While CPUs sped up tremendously, at least in MHz and throughput terms, over the past three decades, we can't say the same for the memory. In the mid-80's 80286 PC-AT days, the high-end PC memory ran at the same speed as the CPU, up to 12 MHz. Then, six years ago, when the first 1+ GHz PCs came out, the fastest memory on them was 133 MHz SDRAM, with 1/8 the clock of the CPU.Check it out over here.
Now, things look a little better bandwidth-wise, with DDR3 routinely providing throughput at around half the CPU frequency - a 3 GHz Core 2 Extreme may be fed by DDR3-1500 memory, for instance.
However, despite the bandwidth improvements, it is memory latency, the time it takes to write or read the first word in a transfer in particular, that had advanced at a snail's pace all this time. And, it can impact the performance, despite all the caching, streaming and other "optimisations".
What to DRAM latencies mean?
Posted on Saturday, August 11 2007 @ 16:30 CEST by Thomas De Maesschalck
Still wondering what memory latencies like 7-7-7-18 mean? The Inq just wrote an article which explains DRAM latencies: