Mtool: an integrated system for performance debugging shared memory multiprocessor applications

Goldberg, A. J.; Hennessy, John L.

doi:10.1109/71.205651

Cited by 57 publications

(19 citation statements)

References 14 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most existing cache and data locality analyzers measure the locality or the cache misses and indicate at which locations in the source code, or for which data structures, most cache misses occur [2,4,5,8,12,13,20,21,23,28,29,32]. While this information is helpful in identifying the main bottlenecks in the program, it can still be difficult to deduce a suitable program transformation from it.…”

Section: Related Workmentioning

confidence: 99%

Intermediately executed code is the key to find refactorings that improve temporal data locality

Beyls

D’Hollander

2006

Proceedings of the 3rd Conference on Computing Frontiers

View full text Add to dashboard Cite

The growing speed gap between memory and processor makes an efficient use of the cache ever more important to reach high performance. One of the most important ways to improve cache behavior is to increase the data locality. While many cache analysis tools have been developed, most of them only indicate the locations in the code where cache misses occur. Often, optimizing the program, even after pinpointing the cache bottlenecks in the source code, remains hard with these tools.In this paper, we present two related tools that not only pinpoint the locations of cache misses, but also suggest source code refactorings which improve temporal locality and thereby eliminate the majority of the cache misses. In both tools, the key to find the appropriate refactorings is an analysis of the code executed between a data use and the next use of the same data, which we call the Intermediately Executed Code (IEC). The first tool, the Reuse Distance VISualizer (RD-VIS), performs a clustering on the IECs, which reduces the amount of work to find required refactorings. The second tool, SLO (short for "Suggestions for Locality Optimizations"), suggests a number of refactorings by analyzing the call graph and loop structure of the IEC. Using these tools, we have pinpointed the most important optimizations for a number of SPEC2000 programs, resulting in an average speedup of 2.3 on a number of different platforms.

show abstract

Section: Related Workmentioning

confidence: 99%

Intermediately executed code is the key to find refactorings that improve temporal data locality

Beyls

D’Hollander

2006

Proceedings of the 3rd Conference on Computing Frontiers

View full text Add to dashboard Cite

show abstract

“…Although the arithmetic complexity of these two code segments is equivalent, the second version produces approximately a 9% speedup over the first version on a 300Mhz Sun Ultra10 workstation 1 .…”

Section: The Basics Of Cache Memorymentioning

confidence: 99%

“…In this case, programmers can benefit from a profile that focuses specifically on a program's cache behavior [8,1,11,10], identifying problematic code sections and data structures. A simple cache profile that annotates source lines with the number of cache misses it incurs is certainly beneficial.…”

Section: A Cache Profilementioning

confidence: 99%

Cache conscious programming in undergraduate computer science

Lebeck

1999

The Proceedings of the Thirtieth SIGCSE Technical Symposium on Computer Science Education

View full text Add to dashboard Cite

show abstract

“…Mtool [4] provides information about the amount of performance lost due to the memory hierarchy, but only relates this information back to program source lines, not data structures. A system with more similarity to the techniques in this paper is MemSpy [7].…”

mentioning

confidence: 99%