June 12th, 2017

I will discuss technologies our group helped develop, including Micron’s Hybrid Memory Cube, flash-based main memories, and high-bandwidth/high-capacity memory; I will discuss the impact these will have on applications and operating systems. Energy and power costs are the primary reasons that our system-wide execution throughput (OPS) is no better than it currently is … while one could staple together 100 Oak Ridge Titans to create an exascale system, not many could afford to pay the resulting electric bill. And yet, a significant amount of research is still focused on increasing processor performance, rather than decreasing power and energy-to-solution. Modern high-performance systems are not throughput-bound; they are power-bound. Processing is so cheap it is effectively free; shaving power and energy costs at every opportunity, and at every level of the system, is the trick. imilarly, memory and communication are the primary reasons that our time-to-solution is no better than it currently is … the memory system is slow; the communication overhead is high; and yet a significant amount of research is still focused on increasing processor performance, rather than decreasing (the cost of) data movement. Modern high-performance systems are not compute-bound; they are data-bound. ALUs are so cheap that some propose to put them out in the memory … processing is free; getting the right data to the right place, cheaply, is the trick. This talk will discuss recent technologies that our group has helped to develop in high-performance systems, including Micron’s Hybrid Memory Cube, flash-based main memories, and high-bandwidth/high-capacity memory, and will discuss the impact of tomorrow’s memory technologies on tomorrow’s applications and operating systems