> We are *comparing* implementations on the same machine, with the
same<br />&gt; array, with the same simple access patterns and averaging
the running times<br />&gt; over 1000 runs. I even toggled which test runs
first or second. IF the L1<br />&gt; cache misses are an issue, that would
slow *both* down, so multi_array<br />&gt; must be EVEN WORSE than the
test times showed right?<br />I wans't speaking of L1 cache miss on this
particuliar test sorry for the inconvenience<br /><br />&gt; I think the
conclusion is that the pointer based approach has a<br />&gt; significant
(up to20 times on my system) performance improvement over <br />&gt;
base+index approach (at least as implemented by multi_array).<br />Yes I
came to the same conclusion. I was just pointing the fatc that the
base+pointer is not the only way to do something (see my attachment in my
previous post)<br /><br />Again sorry for our misandurstanding