Inferred call path profiling

Mytkowicz, Todd; Coughlin, Devin; Diwan, Amer

doi:10.1145/1640089.1640102

Cited by 23 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A significant amount of recent research is devoted solely to collecting unbiased edge, path, and call stack profiles [31,37,46,47], and one such paper even won the best paper award at PLDI 2009 [2]. This ostensibly simple feature should have long ago become a commodity, programmable and accessible from user space.…”

Section: A Pragmatic Propositionmentioning

confidence: 99%

Hardware Performance Monitoring for the Rest of Us: A Position and Survey

Moseley

Vachharajani

Jalby

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Section: A Pragmatic Propositionmentioning

confidence: 99%

Hardware Performance Monitoring for the Rest of Us: A Position and Survey

Moseley

Vachharajani

Jalby

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

“…Decoding is not supported in this technique. More recently, [13] uses the height of the call stack to identify calling contexts and mutates the size of stack frames to differentiate conflicting stack heights with empirically high probability. Our approach also uses the height of the call stack to disambiguate calling contexts, but in contrast, we only use it to eliminate instrumentation and path numbering where it can be shown that it is safe to do so.…”

Section: Discussionmentioning

confidence: 99%

Precise Calling Context Encoding

Sumner

Zheng

Weeratunge

et al. 2012

IIEEE Trans. Software Eng.

View full text Add to dashboard Cite

Calling contexts are very important for a wide range of applications such as profiling, debugging, and event logging. Most applications perform expensive stack walking to recover contexts. The resulting contexts are often explicitly represented as a sequence of call sites and hence bulky. We propose a technique to encode the current calling context of any point during an execution. In particular, an acyclic call path is encoded into one number through only integer additions. Recursive call paths are divided into acyclic subsequences and encoded independently. We leverage stack depth in a safe way to optimize encoding: if a calling context can be safely and uniquely identified by its stack depth, we do not perform encoding. We propose an algorithm to seamlessly fuse encoding and stack depth based identification. The algorithm is safe because different contexts are guaranteed to have different IDs. It also ensures contexts can be faithfully decoded. Our experiments show that our technique incurs negligible overhead (1.89% on average). For most medium-sized programs, it can encode all contexts with just one number. For large programs, we are able to encode most calling contexts to a few numbers.

show abstract

“…In the example of Figure 7(A), cache miss events generated by Method D are distributed into two paths A-B-D and A-F-D in proportion to the estimated hotnesses of the edges B-D and F-D, which we have already calculated when we built the CCT. If this uncertainty affects the overall profile too greatly, we can change the stack frame size of a method by simply adding padding in the stack frame and retry the profiling [21]. The lack of precision of the HPM interrupts in POWER6 is a more severe problem.…”

Section: Mapping Hpm Events On Calling Context Treementioning

confidence: 99%

How a Java VM can get more from a hardware performance monitor

Inoue

Nakatani

2009

Proceedings of the 24th ACM SIGPLAN Conference on Object Oriented Programming Systems Languages and Applications

View full text Add to dashboard Cite

This paper describes our sampling-based profiler that exploits a processor's HPM (Hardware Performance Monitor) to collect information on running Java applications for use by the Java VM. Our profiler provides two novel features: Java-level event profiling and lightweight context-sensitive event profiling. For Java events, we propose new techniques to leverage the sampling facility of the HPM to generate object creation profiles and lock activity profiles. The HPM sampling is the key to achieve a smaller overhead compared to profilers that do not rely on a hardware help. To sample the object creations with the HPM, which can only sample hardware events such as executed instructions or cache misses, we correlate the object creations with the store instructions for Java object headers. For the lock activity profile, we introduce an instrumentation-based technique, called ProbeNOP, which uses a special NOP instruction whose executions are counted by the HPM. For the contextsensitive event profiling, we propose a new technique called CallerChaining, which detects the calling context of HPM events based on the call stack depth (the value of the stack frame pointer). We show that it can detect the calling contexts in many programs including a large commercial application. Our proposed techniques enable both programmers and runtime systems to get more valuable information from the HPM to understand and optimize the programs without adding significant runtime overhead.

show abstract

Inferred call path profiling

Cited by 23 publications

References 21 publications

Hardware Performance Monitoring for the Rest of Us: A Position and Survey

Hardware Performance Monitoring for the Rest of Us: A Position and Survey

Precise Calling Context Encoding

How a Java VM can get more from a hardware performance monitor

Contact Info

Product

Resources

About