Similar Items: TLX: Hardware-Native, Evolvable MIMW GPU Compiler for Large-scale Production Environments
- CuLifter: Lifting GPU Binaries to Typed IR
- RAG-Enhanced Kernel-Based Heuristic Synthesis (RKHS): A Structured Methodology Using Large Language Models for Hardware Design
- The Anatomy of Silent Data Corruption: GPU Error Pattern Study and Modeling Guidance
- DPU or GPU for Accelerating Neural Networks Inference -- Why not both? Split CNN Inference
- HyDRA: Deadline and Reuse-Aware Cacheability for Hardware Accelerators
- Effective and Memory-Efficient Alternatives to ECC for Reliable Large-Scale DNNs