Constructing Concurrent Data Structures on FPGA with Channels

Yan, Hui; Li, Zhaoshi; Liu, Leibo; Yin, Shouyi; Wei, Shaojun

doi:10.1145/3289602.3293921

Cited by 4 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ramanathan et al [11] studied HLS-based work-stealing with K-means algorithm as a case study, and the OpenCL atomic operation is used for synchronization among PEs. Later, Yan et al [23] improved their performance by replacing the work-stealing with a round-robin work distributor. Geng et al [14] proposed an HDLbased runtime workload balancing method for graph convolutional networks.…”

Section: Related Workmentioning

confidence: 99%

Skew-Oblivious Data Routing for Data-Intensive Applications on FPGAs with HLS

Chen¹,

Tan²,

Chen³

et al. 2021

Preprint

View full text Add to dashboard Cite

FPGAs have become emerging computing infrastructures for accelerating applications in datacenters. Meanwhile, high-level synthesis (HLS) tools have been proposed to ease the programming of FPGAs. Even with HLS, irregular data-intensive applications require explicit optimizations, among which multiple processing elements (PEs) with each owning a private BRAM-based buffer are usually adopted to process multiple data per cycle. Data routing, which dynamically dispatches multiple data to designated PEs, avoids data replication in buffers compared to statically assigning data to PEs, hence saving BRAM usage. However, the workload imbalance among PEs vastly diminishes performance when processing skew datasets. In this paper, we propose a skew-oblivious data routing architecture that allocates secondary PEs and schedules them to share the workload of the overloaded PEs at run-time.In addition, we integrate the proposed architecture into a framework called Ditto to minimize the development efforts for applications that require skew handling. We evaluate Ditto on five commonly used applications: histogram building, data partitioning, pagerank, heavy hitter detection and hyperloglog. The results demonstrate that the generated implementations are robust to skew datasets and outperform the stateof-the-art designs in both throughput and BRAM usage efficiency.1 Ditto, a Transform Pokémon, which is able to reconstitute entire cellular structure to change into what it sees.

show abstract

Section: Related Workmentioning

confidence: 99%