SYSTEMS · GPU RUNTIME
A universal hardware optimization runtime that unifies GPU acceleration across CUDA, ROCm, Metal and OpenCL behind one decorator.
↓ SCROLL
GPU acceleration is fragmented across vendors — CUDA, ROCm/HIP, Metal, OpenCL, each with its own toolchain. Writing fast code that runs everywhere usually means hand-porting the same kernel four times, or picking one vendor and locking out the rest.
UHOP detects the machine's available backends, dispatches each operation to the fastest one, and caches the winning implementation per device so the choice is made once, not on every run. A single `@uhop.optimize("op")` decorator drops acceleration into existing Python code, and an AI kernel generator can write and validate new OpenCL/CUDA/Triton implementations when no hand-written one exists.
The @uhop.optimize decorator accelerates an operation like matmul with no rewrite.
Generates and validates new GPU kernels when no hand-written implementation exists yet.
uhop policy explain shows exactly why a given backend was picked for a device.
Per-backend selection counts, OpenCL matmul GFLOPS, and Conv2D stage timings via one CLI command.