Expand description
Roofline model implementation per Williams, Waterman & Patterson (2009) [4]. Supports hierarchical GPU roofline per Yang et al. (2020) [13]. Uses Empirical Roofline Toolkit (ERT) methodology [6].
Structs§
- Empirical
Result - Empirical roofline measurement results.
- Kernel
Roofline Point - A kernel’s position on the roofline chart.
- Roofline
Model - Roofline model for a specific hardware target. Implements the Empirical Roofline Toolkit (ERT) methodology [6].
Enums§
- Bound
- Whether a kernel is compute-bound or memory-bound.
- Memory
Level - Memory hierarchy levels for hierarchical roofline [13].
- Precision
- Floating-point precision levels.
Functions§
- measure_
empirical - Run empirical roofline measurement and return enhanced model.
- run_
roofline - Run the
cgp rooflinecommand.