Problem
Research questions and friction points this paper is trying to address.
Soft Errors
Deep Neural Networks
Reliability
Error Protection
Computational Overhead
UniCASE: A Unified 16-bit Floating-Point Format with Criticality-Aware Selective ECC for Efficient DNN Protection
🤖 AI Summary
本文提出UniCASE，一种统一16位浮点格式，通过选择性ECC优化数据表示和错误保护，以高效保护DNN免受软错误影响。
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Unified 16-bit Floating-Point Format
Criticality-Aware Selective ECC
Soft Error Resilience
🔎 Similar Papers
No similar papers found.
