Why Julia on iGPU / APU
On our servers the Intel UHD 770 iGPU is exposed via OpenCL: accelerate linear algebra, simulation and data processing at minimal cost (from €14.99/month).
iGPU / APU use case
Julia accelerated on an integrated GPU (iGPU / APU)
Run your Julia jobs and notebooks on an integrated-GPU server for accelerated scientific computing without the cost of a dedicated GPU.
OpenCL, ready to go
The integrated GPU is reachable through OpenCL (Intel runtime / oneAPI). Julia OpenCL packages offload work from the CPU.
using OpenCL
for d in cl.devices()
println(d)
endFrom notebook to cluster
Work over SSH, expose a Jupyter/Pluto, or orchestrate several nodes with k3s / Kubernetes. Root SSH, IPv6 included, LUKS encryption.