In order to classify packet, we propose a novel IP classification based the non-collision hash and jumping table trie-tree (NHJTTT) algorithm, which is based on noncollision hash Trie-tree and Lakshman and Stiliadis p...In order to classify packet, we propose a novel IP classification based the non-collision hash and jumping table trie-tree (NHJTTT) algorithm, which is based on noncollision hash Trie-tree and Lakshman and Stiliadis proposing a 2-dimensional classification algorithm (LS algorithm). The core of algorithm consists of two parts: structure the non-collision hash function, which is constructed mainly based on destination/source port and protocol type field so that the hash function can avoid space explosion problem; introduce jumping table Trie-tree based LS algorithm in order to reduce time complexity. The test results show that the classification rate of NHJTTT algorithm is up to 1 million packets per second and the maximum memory consumed is 9 MB for 10 000 rules. Key words IP classification - lookup algorithm - trie-tree - non-collision hash - jumping table CLC number TN 393.06 Foundation item: Supported by the Chongqing of Posts and Telecommunications Younger Teacher Fundation (A2003-03).Biography: SHANG Feng-jun (1972-), male, Ph.D. candidate, lecture, research direction: the smart instrument and network.展开更多
The explosively developed era of big-data compels the increasing demand of nonvolatile memory with high efficiency and excellent storage properties.Herein,we fabricated a high-speed photoelectric multilevel memory dev...The explosively developed era of big-data compels the increasing demand of nonvolatile memory with high efficiency and excellent storage properties.Herein,we fabricated a high-speed photoelectric multilevel memory device for neuromorphic computing.The novel two-dimensional(2D)MoSSe with a unique Janus structure was employed as the channel,and the stack of Al_(2)O_(3)/black phosphorus quantum dots(BPQDs)/Al_(2)O_(3)was adopted as the dielectric.The storage performance of the resulting memory could be verified by the endurance and retention tests,in which the device could remain stable states of programming and erasing even after 1,000 cycles and 1,000 s.The multibit storage could be realized through both different voltage amplitudes and pulse numbers,which could achieve 6 bits(64 distinguishable levels)under pulse width of 50 ns.Furthermore,our memory device also could realize the simulations of synapses in human brain with optical and electric modulations synergistically,such as excitatory post-synaptic current(EPSC),long-term potentiation/depression(LTP/LTD),and spike-timing-dependent plasticity(STDP).Neuromorphic computing was successfully achieved through a high recognition of handwritten digits up to 92.5%after 103 epochs.This research is a promising avenue for the future development of efficient memory and artificial neural network systems.展开更多
文摘In order to classify packet, we propose a novel IP classification based the non-collision hash and jumping table trie-tree (NHJTTT) algorithm, which is based on noncollision hash Trie-tree and Lakshman and Stiliadis proposing a 2-dimensional classification algorithm (LS algorithm). The core of algorithm consists of two parts: structure the non-collision hash function, which is constructed mainly based on destination/source port and protocol type field so that the hash function can avoid space explosion problem; introduce jumping table Trie-tree based LS algorithm in order to reduce time complexity. The test results show that the classification rate of NHJTTT algorithm is up to 1 million packets per second and the maximum memory consumed is 9 MB for 10 000 rules. Key words IP classification - lookup algorithm - trie-tree - non-collision hash - jumping table CLC number TN 393.06 Foundation item: Supported by the Chongqing of Posts and Telecommunications Younger Teacher Fundation (A2003-03).Biography: SHANG Feng-jun (1972-), male, Ph.D. candidate, lecture, research direction: the smart instrument and network.
基金the National Natural Science Foundation of China(NSFC)(Nos.92064009,61904033,and 62004044)Shanghai Rising-Star Program(No.19QA1400600)+1 种基金the Program of Shanghai Subject Chief Scientist(No.18XD1402800)the Support Plans for the Youth Top-Notch Talents of China,and the National Postdoctoral Program for Innovative Talents(No.BX2021070).
文摘The explosively developed era of big-data compels the increasing demand of nonvolatile memory with high efficiency and excellent storage properties.Herein,we fabricated a high-speed photoelectric multilevel memory device for neuromorphic computing.The novel two-dimensional(2D)MoSSe with a unique Janus structure was employed as the channel,and the stack of Al_(2)O_(3)/black phosphorus quantum dots(BPQDs)/Al_(2)O_(3)was adopted as the dielectric.The storage performance of the resulting memory could be verified by the endurance and retention tests,in which the device could remain stable states of programming and erasing even after 1,000 cycles and 1,000 s.The multibit storage could be realized through both different voltage amplitudes and pulse numbers,which could achieve 6 bits(64 distinguishable levels)under pulse width of 50 ns.Furthermore,our memory device also could realize the simulations of synapses in human brain with optical and electric modulations synergistically,such as excitatory post-synaptic current(EPSC),long-term potentiation/depression(LTP/LTD),and spike-timing-dependent plasticity(STDP).Neuromorphic computing was successfully achieved through a high recognition of handwritten digits up to 92.5%after 103 epochs.This research is a promising avenue for the future development of efficient memory and artificial neural network systems.
