The problem of how to efficiently store and query the clustering results was considered. Three different storage schemas for clustering results using relational database were proposed, namely, full schema (f-schema), ...The problem of how to efficiently store and query the clustering results was considered. Three different storage schemas for clustering results using relational database were proposed, namely, full schema (f-schema), partial schema (p-schema) and compressed schema (c-schema). At the same time, a classification for queries issued to the clustering results was also presented. Finally, we empirically studied the performance of proposed queries on different storage schemas. To our knowledge, this is the first work to address the problem.展开更多
ABC95 array computer is a multi-function network computer based on FPGA technology. A notable feature of ABC95 array computer is the support of complex interconnection, which determines that the computer must have eno...ABC95 array computer is a multi-function network computer based on FPGA technology. A notable feature of ABC95 array computer is the support of complex interconnection, which determines that the computer must have enough I/O band and flexible communications between Pes. The authors designed the interconnecting network chips of ABC95 and realized a form of multi-function interconnection. The multi-function interconnecting network supports conflict-free access from processors to memory matrix and the MESH network of enhanced processors to processor communications. The design scheme has been proved feasible by experiment.展开更多
Indirect association is a high level relationship between items and frequent itemsets in data. Current research approaches on indirect association mining are limited to indirect association between itempairs, which wi...Indirect association is a high level relationship between items and frequent itemsets in data. Current research approaches on indirect association mining are limited to indirect association between itempairs, which will discovertoo many rules from dataset. A formal definition of indirect association between multiple items is presented, along with an algorithm, SET-NIA,for mining this kind of indirect associations based on anti-monotonicity of indirect associations and frequent itempair support matrix. While the found rules contain same information as compared to the rules found by indirect association between itempairs mining algorithms, this notion brings space-saving in storage ofthe rules as well as superiority for human to understand and apply the rules. Experiments conducted on two real-word datasets show that SET-NIA can effectively find fewer rules than existing algorithms which mine indirect association between itempairs, the experimental results also prove that SET-NIA has better performance than existing algorithms.展开更多
Transient fault detection mechanism is added to simultaneous multithreading architecture. By exploiting both ILP (Instruction Level Parallelism) and TLP (Thread Level Parallelism), Simultaneous Multithreading (SMT) Fa...Transient fault detection mechanism is added to simultaneous multithreading architecture. By exploiting both ILP (Instruction Level Parallelism) and TLP (Thread Level Parallelism), Simultaneous Multithreading (SMT) Fault Tolerance Processor can be expected to achieve better tradeoff between performance and hardware cost than traditional Fault Tolerance Processors. Detailed simulations of 3 of SPEC95 benchmarks show that executing two redundant programs on the fault-tolerant microarchitecture takes only 40%–61%longer than running a single version of the program. The new instruction fetch algorithm enhances the performance by 0.4%~1%to most of the benchmarks we choose randomly.展开更多
摘要The problem of how to efficiently store and query the clustering results was considered. Three different storage schemas for clustering results using relational database were proposed, namely, full schema (f-schema), partial schema (p-schema) and compressed schema (c-schema). At the same time, a classification for queries issued to the clustering results was also presented. Finally, we empirically studied the performance of proposed queries on different storage schemas. To our knowledge, this is the first work to address the problem.
摘要ABC95 array computer is a multi-function network computer based on FPGA technology. A notable feature of ABC95 array computer is the support of complex interconnection, which determines that the computer must have enough I/O band and flexible communications between Pes. The authors designed the interconnecting network chips of ABC95 and realized a form of multi-function interconnection. The multi-function interconnecting network supports conflict-free access from processors to memory matrix and the MESH network of enhanced processors to processor communications. The design scheme has been proved feasible by experiment.
摘要Indirect association is a high level relationship between items and frequent itemsets in data. Current research approaches on indirect association mining are limited to indirect association between itempairs, which will discovertoo many rules from dataset. A formal definition of indirect association between multiple items is presented, along with an algorithm, SET-NIA,for mining this kind of indirect associations based on anti-monotonicity of indirect associations and frequent itempair support matrix. While the found rules contain same information as compared to the rules found by indirect association between itempairs mining algorithms, this notion brings space-saving in storage ofthe rules as well as superiority for human to understand and apply the rules. Experiments conducted on two real-word datasets show that SET-NIA can effectively find fewer rules than existing algorithms which mine indirect association between itempairs, the experimental results also prove that SET-NIA has better performance than existing algorithms.
基金Supported by the National Natural Science Funda tion of China (60103002)
摘要Transient fault detection mechanism is added to simultaneous multithreading architecture. By exploiting both ILP (Instruction Level Parallelism) and TLP (Thread Level Parallelism), Simultaneous Multithreading (SMT) Fault Tolerance Processor can be expected to achieve better tradeoff between performance and hardware cost than traditional Fault Tolerance Processors. Detailed simulations of 3 of SPEC95 benchmarks show that executing two redundant programs on the fault-tolerant microarchitecture takes only 40%–61%longer than running a single version of the program. The new instruction fetch algorithm enhances the performance by 0.4%~1%to most of the benchmarks we choose randomly.