sutton037

Since the 1950s there have been three main families of collectors: semi-space, mark-sweep and mark-compact. Almost all production GCs have been generational mark-sweep even though they exhibit pathological performance when the nursery is full of survivors because they are marked, (physically) copied and all references to them updated which is ~3x slower than necessary and is practically useful when filling a hash table with heap-allocated keys and/or values. The Beltway (2002) and Immix (2008) garbage collectors introduced the new family called the mark-region GCs. With a mark-region GC the entire heap is a collection of regions and so is the nursery generation so it can be logically aged by replacing it with another region when it is full of survivors. Sun's Hotspot JVM introduced the first mainstream mark-region GC with its G1 collector. The advent of multicore in 2005 has meant more emphasis on parallel and concurrent garbage collectors. The Staccato (2008) garbage collector ...

Mono 2.2 was recently shipped and a new JIT code generator was the main selling point promoted by the Mono project because it provides the first significant performance improvement Mono has seen for many years. We used the F# version of the SciMark2 benchmark to benchmark this new version of Mono against Mono 2.0 and some competing VMs using their native SciMark2 implementations: The composite results show that the new code generator in Mono is indeed substantially better at producing code that is 40% faster on average than the previous code generator from Mono 2.0 according to these results. However, Mono 2.2 is still a long way behind its competitors. Specifically, both LLVM and Sun's JVM are over 2.2× faster than the latest version of Mono. SciMark2 is composed of five different tests: Fast Fourier transform, successive over-relaxation, Monte Carlo, sparse matrix-vector multiply and LU matrix decomposition. We can get more detailed comparison of the VMs by looking at the indiv...