Critical Path Computing

关键路径计算

• 批准号: 0105743
• 负责人: Dean Tullsen
• 金额: $ 30万
• 依托单位: University of California-San Diego
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2001
• 资助国家: 美国
• 起止时间: 2001-09-01 至 2004-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0105743&HistoricalAwards=false
• 关键词: Critical; Path; Computing

Critical path prediction is a processor architecture technique that uses the past behavior of instructions in the instruction stream to predict whichfetched instructions will be on the critical path; that is, which instructions will have a significant impact on processor performance, and which will not. This information can then be used to guide the selective application of a variety of processor optimizations.Modern processors remove most artificial constraints on executionthroughput. Therefore, the bottleneck for many workloads on current processors is the true dependences in the code. Chains of dependent instructions constrain the overall throughput of the machine, often leaving aggressive processor technology highly underutilized. These chains of dependent instructions constitute the critical performance path, or critical path (CP), though the code.The performance of the processor is thus determined by the speed atwhich it executes the instructions along this critical path. In ourefforts to get the maximum performance from the processor, it is nolonger reasonable to treat all instructions the same. If we can knowwhich instructions are critical to performance, we can acceleratetheir execution, possibly at the expense of instructions not on thecritical path.This research will attempt to identify these critical instructionsdynamically in hardware. We call this critical path prediction. This prediction is based on the behavior of previous invocations of the instruction in the pipeline. This prediction will enable the processor to make better decisions about where to apply certain policies and optimizations. A variety of critical path predictors will be examined.In many cases, critical path prediction will enable more effective application of other resources or optimizations. Possible applications of critical path prediction include guiding value prediction, instruction reuse, instruction issue priority, instruction scheduling on a clustered architecture, speculation control on a power-constrained processor, arbitration between instructions or threads on a multithreaded architecture, or to guide the spawning of speculative threads in a speculative multithreaded processor.

关键路径预测是一种处理器体系结构技术，它使用指令流中指令的过去行为来预测哪些获取的指令将在关键路径上;也就是说，哪些指令将对处理器性能产生重大影响，哪些不会。 这些信息可以用来指导各种处理器优化的选择性应用。现代处理器消除了对执行吞吐量的大多数人为限制。 因此，当前处理器上的许多工作负载的瓶颈是代码中的真实依赖性。 依赖指令链限制了机器的总体吞吐量，通常使积极的处理器技术高度未得到利用。 这些相关的指令链通过代码构成了关键性能路径，或称为关键路径（CP）。因此，处理器的性能取决于它执行沿着这条关键路径的指令的速度。为了从处理器中获得最大的性能，对所有指令都一视同仁是不合理的。 如果我们能知道哪些指令对性能是关键的，我们就能加速它们的执行，这可能是以牺牲不在关键路径上的指令为代价。 我们称之为关键路径预测。 此预测基于流水线中指令的先前调用的行为。 这种预测将使处理器能够更好地决定在何处应用某些策略和优化。 我们将研究各种关键路径预测器。在许多情况下，关键路径预测可以更有效地应用其他资源或优化。 关键路径预测的可能应用包括指导值预测、指令重用、指令发布优先级、集群架构上的指令调度、功率受限处理器上的推测控制、多线程架构上的指令或线程之间的仲裁，或者指导推测多线程处理器中推测线程的产生。