3
0
Mirror von https://github.com/PaperMC/Velocity.git synchronisiert 2024-12-24 23:30:26 +01:00
Velocity/native
Andrew Steinborn 8588e7f1fe Optimize native handling further.
We now try to work within the boundaries given by the native. In the
case of Java natives, we work with byte arrays. With natives, always use
direct buffers.

However, the numbers do favor the natives, since they work with direct
byte buffers, without any copying. For the most part, this commit is
intended to improve the lives of Velocity users on Windows.
2018-12-30 06:16:04 -05:00
..
src Optimize native handling further. 2018-12-30 06:16:04 -05:00
build.gradle Improve efficiency of Java implementation of natives. 2018-12-28 13:02:46 -05:00
compile-linux.sh Generic MBEDTLS_ROOT 2018-12-24 12:18:36 -05:00
compile-osx.sh Generic MBEDTLS_ROOT 2018-12-24 12:18:36 -05:00
README.md Native cryptography support using mbed TLS 2018-08-04 23:46:41 -04:00

velocity-natives

This directory contains native acceleration code for Velocity, along with traditional Java fallbacks.

Compression

  • Supported platforms: macOS 10.13, Linux amd64 (precompiled binary is built on Debian 9 with JDK 8)
  • Rationale: Using a native zlib wrapper, we can avoid multiple trips into Java just to copy memory around.

Encryption

  • Supported platforms: macOS 10.13, Linux amd64
  • Rationale: Using a C library for encryption means we can limit memory copies. Prior to Java 7, this was the only way to use AES-NI extensions on modern processors, but this is less important since JDK 8 has native support.
  • Note: Due to U.S. restrictions on cryptography export, this native is provided in source code form only for now.

OS support

If you are on Alpine Linux, apk add libc6-compat will enable native support.