mov ar.lc = r14
.L4:
// Loop is unrolled, but the address givs are not splitted.
// Register r17, r19 is used to calculate all the addresses
// of the array elements.
	.mmb
	ldfd f7 = [r17]
	ldfd f6 = [r19]
	nop 0
	.mmi
	add r17 = r15, r33
	add r19 = r15, r34
	shladd r15 = r18, 3, r0
	;;
	.mmf
	nop 0
	nop 0
	fma.d f8 = f7, f6, f9
	.mmi
	ldfd f7 = [r17]
	ldfd f6 = [r19]
	add r17 = r15, r33
	.mfi
	add r19 = r15, r34
	nop 0
	shladd r15 = r16, 3, r0
	;;
	.mmf
	nop 0
	nop 0
	fma.d f8 = f7, f6, f8
	.mmi
	ldfd f7 = [r17]
	ldfd f6 = [r19]
	add r17 = r15, r33
	.mmb
	nop 0
	add r19 = r15, r34
	nop 0
	;;
	.mmf
	nop 0
	nop 0
	fma.d f8 = f7, f6, f8
	.mmb
	ldfd f7 = [r17]
	ldfd f6 = [r19]
	nop 0
	;;
	.mmf
	nop 0
	nop 0
	fma.d f8 = f7, f6, f8
	;;
	.mfb
	nop 0
	mov f9 = f8
	br.cloop.sptk.few .L4
        ...
	.endp dot_product__#
	.ident	"GCC: (GNU) 4.1.0 20050302 (experimental)"