移动甜点:高阶弹性问题的高性能无矩阵方法
Shifting the Sweet Spot: High-Performance Matrix-Free Method for High-Order Elasticity
AI总结:
针对MFEM中线性弹性部分组装算子在p≈2时性能最佳的问题,集成四种张量积优化技术,将算子吞吐量甜点移至p≥6,在AMD EPYC 7713上实现7-83倍内核加速和3.6-16.8倍端到端加速。
摘要:
MFEM是一个广泛使用的有限元库,但其原生的线性弹性部分组装(PA)路径在单元算子中仍然应用$O((p+1)^6)$的收缩,导致在我们的基线测量中CPU算子吞吐量甜点位于$p\approx 2$附近。本文通过将四种成熟的张量积PA优化技术(和分解、Voigt记号、宏核融合和切片级循环重组)集成到MFEM的原生线性弹性PA路径中,填补了仿射张量积六面体网格上MFEM线性弹性的实现空白。得到的算子在MFEM的几何多重网格(GMG)组件中用于高阶GMG-PCG求解。在AMD EPYC 7713上,优化后的算子在$p\in\{1,2,4,8\}$范围内实现了$7\text{--}83\times$的内核加速和$3.6\text{--}16.8\times$的端到端加速。在固定问题规模下,内核时间算子吞吐量在$p=6$附近达到峰值,并在$p=8$时保持较高水平,将算子吞吐量甜点移至$p\ge 6$。同样的趋势在华为鲲鹏920(ARMv8.2)上得到复现。这些结果附有逐阶段消融和硬件计数器特征分析;实现代码将在GitHub上发布。
英文摘要:
MFEM is a widely used finite-element library, but its native linear-elasticity Partial Assembly (PA) path still applies an $O((p+1)^6)$ contraction in the element operator, leaving the CPU operator-throughput sweet spot near $p\approx 2$ in our baseline measurements. This work closes this implementation gap for MFEM linear elasticity on affine tensor-product hexahedral meshes by integrating four well-established tensor-product PA optimizations (sum factorization, Voigt notation, macro-kernel fusion, and slice-wise loop reorganization) into MFEM's native linear-elasticity PA path. The resulting operator is evaluated in high-order GMG-PCG solves using MFEM's geometric multigrid (GMG) components. On AMD EPYC 7713, the optimized operator achieves $7\text{--}83\times$ kernel speedup and $3.6\text{--}16.8\times$ end-to-end speedup across $p\in\{1,2,4,8\}$. At fixed problem size, the kernel-time operator throughput peaks around $p=6$ and remains high at $p=8$, shifting the operator-throughput sweet spot to $p\ge 6$. The same trend is reproduced on Huawei~Kunpeng~920 (ARMv8.2). These results are accompanied by per-stage ablation and hardware-counter characterization; the implementation will be released on GitHub.
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。