Sigma: Compiling Einstein Summations to Locality-Aware Dataflow.

ASPLOS (2)(2023)

引用 0|浏览12
暂无评分
摘要
Most dataflow accelerator compilers achieve high performance by mapping each node in a dataflow program to a dedicated hardware element on a dataflow accelerator. However, this approach misses critical data reuse optimizations required to exploit the data bandwidth from fine-grained memory elements, e.g., FIFOs and pipeline registers. Moreover, writing performant dataflow programs requires users to have domain expertise in the underlying dataflow accelerators. To address these issues, we designed Sigma, a novel compiler that supports high-level programming constructs such as Einstein summations, index notations, and tensors, finds opportunities for data reuse from high-level dataflow graphs, and exploits on-chip data bandwidth from fine-grained memory elements. Sigma targeting a research dataflow accelerator demonstrates a 5.4x speedup and 44.6x area-normalized speedup over Nvidia's V100 accelerator, and a 7.1x speedup over hand-written dataflow programs.
更多
查看译文
关键词
machine learning, neural networks, reconfigurable dataflow accelerator, hardware acceleration, compiler, domain-specific language, index notation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要