Publications

As computation scales downward in area, the limitations imposed by the batteries required to power that computation become more pronounced. Thus, many future devices will forgo batteries and harvest energy from their environment. Harvested energy, with its frequent power cycles, is at odds with current models of long-running computation. To enable the correct execution of long-running applications on harvested energy-without requiring specialpurpose hardware or programmer intervention-we propose Ratchet. Ratchet is a compiler that adds lightweight checkpoints to unmodified programs that allow existing programs to execute across power cycles correctly. Ratchet leverages the idea of idempotency, decomposing programs into a continuous stream of re-executable sections connected by lightweight checkpoints, stored in non-volatile memory. We implement Ratchet on top of LLVM, targeted at embedded systems with highperformance non-volatile main memory. Using eight embedded systems benchmarks, we show that Ratchet correctly stretches program execution across frequent, random power cycles. Experimental results show that Ratchet enables a range of existing programs to run on intermittent power, with total run-time overhead averaging below 60%-comparable to approaches that require hardware support or programmer intervention.

With the continued reduction in size and cost of computing, power becomes an increasingly heavy burden on system designers for embedded applications. While energy harvesting techniques are an increasingly desirable solution for many deeply embedded applications where size and lifetime are a priority, previous work has shown that energy harvesting provides insufficient power for long running computation. We present Ratchet, which to the authors knowledge is the first automatic, software-only checkpointing system for energy harvesting platforms. We show that Ratchet provides a means to extend computation across power cycles, consistent with those experienced by energy harvesting devices. We demonstrate the correctness of our system under frequent failures and show that it has an average overhead of 58.9% across a suite of benchmarks representative for embedded applications.

Abstract not provided.