{"ID":2854488,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.14393","arxiv_id":"2510.14393","title":"Low Power Vision Transformer Accelerator with Hardware-Aware Pruning and Optimized Dataflow","abstract":"Current transformer accelerators primarily focus on optimizing self-attention due to its quadratic complexity. However, this focus is less relevant for vision transformers with short token lengths, where the Feed-Forward Network (FFN) tends to be the dominant computational bottleneck. This paper presents a low power Vision Transformer accelerator, optimized through algorithm-hardware co-design. The model complexity is reduced using hardware-friendly dynamic token pruning without introducing complex mechanisms. Sparsity is further improved by replacing GELU with ReLU activations and employing dynamic FFN2 pruning, achieving a 61.5\\% reduction in operations and a 59.3\\% reduction in FFN2 weights, with an accuracy loss of less than 2\\%. The hardware adopts a row-wise dataflow with output-oriented data access to eliminate data transposition, and supports dynamic operations with minimal area overhead. Implemented in TSMC's 28nm CMOS technology, our design occupies 496.4K gates and includes a 232KB SRAM buffer, achieving a peak throughput of 1024 GOPS at 1GHz, with an energy efficiency of 2.31 TOPS/W and an area efficiency of 858.61 GOPS/mm2.","short_abstract":"Current transformer accelerators primarily focus on optimizing self-attention due to its quadratic complexity. However, this focus is less relevant for vision transformers with short token lengths, where the Feed-Forward Network (FFN) tends to be the dominant computational bottleneck. This paper presents a low power Vi...","url_abs":"https://arxiv.org/abs/2510.14393","url_pdf":"https://arxiv.org/pdf/2510.14393v1","authors":"[\"Ching-Lin Hsiung\",\"Tian-Sheuan Chang\"]","published":"2025-10-16T07:44:42Z","proceeding":"cs.AR","tasks":"[\"cs.AR\",\"cs.LG\"]","methods":"[\"Vision Transformer\",\"Transformer\"]","has_code":false}