[update benchmark comments
peter@cordes.ca**20080315060309] {
hunk ./rshift.asm 75
-C AMD K8, movhlps version
-C size 496		3.048		cycles/limb
+C AMD K8 (Opteron 2218)
+C size 1		15.938		cycles
+C size 496		3.044		cycles/limb
hunk ./rshift.asm 79
+C Core 2 Conroe (2.4GHz)
+C size 1		12.224		cycles  (11.968 with pxor after the loop)
+C size 4		6.420		cycles  (4.0 with movdqa ; shufpd version uncommented instead.)
+C size 496		2.036-2.068	cycles/limb
+
+C Core 2 Harpertown (2.8GHz)
+C size 1		12.049		cycles
+C size 496		2.062		cycles/limb
}