Trireme: Exploring Hierarchical Multi-Level Parallelism for Domain Specific Hardware Acceleration

• DOI: 10.48550/arxiv.2201.08603
• Publication Date: 2022-01-01
• Authors: Georgios Zacharop...; Adel Ejjeh; Ying Jing; En-Yu Yang; Tianyu Jia; Iulian Brumar; Jeremy Intan; Muhammad Huzaifa; Sarita V. Adve; Vikram Adve; Gu-Yeon Wei; David J. Brooks
• Keywords: Speedup; Hardware acceleration; Implementation

The design of heterogeneous systems that include domain specific accelerators is a challenging and time-consuming process. While taking into account area constraints, designers must decide which parts an application to accelerate in hardware leave software. Moreover, applications domains such as Extended Reality (XR) offer opportunities for various forms parallel execution, including loop level, task level pipeline parallelism. To assist the process expose every possible parallelism, we present Trireme, fully automated tool-chain explores multiple levels parallelism produces accelerator designs configurations maximize performance, given budget. Experiments on demanding benchmarks from XR revealed speedup up 20x, well 37x smaller applications, compared software-only implementations.