Unicorn-CIM shows that FP16 DNNs on SRAM CIM crash from exponent bit flips, and a shared-exponent fine-tuning plus lightweight Hamming ECC restores resilience with about 9% logic overhead.
34.8 a 22nm 16mb floating-point reram compute-in-memory macro with 31.2tflops/w for ai edge devices,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Unicorn-CIM: Uncovering the Vulnerability and Improving the Resilience of High-Precision Compute-in-Memory
Unicorn-CIM shows that FP16 DNNs on SRAM CIM crash from exponent bit flips, and a shared-exponent fine-tuning plus lightweight Hamming ECC restores resilience with about 9% logic overhead.