!気づいたら 7月. 2017年も後半戦がスタート. !メモ * 今度読む Heracles: Improving Resource Efficiency at Scale http://dl.acm.org/citation.cfm?doid=2872887.2749475 * 今度読む CCIX, GEN-Z, OpenCAPI: OVERVIEW & COMPARISON https://www.openfabrics.org/images/eventpresos/2017presentations/213_CCIXGen-Z_BBenton.pdf * 今度読む Software Design Philosophy https://ramcloud.atlassian.net/wiki/display/RAM/Software+Design+Philosophy * Comparing Micron's Automata processor to GPGPU, FPGA and classic co-processors http://www.techradar.com/news/computing-components/processors/comparing-micron-s-automata-processor-to-gpgpu-fpga-and-classic-co-processors-1238086/2 * Automata Computing http://www.cs.utah.edu/~rajeev/stan15.pdf * Micron Automata Processor http://www.hpcuserforum.com/presentations/santafe2014/Micron.pdf * imSitu is a dataset supporting situation recognition http://imsitu.org * Bi-directional Attention Flow Demo https://allenai.github.io/bi-att-flow/demo/ * 今度読む LCNN: Lookup-based Convolutional Neural Network https://arxiv.org/abs/1611.06473 * 今度読む High Level Programming for Heterogeneous Architectures https://arxiv.org/pdf/1408.4964.pdf * 今度読む PRIME: A Novel Processing-in-memory Architecture for Neural Network Computation in ReRAM-based Main Memory https://seal.ece.ucsb.edu/sites/seal.ece.ucsb.edu/files/publications/prime_isca_2016.pdf * 今度読む Cambricon: An Instruction Set Architecture for Neural Networks http://dl.acm.org/citation.cfm?id=3001179 * Embedded Learning Libraryかあ https://github.com/Microsoft/ELL * 今度読む Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation https://arxiv.org/abs/1602.05179