GOMA: 通过分析建模实现空间加速器的几何最优映射
GOMA: Geometrically Optimal Mapping via Analytical Modeling for Spatial Accelerators
AI总结:
GOMA通过几何抽象和分析建模,为空间加速器的通用矩阵乘法提供全局最优映射框架,显著提升能效和求解速度。
摘要:
在空间加速器上执行通用矩阵乘法(GEMM)对映射选择高度敏感,涉及执行效率和能耗。然而,映射空间呈现组合爆炸,使在可接受时间内获得最优映射极具挑战性。现有方法面临缺乏全局最优保证和求解速度慢的问题。为解决这些问题,我们提出了GOMA,一种基于几何抽象的全局最优GEMM映射框架,通过分析建模实现高效求解并保证最优性。GOMA从原理上引入几何抽象,得到精确的分析能耗目标,其评估复杂度为O(1)。然后,GOMA将映射选择建模为整数优化问题,在硬件和映射约束下使用分析能耗模型自动搜索映射。GOMA能够快速计算任意(GEMM工作负载,目标硬件)对的全局最优映射,首次在映射空间探索中实现此目标。实验表明,在代表性加速器和大语言模型预填工作负载上,GOMA在能耗-延迟乘积(EDP)方面比现有最佳映射器提升2.24至4.24倍,同时将求解时间缩短3.83至73.6倍。
英文摘要:
General matrix multiplication (GEMM) on spatial accelerators is highly sensitive to mapping choices in both execution efficiency and energy consumption. However, the mapping space exhibits combinatorial explosion, which makes it extremely challenging to obtain optimal mappings within an acceptable time budget. Existing approaches typically face challenges: They often lack global-optimality guarantees and become prohibitively slow as the mapping space grows. To address these limitations, we propose \textsc{GOMA}, a geometric-abstraction-based, globally optimal GEMM mapping framework via analytical modeling, which achieves efficient solving while guaranteeing optimality. \textsc{GOMA} introduces, from first principles, a geometric abstraction for GEMM mapping, yielding an exact analytical energy objective with $O(1)$ evaluation for any given mapping. The objective is highly accurate. \textsc{GOMA} then formulates mapping selection as an integer optimization problem under hardware and mapping constraints, using the analytical energy model as the objective to automate mapping search. \textsc{GOMA} can quickly compute a global-optimal mapping for any (GEMM workload, target hardware) pair, achieving this for the first time in mapping space exploration. Experiments confirm that across representative accelerators and large language model prefill workloads, \textsc{GOMA} improves the energy--delay product (EDP) by $2.24$--$4.24\times$ over SOTA mappers, while accelerating time-to-solution by $3.83$--$73.6\times$.
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。