The Sparse Abstract Machine
The Sparse Abstract Machine
复制标题
DOI：
10.1145/3582016.3582051
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
Olivia Hsu;Maxwell Strange;Jaeyeon Won;Ritvik Sharma;K. Olukotun;J. Emer;M. Horowitz;Fredrik Kjolstad
中科院分区：
文献类型：
--
作者：
Olivia Hsu;Maxwell Strange;Jaeyeon Won;Ritvik Sharma;K. Olukotun;J. Emer;M. Horowitz;Fredrik Kjolstad
我们提出了稀疏抽象机（SAM），一个抽象的机器模型，针对稀疏张量代数可重构和固定功能的空间可重构加速器。SAM定义了一个具有稀疏基元的流媒体抽象，这些基元包含大量预定的张量代数表达式。SAM Escherlow图自然地将张量格式与算法分开，并且具有足够的表达能力，可以合并任意的迭代顺序和许多特定于硬件的优化。我们还介绍了奶油冻，编译器从一个高级语言SAM，证明SAM的有用性作为一个中间表示。我们自动从SAM绑定到流媒体模拟器。我们评估SAM的通用性和可扩展性，探索使用SAM的稀疏张量代数优化的性能空间，并显示SAM的能力，以代表低硬件。
We propose the Sparse Abstract Machine (SAM), an abstract machine model for targeting sparse tensor algebra to reconfigurable and fixed-function spatial dataflow accelerators. SAM defines a streaming dataflow abstraction with sparse primitives that encompass a large space of scheduled tensor algebra expressions. SAM dataflow graphs naturally separate tensor formats from algorithms and are expressive enough to incorporate arbitrary iteration orderings and many hardware-specific optimizations. We also present Custard, a compiler from a high-level language to SAM that demonstrates SAM's usefulness as an intermediate representation. We automatically bind from SAM to a streaming dataflow simulator. We evaluate the generality and extensibility of SAM, explore the performance space of sparse tensor algebra optimizations using SAM, and show SAM's ability to represent dataflow hardware.