 2014-2015, 2017, 2022 Synopsys, Inc. (www.synopsys.com) * Copyright (C) 2007 ARC International (UK) LTD * * Licensed under the LGPL v2.1 or later, see the file COPYING.LIB in this tarball. @@ -7,14 +7,11 @@ #include <features.h> #include <sysdep.h> - -#if !defined(__ARC700__) && !defined(__ARCHS__) -#error "Neither ARC700 nor ARCHS is defined!" -#endif +#include <asm.h> ENTRY(strcmp) -#ifdef __ARC700__ +#if defined(__ARC700__) || defined(__ARC64_ARCH32__) /* This is optimized primarily for the ARC700. It would be possible to speed up the loops by one cycle / word respective one cycle / byte by forcing double source 1 alignment, unrolling @@ -38,7 +35,7 @@ ENTRY(strcmp) breq r2,r3,.Lwordloop #ifdef __LITTLE_ENDIAN__ xor r0,r2,r3 ; mask for difference - sub_s r1,r0,1 + SUBR_S r1,r0,1 bic_s r0,r0,r1 ; mask for least significant difference bit sub r1,r5,r0 xor r0,r5,r1 ; mask for least significant difference byte @@ -55,7 +52,7 @@ ENTRY(strcmp) .Lfound0: xor r0,r2,r3 ; mask for difference or r0,r0,r4 ; or in zero indicator - sub_s r1,r0,1 + SUBR_S r1,r0,1 bic_s r0,r0,r1 ; mask for least significant difference bit sub r1,r5,r0 xor r0,r5,r1 ; mask for least significant difference byte @@ -99,31 +96,28 @@ ENTRY(strcmp) .Lcmpend: j_s.d [blink] sub r0,r2,r3 -#endif /* __ARC700__ */ -#ifdef __ARCHS__ +#elif defined(__ARCHS__) or r2, r0, r1 bmsk_s r2, r2, 1 brne r2, 0, @.Lcharloop ;;; s1 and s2 are word aligned - ld.ab r2, [r0, 4] mov_s r12, 0x01010101 ror r11, r12 .align 4 .LwordLoop: + ld.ab r2, [r0, 4] + sub r4, r2, r12 ld.ab r3, [r1, 4] ;; Detect NULL char in str1 - sub r4, r2, r12 - ld.ab r5, [r0, 4] bic r4, r4, r2 and r4, r4, r11 brne.d.nt r4, 0, .LfoundNULL ;; Check if the read locations are the same cmp r2, r3 - beq.d .LwordLoop - mov.eq r2, r5 + beq .LwordLoop ;; A match is found, spot it out #ifdef __LITTLE_ENDIAN__ @@ -168,7 +162,10 @@ ENTRY(strcmp) .Lcmpend: j_s.d [blink] sub r0, r2, r3 -#endif /* __ARCHS__ */ + +#else +#error "Unsupported ARC CPU type" +#endif END(strcmp) libc_hidden_def(strcmp) |