Cache Hierarchy

Shared Foundations · Execution Hardware · cache-hierarchy.yaml

Successive levels trade capacity for latency and bandwidth. Almost every optimisation below the algorithmic level is a rearrangement to make a working set fit one level higher up.

• supersedescorrects · extends
• classifiesspecializes · part-of
• substitutes forapproximates · alternative-to
• depends onrequires · validates

Colour is the family; a dashed line is the second member of it.

Referenced by

• requiresFlashAttention does not work without thisit tiles attention to fit in on-chip memory

References

• Background — Cache hierarchy on Wikipedia