numr 0.5.1

High-performance numerical computing with multi-backend GPU acceleration (CPU/CUDA/WebGPU)
Documentation
1
2
3
4
5
6
7
8
9
10
11
12
13
//! SIMD-accelerated fused elementwise operations.
//!
//! See [`dispatch`] for the public dispatch functions and scalar fallbacks.

#[cfg(target_arch = "x86_64")]
pub(crate) mod x86_64;

#[cfg(target_arch = "aarch64")]
pub(crate) mod aarch64;

pub(crate) mod dispatch;

pub use dispatch::*;