Support for TE0821 modules with Vitis AI 3.0 DPU
DescriptionThis application note how to design custom HW platform with AMD DPU for Vitis 2022.2 AI 3.0 inference for family of Trenz Electronic modules TE0821 with AMD Zynq Ultrascale+ device.
This application note is using AMD Vitis 2022.2 and PetaLinux 2022 tools installed on Ubuntu 20.04. The described configuration integrated AMD DPU IP, version v4.1.0, with architecture DPUCZDX8G.
Described board configuration can operate as small standalone computer with 1 Gb Ethernet connectivity, and remote X11 desktop. Support package for this application note will be available for public download from.
The installed AMD DPU configurations require recompilation of Vitis AI 3.0 examples and inference models in the Vitis AI framework. This compilation process will be described in separate application note.
Package Summary
| Title | Support for TE0821 modules with Vitis AI 3.0 DPU |
| Filenames | te0821_AI_3_0_eval_package.zip (3,73 kB) sd_card.img (2,95 GB) TE0821_AI_3_0_rev03.pdf (19,7 MB) |
| License | See application note for licensing conditions. |
| Package content | ZIP archive with support files as described in application note. SD card image with Petalinux and AMD DPU in B1600 configuration. |
| Size | ZIP file: 5 922 Bytes IMG file: 3 171 942 400 Bytes PDF file: 20 762 232 Bytes |
| Required tools & platform |
AMD Vitis 2022.2, AMD Vitis AI 3.0 |
| Installation notes | See application note |
Result Category
| Project number | Project acronym | Year | RIV category | Comment |
| 9A23008 | EECONE | 2024 | Gfunk | Functional sample (demo) |