Scientific benchmarking of parallel computing systems: twelve ways to tell the masses when reporting performance results
Measuring and reporting performance of parallel computers constitutes the basis for
scientific advancement of high-performance computing (HPC). Most scientific reports show …
scientific advancement of high-performance computing (HPC). Most scientific reports show …
Performance overhead comparison between hypervisor and container based virtualization
The current virtualization solution in the Cloud widely relies on hypervisor-based
technologies. Along with the recent popularity of Docker, the container-based virtualization …
technologies. Along with the recent popularity of Docker, the container-based virtualization …
uFLIP: Understanding flash IO patterns
Does the advent of flash devices constitute a radical change for secondary storage? How
should database systems adapt to this new form of secondary storage? Before we can …
should database systems adapt to this new form of secondary storage? Before we can …
Dynamic software updates: a VM-centric approach
S Subramanian, M Hicks, KS McKinley - Proceedings of the 30th ACM …, 2009 - dl.acm.org
Software evolves to fix bugs and add features. Stopping and restarting programs to apply
changes is inconvenient and often costly. Dynamic software updating (DSU) addresses this …
changes is inconvenient and often costly. Dynamic software updating (DSU) addresses this …
What's wrong with my benchmark results? Studying bad practices in JMH benchmarks
Microbenchmarking frameworks, such as Java's Microbenchmark Harness (JMH), allow
developers to write fine-grained performance test suites at the method or statement level …
developers to write fine-grained performance test suites at the method or statement level …
Write-rationing garbage collection for hybrid memories
Emerging Non-Volatile Memory (NVM) technologies offer high capacity and energy
efficiency compared to DRAM, but suffer from limited write endurance and longer latencies …
efficiency compared to DRAM, but suffer from limited write endurance and longer latencies …
A data generator for cloud-scale benchmarking
In many fields of research and business data sizes are breaking the petabyte barrier. This
imposes new problems and research possibilities for the database community. Usually, data …
imposes new problems and research possibilities for the database community. Usually, data …
CEEM: A practical methodology for cloud services evaluation
Given an increasing number of Cloud services available in the market, evaluating candidate
Cloud services is crucial and beneficial for both service customers (eg cost benefit analysis) …
Cloud services is crucial and beneficial for both service customers (eg cost benefit analysis) …
Looking back on the language and hardware revolutions: measured power, performance, and scaling
This paper reports and analyzes measured chip power and performance on five process
technology generations executing 61 diverse benchmarks with a rigorous methodology. We …
technology generations executing 61 diverse benchmarks with a rigorous methodology. We …
Repeatability, reproducibility, and rigor in systems research
J Vitek, T Kalibera - Proceedings of the ninth ACM international …, 2011 - dl.acm.org
Computer systems research spans sub-disciplines that include embedded and real-time
systems, compilers, networking, and operating systems. Our contention is that a number of …
systems, compilers, networking, and operating systems. Our contention is that a number of …