/*
 * Written by J.T. Conklin <jtc@NetBSD.org>.
 * Public domain.
 */

#include <machine/asm.h>

#if defined(LIBC_SCCS)
        RCSID("$NetBSD: strncmp.S,v 1.4 2014/05/22 15:01:57 uebayasi Exp $")
#endif

/*
 * NOTE: I've unrolled the loop eight times: large enough to make a
 * significant difference, and small enough not to totally trash the
 * cache.
 */

ENTRY(strncmp)
        testq   %rdx,%rdx
        jmp     L2                      /* Jump into the loop! */

L1:     incq    %rdi
        incq    %rsi
        decq    %rdx
L2:     jz      L4                      /* strings are equal */
        movb    (%rdi),%al
        testb   %al,%al
        jz      L3
        cmpb    %al,(%rsi)
        jne     L3

        incq    %rdi
        incq    %rsi
        decq    %rdx
        jz      L4
        movb    (%rdi),%al
        testb   %al,%al
        jz      L3
        cmpb    %al,(%rsi)
        jne     L3

        incq    %rdi
        incq    %rsi
        decq    %rdx
        jz      L4
        movb    (%rdi),%al
        testb   %al,%al
        jz      L3
        cmpb    %al,(%rsi)
        jne     L3

        incq    %rdi
        incq    %rsi
        decq    %rdx
        jz      L4
        movb    (%rdi),%al
        testb   %al,%al
        jz      L3
        cmpb    %al,(%rsi)
        jne     L3

        incq    %rdi
        incq    %rsi
        decq    %rdx
        jz      L4
        movb    (%rdi),%al
        testb   %al,%al
        jz      L3
        cmpb    %al,(%rsi)
        jne     L3

        incq    %rdi
        incq    %rsi
        decq    %rdx
        jz      L4
        movb    (%rdi),%al
        testb   %al,%al
        jz      L3
        cmpb    %al,(%rsi)
        jne     L3

        incq    %rdi
        incq    %rsi
        decq    %rdx
        jz      L4
        movb    (%rdi),%al
        testb   %al,%al
        jz      L3
        cmpb    %al,(%rsi)
        jne     L3

        incq    %rdi
        incq    %rsi
        decq    %rdx
        jz      L4
        movb    (%rdi),%al
        testb   %al,%al
        jz      L3
        cmpb    %al,(%rsi)
        je      L1

L3:     movzbl  (%rdi),%eax             /* unsigned comparison */
        movzbl  (%rsi),%ecx
        subl    %ecx,%eax
        ret
L4:     xorl    %eax,%eax
        ret
END(strncmp)