ALL libraries (COBIB.SI union bibliographic/catalogue database)
  • Towards deploying highly quantized neural networks on FPGA using chisel [Elektronski vir]
    Vreča, Jure ; Biasizzo, Anton, (računalništvo)
    We present chisel4ml, a Chisel-based tool that generates hardware for highly quantized neural networks described in QKeras. Such networks typically use parameters with bitwidths less than 8 bits and ... may have pruned connections. Chisel4ml can generate the highly quantized neural network as a single combinational circuit with pipeline registers in between the different layers. It supports heterogeneous quantization where each layer can have a different precision. The full parallelization enables very low-latency and high throughput inference, that are required for certain tasks. We illustrate this on the triggering system for the CERN Large Hadron Collider, which filters out events of interest and sends them on for further processing. We compare our tool against hls4ml, a high-level synthesis based approach for deploying similar neural networks. Chisel4ml is still under development. However, it already achieves comparable results to hls4ml for some neural network architectures. Chisel4ml is available on https://github.com/cs-jsi/chisel4ml.
    Source: 2023 26th Euromicro Conference on Digital System Design [Elektronski vir] : DSD 2023 : proceedings : virtual conference : 06-08 September 2023, Golem, Durres, Albania (Str. 161-167)
    Type of material - conference contribution ; adult, serious
    Publish date - 2023
    Language - english
    COBISS.SI-ID - 190218499

    Link(s):

    https://ieeexplore.ieee.org/document/10456782/authors#authors
    DiRROS - Digital repository of Slovenian research organizations
    DOI

Shelf entry