Early work on modeling computational sprinting
Early work on modeling computational sprinting
复制标题
DOI：
10.1145/3127479.3132691
复制
发表时间：
2017-09
期刊：
影响因子：
--
通讯作者：
Nathaniel Morris;Christopher Stewart;R. Birke;L. Chen;Jaimie Kelley
中科院分区：
文献类型：
--
作者：
Nathaniel Morris;Christopher Stewart;R. Birke;L. Chen;Jaimie Kelley
不断收紧的功率上限限制了现代处理器的持续处理速度。通过计算冲刺，处理器保留了一个小的功率预算，可用于提高短脉冲的处理速度。计算冲刺加快了查询执行速度，否则会导致响应时间变慢。用于冲刺的常见机制包括DVFS、核心扩展、CPU节流和特定于应用程序的加速器。
Ever tightening power caps constrain the sustained processing speed of modern processors. With computational sprinting, processors reserve a small power budget that can be used to increase processing speed for short bursts. Computational sprinting speeds up query executions that would otherwise yield slow response time. Common mechanisms used for sprinting include DVFS, core scaling, CPU throttling and application-specific accelerators.