Daily | Yixun Hong

Filtered by: Architecture × LLM × Clear all

Can LLMs Perform Deep Technical Comprehension of Computer Architecture Papers?

Nishant Aggarwal, Ayushi Dubal, Sreeraj Kannakarankodi, Ian McDougall 2026-07-14

Agentic Architecture × LLM × Agent

Can large language models perform deep technical comprehension of computer architecture papers -- not summarization, but structured critique that names the core mechanism, surfaces buried assumptions, and connects a contribution beyond its own scope? We study Gauntlet, an open-source pipeline that.

PDF

GPU-Tile-Sim: A Tile-Centric GPU Simulation Framework for LLM Hardware-Software Co-Design

Yitong Ding, Jiawei Huang, Renyang Guan, Yangjie Zhou 2026-07-14

GPU Simulation LLM × Hardware Design Workload Scheduling Architecture ×

Modern LLM (large language model) workloads increasingly rely on optimized GPU kernels through hardware-software co-design. These kernels achieve high-performance through fine-grained dependency scheduling and computation-memory overlap.

PDF