arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.07436cs.CE
收藏

现代架构上核无关快速多极子方法的 M2L 转换算子

M2L Translation Operators for Kernel Independent Fast Multipole Methods on Modern Architectures

Srinath Kailasa, Timo Betcke, Sarah El Kazdadi

AI总结:

针对核无关快速多极子方法中带宽受限的 M2L 转换算子,提出结合随机低秩压缩的 BLAS 策略,实现高性能与可移植性,并在 CPU 上通过基准测试明确了 FFT 与 BLAS 策略在不同精度和粒子动态场景下的适用优势。

摘要:

硬件趋势倾向于最大化每 FLOP 数据复用的算法设计。我们为核无关快速多极子方法(kiFMM)开发并基准测试了高性能的多极子到局部(M2L)转换算子,这是一种广泛采用的 FMM 变体,支持广泛的核函数类别,并因其简单的规范而受到近期实现的青睐。简单实现的 M2L 受带宽限制,因此是 FMM 中的关键瓶颈。基于 FFT 的最先进 M2L 实现虽然优雅且设置时间快,但运算强度低且需要特定架构优化。我们证明,基于 BLAS 的 M2L 结合随机低秩压缩,利用现有 BLAS 基础设施,实现了具有竞争力的性能、更高的可移植性和更简单的实现,代价是设置时间更长——尤其是在双精度的高精度设置中。我们基于 Rust 的实现能够在策略间无缝切换以进行公平基准测试。CPU 上的结果显示,基于 FFT 的 M2L 在低精度设置或动态粒子模拟中具有优势,而基于 BLAS 的 M2L 在静态粒子分布的高精度设置中更受青睐,其较高的设置成本在 FMM 的许多实际应用中被摊销。

英文摘要:

Hardware trends favor algorithm designs that maximize data reuse per FLOP. We develop and benchmark high-performance Multipole-to-Local (M2L) translation operators for the kernel-independent Fast Multipole Method (kiFMM), a widely adopted FMM variant that supports a broad class of kernels and has been favored by recent implementations for its simple specification. Naively implemented, M2L is bandwidth-limited and therefore a key bottleneck in the FMM. State-of-the-art FFT-based M2L implementations, though elegant and with a fast setup time, suffer from low operational intensity and require architecture-specific optimizations. We demonstrate that a BLAS-based M2L, combined with randomized low-rank compression, achieves competitive performance with greater portability and a simpler implementation leveraging existing BLAS infrastructure, at the cost of higher setup times-especially for high-accuracy settings in double precision. Our Rust-based implementation enables seamless switching between strategies for fair benchmarking. Results on CPUs show that FFT-based M2L is favorable in low-accuracy settings or dynamic particle simulations, while BLAS-based M2L is favored for high-accuracy settings for static particle distributions, where its higher setup costs are amortized in many practical applications of the FMM.

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。

↑