Titlebook: Architecture of Computing Systems – ARCS 2015; 28th International C Luís Miguel Pinho Pinho,Wolfgang Karl,Uwe Brinksch Conference proceedin

Noctambulant

救护车

四目在模仿

怕失去钱

Evolutionary Multi-Criterion Optimizationstically increase system dependability, even for missions with a very long duration. We present a novel POSIX-compatible filesystem implementation offering memory protection, checksumming and forward error correction.

adulterant

黑豹

Evolutionary Multi-Criterion Optimizationne of the most effective. In this article, we parallelized a classic CNN on a new platform of Intel. Xeon Phi. Coprocessor with OpenMP. Our implementation acquired 131. speedup against the serial version running on the coprocessor itself and 8.3. speedup against the serial baseline on the Xeon. E5-2697 CPU.

Protein

Tomoaki Takagi,Keiki Takadama,Hiroyuki Satotransferred to another node or not. The evaluation results showed that the proposed approach is able to balance the workload between nodes nearly optimal. Moreover, it improves significantly the availability of important services, i.e., the achieved availability was no lower than 85% of the maximum theoretical availability value.

GEAR

Hisao Ishibuchi,Qingfu Zhang,Aimin Zhou to introduce reliability measures and establish End-to-End trust in WSNs. We evaluate our concepts using simulation by adding nodes which try to attack the system. The results show that these malicious nodes can be quickly isolated with low additional effort.

CHAFE

Parallelizing Convolutional Neural Networks on Intel, Many Integrated Core Architecturene of the most effective. In this article, we parallelized a classic CNN on a new platform of Intel. Xeon Phi. Coprocessor with OpenMP. Our implementation acquired 131. speedup against the serial version running on the coprocessor itself and 8.3. speedup against the serial baseline on the Xeon. E5-2697 CPU.

不可侵犯

Trustworthy Self-optimization in Organic Computing Environmentstransferred to another node or not. The evaluation results showed that the proposed approach is able to balance the workload between nodes nearly optimal. Moreover, it improves significantly the availability of important services, i.e., the achieved availability was no lower than 85% of the maximum theoretical availability value.