Recent breakthroughs in ML have produced new classes of models that allow ML inference to run directly on milliwatt-powered IoT devices. On one hand, existing ML-to-FPGA compilers are designed for deep neural-networks on large FPGAs. On the other hand, general-purpose HLS tools fail to exploit properties specific to ML inference, thereby resulting in suboptimal performance. We propose MAFIA, a tool to compile ML inference on small form-factor FPGAs for IoT applications. MAFIA provides native support for linear algebra operations and can express a variety of ML algorithms, including state-of-the-art models. We show that MAFIA-generated programs outperform best-performing variant of a commercial HLS compiler by 2.5x on average.
翻译：近期ML的突破产生了新的模型类别,使ML推论能够直接运行于毫瓦特动力 IoT 设备上。一方面,现有的 ML--FPGA 编译器是为大型 FPGA 上的深神经网络设计的。另一方面,一般用途HLS 工具未能利用ML 推论所特有的特性,从而导致不最佳性能。我们建议MAFIA, 这是一种工具,用于为 IoT 应用程序汇编小表因子 FPGAs 的ML推论。MAFIA 提供线形代数操作的本地支持,并可以表达各种 ML 算法, 包括最先进的模型。 我们显示, MAFIA 生成的程序比商业HLS 编译器的最好性变式平均为 2.5x 。
相关内容
微信扫码咨询专知VIP会员