E-Hong
New ContributorJoined 4 years ago
User Profile
New Contributor
User Widgets
Contributions
Total register & logic consumed from Arria 10 PAC
Hi, Is there any ways to obtain the amount of register and logic consumed from running inference on the Arria 10 PAC? I am trying to get the sof/pof report like those generated on Quartus when running synthesis. Does programming a bitstream on the Arria 10 PAC generate a report? Thank you.Re: [N3000 setup] Pr Interface ID: eeeeeeee-eeee-eeee-2222-222222222222
Hi, If I install solely the first link mentioned by you, I am unable to run `aocl diagnose`, that's how I ended up installing both. Thanks for the clarification! My goal is to run deep learning inference targeting `HETERO:FPGA,CPU`, is the N3000 PAC capable of doing this? Another question, how do I run `aocl diagnose` on the N3000 pac? And, if I installed only N3000 Acceleration Stack, `sudo fpgainfo fme` is not working as well. Thank you.[N3000 setup] Pr Interface ID: eeeeeeee-eeee-eeee-2222-222222222222
Hi, I am installing N3000 PAC on a Xeon CPU. I installed the setup according to this https://www.intel.com/content/www/us/en/programmable/documentation/xgz1560360700260.html Installed Arria 10 Acceleration Stack for PAC from here https://www.intel.com/content/www/us/en/programmable/documentation/iyu1522005567196.html Then when I source the `init_env.sh`, I am able to source all environments and scripts without error. I am able to run `aocl diagnose`, below is the output. The diagnostics is passing but PAC remains uninitialized Latter when I tried programming a bitstream file into the PAC, it shows this error I ran `sudo fpgainfo fme`, and the Pr Interface ID: eeeeeeee-eeee-eeee-2222-222222222222 seems weird. It's not expected per the setup manual, and the ID is definitely off. Not to mention my Bitstream version is 0.0.0 and MAX10 version is too low. Did I missed out some steps will installing the PAC that leads to the error above? I tried re-installing but it and still same problem. Any help will be very appreciated! OS: CentOS 7.9 3.10.0-1160.25.1.el7.x86_64 Thank you.Re: Getting OpenVINO Inference Time per Layer
Hi Hazlina, I am using a VGG16/19 deep learning model. My goal is to run inference targeting the Arria 10 PAC card. I am able to calculate the time taken for the whole inference process, but I hope to time the inference time per model's layer as well. Thank you.
