Finally got Scotty3D to build on the FPGA!!
This week has been hard to get any progress done since I was reviewing for the Design Review presentation and working on the paper. I feel we are behind schedule due to so much time being dedicated towards presentations.
Currently we are trying to get Scotty3D to run on the fabric, so we can compare that to the FPGA version of Scotty3D.
Over the past week we’ve had issues with the FPGA crashing, presumably due to high CPU usage, and I realized that the probability of being able to render graphics on the CPU is low. We might pivot to having a non-graphical version of Scotty3D run on the FPGA, and then output into some sort of text file the 3D position of each of the 512 particles per frame, and let some host computer (such as my PC or my laptop) to the rendering instead. This is after all how big data companies structure their platforms. I am still trying to investigate this with Jeremy and Ziyi for another day or 2 further before making any decisions. This is of course linked to my task for running the simulation headless. Another option is to have the FPGA communicate with the laptop through USB.
Next week my goal is to address this issue. It seems a bit pressing since it might require an architecture change.