CUTEv2: Unified and Configurable Matrix Extension for Diverse CPU Architectures with Minimal Design Overhead

Documenti analoghi

• EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge
  di: Bai, Kangbo, et al.
  Pubblicazione: (2025)
• AgileWatts: An Energy-Efficient CPU Core Idle-State Architecture for Latency-Sensitive Server Applications
  di: Yahya, Jawad Haj, et al.
  Pubblicazione: (2022)
• MX: Enhancing RISC-V's Vector ISA for Ultra-Low Overhead, Energy-Efficient Matrix Multiplication
  di: Perotti, Matteo, et al.
  Pubblicazione: (2024)
• ArchPower: Dataset for Architecture-Level Power Modeling of Modern CPU Design
  di: Zhang, Qijun, et al.
  Pubblicazione: (2025)
• RTLSeek: Boosting the LLM-Based RTL Generation with Multi-Stage Diversity-Oriented Reinforcement Learning
  di: Zhang, Xinyu, et al.
  Pubblicazione: (2026)