1 Repo
Methods of dividing large datasets into blocks to optimize cache usage and compute throughput.
Distinct from Memory-Efficient Data Streaming: Distinct from Memory-Efficient Data Streaming: focuses on matrix/tensor tiling for hardware compute utilization rather than sequential chunking for stream processing
Explore 1 awesome GitHub repository matching data & databases · Tiling Strategies. Refine with filters or upvote what's useful.
AISystem is a comprehensive AI full-stack infrastructure project covering the entire pipeline from AI chip architecture to high-level training frameworks. It encompasses the development of AI compiler frameworks, inference engines, and distributed training orchestrators designed to coordinate workloads across a heterogeneous compute stack of CPUs, GPUs, and NPUs. The project focuses on the deep integration of software and hardware, employing software-hardware co-design to align tensor layouts with physical memory structures. It provides specialized capabilities for accelerating Transformer mo
Divides large matrices into smaller blocks to balance memory bandwidth and maximize hardware compute utilization.