mov ar.lc = r16
.L28:
[.L3:]
[.L2:]
        ...
// The loop is unrolled, and the address givs are splitted. 
// Register r14, r8, r3, r35, r33, r31,r28, r29 is used to
// caculate the address of each array element respectively.
	.mmi
	ldfd f38 = [r14]
	ldfd f39 = [r8]
	add r31 = r34, r23
	.mmi
	ldfd f35 = [r3]
	ldfd f37 = [r35]
	add r33 = r34, r24
	;;
	.mmb
	ldfd f33 = [r33]
	ldfd f34 = [r31]
	nop 0
	.mmi
	add r28 = r30, r23
	add r29 = r30, r24
	adds r22 = 4, r22
	;;
	.mmf
	ldfd f32 = [r29]
	ldfd f15 = [r28]
	fma.d f36 = f38, f39, f14
	;;
	.mmf
	nop 0
	nop 0
	fma.d f13 = f35, f37, f36
	;;
	.mmf
	nop 0
	nop 0
	fma.d f12 = f33, f34, f13
	;;
	.mfb
	nop 0
	fma.d f14 = f32, f15, f12
	br.cloop.sptk.few .L28
	;;
.L9:
	.mfb
	stfd [r32] = f14
	nop 0
	nop 0
        ...
	.endp dot_product__#
	.ident	"GCC: (GNU) 3.5-tree-ssa 20031221 (CCRG)"