用全晶体管电路实现扩散模型，能效比GPU高一万倍。
An efficient probabilistic hardware architecture for diffusion-like models
- 全晶体管硬件直接运行扩散模型的去噪过程
- 实测在图像任务上能效比GPU高10000倍
- 适合需要极致低功耗的边缘推理场景
概率型人工智能的兴起推动了专用随机计算设备的发展。尽管这些方案理论上可提升效率，但因依赖基础受限的建模方法和难以扩展的异构硬件而未被广泛采用。本文提出一种全晶体管的概率计算机，可在硬件层面实现强大的去噪模型。系统级分析表明，基于该架构的设备在简单图像基准测试中，性能可与GPU相当，但能耗仅约为其1/10000。
原文摘要 · Abstract (English)
The proliferation of probabilistic AI has prompted proposals for specialized stochastic computers. Despite promising efficiency gains, these proposals have failed to gain traction because they rely on fundamentally limited modeling techniques and exotic, unscalable hardware. In this work, we address these shortcomings by proposing an all-transistor probabilistic computer that implements powerful denoising models at the hardware level. A system-level analysis indicates that devices based on our architecture could achieve performance parity with GPUs on a simple image benchmark using approximately 10,000 times less energy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。