Section: New Results

Dynamic Languages: Virtual Machines

VM Profiler. Code profiling enables a user to know where in an application or function the execution time is spent. The Pharo ecosystem offers several code profilers. However, most of the publicly available profilers (MessageTally, Spy, GadgetProfiler) largely ignore the activity carried out by the virtual machine, thus incurring inaccuracy in the gathered information and missing important information, such as the Just-in-time compiler activity. We describe the motivations and the latest improvements carried out in VMProfiler, a code execution pro-filer hooked into the virtual machine, that performs its analysis by monitoring the virtual machine execution. These improvements address some limitations related to assessing the activity of native functions (resulting from a Just-in-time compiler operation): as of now, VMProfiler provides more detailed profiling reports, showing for native code functions in which bytecode range the execution time is spent. [28]

Sista: Saving Optimized Code in Snapshots for Fast Start-Up. Modern virtual machines for object-oriented languages such as Java HotSpot, Javascript V8 or Python PyPy reach high performance through just-in-time compilation techniques, involving on-the-fly optimization and deoptimization of the executed code. These techniques require a warm-up time for the virtual machine to collect information about the code it executes to be able to generate highly optimized code. This warm-up time required before reaching peak performance can be considerable and problematic. We propose an approach, Sista (Speculative Inlining SmallTalk Architecture) to persist optimized code in a platform-independent representation as part of a snapshot. After explaining the overall approach, we show on a large set of benchmarks that the Sista virtual machine can reach peak performance almost immediately after start-up when using a snapshot where optimized code was persisted. [24]