Balancing FP8 Computation Accuracy and Efficiency on Digital CIM via Shift-Aware On-the-fly Aligned-Mantissa Bitwidth Prediction

Documenti analoghi

• DS-CIM: Digital Stochastic Computing-In-Memory Featuring Accurate OR-Accumulation via Sample Region Remapping for Edge AI Models
  di: Shao, Kunming, et al.
  Pubblicazione: (2026)
• DIRC-RAG: Accelerating Edge RAG with Robust High-Density and High-Loading-Bandwidth Digital In-ReRAM Computation
  di: Shao, Kunming, et al.
  Pubblicazione: (2025)
• A Memory-Efficient Retrieval Architecture for RAG-Enabled Wearable Medical LLMs-Agents
  di: Liao, Zhipeng, et al.
  Pubblicazione: (2025)
• A Flexible Precision Scaling Deep Neural Network Accelerator with Efficient Weight Combination
  di: Zhao, Liang, et al.
  Pubblicazione: (2025)
• SynDCIM: A Performance-Aware Digital Computing-in-Memory Compiler with Multi-Spec-Oriented Subcircuit Synthesis
  di: Shao, Kunming, et al.
  Pubblicazione: (2024)