UniCASE：一种具有关键性感知选择性ECC的统一16位浮点格式，用于高效的DNN保护
UniCASE: A Unified 16-bit Floating-Point Format with Criticality-Aware Selective ECC for Efficient DNN Protection
浏览论文内容
中文总结 AI 辅助
UniCASE提出统一16位浮点格式，通过关键性感知选择性ECC，在降低编码解码成本30%的同时保持精度，并增强DNN软错误韧性。
中文摘要 AI 辅助
软错误对深度神经网络执行日益构成可靠性担忧，因为它们可能破坏参数，导致精度下降。虽然传统ECC提供强大的故障保护，但它会带来额外的奇偶校验存储和计算开销。嵌入式奇偶校验格式通过重用最低有效位来降低存储成本，但在降低计算开销的同时并未优化保护。我们提出UniCASE，一种统一的16位浮点（FP）格式，它联合优化数据表示和错误保护，以实现可靠的DNN执行。它识别FP64、FP32、FP16和BFloat16中可映射到统一表示的稳定块。基于位级关键性分析，UniCASE使用选择性ECC，根据数据位对软错误的韧性为其分配不同级别的保护。实验结果表明，UniCASE将编码器/解码器成本降低高达30%，将模型精度保持在FP32基线的1%以内，并提供比现有嵌入式奇偶校验方法显著更强的软错误韧性。
英文摘要
Soft errors are an increasing reliability concern for Deep Neural Network execution because they can corrupt parameters, leading to accuracy degradation. While conventional ECC offers strong fault protection, it incurs additional parity storage and computational overhead. Embedded-parity formats reduce storage cost by reusing the least-significant bits, but they do not optimize protection while reducing computational overhead. We propose UniCASE, a unified 16-bit floating-point (FP) format that jointly optimizes data representation and error protection for reliable DNN execution. It identifies stable blocks across FP64, FP32, FP16, and BFloat16 that can be mapped into a unified representation. Based on bit-level criticality analysis, UniCASE uses selective ECC that assigns distinct levels of protection to different data bits according to their resilience against soft errors. Experimental results show that UniCASE reduces encoder/decoder cost by up to 30%, preserves model accuracy within 1% of the FP32 baseline, and provides significantly stronger soft error resilience than existing embedded-parity methods.
发表机构
- University of Amsterdam（阿姆斯特丹大学）
机构由 AI 辅助整理，请以论文原文为准。
