search

google / CFU-Playground

Want a faster ML processor? Do it yourself! -- A framework for playing with custom opcodes to accelerate TensorFlow Lite for Microcontrollers (TFLM). . . . . . Online tutorial: https://google.github.io/CFU-Playground/ For reference docs, see the link below.
http://cfu-playground.rtfd.io/
Apache License 2.0
452 stars 116 forks source link

Failing CI for Lattice Nexus / prjoxide tests #803

Open tcal-x opened 10 months ago

tcal-x commented 10 months ago

To reproduce locally:

make env
make enter
cd proj/hps_accel
make bitstream

Symptom is an error from nextpnr-nexus:

ERROR: Cell type 'CCU2' instantiated as 'tx_phase_FD1P3IX_Q_8_D_LUT4_Z_D_CCU2_S1_S0_CCU2_S1_CIN_CCU2_COUT' is not supported by this device.

Our device is LIFCL-17-8UWG72C.

It could be that our Litex is too far out of date. In an updated pure Litex installation, I can build the litex-boards target for the EVN board:

./lattice_crosslink_nx_evn.py --build --toolchain=oxide

This netlist does contain CCU2 cells. Its device is LIFCL-40-9BG400C.