Blogs (28) >>
ECOOP 2016
Sun 17 - Fri 22 July 2016 Rome, Italy
Mon 18 Jul 2016 11:35 - 12:05 at Alfieri - Session 2 Chair(s): Tomas Kalibera

Virtual Machines (VMs) with Just-In-Time (JIT) compilers are traditionally thought to execute programs in two phases: first the \emph{warmup} phase determines which parts of a program would most benefit from dynamic compilation; after compilation has occurred the program is said to be at \emph{peak performance}. When measuring the performance of JIT compiling VMs, data collected during the warmup phase is generally discarded, placing the focus on peak performance. In this paper we run a number of small, deterministic benchmarks on a variety of well known VMs. In our experiment, less than one quarter of the benchmark/VM pairs conform to the traditional notion of warmup, and none of the VMs we tested consistently warms up in the traditional notion. This raises a number of questions about VM benchmarking, which are of interest to both VM authors and end users.

Preprint (icooolps-final12.pdf)833KiB

Mon 18 Jul

10:05 - 12:25: ICOOOLPS - Session 2 at Alfieri
Chair(s): Tomas KaliberaNortheastern University
ICOOOLPS-2016146882910000010:05 - 11:05
Lubomír BulejCharles University
Media Attached File Attached
ICOOOLPS-2016146883270000011:05 - 11:35
Forrest AlexanderPortland State University, Andrew BlackPortland State University
Media Attached File Attached
ICOOOLPS-2016146883450000011:35 - 12:05
Edd BarrettKing's College London, Carl Friedrich Bolz-TereickKing's College London , Rebecca KillickDepartment of Mathematics and Statistics, University of Lancaster, Vincent KnightSchool of Mathematics, Cardiff University, Sarah MountKing's College London, Laurence TrattKing's College London
Link to publication Media Attached File Attached
ICOOOLPS-2016146883630000012:05 - 12:25