No abstract

Abstract. Tropical rain forests are among the most important and least monitored of terrestrial ecosystems. In recent years, their influence on atmospheric concentrations of carbon dioxide and water vapor has become the subject of much speculation. Here we present results from a yearlong study of CO2 fluxes at a tropical forest in central Amazonia, using the micrometeorological technique of eddy covariance. The diurnal cycle of CO2 flux was consistent with previous shortterm studies in tropical rain forests, implying that the Amazonian rain forest shows a fair degree of spatial uniformity in bulk ecophysiological characteristics. Typical peak daytime photosynthesis rates were 24-28 gmol CO2 m -2 s -1, and respiration rates were 6-8 gmol CO2 m -2 s -1. There was significant seasonality in peak photosynthesis over the year, which appeared strongly correlated with soil moisture content. On the other hand, there was no evidence of strong seasonality in soil respiration. Central Amazonia has only a short, 3-month dry season, not atypical of tropical rain forest, and it is therefore likely that large areas o•' Amazonia exhibit significant seasonality in photosynthetic capacity. The gross primary production was calculated to be 30 t C ha -1 yr -1. An analysis of data quality is included in the appendix.

No abstract

No abstract

Evolving technology and increasing pin-bandwidth motivate the use of high-radix routers to reduce the diameter, latency, and cost of interconnection networks. High-radix networks, however, require longer cables than their low-radix counterparts. Because cables dominate network cost, the number of cables, and particularly the number of long, global cables should be minimized to realize an efficient network. In this paper, we introduce the dragonfly topology which uses a group of high-radix routers as a virtual router to increase the effective radix of the network. With this organization, each minimally routed packet traverses at most one global channel. By reducing global channels, a dragonfly reduces cost by 20% compared to a flattened butterfly and by 52% compared to a folded Clos network in configurations with ≥ 16K nodes.We also introduce two new variants of global adaptive routing that enable load-balanced routing in the dragonfly. Each router in a dragonfly must make an adaptive routing decision based on the state of a global channel connected to a different router. Because of the indirect nature of this routing decision, conventional adaptive routing algorithms give degraded performance. We introduce the use of selective virtual-channel discrimination and the use of credit round-trip latency to both sense and signal channel congestion. The combination of these two methods gives throughput and latency that approaches that of an ideal adaptive routing algorithm.