Skip to main content

Crate ironaccelerator

Crate ironaccelerator 

Source
Expand description

§IronAccelerator

Low-level, hardware-agnostic Rust interface over CUDA, ROCm, Metal, and other accelerators. This facade crate re-exports each backend behind a feature flag and exposes a Runtime that surveys the backends and devices reachable from this process. Most CUDA users will pull in ironaccelerator-cuda directly — it doubles as a drop-in replacement for cudarc that’s measurably faster on every host-side hot path.

§Crate layout

cratepurpose
ironaccelerator-coreshared types, errors, capability flags
ironaccelerator-cuda-sysclean-room CUDA 13.2 FFI + dynamic loader (no link deps)
ironaccelerator-cudasafe CUDA driver wrappers + cudarc-shaped compatibility
ironaccelerator-rocmsafe ROCm/HIP driver wrappers (same fast-path pattern)
ironaccelerator-metalApple Metal compute (ComputeDevice)
ironaccelerator-qnnQualcomm Hexagon NPU (QNN AOT graph substrate)
ironaccelerator-vulkanVulkan compute: enumerate, buffers, SPIR-V pipeline, dispatch
ironaccelerator-dx12Direct3D 12 compute: enumerate, buffers, DXIL pipeline, dispatch
ironaccelerator-openglOpenGL 4.3+ compute-shader fallback (host-bound GL context)
ironaccelerator-webgpubrowser/WASM adapter binding (host owns the GPUDevice)
ironaccelerator-levelzeroIntel GPU/NPU via Level Zero (ComputeDevice)
ironaccelerator-tpuGoogle TPU via PJRT plugin (probe/enumerate)
ironaccelerator-neuronAWS Trainium/Inferentia via libnrt (probe + NEFF load/exec)
ironaccelerator-fpgaAMD/Xilinx FPGA via XRT (probe/enumerate)

§Native vs browser

On native hosts the GPU backends talk to the platform driver directly: CUDA and ROCm for the vendor stacks, Vulkan for cross-vendor compute, Metal on Apple, D3D12 on Windows, OpenGL as the legacy fallback. ironaccelerator-webgpu is the browser path only — on native it reaches nothing the others do not, so it does not try.

§One compute surface across backends

The Vulkan, D3D12, OpenGL, Metal, and Level Zero backends implement ComputeDevice, so a generic routine — upload → build a pipeline from backend-native bytecode → dispatch → download — runs unchanged on any of them. See the unified_compute test for a single function driven across Vulkan and D3D12.

§Scope

IronAccelerator stops at the driver. Workload descriptors, execution-strategy selection, tensor descriptors, quantization schemes, and the accelerator ontology used to rank kernel strategies live in the inference engine on top (IronWorks) — not here.

use ironaccelerator_cuda::cudarc_compat::*;

let dev = CudaDevice::new(0)?;
let stream = dev.default_stream();
let xs = stream.htod_copy(vec![1.0f32, 2.0, 3.0])?;
let out = stream.dtoh_sync_copy(&xs)?;

§Cross-backend device survey (this facade)

use ironaccelerator::prelude::*;

let runtime = ironaccelerator::init();
for dev in runtime.devices_with(CapabilityFlags::FP8_E4M3) {
    println!("{} ({}) — {:?}", dev.name, dev.arch, dev.id.backend);
}

Note: the survey covers backends that implement ironaccelerator_core::Backend. The CUDA crate intentionally does not — it ships only driver wrappers. Use the CUDA crate directly when you want fine-grained driver control or the cudarc-shaped API.

Re-exports§

pub use ironaccelerator_core as core;
pub use ironaccelerator_cuda as cuda;
pub use ironaccelerator_metal as metal;
pub use ironaccelerator_qnn as qnn;
pub use ironaccelerator_rocm as rocm;

Modules§

prelude
Common imports: core traits, device types and error types.

Structs§

Runtime
Process-wide registry of the compiled-in backends plus device discovery across them.

Functions§

init
Convenience: build a runtime with every compiled-in backend registered.