This is a fork of the original Savina Benchmark suite (see below). This fork
extends the benchmark runner by a CLI option (-workers
) for specifying the
precise number of workers for processing the benchmark workload.
Savina is an Actor Benchmark Suite.
Our goal is to provide a standard benchmark suite that enables researchers and application developers to compare different actor implementations and identify those that deliver the best performance for a given use-case. The benchmarks in Savina are diverse, realistic, and represent compute (rather than I/O) intensive applications. They range from popular micro-benchmarks to classical concurrency problems to applications that demonstrate various styles of parallelism. Implementations of the benchmarks on various actor libraries will be made publicly available through this open source release. This will allow other developers and researchers to compare the performance of their actor libraries on these common set of benchmarks.
Please refer to the following paper for further details:
Savina - An Actor Benchmark Suite.
Shams Imam,
Vivek Sarkar.
4th International Workshop on Programming based on Actors, Agents, and Decentralized Control (AGERE! 2014),
October 2014.
- Akka 2.3.2
- Functional-Java 4.1
- GPars 1.2.1
- Habanero-Java library 0.1.3 (includes actors and selectors)
- Jetlang 0.2.12
- Jumi 0.1.196
- Lift 2.6-M4
- Scala 2.11.0
- Scalaz 7.1.0-M6.
- CAF 0.15.3
- Optional
- Java + Scala + Maven
- CAF
-
Java/Scala benchmarks
cd savina mvn compile mvn package
-
CAF benchmarks
cd savina mkdir build cd build cmake [-DCAF_ROOT_DIR=/path/to/caf/build/directory] .. make
-
Java/Scala
cd savina/target java -cp savina-0.0.1-SNAPSHOT-jar-with-dependencies.jar edu/rice/habanero/benchmarks/pingpong/PingPongAkkaActorBenchmark [--iterations=X] [--no_evaluation] -- [benchmark specific options]
-
CAF
cd build/bin ./caf_01_pingpong [--iterations=X] [--no_evaluation] -- [benchmark specific options]