Atik: A Shared-Mesh Transformer Accelerator for RISC-V

We present Atik, an open-source RoCC accelerator for RocketChip that executes matrix multiplication and dense attention through one shared fixed-point MAC mesh. It comes from a paper posted to arXiv on 9 November 2026. Transformer inference repeatedly invokes dense matrix multiplication and attention, including its data-dependent softmax normalization. Atik accepts and returns BF16 tensors, uses a streaming online-softmax schedule that never materializes the full score matrix, and is invoked through a small descriptor-based ABI. We evaluate three meshes cycle-by-cycle on FireSim and report standalone Sky130 physical-design area. Across 137 logged FireSim test records, all tests pass their benchmark tolerance with zero reported output mismatches. Relative to the same scalar Rocket BF16 reference, the 8x8 configuration reaches 31.5x peak matmul speedup and 225.8x peak attention speedup. Hybrid projections for the single-layer workload-derived C models, using directly measured accelerator-kernel cycles, give aggregate speedups of 44.2x, 77.1x, and 32.3x for ViT, TinyBERT, and GPT-2 prefill, respectively; these are not full-model hardware replays.

Why it counts

We present Atik, an open-source RoCC accelerator for RocketChip that executes matrix multiplication and dense attention through one shared fixed-point MAC mesh. Across 137 logged FireSim test records, all tests pass their benchmark tolerance with zero reported output mismatches. Hybrid projections for the single-layer workload-derived C models, using directly measured accelerator-kernel cycles, give aggregate speedups of 44.2x, 77.1x, and 32.3x for ViT, TinyBERT, and GPT-2 prefill, respectively; these are not full-model hardware replays.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.