📝 SummarXiv

Abstract

While deep neural networks (DNNs) have achieved state-of-the-art performance in fields from computer vision to natural language processing, efficiently running these computationally demanding models requires hardware accelerators. However, designing these accelerators is a time-consuming, labor-intensive process that does not scale well. While prior efforts have sought to automate DNN accelerator generation, they offer limited parameterization, cannot produce high-performance, tapeout-ready designs, provide limited support for datatypes and quantization schemes, and lack an integrated, end-to-end software compiler. This work proposes Voyager, a high-level synthesis (HLS)-based framework for design space exploration (DSE) and generation of DNN accelerators. Voyager overcomes the limitations of prior work by offering extensive configurability across technology nodes, clock frequencies, and scales, with customizable parameters such as number of processing elements, on-chip buffer sizes, and external memory bandwidth. Voyager supports a wider variety of datatypes and quantization schemes versus prior work, including both built-in floating-point, posit and integer formats, as well as user-defined formats with both per-tensor scaling and microscaling quantization. Voyager's PyTorch-based compiler efficiently maps networks end-to-end on the generated hardware, with support for quantization, fusion, and tiling. We evaluate Voyager on state-of-the-art vision and language models. Voyager enables fast DSE with full-dataset accuracy evaluation for datatypes and quantization schemes. Generated designs achieve a high utilization across models and scales, up to 99.8%, and outperform prior generators with up to 61% lower latency and 56% lower area. Compared to hand-optimized accelerators, Voyager achieves comparable performance, while offering much greater automation in design and workload mapping.