Quality-Configurable Memory Hierarchy Through Approximation

The memory subsystem is a major contributor to the overall performance and energy consumption of embedded computing platforms. The emergence of "killer" applications such as data-intensive recognition, mining, and synthesis (RMS) applications puts even more stress on the memory subsystem and exacerbates its energy consumption. Traditional mechanisms to ensure data integrity deploy overdesign (e.g., redundancy and error detection/correction) and/or guardbanding that consumes a signi cant part of the energy consumed in the memory subsystem. We explore opportunities for energy e ciency by exploiting the intrinsic tolerance of a vast class of approximate computing applications to some level of error in the on-chip memory hierarchy. We present two exemplars outlining the typical software and hardware mechanisms that are required for di erent components in the memory hierarchy, implemented in varying technologies such as SRAM and STT-MRAM.