Tag
This blog post details three recent optimizations to LLVM's BumpPtrAllocator, reducing fast-path overhead by removing redundant alignment, null pointer checks, and per-allocation accounting, resulting in improved performance for Clang, lld, and other LLVM components.
This article revisits techniques for creating extremely small ELF executables on Linux, exploring how to reduce size to 45 bytes by abusing header fields and overlapping structures while maintaining ELF specification conformance.
This talk analyzes Rust's performance strengths and weaknesses compared to C++, providing benchmarks and best practices. Slides and reading materials are available.
libwce is a minimal, patent-clean Rust library implementing a Bit-Plane Count (BPC) entropy layer for wavelet codecs, providing a stateless and dependency-free module for entropy coding.
A technical blog post exploring how to use SBCL as a breadboard for assembly code, focusing on stack-based virtual machine techniques such as rotating stacks and efficient primop dispatch, with references to the F18 processor and x87 stack.
A bug in the Windows debugging engine for x86-64 incorrectly reported the parity flag, going unnoticed for over two decades, highlighting how rarely the flag is debugged.
ymawky is a web server written entirely in ARM64 assembly for macOS, featuring syscall-only operations without libc and basic HTTP capabilities.
The article introduces 'ymawky', a minimal HTTP web server written entirely in aarch64 assembly for macOS, using raw syscalls without libc wrappers to explore low-level system mechanics.