2025/05/24 by Chi Zhang, Luca Colagrande, Zhang, Chi +15 · 1 citation
Computer Science · Engineering · #Advanced Memory and Neural Computing #CCD and CMOS Imaging Sensors #FOS: Computer and information sciences #Hardware Architecture (cs.AR) #Quantum-Dot Cellular Automata
paper · pdf · doi:10.48550/arxiv.2505.18824
openalex publication_date 2025/05/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Multi-Head Attention (MHA) is a critical computational kernel in transformer-based AI models. Emerging scalable tile-based accelerator architectures integrate increasing numbers of tightly-packed processing elements (PEs) with tensor units. MHA dataflow mapping is crucial for achieving high utilization of the available units. We propose FlatAttention, a new dataflow for MHA on tile-based many-PE accelerators, minimizing costly main memory (HBM) accesses by leveraging collective primitives integrated into the on-chip network fabric. FlatAttention achieves up to 89.3% utilization, and 4.1x performance speedup over FlashAttention-3 dataflow on tile-based accelerators whilst reducing HBM traffic by 16x. Through algorithm-architecture co-exploration, we identify an optimal configuration for a large scaled-out tile-based accelerator featuring a 32x32 tile mesh with 1024 TFLOPS @ FP16 peak performance, comparable to the state-of-the-art Nvidia H100 GPU. FlatAttention in this configuration achieves up to 1.3x higher utilization over FlashAttention-3 on the H100 GPU. Meanwhile, this tile-based accelerator configuration requires 40% less HBM bandwidth compared to the H100, enabling a 1.8x reduction in die size, estimated on the same technology node.