matrixmultiply
v0.3.11 GrowingGeneral matrix multiplication for f32 and f64 matrices. Operates on matrices with general layout (they can use arbitrary row and column stride). Detects and uses SIMD features on x86/x86-64 and AArch64 transparently for higher performance. Uses a microkernel strategy, so that the implementation is easy to parallelize and optimize. Supports multithreading.
Quick Verdict
- โActively maintained (updated 87d ago)
- !Pre-1.0: API may have breaking changes
- โTrusted by 962 crates
- โTeam maintained (3 owners)
- โPermissive license (MIT/Apache-2.0)
Security
Deep Insights
12.6M downloads in the last 30 days (419.5K/day), up 13% from the previous period.
962 crates depend on matrixmultiply. Reasonable ecosystem adoption, though not yet a core dependency.
This crate is maintained by a team (3 owners), reducing bus-factor risk and ensuring continuity.
Despite being 10+ years old, matrixmultiply hasn't reached 1.0 yet. Expect potential API changes between versions.
Notable dependents include ndarray, nalgebra, burn-ndarray, peroxide, rulinalg. When high-quality crates choose matrixmultiply, it's a strong quality signal.
Health Breakdown
Recency, release consistency, active ratio
Yanked ratio, deps, size, maturity, features
Reverse deps, ownership, ecosystem
Downloads, momentum, growth trend
Docs, repo, license, metadata
Download Trend
Top Dependents
Most downloaded crates that depend on matrixmultiply
Version Adoption
Release Timeline
Feature Flags
default =["std", "avx512"]