Dataflow&Tiling Strategies in Edge-AI FPGA Accelerators: A Comprehensive Literature Review

📅 2025-05-13
📈 Citations: 0
Influential: 0
📄 PDF

career value

192K/year
🤖 AI Summary
This work addresses resource and power constraints of FPGA-based neural network accelerators in edge AI scenarios, focusing on two core design challenges: dataflow architecture and tensor tiling strategies. Methodologically, it introduces an extended dataflow taxonomy—including the novel “No-Local-Reuse” paradigm—and establishes a unified evaluation matrix enabling, for the first time, cross-dimensional comparison of heterogeneous open-source accelerators (e.g., FINN/R, FlightLLM, SSR). Leveraging MAESTRO/Timeloop modeling, it integrates multi-level memory optimization (registers, LUTRAM, BRAM, HBM) with loop unrolling, pipelining, and sparsity-aware transformations to derive automated HLS/DSL/RTL design heuristics. A standardized benchmark is proposed, covering platform compatibility, accuracy, throughput, resource utilization, and energy efficiency. The contributions include a theoretical framework and practical guidelines for edge AI–FPGA co-design, identifying partial reconfiguration, hybrid dataflows, and domain-specific compilers as three key evolutionary directions.

Technology Category

Application Category

📝 Abstract
Edge-AI applications demand high-throughput, low-latency inference on FPGAs under tight resource and power constraints. This survey provides a comprehensive review of two key architectural decisions for FPGA-based neural network accelerators: (i) the dataflow (the order and manner in which data is moved and reused on chip), and (ii) the tiling/blocking strategy (how large tensors are partitioned to fit on-chip). We first present a broadened taxonomy of canonical dataflow styles: Weight-Stationary, Output-Stationary, Row-Stationary, and No-Local-Reuse, including formal definitions, pseudocode/diagrams, and real FPGA examples. We then discuss analytical frameworks (MAESTRO, Timeloop) and compare them with a concise feature table, illustrating how they model reuse, performance, and hardware costs. Next, we detail multi-level tiling and loop unrolling/pipelining strategies for FPGAs, clarifying how each memory tier (registers, LUTRAM, BRAM, HBM) can be exploited. Our four case studies - FINN, FINN-R, FlightLLM, and SSR - highlight distinct dataflows (from binary streaming to hybrid sparse transformations) and tiling patterns. We include a unified comparison matrix covering platform, precision, throughput, resource utilization, and energy efficiency, plus small block diagrams for each design. We conclude by examining design automation trade-offs among HLS, DSL, and hand-coded RTL, offering a"lessons learned"summary box, and charting future research directions in partial reconfiguration, hybrid dataflows, and domain-specific compiler flows for next-generation edge AI FPGA accelerators.
Problem

Research questions and friction points this paper is trying to address.

Review dataflow and tiling strategies for FPGA-based Edge-AI accelerators
Compare analytical frameworks for modeling reuse and hardware costs
Explore design automation trade-offs in Edge-AI FPGA accelerators
Innovation

Methods, ideas, or system contributions that make the work stand out.

Review dataflow styles for FPGA neural networks
Analyze tiling strategies for memory optimization
Compare design automation tools for Edge-AI