A fast in-place interpreter for WebAssembly

TL;DR

This paper introduces a fast in-place interpreter for WebAssembly that enables quicker startup times and lower memory usage by interpreting Wasm code directly without rewriting or separate formats.

Contribution

We present a novel in-place interpretation method for WebAssembly that improves startup speed and memory efficiency over traditional compilation and interpretation approaches.

Findings

In-place interpretation achieves performance comparable to custom internal formats.

The approach reduces startup time significantly compared to baseline compilers.

Memory footprint is lowered due to no need for code rewriting or separate formats.

Abstract

WebAssembly (Wasm) is a compact, well-specified bytecode format that offers a portable compilation target with near-native execution speed. The bytecode format was specifically designed to be fast to parse, validate, and compile, positioning itself as a portable alternative to native code. It was pointedly not designed to be interpreted directly. Instead, design considerations at the time focused on competing with native code, utilizing optimizing compilers as the primary execution tier. Yet, in JIT scenarios, compilation time and memory consumption critically impact application startup, leading many Wasm engines to later deploy baseline (single-pass) compilers. Though faster, baseline compilers still take time and waste code space for infrequently executed code. A typical interpreter being infeasible, some engines resort to compiling Wasm not to machine code, but to a more compact, but easy to interpret format. This still takes time and wastes memory. Instead, we introduce in this article a fast in-place interpreter for WebAssembly, where no rewrite and no separate format is necessary. Our evaluation shows that in-place interpretation of Wasm code is space-efficient and fast, achieving performance on-par with interpreting a custom-designed internal format. This fills a hole in the execution tier space for Wasm, allowing for even faster startup and lower memory footprint than previous engine configurations.