Preserving Virtual Memory by Mitigating the Address Translation Wall

Abstract

Successfully preserving virtual memory will require rearchitecting the hardware-software interface so that these layers operate in tandem, rather than at odds with one another. Encouragingly, there is evidence that both chip vendors and OS designers are willing to innovate at this layer, as seen by a recent implementation of CPU TLB coalescing techniques and rapid changes in GPU address-translation hardware. But several important open problems persist, and new ones are presenting themselves rapidly. As just one example, a recent work by Javier Picorel and colleagues looks at the challenges posed by address translation on near-memory accelerators. The bottom line is that these trends present both an opportunity and a challenge for researchers in computer systems. The evolving landscape of hardware and software means that virtual memory abstraction is in flux, but also that simple mechanisms to mitigate the address translation wall are likely to be useful to real-world systems and products.