development/deno
development/deno
1
0
Fork 0
mirror of https://github.com/denoland/deno synced 2024-11-05 18:45:24 +00:00
Code Issues Projects Releases Packages Wiki Activity
deno/ext/ffi
History
David Sherret 10e4b2e140
chore: update copyright year to 2023 (#17247) 
Yearly tradition of creating extra noise in git.
2023-01-02 21:00:42 +00:00
..
00_ffi.js chore: update copyright year to 2023 (#17247) 2023-01-02 21:00:42 +00:00
call.rs chore: update copyright year to 2023 (#17247) 2023-01-02 21:00:42 +00:00
callback.rs chore: update copyright year to 2023 (#17247) 2023-01-02 21:00:42 +00:00
Cargo.toml chore: update copyright year to 2023 (#17247) 2023-01-02 21:00:42 +00:00
dlfcn.rs chore: update copyright year to 2023 (#17247) 2023-01-02 21:00:42 +00:00
ir.rs chore: update copyright year to 2023 (#17247) 2023-01-02 21:00:42 +00:00
lib.rs chore: update copyright year to 2023 (#17247) 2023-01-02 21:00:42 +00:00
README.md fix(ext/ffi): trampoline for fast calls (#15139) 2022-07-12 06:33:05 +05:30
repr.rs chore: update copyright year to 2023 (#17247) 2023-01-02 21:00:42 +00:00
static.rs chore: update copyright year to 2023 (#17247) 2023-01-02 21:00:42 +00:00
symbol.rs chore: update copyright year to 2023 (#17247) 2023-01-02 21:00:42 +00:00
turbocall.rs chore: update copyright year to 2023 (#17247) 2023-01-02 21:00:42 +00:00

README.md

deno_ffi

This crate implements dynamic library ffi.

Performance

Deno FFI calls have extremely low overhead (~1ns on M1 16GB RAM) and perform on par with native code. Deno leverages V8 fast api calls and JIT compiled bindings to achieve these high speeds.

Deno.dlopen generates an optimized and a fallback path. Optimized paths are triggered when V8 decides to optimize the function, hence call through the Fast API. Fallback paths handle types like function callbacks and implement proper error handling for unexpected types, that is not supported in Fast calls.

Optimized calls enter a JIT compiled function "trampoline" that translates Fast API values directly for symbol calls. JIT compilation itself is super fast, thanks to tinycc. Currently, the optimized path is only supported on Linux and MacOS.

To run benchmarks:

target/release/deno bench --allow-ffi --allow-read --unstable ./test_ffi/tests/bench.js