Searcharxiv⌕ Search

arXiv subjects

John Madden

Publications and source records attributed to John Madden.

2 recordsLinked to original sources

Energy Aware Optimization of Non-Deterministic Task-Based Intermittent Computing Nodes with Thimble

Intermittent computing nodes run on harvested energy, which they store in capacitors and spend in short bursts of computation. Choosing those capacitors is a trade-off: large capacitors can power large tasks but leak more current, wasting harvested energy, while small capacitors leak less but cannot power large tasks. Recent work, LEACS, showed that selecting capacitors and mapping tasks to them at compile time improves inference throughput. However, LEACS optimizes the mapping for a predetermined workload, whereas sensor nodes often run data-dependent workloads in which the next task depends on the outcome of earlier ones. We present Thimble, an energy storage system that maps a node's tasks to capacitors at runtime. Thimble models the workload as a Markov chain over tasks and assigns each task to a capacitor by weighing capacitor leakage, the task's energy demand and, when it replans, the likelihood of each future task. We compare Thimble against a reimplementation of LEACS, which ranks every static plan by simulation. When the training trace resembles deployment, Thimble's single design-time solve comes within 0.3--4% of LEACS's throughput. When the deployment conditions drift from the characteristics of the training set, LEACS's throughput-focused static plans can fail sharply. On the lowest-power source we consider, LEACS's plan stalls on deployment traces that harvest less than its training trace, and on some never wakes; Thimble avoids this, with 22--29% higher throughput at the reference workload. A sensitivity sweep over 25 workload profiles on that source shows that Thimble with depth replanning leads LEACS by 22--42% throughout, and what run-time remapping adds: replanning at a fixed interval matches or improves on the static map at 21 of 25 points, by up to 7%.

cs.NI↗

Eight New Radio Pulsars in the Large Magellanic Cloud

We present the discovery of eight new radio pulsars located in the Large Magellanic Cloud (LMC). Five of these pulsars were found from reprocessing the Parkes Multibeam Survey of the Magellanic Clouds, while the remaining three were from an ongoing new survey at Parkes with a high resolution data acquisition system. It is possible that these pulsars were missed in the earlier processing due to radio frequency interference, visual judgment, or the large number of candidates that must be analysed. One of these new pulsars has a dispersion measure of 273 pc cm$^{-3}$, almost twice the highest previously known value, making it possibly the most distant LMC pulsar. In addition, we present the null result of a radio pulse search of an X-ray point source located in SNR J0047.2$-$7308 in the Small Magellanic Cloud (SMC). Although no millisecond pulsars have been found, these discoveries have increased the known rotation powered pulsar population in the LMC by more than 50%. Using the current sample of LMC pulsars, we used a Bayesian analysis to constrain the number of potentially observable pulsars in the LMC to within a 95% credible interval of 57000$^{+70000}_{-30000}$. The new survey at Parkes is $\sim$20% complete and it is expected to yield at most six millisecond pulsars in the LMC and SMC. Although it is very sensitive to short period pulsars, this new survey provides only a marginal increase in sensitivity to long periods. The limiting luminosity for this survey is 125 mJy kpc$^2$ for the LMC which covers the upper 10% of all known radio pulsars. The luminosity function for normal pulsars in the LMC is consistent with their counterparts in the Galactic disk. The maximum 1400 MHz radio luminosity for LMC pulsars is $\sim 1000$ mJy kpc$^2$.

astro-ph.GA↗