The paper shows how applying knowledge about the underlying computer hardware to the code for a simple but computationally intensive algorithm can significantly improve performance. The paper also discusses how to rearrange code so that it accommodates the peculiarities of the memory system and consequently reduces execution time.
No takes yet. Share an insight, caveat, or question.
Pancratov et al. (2008) studied this question.
Synapse has enriched 5 related papers. Consider them for comparative context: