Custom hardware accelerators for Deep Neural Networks are increasingly popular: in fact, the flexibility and performance offered by FPGAs are well-suited to the computational effort and low latency constraints required by many image recognition and natural language processing tasks. The gap between high-level Machine Learning frameworks (e.g., Tensorflow, Pytorch) and low-level hardware design in Verilog/VHDL creates a barrier to widespread adoption of FPGAs, which can be overcome with the help of High-Level Synthesis. hls4ml is a framework that translates Deep Neural Networks into annotated C++ code for High-Level Synthesis, offering a complete and user-friendly design process that has been enthusiastically adopted in physics research. We analyze the strengths and weaknesses of hls4ml, drafting a plan to enhance its core library of components in order to allow more advanced optimizations, target a wider selection of FPGAs, and support larger Neural Network models.
High-level synthesis (HLS) has been widely adopted as it significantly improves the hardware design productivity and enables efficient design space exploration (DSE). Existing HLS tools are built using compiler infrastructures largely based on a single-level abstraction, such as LLVM. However, as HLS designs typically come with intrinsic structural or functional hierarchies, different HLS optimization problems are often better solved with different levels of abstractions. This paper proposes ScaleHLS, a new scalable and customizable HLS framework, on top of a multi-level compiler infrastructur…
High-level synthesis (HLS) has been researched for decades and is still limited to fast FPGA prototyping and algorithmic RTL generation. A feasible end-to-end system-level synthesis solution has never been rigorously proven. Modularity and composability are the keys to enabling such a system-level synthesis framework that bridges the huge gap between system-level specification and physical level design. It implies that 1) modules in each abstraction level should be physically composable without any irregular glue logic involved and 2) the cost of each module in each abstraction level is accura…
High-level synthesis (HLS) tools have brought FPGA development into the mainstream, by allowing programmers to design architectures using familiar languages such as C, C++, and OpenCL. While the move to these languages has brought significant benefits, many aspects of traditional software engineering are still unsupported, or not exploited by developers in practice. Furthermore, designing reconfigurable architectures requires support for hardware constructs, such as FIFOs and shift registers, that are not native to CPU-oriented languages. To address this gap, we have developed hlslib, a collec…
FPGA-based accelerators are becoming more popular for deep neural network due to the ability to scale performance with increasing degree of specialization with dataflow architectures or custom data types. To reduce the barrier for software engineers and data scientists to adopt FPGAs, C++- and OpenCL-based design entries with high-level synthesis (HLS) have been introduced. They provide higher abstraction compared to register-transfer level (RTL)-based design. HLS offers faster development time, better maintainability and more flexibility in code exploration, when evaluating options for multi-…
The growing proliferation of FPGAs and High-level Synthesis (HLS) tools has led to a large interest in designing hardware accelerators for complex operations and algorithms. However, existing HLS toolflows typically require a significant amount of user knowledge or training to be effective in both industrial and research applications. In this paper, we propose using the Julia language as the basis for an HLS tool. The Julia HLS tool aims to decrease the barrier to entry for hardware acceleration by taking advantage of the readability of the Julia language and by allowing the use of the existin…
FPGA accelerators designed for graph processing are gaining popularity. Domain Specific Language (DSL) frameworks for graph processing can reduce the programming complexity and development cost of algorithm design. However, accelerator-specific development requires certain technical expertise and significant effort to devise, implement, and validate the system. For most algorithm designers, the expensive cost for hardware programming experience makes FPGA accelerators either unavailable or uneconomic. Although general-purpose High-Level Synthesis (HLS) tools help to map high-level language to …
University of Kaiserslautern（凯泽斯劳滕大学）；Xilinx Research Labs（赛灵思研究院）
It is well known that many types of artificial neural networks, including recurrent networks, can achieve a high classification accuracy even with low-precision weights and activations. The reduction in precision generally yields much more efficient hardware implementations in regards to hardware cost, memory requirements, energy, and achievable throughput. In this paper, we present the first systematic exploration of this design space as a function of precision for Bidirectional Long Short-Term Memory (BiLSTM) neural network. Specifically, we include an in-depth investigation of precision vs.…
In recent years, number of edge computing devices and artificial intelligence applications on them have advanced excessively. In edge computing, decision making processes and computations are moved from servers to edge devices. Hence, cheap and low power devices are required. FPGAs are very low power, inclined to do parallel operations and deeply suitable devices for running Convolutional Neural Networks (CNN) which are the fundamental unit of an artificial intelligence application. Face detection on surveillance systems is the most expected application on the security market. In this work, Ti…
Hong Kong University of Science and Technology（香港科技大学）；Alibaba Group（阿里巴巴集团）；India Institute of Technology Goa（印度理工学院果阿分校）
Fast and accurate depth estimation, or stereo matching, is essential in embedded stereo vision systems, requiring substantial design effort to achieve an appropriate balance among accuracy, speed and hardware cost. To reduce the design effort and achieve the right balance, we propose FP-Stereo for building high-performance stereo matching pipelines on FPGAs automatically. FP-Stereo consists of an open-source hardware-efficient library, allowing designers to obtain the desired implementation instantly. Diverse methods are supported in our library for each stage of the stereo matching pipeline a…
Neural Network Acceleration on MPSoC board: Integrating SLAC's SNL, Rogue Software and Auto-SNL
SLAC National Accelerator Laboratory（SLAC国家加速器实验室）；Interdisciplinary Institute for Technological Innovation（跨学科技术创新研究院）；University of Sherbrooke（Sherbrooke大学）
