No abstract

The MapReduce model is becoming prominent for the large-scale data analysis in the cloud. In this paper, we present the benchmarking, evaluation and characterization of Hadoop, an open-source implementation of MapReduce. We first introduce HiBench, a new benchmark suite for Hadoop. It consists of a set of Hadoop programs, including both synthetic micro-benchmarks and real-world Hadoop applications. We then evaluate and characterize the Hadoop framework using HiBench, in terms of speed (i.e., job running time), throughput (i.e., the number of tasks completed per minute), HDFS bandwidth, system resource (e.g., CPU, memory and I/O) utilizations, and data access patterns.

The highly active surfaces of Ni-rich cathodes usually result in rapid surface degradation, which is manifested by poor cycle and rate capabilities. In this work, we propose a simple method to restore those degraded surfaces after storage. More importantly, the mechanism of surface degradation and recovery are investigated thoroughly. As storage in moist air, a lithium carbonate (Li 2 CO 3 ) dominated impurity layer formed and tightly coated on the surface of the LiNi 0.70 Co 0.15 Mn 0.15 O 2 particles. Except for the Li 2 CO 3 layer, a NiO rock-salt structure was also found at near surface region by high-resolution transmission electron microscopy. These two inert species together impedance the transport of lithium ions and electrons, which result in no capacity at 4.3 V charge cutoff voltage of the stored material. We proposed a simple and effective method, i.e., three h calcination at 800 °C under oxygen flow. The restored LiNi 0.70 Co 0.15 Mn 0.15 O 2 shows equivalent electrochemical performance compared to the pristine one. This is because the lithium ions in Li 2 CO 3 layer return to the surface lattice of LiNi 0.70 Co 0.15 Mn 0.15 O 2 , and the NiO cubic phase transforms back to the layered structure with the oxidation of Ni 2+ . This method is not only insightful for cathode material design but also beneficial for practical application.

No abstract

Surface degradation is a common challenge for many electrode materials.

Modern network processors employs parallel processing engines (PEs) to keep up with explosive internet packet processing demands. Most network processors further allow processing engines to be organized in a pipelined fashion to enable higher processing throughput and flexibility. In this paper, we present a novel program transformation technique to exploit parallel and pipelined computing power of modern network processors. Our proposed method automatically partitions a sequential packet processing application into coordinated pipelined parallel subtasks which can be naturally mapped to contemporary high-performance network processors. Our transformation technique ensures that packet processing tasks are balanced among pipeline stages and that data transmission between pipeline stages is minimized. We have implemented the proposed transformation method in an auto-partitioning C compiler product for Intel Network Processors. Experimental results show that our method provides impressive speed up for the commonly used NPF IPv4 forwarding and IP forwarding benchmarks. For a 9-stage pipeline, our auto-partitioning C compiler obtained more than 4X speedup for the IPv4 forwarding PPS and the IP forwarding PPS (for both the IPv4 traffic and IPv6 traffic).

No abstract

Lithium (Li) metal anode has attracted tremendous attention for its highest capacity (3860 mAh g–1). Herein, we report that the formation of dead Li can be effectively suppressed through Li plating on porous lithiated graphite lamina (PLGL). A lithiophilic carbon layer was decorated on the lithiophobic basal plane of porous graphite lamina (PGL) with an industry-scalable slurry-coating strategy. Moreover, the higher delithiation potential of PLGL will ensure the complete stripping of the plated Li before its delithiation, thus dramatically enhancing the average Coulombic efficiency (ACE) of Li plating/stripping to 98.5% at a high Li plating/stripping capacity of 2 mAh cm–2 (∼1100 mAh g–1) at 2 mA cm–2. Even at an ultrahigh current density of 4 mA cm–2 (with Li capacity of 4 mAh cm–2 (∼1900 mAh g–1)), the ACE could still be maintained at 96.2% in an ordinary carbonate electrolyte.