Intermediately executed code is the key to find refactorings that improve temporal data locality
Proceedings of the 3rd conference on Computing frontiers
Comprehensive cache performance tuning with a toolset
Future Generation Computer Systems
YACO: a user conducted visualization tool for supporting cache optimization
HPCC'05 Proceedings of the First international conference on High Performance Computing and Communications
Supporting cache locality optimization with a toolset
Euro-Par'06 Proceedings of the 12th international conference on Parallel Processing
RDVIS: a tool that visualizes the causes of low locality and hints program optimizations
ICCS'05 Proceedings of the 5th international conference on Computational Science - Volume Part II
Optimization-Oriented visualization of cache access behavior
ICCS'05 Proceedings of the 5th international conference on Computational Science - Volume Part II
Interactive visualization for memory reference traces
EuroVis'08 Proceedings of the 10th Joint Eurographics / IEEE - VGTC conference on Visualization
| Hi-index | 0.00 |
The global cache misses ratio of a program does notreveal the time distribution of the memory reference patternsin detail. On the other hand, cache visualization ishampered by the huge amount of memory references to display.Therefore, many visualizers focus on a snapshot ofthe cache content, instead of viewing all memory transactions.In this paper, a cache visualizer is introduced whichpresents the integral cache behavior of a program in severalcomplementary views. The density view of the cache missesshows the hot spots of the program; the reuse distances viewshows the data locality and its effect on performance; thehistogram view shows the periodical patterns that occursin the trace. In a number of experiments, the visualizer hasbeen used to characterize the cache behavior and effectivelyimprove the cache behavior and program performance.