You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Figure 1 in the ECP report Milestone M7 Report: Reducing Excess Data Movement Part 2 plots spatial vs temporal locality for their benchmark suite (copied below). It would be nice if Spatter could automatically extract patterns that match these values. The difficulty would arise in the fact that these locality values are dynamic, as shown in Figures 2 and 3. Perhaps phase analysis could make it more feasible.
I think this would be an excellent research project for Spatter, and would give have reasonably well-defined success conditions. Before starting, check related work on statistical memory trace generation.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Figure 1 in the ECP report Milestone M7 Report: Reducing Excess Data Movement Part 2 plots spatial vs temporal locality for their benchmark suite (copied below). It would be nice if Spatter could automatically extract patterns that match these values. The difficulty would arise in the fact that these locality values are dynamic, as shown in Figures 2 and 3. Perhaps phase analysis could make it more feasible.
I think this would be an excellent research project for Spatter, and would give have reasonably well-defined success conditions. Before starting, check related work on statistical memory trace generation.
Beta Was this translation helpful? Give feedback.
All reactions