Browsing by Subject "Computer networks--Workload"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Automatic workload synthesis for early design studies and performance model validation(2005) Bell, Robert Henry; John, Lizy KurianComputer designers rely on simulation systems to assess the performance of their designs before the design is transferred to silicon and manufactured. Simulators are used in early design studies to obtain projections of performance and power over a large space of potential designs. Modern simulation systems can be four orders of magnitude slower than native hardware execution. At the same time, the numbers of applications and their dynamic instruction counts have expanded dramatically. In addition, simulation systems need to be validated against cycle-accurate models to ensure accurate performance projections. In prior work, long running applications are used for early design studies while hand-coded microbenchmarks are used for performance model validation. One proposed solution for early design studies is statistical simulation, in which statistics from the workload characterization of an executing application are used to create a synthetic instruction trace that is executed on a fast performance simulator. In prior work, workload statistics are collected as average behaviors based on instruction types. In the present research, statistics are collected at the granularity of the basic block. This improves the simulation accuracy of individual instructions. The basic block statistics form a statistical flow graph that provides a reduced representation of the application. The synthetic trace generated from a traversal of the flow graph is combined with memory access models, branching models and novel program synthesis techniques to automatically create executable code that is useful for performance model validation. Runtimes for the synthetic versions of the SPEC CPU, STREAM, TPC-C and Java applications are orders of magnitude faster than the runtimes of the original applications with performance and power dissipation correlating to within 2.4% and 6.4%, respectively, on average. The synthetic codes are portable to a variety of platforms, permitting validations between diverse models and hardware. Synthetic workload characteristics can easily be modified to model different or future workloads. The use of statistics abstracts proprietary code, encouraging code sharing between industry and academia. The significantly reduced execution times consolidate the traditionally disparate workloads used for early design studies and model validation.Item Frequency allocation, transmit power control, and load balancing with site specific knowledge for optimizing wireless network performance(2007-05) Chen, Jeremy Kang-pen; Rappaport, Theodore S., 1960-; Veciana, Gustavo deThis dissertation is the first analytical and algorithmic work to exhibit the substantial gains that result from applying site specific knowledge to frequency allocation, transmit power control, and load balancing in wireless networks. Site specific knowledge refers to the use of knowledge of the surrounding propagation environment, building layouts, the locations of access points (APs) and clients, and the locations and electrical properties of physical objects. We assume a central network controller communicates with all APs, and has site specific knowledge which enables the controller to differentiate the sources of RF interference at every AP or user. By predicting the power from each interference source, the controller can allocate frequency channels, adjust transmit power levels, and balance loads among APs and clients in order to optimize throughput of the network. When site specific knowledge is not available, measurement-based algorithms may be used; we present three measurement-based frequency allocation algorithms that outperform the best published work by 18% for median user throughput. Then we present two site-specific knowledge-based frequency allocations that outperform the proposed measurement-based algorithms particularly for uplifting throughputs of the users who suffer low throughputs, e.g., we have gains of 3.75%, 11.8%, 10.2%, 18.2%, 33.3%, and 459% for 50, 25, 20, 15, 10, and 5 percentiles of user throughputs, respectively, over the proposed measurement-based algorithms. Furthermore, we employ transmit power control to further improve clients’ throughputs achieved by optimal site-specific knowledgebased frequency allocations; transmit power control can improve the 25, 10, 5, and 3 percentiles of users’ throughputs by up to 4.2%, 9.9%, 38%, and 110%, and save power by 20%. Finally, a load balancing algorithm is proposed as an add-on that works seamlessly with frequency allocation and transmit power control algorithms. The load-balancing algorithm can improve median user throughput by about 26%. The work in this dissertation shows that site specific knowledge is an important means for optimizing performance of wireless networks.