arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.00909cs.AR
收藏

Capstone: 为粗粒度可重构数组编译器设计的功率受限流水线

Capstone: Power-Capped Pipelining for Coarse-Grained Reconfigurable Array Compilers

University of Southern California(南加州大学)

Sabrina Yarzada, Christopher Torng

AI总结:

Capstone通过功率感知流水线技术,优化CGRA编译器在功率限制下的性能与能效。

摘要:

粗粒度可重构数组(CGRAs)因其在性能和能效方面与ASICs相当,同时保持与FPGAs相似的灵活性而受到越来越多的关注。这些特性使CGRAs在加速器和其他功率受限系统中具有吸引力。然而,现代CGRA编译器为了提高频率和性能而积极进行流水线操作,往往违反了硬性功率预算。我们实证表明,在最先进的CGRA编译器如Cascade中,放置和路由(post-PnR)流水线在不同工作负载下功率单调增加,并最终超过固定的功率上限。为此,我们引入了Capstone,它是Cascade的一个功率感知扩展,集成了一个快速的编译器驻留功率模型和一个可调控制器,该控制器指导位流选择过程以优化目标。Capstone在post-PnR编译循环中直接预测每个迭代的功率,并选择一个或少量的PnR配置,使得至少一个配置满足用户指定的功率上限。因此,我们将目标从无差别地最大化频率转变为在离散功率上限下最大化安全频率。在一系列涵盖基本密集和稀疏应用的内核上,Capstone满足功率上限并最小化剩余功率余量,同时保持可行的性能。我们的结果表明,功率感知编译既是必要也是可行的,因为编译器可以主动选择符合功率限制的点,并在功率约束下暴露可预测的性能。

英文摘要:

Coarse-grained reconfigurable arrays (CGRAs) have attracted growing interest because they exhibit performance and energy efficiency competitive with ASICs while maintaining flexibility similar to FPGAs. These properties make CGRAs attractive in accelerator and other power-constrained system contexts. However, modern CGRA compilers aggressively pipeline for frequency and performance improvements, often violating hard power budgets. We empirically show that, in state-of-the-art CGRA compilers such as Cascade, post-place-and-route (post-PnR) pipelining increases power monotonically and ultimately exceeds fixed power caps across diverse workloads. In response, we introduce \emph{Capstone}, a power-aware extension of Cascade that integrates a fast, compiler-resident power model with a user-tunable controller that guides the bitstream selection process towards optimization targets. Capstone predicts per-iteration power directly inside the post-PnR compilation loop and selects one or a small set of PnR configurations such that at least one meets a user-specified power cap. Thus, we shift the objective from indiscriminately maximizing frequency to maximizing safe frequency under a discrete power cap. On a suite of kernels spanning fundamental dense and sparse applications, Capstone meets a power cap and minimizes remaining power headroom while preserving feasible performance. Our results indicate that cap-aware compilation is both necessary and practical, as the compiler can proactively land on cap-compliant points and expose predictable performance under power constraints.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑