AI Architecture & Systems
1
Microarchitecture
2
Kernel
3
Compiler
4
Architecture
5
System
6
Algorithms
Compiler
/
§3.7
Layout and Data-Movement Optimization
3.7.1
Layout Inference and Layout Propagation
#
3.7.2
Blocked Layout, Swizzle, and Thread Mapping
#
3.7.3
Insertion and Elimination of Layout Conversions
#
3.7.4
Cache/Scratchpad Placement and Data Reuse
#
3.7.5
Asynchronous DMA, Prefetch, and Transfer Scheduling
#
← Previous
3.6 Loop Transformation and Tensorization
→ Next
3.8 Memory Planning and Buffer Management