Code generated for a simple memory copy loop

[Narasimha Datta]

Hello,

Here's a simple memory copy macro:

#define MYMEMCOPY(dp, sp, len) \
do { \
        long __len = len; \
        while (--__len >= 0) \
                (dp)[__len] = (sp)[__len]; \
} while (0)

void foo(unsigned char *dp, const unsigned char *sp, unsigned long size) {
        MYMEMCOPY(dp, sp, size);
}

void bar(unsigned char *dp, const unsigned char *sp) {
        MYMEMCOPY(dp, sp, 128);
}

The code fragments generated for the foo and bar functions with -O and -O2 
optimizations respectively is as follows:

/* ===== With -O switch ===== */
/* function foo */
.L4:
        movzbl  -1(%rcx), %eax
        movb    %al, -1(%rdx)
        subq    $1, %rcx
        subq    $1, %rdx
        subq    $1, %r8
        jns     .L4

/* function bar */
        movl    $126, %edx
.L8:
.LBB3:
        .loc 1 13 0
        movzbl  1(%rdx,%rsi), %eax
        movb    %al, 1(%rdx,%rdi)
        subq    $1, %rdx
        cmpq    $-2, %rdx
        jne     .L8

/* ===== With -O2 switch =====*/
/* function foo */
.L4:
        movzbl  -1(%rsi), %eax
        addq    $1, %rdi
        subq    $1, %rsi
        movb    %al, -1(%rcx)
        subq    $1, %rcx
        cmpq    %rdx, %rdi
        jne     .L4

/* function bar */
        movl    $126, %edx
.L9:
.LBB3:
        .loc 1 13 0
        movzbl  1(%rdx,%rsi), %eax
        movb    %al, 1(%rdx,%rdi)
        subq    $1, %rdx
        cmpq    $-2, %rdx
        jne     .L9

Now my questions are:
(i) Why does the compiler generate an addq, cmpq and jne for the foo function 
with -O2? Isn't subq/jns more efficient, as seen from the output from -O?
(ii) For function bar, why is the "cmpq $-2, %rdx" instruction generated? Won't 
it be better to count down from 128 to 0 instead of 126 to -2?

Here's my OS and compiler version (I'm running a 64-bit FreeBSD):
$ uname -a
FreeBSD xxx 7.0-RELEASE FreeBSD 7.0-RELEASE #0: Wed Nov 12 18:54:21 PST 2008    
 r...@wc7:/usr/obj/usr/src/sys/SMKERNEL  amd64
$ cc --version
cc (GCC) 4.2.1 20070719  [FreeBSD]
Copyright (C) 2007 Free Software Foundation, Inc.
This is free software; see the source for copying conditions.  There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

And these are the commands I used to compile the program:
cc -S -O -g test.c
cc -S -O2 -g test.c

Any pointers would be appreciated. Thanks!

Regards,
N Datta



      Add more friends to your messenger and enjoy! Go to 
http://messenger.yahoo.com/invite/