Optimizing rav1d, the Rust AV1 decoder (Prossimo)
Description
Engineering writeup from ISRG's Prossimo on closing the performance gap between rav1d and dav1d, detailing the specific Rust codegen and memory-layout changes that mattered.
Resource details
- Category path
- Encoding & Codecs›Benchmarking & Performance Tools for Codecs
- Classification
- Not yet classified
Optimizing rav1d, the Rust AV1 decoder (Prossimo) is cataloged in Encoding & Codecs and Benchmarking & Performance Tools for Codecs.
URL
Related resources
- Are We Compressed YetDistributed encode/decode + BD-rate + VMAF benchmarking harness originally for Daala, adopted by AOM community for comparative testing of A…
- Differentiable VMAF Re-implementation on PyTorchDifferentiable PyTorch reimplementation of VMAF metric enabling gradient-based codec/RDO optimization, with companion code.
- Applying Objective Quality Metrics to Video-Codec ComparisonStudy of 789 encoded streams and 320k subjective scores analyzing VMAF correlation per colorspace for codec comparison.
- Benchmarking Conventional and Learned Video Codecs with a Low-Delay ConfigurationAcademic benchmark comparing traditional (HEVC/VVC) and learned video codecs under low-delay configuration constraints.
- FOSDEM 2024: VVdeC<>Arm — Optimizing an Open Source VVC Decoder for Arm ArchitecturesFOSDEM Open Media devroom talk detailing Arm-specific performance optimization work on the open-source VVdeC VVC decoder.
- AV1 Encoding with libsvtav1 on QencodeThe libsvtav1 encoder (SVT-AV1) is an AV1 implementation tuned for both compression efficiency and parallel performance. This guide covers…
- dav1d.wasmWASM port of the dav1d AV1 decoder, SIMD-optimized with TypeScript interfaces, aimed at production use in browsers.
- Performance Comparison of AV1, JEM, VP9, and HEVC EncodersFraunhofer HHI SPIE 2017 paper comparing codec internals, BD-BR, and complexity across AV1, JEM, VP9, and HEVC.
- nano-hevcMinimal educational HEVC encoder written in pure Python, readable-over-fast, for teaching codec internals.
- Opus (xiph/opus)Reference implementation of the Opus audio codec, recently adding deep-learning-based packet loss concealment.
- jxs (JPEG XS reference)Reference software implementation of ISO/IEC 21122-5 (JPEG XS) including jxs_encoder binary, supports PNM/PGX/raw YUV/RGB input.