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
为研究异构多核片上系统(multi-processor system on chip,MPSoC)在密集并行计算任务中的潜力,文章设计并实现了一种适用于粗粒度数据特征、面向任务级并行应用的异构多核系统动态调度协处理器,采用了片上缓存、任务输出的多级写回管理...为研究异构多核片上系统(multi-processor system on chip,MPSoC)在密集并行计算任务中的潜力,文章设计并实现了一种适用于粗粒度数据特征、面向任务级并行应用的异构多核系统动态调度协处理器,采用了片上缓存、任务输出的多级写回管理、任务自动映射、通讯任务乱序执行等机制。实验结果表明,该动态调度协处理器不仅能够实现任务级乱序执行等基本设计目标,还具有极低的调度开销,相较于基于动态记分牌算法的调度器,运行多个子孔径距离压缩算法的时间降低达17.13%。研究结果证明文章设计的动态调度协处理器能够有效优化目标场景下的任务调度效果。展开更多
Thread level speculation provides not only a simple parallel programming model,but also an effective mech-anism for thread-level parallelism exploitation.The performance of software speculative parallel models is limi...Thread level speculation provides not only a simple parallel programming model,but also an effective mech-anism for thread-level parallelism exploitation.The performance of software speculative parallel models is limited by high global overheads caused by different types of loops.These loops usually have different characteristics of dependencies and different requirements of optimization strategies.In this paper,we propose three comprehensive optimization techniques to reduce different factors of global overheads,aiming at requirements from different types of loops.Inter-thread fetching can reduce the high mis-speculation rate of the loops with frequent dependencies and out-of-order committing can reduce the control overhead of the loops with infrequent dependencies,while enhanced dynamic task granularity resizing can reduce the control overhead and optimize the global overhead of the loops with changing characteristics of dependencies.All these three optimization techniques have been implemented in HEUSPEC~a software TLS system.Experimental results indicate that they can satisfy tile demands from different groups of benchmarks.The combination of these techniques can improve the performance of all benchmarks and reach a higher average speedup.展开更多
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.
摘要为研究异构多核片上系统(multi-processor system on chip,MPSoC)在密集并行计算任务中的潜力,文章设计并实现了一种适用于粗粒度数据特征、面向任务级并行应用的异构多核系统动态调度协处理器,采用了片上缓存、任务输出的多级写回管理、任务自动映射、通讯任务乱序执行等机制。实验结果表明,该动态调度协处理器不仅能够实现任务级乱序执行等基本设计目标,还具有极低的调度开销,相较于基于动态记分牌算法的调度器,运行多个子孔径距离压缩算法的时间降低达17.13%。研究结果证明文章设计的动态调度协处理器能够有效优化目标场景下的任务调度效果。
基金supported by the National High Technology Research and Development 863 Program of China under Grant No.2012AA010905the National Natural Science Foundation of China under Grant Nos.61272143 and 61472431.
摘要Thread level speculation provides not only a simple parallel programming model,but also an effective mech-anism for thread-level parallelism exploitation.The performance of software speculative parallel models is limited by high global overheads caused by different types of loops.These loops usually have different characteristics of dependencies and different requirements of optimization strategies.In this paper,we propose three comprehensive optimization techniques to reduce different factors of global overheads,aiming at requirements from different types of loops.Inter-thread fetching can reduce the high mis-speculation rate of the loops with frequent dependencies and out-of-order committing can reduce the control overhead of the loops with infrequent dependencies,while enhanced dynamic task granularity resizing can reduce the control overhead and optimize the global overhead of the loops with changing characteristics of dependencies.All these three optimization techniques have been implemented in HEUSPEC~a software TLS system.Experimental results indicate that they can satisfy tile demands from different groups of benchmarks.The combination of these techniques can improve the performance of all benchmarks and reach a higher average speedup.
摘要随着基于高层体系结构HLA(High Level Architecture)仿真应用的不断深入,系统仿真规模不断扩大,仿真模型越来越复杂,仿真节点之间的交互更加频繁,使得仿真系统对通信资源与计算资源的需求不断提高。多核集群能够提供数据并行处理和高效通信的性能潜力,因此通过在多核集群上进行仿真加速正成为提高HLA仿真运行效率的重要途径。然而传统的仿真运行支撑平台RTI(Run Time Infrastructure)主要面向分布式网络环境,一般不支持并行通信和消息并行处理,从而难以发挥多核集群的高效通信和并行计算的性能优势。因此,为了提高多核集群下大规模HLA仿真的运行效率,提出了基于多通道的并行通信结构和基于消息分类的多线程处理技术,并已经应用于正在开发的并行shmRTI中,与国际同类商业软件pRTI1516进行的对比测试结果表明,性能可提升30%以上。