|
|
Performance Analysis of Programs Based on PIN Framework
Močáry, Peter ; Fiedor, Jan (oponent) ; Pavela, Jiří (vedoucí práce)
The goal of this thesis is to extend the Performance Version System - Perun by implementing a new Tracer engine leveraging PIN instrumentation framework. This extension implements basic Tracer functionality and, in addition to that, a recording of function arguments' values as well as basic block run-times. The additional data, along with the visualizations introduced in this thesis, provide the necessary context that simplifies the detection of performance degradation. Besides the PIN framework, the new Tracer engine implements an analysis of debug information in DWARF format (using the python pyelftools library) to gather details about function arguments before the data collection process. The resulting engine was tested on multiple implementations of sorting algorithms and successfully detected the most time consuming functions along with the information about the effect of its parameter value on the functions complexity. Testing the PIN engine on a larger-scale project revealed that, in comparison to other Tracer engine implementations, the engine performs better or comparably, and produces the correct output.
|
|
|
Performance Analysis Based on Noise Injection
Liščinský, Matúš ; Malík, Viktor (oponent) ; Fiedor, Tomáš (vedoucí práce)
In this work, we proposed a Perun-Blower framework which utilises the perfblowing technique: injecting of noise into the functions of the tested program, followed by collecting of runtime data of these functions from the program run and evaluating the impact of the noise on the program performance. We build on the dynamic binary instrumentation of the Pin framework to inject the noise into program. We then focus on finding functions with high impact on performance as well as estimate the thread run's potential acceleration when optimising the particular functions. Moreover, we have extended the existing Trace collector used in the Perun framework to collect the runtime of functions with a new so-called engine based on the Pin framework. We tested the functionality of our implementation on two non-trivial projects, where we were able to find functions (1) with considerable impact on performance, (2) with the most significant optimisation benefit, and (3) whose degradation forces the non-termination of the program after several hours of running.
|
|
|
Performance Analysis of Programs Based on PIN Framework
Močáry, Peter ; Fiedor, Jan (oponent) ; Pavela, Jiří (vedoucí práce)
The goal of this thesis is to extend the Performance Version System - Perun by implementing a new Tracer engine leveraging PIN instrumentation framework. This extension implements basic Tracer functionality and, in addition to that, a recording of function arguments' values as well as basic block run-times. The additional data, along with the visualizations introduced in this thesis, provide the necessary context that simplifies the detection of performance degradation. Besides the PIN framework, the new Tracer engine implements an analysis of debug information in DWARF format (using the python pyelftools library) to gather details about function arguments before the data collection process. The resulting engine was tested on multiple implementations of sorting algorithms and successfully detected the most time consuming functions along with the information about the effect of its parameter value on the functions complexity. Testing the PIN engine on a larger-scale project revealed that, in comparison to other Tracer engine implementations, the engine performs better or comparably, and produces the correct output.
|
|
|
Performance Analysis Based on Noise Injection
Liščinský, Matúš ; Malík, Viktor (oponent) ; Fiedor, Tomáš (vedoucí práce)
In this work, we proposed a Perun-Blower framework which utilises the perfblowing technique: injecting of noise into the functions of the tested program, followed by collecting of runtime data of these functions from the program run and evaluating the impact of the noise on the program performance. We build on the dynamic binary instrumentation of the Pin framework to inject the noise into program. We then focus on finding functions with high impact on performance as well as estimate the thread run's potential acceleration when optimising the particular functions. Moreover, we have extended the existing Trace collector used in the Perun framework to collect the runtime of functions with a new so-called engine based on the Pin framework. We tested the functionality of our implementation on two non-trivial projects, where we were able to find functions (1) with considerable impact on performance, (2) with the most significant optimisation benefit, and (3) whose degradation forces the non-termination of the program after several hours of running.
|
host ::
RSS.