simd

This blog post traces the execution of NumPy's np.add function from Python down to C, explaining the internal machinery and SIMD optimization involved in numerical addition.

The author implemented a vectorized FMA for Rust's fearless_simd library, leading to performance improvements and the discovery of bugs in Rust and musl libc standard libraries.

The article explains an optimized method for parsing IPv4 addresses in C# using AVX-512 SIMD instructions, leveraging .NET 10's masked loads to achieve high performance with UTF-16 strings.

This article provides a historical overview of Intel's Pentium MMX SIMD instructions introduced in the 1990s, explaining their role in bringing parallel processing to mainstream desktop CPUs for multimedia applications.

fearless_simd v0.7 adds 64-bit integer support, SSE2 level, improved generics, and more operations, with v1.0 upcoming.

This technical blog post explains the performance impact of memory alignment in SIMD vectorization, covering architectures with strict alignment requirements, cacheline crossing, and the behavior of modern CPUs.

A technical blog post explains how to perform integer division and remainder using floating-point division and fused multiply-add, with constraints on operand bit widths, and discusses practical considerations for SIMD and rounding modes.

VectorWare announces that Rust's portable SIMD (core::simd) now works on the GPU, mapping SIMD vectors to warp lanes and enabling familiar Rust abstractions for GPU programming.

A technical blog post explaining the FastLanes Unified Transport Layout, a SIMD-friendly data layout for parallel delta decoding, and how it enables data-parallel processing with wide virtual registers.

pgrust 0.2 rebuilds the Postgres query engine with batching, operator fusion, and SIMD, achieving 300x faster analytical queries and 30% faster OLTP than Postgres.

A Rust crate implementing Viterbi and Reed-Solomon forward error correction with SIMD acceleration, achieving faster throughput than the C library libfec on supported codecs.

Rust 1.98 introduces a new API to enable faster floating-point math by allowing more aggressive compiler optimizations, while still giving developers control over rounding errors.

A detailed analysis of Rust's std::simd::swizzle_dyn implementation, exposing performance shortcomings and proposing optimizations to better leverage hardware shuffle instructions.

A blog post by Mitchell Hashimoto arguing that SIMD (Single Instruction, Multiple Data) is simpler than often assumed, demonstrating a common pattern for using SIMD in loops with Zig examples.

This post discusses the use of SIMD to optimize collision detection for convex hulls in Box3D, particularly using wide SIMD and the Separating Axis Test to improve performance for hulls with many edges.

Gigatoken is an open-source tokenizer that achieves up to 1000x speedup over HuggingFace tokenizers and 100x over Tiktoken, using SIMD and caching optimizations. It supports drop-in replacement for existing tokenizer APIs.

A new runtime for the K and Q programming languages that reimagines execution using SIMD, parallelism, fusion, and compression to better leverage modern hardware.

A blog post describing an efficient method to pack ternary numbers into 8-bit bytes using SIMD-friendly unpacking, achieving 1.6 bits per trit, with applications in LLM weight quantization like BitNet b1.58.

A blog post demonstrates how adding a conditional check that appears useless can dramatically improve loop performance by allowing the CPU's branch predictor to eliminate data dependencies, achieving up to 4x speedup in a specific compression algorithm.

Talos-XII is a CLI simulator for Arknights: Endfield's gacha system, built entirely in Rust with a custom autograd engine and small RL/MLP stack (no external ML frameworks). It uses neural networks for environment modeling and pull-decision policy, and includes sophisticated SIMD dispatch and an open experiment called ACHF for adaptive caching.