@Max: "Up until now, DRAM memory ICs presented in DDR3/DDR4 memory modules have offered the optimum tradeoffs among capacity, performance, and power consumption. Though these memory subsystems are incredibly sophisticated, they are not keeping up with today's state-of-the-art application requirements"
In fact, beyond the polemics about Moore's Law being valid or not today, the truth is that memory technology has had a lot of problems to keep the pace with logic/processing performance growth -- the bandwidth just doesn't scale so good!!
Can you imagine if programmable logic starts to be embedded as "slices" into the memory cubes?? There would be endless possibilities for such a "magic dice"!!
> "Can you imagine if programmable logic starts to be embedded as "slices" into the memory cubes?? There would be endless possibilities for such a "magic dice"!!"
I wholeheartedly agree. I look forward to getting my hands on some hypercube hardware, even if it is still external to the FPGA package. It looks like Altera may be the first one 'out of the gate' with hypercube support, but Xilinx is also a member of the consortium, so I look forward to their first press release as well!
It's time things change a little after such a long waiting time. When I started with this stuff we had logic, processors, RAM and ROM ... and that's still what we have today. After 30 years ... I'm doing image processing and thought there might come a time where you get an imaging sensor, DSP and memory in a single package and by memory I mean something like FRAM or MRAM, something you can switch on and off without bothering, no refreshing required, etc. ... Well, I know there are some small devices of that kind, mostly application specific, so a normal person duing project work can't get his hand on them, or they can't be used for long-term products as they vanish as fast as they appear ... So for me it's time to see something really new and 3D stacking of dies has been in the wings for way too long. It's like high-resolution TV - heard it in the 80s, saw in in the 90s, could buy it in the 2000's ...
Replay available now: A handful of emerging network technologies are competing to be the preferred wide-area connection for the Internet of Things. All claim lower costs and power use than cellular but none have wide deployment yet. Listen in as proponents of leading contenders make their case to be the metro or national IoT network of the future. Rick Merritt, EE Times Silicon Valley Bureau Chief, moderators this discussion. Join in and ask his guests questions.