• Publications
  • Influence
Analyzing the Impact of CPU Pinning and Partial CPU Loads on Performance and Energy Efficiency
TLDR
In this paper we study the impact of CPU pinning on performance interference and energy efficiency for pairs of collocated workloads. Expand
  • 35
  • 4
  • PDF
Benchmark Precision and Random Initial State
TLDR
We show that this approach ignores an inherent and unavoidable nondeterminism in the initial state of the system that is evaluated, often leading to an implausible estimate of result precision. Expand
  • 47
  • 4
  • PDF
Unit Testing Performance in Java Projects: Are We There Yet?
TLDR
This paper is motivated by two observations, one related to performance testing and one to software testing activities in general: – Software performance testing is widely recognized as an essential software quality assurance tool. Expand
  • 16
  • 4
  • PDF
Renaissance: benchmarking suite for parallel applications on the JVM
TLDR
We present Renaissance, a new benchmark suite composed of modern, real-world, concurrent, and object-oriented workloads that exercise various concurrency primitives of the JVM. Expand
  • 16
  • 3
  • PDF
CORBA benchmarking: a course with hidden obstacles
TLDR
We point out common causes of such imprecision related to the gathering of timing information and the effects of warm-up, randomization, cross talk and delayed or hidden functionality that can distort the results of the evaluation. Expand
  • 32
  • 2
  • PDF
Automated detection of performance regressions: the mono experience
TLDR
We show how to tackle the problem of nondeterminism inherent to contemporary computer systems and execution environments with statistical methods. Expand
  • 32
  • 2
  • PDF
On the limits of modeling generational garbage collector performance
TLDR
We investigate the difference between the behavior of a real garbage collector implementation and a simplified model on a selection of workloads, focusing on the accuracy achievable with particular input information (sizes, references, lifetimes). Expand
  • 17
  • 2
  • PDF
Repeated results analysis for middleware regression benchmarking
TLDR
The paper outlines the concept of regression benchmarking as a variant of regression testing focused at detecting performance regressions. Expand
  • 39
  • 1
Characteristics of dynamic JVM languages
TLDR
We use various metrics to characterize the dynamic behavior of a variety of programs written in three dynamic languages (Clojure, Python, and Ruby) executing on the JVM. Expand
  • 19
  • 1
  • PDF
Estimating the Impact of Code Additions on Garbage Collection Overhead
TLDR
We propose a method to estimate the impact of code changes with additional allocations on garbage collection time, which can be applied, e.g., when assessing the overall performance impact of alternative changes. Expand
  • 7
  • 1