Architecture exploration for ambient energy harvesting nonvolatile processors

Abstract

Energy harvesting has been widely investigated as a promising method of providing power for ultra-low-power applications. Such energy sources include solar energy, radiofrequency (RF) radiation, piezoelectricity, thermal gradients, etc. However, the power supplied by these sources is highly unreliable and dependent upon ambient environment factors. Hence, it is necessary to develop specialized systems that are tolerant to this power variation, and also capable of making forward progress on the computation tasks. The simulation platform in this paper is calibrated using measured results from a fabricated nonvolatile processor and used to explore the design space for a nonvolatile processor with different architectures, different input power sources, and policies for maximizing forward progress.

Optimal checkpointing for secure intermittently-powered IoT devices

“…Checkpointing has also been used to guarantee forward progress in intermittently powered devices [6], [12]- [14], [19], [20]. Mementos [20] inserts trigger points in the software at compile time and, at run time, checkpoints when the stored energy level falls below a threshold at a trigger point.…”

“…The quantized power over the six levels is shown in Fig 5b. Once the transition matrix and the transition probability matrix is obtained, we can use the Markov chain model to obtain new synthetic power traces. An example of a synthetic power trace generated using this model is shown in Fig 5c. We assume a battery with a 2 µJ capacity which is smaller than the ≈ 20µJ battery assumed in QuickRecall [14] but larger than the ≈ 0.5µJ capacity in [6]. Table I shows the estimated energy consumption for different components of our system, the average incoming energy, and battery parameters.…”

“…The processor is then turned off and restored only when the battery level exceeds another threshold, which is at least the amount of energy required to read and decrypt data from the nonvolatile memory plus the energy to perform a checkpoint. The policy is conservative in that it accumulates the energy required to perform a full checkpoint in battery before starting the [12] and conservative policies [6], [13]. For each testbench, runtime is normalized with respect to the baseline execution time (without energy failure) for that testbench.…”

“…The amount of energy harvested is highly time varying and the energy supply is intermittent. For this reason, processors with off-chip nonvolatile main memory (and potentially even on-chip caches and register files) have been proposed [1], [6] to guarantee forward progress of program execution. In these approaches, the processor saves its intermediate results in non-volatile memory when the energy supply is too low for the processor to operate.…”

Invited - Energy harvesting and transient computing

“…However, as read/write operations to NVM typically consume more power than their volatile counterparts, the steady-state consumption increases [7]. Recent attempts overcome such limitations using a non-volatile processor, which have no volatile state to checkpoint at all [8]. …”