can anyone direct me to a good reference for this? i haven't been able to google up anything really useful. when i prefetch the data to be processed in future iterations, i get no improvement. i can't tell if the vs optimizer is brewing in prefetches, or if i am just not doing it right. this isn't something i know a lot about, so some more illustrative/didactic reading material would be really helpful.
The CPU is pretty good at predicting prefetches on its own. You only need explicit prefetch when the CPU gets it wrong a lot.
that was the conclusion i was coming to, especially since i am essentially always doing sequential access. the best i was able to do was not make it worse.
i did find this, however: