🚀 go-pugleaf

I have some code like the following which I am using on a Sun Sparc:

    #define SIZE 100000

    int inner(xp, yp, n)
    int *xp, *yp, n;
    {
	int *ep, v;

	v = 0;
	ep = xp + n;

	while (xp < ep)
	    v ^= *xp++ & *yp++;

	return v;
    }

    main()
    {
	int i, x[SIZE], y[SIZE], s;

	for (i = 0; i < SIZE; i++)
	{
	    x[i] = rand();
	    y[i] = rand();
	}

	s = 0;
	for (i = 0; i < 200; i++)
	    s += inner(x, y, SIZE);

	printf("%d\n", s);
    }

The code produced by gcc seems to be slower than that produced by
the Sun compiler /bin/cc (on my machine the Sun code takes an average
of about 6.9 seconds compared to 8.3 for gcc).

The assembly code produced for the function inner() is as follows:

gcc -O2 -funroll-loops:

_inner:
	!#PROLOGUE# 0
	!#PROLOGUE# 1
	sll %o2,2,%o2
	add %o0,%o2,%o2
	cmp %o0,%o2
	bgeu L3
	mov 0,%o3
L4:
	ld [%o1],%g3
	ld [%o0],%g2
	add %o1,4,%o1
	add %o0,4,%o0
	cmp %o0,%o2
	and %g2,%g3,%g2
	blu L4
	xor %o3,%g2,%o3
L3:
	retl
	mov %o3,%o0


cc -O4:

_inner:
!#PROLOGUE# 0
!#PROLOGUE# 1
	save	%sp,-64,%sp
	sll	%i2,2,%i2
	add	%i0,%i2,%i2
	cmp	%i0,%i2
	bcc	L77006
	mov	0,%i5
	add	%i0,12,%o2
	cmp	%o2,%i2
	bcc,a	LY2
	ld	[%i0],%i4
L77003:
	ld	[%i0],%o3
	ld	[%i0+4],%o7
	ld	[%i0+8],%l2
	ld	[%i0+12],%l5
	ld	[%i1],%o4
	ld	[%i1+4],%l0
	ld	[%i1+8],%l3
	ld	[%i1+12],%l6
	and	%o3,%o4,%o3
	xor	%i5,%o3,%i5
	and	%o7,%l0,%o7
	inc	16,%i0
	add	%i0,12,%i3
	xor	%i5,%o7,%i5
	and	%l2,%l3,%l2
	xor	%i5,%l2,%i5
	cmp	%i3,%i2
	and	%l5,%l6,%l5
	inc	16,%i1
	blu	L77003
	xor	%i5,%l5,%i5
	cmp	%i0,%i2
	bcc	L77006
	nop
L77010:
	ld	[%i0],%i4
LY2:					! [internal]
	ld	[%i1],%o0
	inc	4,%i0
	cmp	%i0,%i2
	and	%i4,%o0,%i4
	inc	4,%i1
	bcs	L77010
	xor	%i5,%i4,%i5
L77006:
	ret
	restore	%g0,%i5,%o0


It seems that the Sun compiler unfolds the loop much better by
handling 4 ints at a time instead of just 1 which gcc does.

I have -O2 and -funroll-loops turned on - I believe they give
the most optimization and yet gcc is not unrolling the loop
like the Sun compiler does!

Does anyone have any ideas why this is so?

Allan
--
+------------------------------------------------------------+
| Allan Steel                          allan@maths.su.oz.au  |
| School of Mathematics and Statistics, University of Sydney |
+------------------------------------------------------------+