The memory system has become extremely important. Memory is slow, and this is the primary reason that computers don’t run significantly faster than they do. In large-scale computer installations such as the building-sized systems powering Google.com, Amazon.com, and the financial sector, memory is often the largest dollar cost as well as the largest consumer of energy. Consequently, improvements in the memory system can have significant impact on the real world, improving power and energy, performance, and/or dollar cost.
Moreover, many of the problems we see in the memory system are cross-disciplinary in nature—their solution would likely require work at all levels, from applications to circuits.
Our primary goal with MEMSYS is to showcase interesting ideas that will spark conversation between disparate groups—to get applications people and operating systems people and compiler people and system architecture people and interconnect people and circuits people to talk to each other about the problem.